ICAART 2012 Abstracts


Area 1 - Artificial Intelligence

Full Papers
Paper Nr: 20
Title:

INVESTIGATING MARKOV LOGIC NETWORKS FOR COLLECTIVE CLASSIFICATION

Authors:

Robert Crane and Luke K. McDowell

Abstract: Collective Classification (CC) is the process of simultaneously inferring the class labels of a set of inter-linked nodes, such as the topic of publications in a citation graph. Recently, Markov Logic Networks (MLNs) have attracted significant attention because of their ability to combine first order logic with probabilistic reasoning. A few authors have used this ability of MLNs in order to perform CC over linked data, but the relative advantages of MLNs vs. other CC techniques remains unknown. In response, this paper compares a wide range of MLN learning and inference algorithms to the best previously studied CC algorithms. We find that MLN accuracy is highly dependent on the type of learning and the input rules that are used, which is not unusual given MLNs’ flexibility. More surprisingly, we find that even the best MLN performance generally lags that of the best previously studied CC algorithms. However, MLNs do excel on the one dataset that exhibited the most complex linking patterns. Ultimately, we find that MLNs may be worthwhile for CC tasks involving data with complex relationships, but that MLN learning for such data remains a challenge.

Paper Nr: 21
Title:

CONTINUAL HTN PLANNING AND ACTING IN OPEN-ENDED DOMAINS - Considering Knowledge Acquisition Opportunities

Authors:

Dominik Off and Jianwei Zhang

Abstract: Generating plans in order to perform high-level tasks is difficult for agents that act in open-ended domains where it is unreasonable to assume that all necessary information is available a priori. This paper addresses this challenge by presenting a planning-based control system that is able to perform tasks in open-ended domains. The control system is based on a new HTN planning approach that additionally considers decompositions that would be applicable with respect to a consistent extension of the domain model at hand. The proposed control system constitutes a continual planning and acting system that interleaves planning and acting so that missing information can be acquired by means of active information gathering. Experimental results demonstrate that this control architecture can perform tasks in several domains even if the agent initially has no factual knowledge.

Paper Nr: 24
Title:

FLEXIBLE COMMAND INTERPRETATION ON AN INTERACTIVE DOMESTIC SERVICE ROBOT

Authors:

Stefan Schiffer, Niklas Hoppe and Gerhard Lakemeyer

Abstract: In this paper, we propose a system for robust and flexible command interpretation on a mobile robot in domestic service robotics applications. Existing language processing for instructing a mobile robot often make use of a simple, restricted grammar where precisely pre-defined utterances are directly mapped to system calls. This does not take into account fallibility of human users and only allows for binary processing; either a command is part of the grammar and hence understood correctly, or it is not part of the grammar and gets rejected. We model the language processing as an interpretation process where the utterance needs to be mapped to a robot’s capabilities. We do so by casting the processing as a (decision-theoretic) planning problem on interpretatory actions. This allows for a flexible system that can resolve ambiguities and which is also capable of initiating steps to achieve clarification.

Paper Nr: 35
Title:

PROPOSITIONAL LOGICS FOR THE REASONING ABOUT KNOWLEDGE INTEGRATIONS

Authors:

Sebastian Bab

Abstract: In this paper we pick up and elaborate ideas presented in (Bab, 2011). We argue on the position that an explicit treatment of knowledge integrations and knowledge representations in a propositional logical layer can be highly beneficial for a broader understanding of the general notion of knowledge and for a sense or concept driven approach to knowledge integration. In the present paper such an approach is regarded as a more natural approach to this question. This naturalness is due to the fact that in the general case knowledge is complex in the sense that it is not an isolated entity, but a phenomenon which is derived from different sources of knowledge. Based on certain general observations on knowledge integration we pick up the scenario of knowledge integration as presented in (Bab, 2011) and show how this scenario can be realized by a certain class of propositional logics – the so-called parameterized ∈T -logics as first introduced in (Zeitz, 2000). Here the term of propositional logics is not to be understood in the classical way, but as a kind of logics in which formulas are explicitly interpreted as propositions, which in turn are explicitly available as semantic entities in the semantics of the logic. A proposition is to be understood in the understanding of Frege as the inherent sense of a formal expression. As a result of the present paper we show that our general observations made on knowledge integrations can be identified, described and studied in our realization of the scenario, enabling the realization to be a formal fundament for describing, studying and reasoning about knowledge integrations.

Paper Nr: 39
Title:

FUZZY LOGIC APPROACH FOR ESTIMATING 85TH PERCENTILE SPEED BASED ON ROAD ATTRIBUTE DATA

Authors:

Bayzid Khan and Yaser E. Hawas

Abstract: This paper discusses the development of fuzzy logic model for estimating the 85th percentile speed of urban roads. Spot speed survey was conducted on four randomly selected urban road segments for a typical weekday and a weekend. The considered road segment attribute data are length of the road segment, number of access points/intersecting links, number of pedestrian crossings, number of lanes, hourly traffic volume, hourly pedestrian volume and current posted speed limits of the selected roads. Such attribute data were collected and used as input variables in the model. Two models for weekday and weekend were developed based on the field survey data. Both models were calibrated using the neuro-fuzzy technique for optimizing the fuzzy logic model (FLM) parameters. Analyses of estimated results show that the FLM can estimate the 85th percentile speed to a reasonable level.

Paper Nr: 60
Title:

AN EXTENSIVE COMPARISON OF METRICS FOR AUTOMATIC EXTRACTION OF KEY TERMS

Authors:

Luis F. S. Teixeira, Gabriel P. Lopes and Rita A. Ribeiro

Abstract: In this paper we compare twenty language independent statistical-based metrics for key term extraction from any document collection. While some of those metrics are widely used, others were recently created. Two different document representations are considered in our experiments. One is based on words and multi-words and the other is based on word prefixes of fixed length (5 characters for the experiments made) for handling morphologically rich languages, namely Portuguese and Czech. English is also experimented, as a non-morphologically rich language. Results are manually evaluated and agreement between evaluators is assessed using k-Statistics. The metrics based on Tf-Idf and Phi-square proved to have higher precision and recall. The use of prefix-based representation of documents enabled a significant improvement for documents written in Portuguese.

Paper Nr: 79
Title:

WHAT DO OBJECTS FEEL LIKE? - Active Perception for a Humanoid Robot

Authors:

Jens Kleesiek, Stephanie Badde, Stefan Wermter and Andreas K. Engel

Abstract: We present a recurrent neural architecture with parametric bias for actively perceiving objects. A humanoid robot learns to extract sensorimotor laws and based on those to classify eight objects by exploring their multi-modal sensory characteristics. The network is either trained with prototype sequences for all objects or just two objects. In both cases the network is able to self-organize the parametric bias space into clusters representing individual objects and due to that, discriminates all eight categories with a very low error rate. We show that the network is able to retrieve stored sensory sequences with a high accuracy. Furthermore, trained with only two objects it is still able to generate fairly accurate sensory predictions for unseen objects. In addition, the approach proves to be very robust against noise.

Paper Nr: 84
Title:

LEARNING TO PLAY K-ARMED BANDIT PROBLEMS

Authors:

Francis Maes, Louis Wehenkel and Damien Ernst

Abstract: We propose a learning approach to pre-compute K-armed bandit playing policies by exploiting prior information describing the class of problems targeted by the player. Our algorithm first samples a set of K-armed bandit problems from the given prior, and then chooses in a space of candidate policies one that gives the best average performances over these problems. The candidate policies use an index for ranking the arms and pick at each play the arm with the highest index; the index for each arm is computed in the form of a linear combination of features describing the history of plays (e.g., number of draws, average reward, variance of rewards and higher order moments), and an estimation of distribution algorithm is used to determine its optimal parameters in the form of feature weights. We carry out simulations in the case where the prior assumes a fixed number of Bernoulli arms, a fixed horizon, and uniformly distributed parameters of the Bernoulli arms. These simulations show that learned strategies perform very well with respect to several other strategies previously proposed in the literature (UCB1, UCB2, UCB-V, KL-UCB and en-GREEDY); they also highlight the robustness of these strategies with respect to wrong prior information.

Paper Nr: 96
Title:

EXPLORATORY SEARCH ON THE MOBILE WEB

Authors:

Günter Neumann and Sven Schmeier

Abstract: We present a mobile touchable application for online topic graph extraction and exploration of web content. The system has been implemented for operation on a tablet computer, i.e. an Apple iPad, and on a mobile device, i.e. Apple iPhone or iPod touch. The topics are extracted from web snippets which are determined by a standard search engine. We consider the extraction of topics as a specific empirical collocation extraction task where collocations are extracted between chunks combined with the cluster descriptions of an online clustering algorithm. Our measure of association strength is based on the pointwise mutual information between chunk pairs which explicitly takes their distance into account. These syntactically–oriented chunk pairs are then semantically ranked and filtered using the cluster descriptions. An initial user evaluation shows that this system is especially helpful for finding new interesting information on topics about which the user has only a vague idea or even no idea at all.

Paper Nr: 119
Title:

USING RELATIONS TO INTERPRET ANAPHORA

Authors:

Parma Nand and Wai Yeap

Abstract: In this paper we present a novel framework for resolving bridging anaphora. The new framework is based on the core set of relations that have been used to describe an entirely different linguistic process, the process of generating a compound noun from two different nouns. We argue that the linguistic processes of compound noun generation and the use of NP anaphora are alike hence have to use the same relational framework. We validated this hypothesis by using human annotators to interpret indirect anaphora from naturally occurring discourses. The annotators were asked to classify the relations between anaphor-antecedent pairs into relation types that have been previously used to describe the relations between a modifier and the head noun of a compound noun. We obtained very encouraging results with a Fleiss’s k value of 0.66 for inter-annotation agreement.

Paper Nr: 125
Title:

BUILDING A TIME SERIES ACTION NETWORK FOR EARTHQUAKE DISASTER

Authors:

The-Minh Nguyen, Takahiro Kawamura, Yasuyuki Tahara and Akihiko Ohsuga

Abstract: Since there is 87% of chance of an approximately 8.0-magnitude earthquake occurring in the Tokai region of Japan within the next 30 years; we are trying to help computers to recommend suitable action patterns for the victims if this massive earthquake happens. For example, the computer will recommend “what should do to go to a safe place”, “how to come back home”, etc. To realize this goal, it is necessary to have a collective intelligence of action patterns, which relate to the earthquake. It is also important to let the computers make a recommendation in time, especially in this kind of emergency situation. This means these action patterns should to be collected in real-time. Additionally, to help the computers understand the meaning of these action patterns, we should build the collective intelligence based on web ontology language (OWL). However, the manual construction of the collective intelligence will take a large cost, and it is difficult in the emergency situation. Therefore, in this paper, we first design a time series action network. We then introduce a novel approach, which can automatically collects the action patterns from Twitter for the action network in realtime. Finally, we propose a novel action-based collaborative filtering, which predicts missing activity data, to complement this action network.

Paper Nr: 127
Title:

BOCHICA: A MODEL-DRIVEN FRAMEWORK FOR ENGINEERING MULTIAGENT SYSTEMS

Authors:

Stefan Warwas, Klaus Fischer, Matthias Klusch and Philipp Slusallek

Abstract: Modeling real world agent-based systems is a complex endeavour. An ideal domain specific agent modeling language would be tailored to a certain application domain (e.g. virtual worlds) as well as to the target execution environment (e.g. a legacy virtual reality platform). This includes the use of specialized domain concepts, information models, software languages (e.g. query languages for reasoning about an agent’s knowledge), as well as custom views and diagrams for designing the system. At the same time it is desirable to reuse application domain independent model artifacts such as interaction protocols (e.g. auction protocols) or goal/plan decompositions of a certain problem domain that already proved their use in similar scenarios. Current agent modeling languages cover the core concepts of multiagent systems but are neither thought to be customized for a certain application domain nor to be extended by external researchers with new or alternative AI and agent concepts. In this paper we propose a model-driven framework for engineering multiagent systems, called BOC HI C A, which is based on a platform independent core modeling language and can be tailored through several extension interfaces to the user’s needs. The framework leverages the reuse of existing design patterns and reduces development time and costs for creating application domain specific modeling solutions. We evaluated our approach on a distributed semantic web based execution platform for virtual worlds.

Paper Nr: 133
Title:

A COMBINED UNIFORM AND HEURISTIC SEARCH ALGORITHM FOR MAINTAINING SHORTEST PATHS ON FULLY DYNAMIC GRAPHS

Authors:

Sandro Castronovo, Björn Kunz and Christian Müller

Abstract: Shortest-path problems on graphs have been studied in depth in Artificial Intelligence and Computer Science. Search on dynamic graphs, i.e. graphs that can change their layout while searching, receives plenty of attention today – mostly in the planning domain. Approaches often assume global knowledge on the dynamic graph, i.e. that topology and dynamic operations are known to the algorithm. There exist use-cases however, where this assumption cannot be made. In vehicular ad-hoc networks, for example, a vehicle is only able to recognize the topology of the graph within wireless network transmission range. In this paper, we propose a combined uniform and heuristic search algorithm, which maintains shortest paths in highly dynamic graphs under the premise that graph operations are not globally known.

Paper Nr: 136
Title:

DISTANCE FEATURES FOR GENERAL GAME PLAYING AGENTS

Authors:

Daniel Michulke and Stephan Schiffel

Abstract: General Game Playing (GGP) is concerned with the development of programs that are able to play previously unknown games well. The main problem such a player is faced with is to come up with a good heuristic evaluation function automatically. Part of these heuristics are distance measures used to estimate, e.g., the distance of a pawn towards the promotion rank. However, current distance heuristics in GGP are based on too specific detection patterns as well as expensive internal simulations, they are limited to the scope of totally ordered domains and/or they apply a uniform Manhattan distance heuristics regardless of the move pattern of the object involved. In this paper we describe a method to automatically construct distance measures by analyzing the game rules. The presented method is an improvement to all previously presented distance estimation methods, because it is not limited to specific structures, such as, Cartesian game boards. Furthermore, the constructed distance measures are admissible. We demonstrate how to use the distance measures in an evaluation function of a general game player and show the effectiveness of our approach by comparing with a state-of-the-art player.

Paper Nr: 152
Title:

EXTRACTING TOPOLOGICAL INFORMATION FROM GRID MAPS FOR ROBOT NAVIGATION

Authors:

David Portugal and Rui P. Rocha

Abstract: In many robotic navigation-related tasks, abstracting the environment where mobile robots carry out some mission can be of a great benefit. In particular, extracting a simple topological graph-like representation from a more complex and detailed metric map is often required for path-planning and navigation. In this work, an approach to perform such extraction in grid maps is presented. The focus is not only on obtaining a diagram or visual representation of possible paths, but also to propose a new way to obtain graph data information related to the connectivity of the environment that can be passed to robots or to a centralized planner, in order to assist the navigation task. The approach proposed is based on image processing techniques. Simulation results prove its simplicity, accuracy and efficiency.

Paper Nr: 155
Title:

NEW REASONING FOR TIMELINE BASED PLANNING - An Introduction to J-TRE and its Features

Authors:

Riccardo De Benedictis and Amedeo Cesta

Abstract: Time and resource reasoning are crucial aspects for modern planners to succeed in several real world domains. A quite natural way to deal with such reasoning is to use timeline based representations that have been exploited in several application-oriented planners. The search aspects of those planners still remain a “black art” for few experts of such particular approach. This paper proposes a new model to conduct search with timelines. It starts from the observation that current timeline based planners spend most search time in doing blind constraint reasoning and explores a different hybrid model to represent and reason on timelines that may overcome such computational burden.

Paper Nr: 164
Title:

A TRACTABLE FORMALISM FOR COMBINING RECTANGULAR CARDINAL RELATIONS WITH METRIC CONSTRAINTS

Authors:

Angelo Montanari, Isabel Navarrete, Guido Sciavicco and Alberto Tonon

Abstract: Knowledge representation and reasoning in real-world applications often require to integrate multiple aspects of space. In this paper, we focus our attention on the so-called Rectangular Cardinal Direction calculus for qualitative spatial reasoning on cardinal relations between rectangles whose sides are aligned to the axes of the plane. We first show how to extend a tractable fragment of such a calculus with metric constraints preserving tractability. Then, we illustrate how the resulting formalism makes it possible to represent available knowledge on directional relations between rectangles and to derive additional information about them, as well as to deal with metric constraints on the height/width of a rectangle or on the vertical/horizontal distance between rectangles.

Paper Nr: 176
Title:

ON UNSUPERVISED NEAREST-NEIGHBOR REGRESSION AND ROBUST LOSS FUNCTIONS

Authors:

Oliver Kramer

Abstract: In many scientific disciplines structures in high-dimensional data have to be detected, e.g., in stellar spectra, in genome data, or in face recognition tasks. We present an approach to non-linear dimensionality reduction based on fitting nearest neighbor regression to the unsupervised regression framework for learning of lowdimensional manifolds. The problem of optimizing latent neighborhoods is difficult to solve, but the UNN formulation allows an efficient strategy of iteratively embedding latent points to fixed neighborhood topologies. The choice of an appropriate loss function is relevant, in particular for noisy, and high-dimensional data spaces. We extend unsupervised nearest neighbor (UNN) regression by the e-insensitive loss, which allows to ignore residuals under a threshold defined by e. In the experimental part of this paper we test the influence of e on the final data space reconstruction error, and present a visualization of UNN embeddings on test data sets.

Paper Nr: 180
Title:

A METHODOLOGY FOR CREATING INTELLIGENT WHEELCHAIR USERS’ PROFILES

Authors:

Brígida Mónica Faria, Sérgio Vasconcelos, Luis Paulo Reis and Nuno Lau

Abstract: Intelligent Wheelchair (IW) is a new concept aiming to allow higher autonomy to people with lower mobility such as disabled or elderly individuals. Some of the more recent IWs have a multimodal interface, enabling multiple command modes such as joystick, voice commands, head movements, or even facial expressions. In these IW it may be very useful to provide the user with the best way of driving it through an adaptive interface. This paper describes the foundations for creating a simple methodology for extracting user profiles, which can be used to adequately select the best IW command mode for each user. The methodology is based on an interactive wizard composed by a flexible set of simple tasks presented to the user, and a method for extracting and analyzing the user’s execution of those tasks. The results achieved showed that it is possible to extract simple user profiles, using the proposed method. Thus, the approach may be further used to extract more complete user profiles, just by extending the set of tasks used, enabling the adaptation of the IW interface to each user’s characteristics.

Paper Nr: 211
Title:

MERGING SUCCESSIVE POSSIBILITY DISTRIBUTIONS FOR TRUST ESTIMATION UNDER UNCERTAINTY IN MULTI-AGENT SYSTEMS

Authors:

Sina Honari, Brigitte Jaumard and Jamal Bentahar

Abstract: In social networks, estimation of the degree of trustworthiness of a target agent through the information acquired from a group of advisor agents, who had direct interactions with the target agent, is challenging. The estimation gets more difficult when, in addition, there is some uncertainty in both advisor and target agents’ trust. The uncertainty is tackled when (1) the advisor agents are self-interested and provide misleading accounts of their past experiences with the target agents and (2) the outcome of each interaction between agents is multi-valued. In this paper, we propose a model for such an evaluation where possibility theory is used to address the uncertainty of an agent’s trust. The trust model of a target agent is then obtained by iteratively merging the possibility distributions of: (1) the trust of the estimator agent in its advisors, and (2) the trust of the advisor agents in a target agent. Extensive experiments validate the proposed model.

Paper Nr: 247
Title:

THE DERIVATIVE MODEL APPROACH TO IMPROVING ICT USABILITY

Authors:

Ritch Macefield

Abstract: This paper describes the novel “Derivative Model approach” to improving the usability of ICT systems, along with a formal usability study to prove the concept of this approach. This approach is grounded in, and makes contemporary, successful research carried out in the 1980s that applied thinking around conceptual and mental models to the field of Human Computer Interaction (HCI). The study found initial evidence that this approach might significantly improve usability in terms of task effectiveness but not in terms of task efficiency. The study also found evidence that the benefits of the approach might improve along with task complexity.

Paper Nr: 251
Title:

COMPONENT & SERVICE-BASED AGENT SYSTEMS: SELF-OSGI

Authors:

Mauro Dragone

Abstract: This paper proposes the adoption of the Belief- Desire-Intention (BDI) agent model for the construction of component & service-based software systems with self-configuring, self-healing, self-optimizing, and self protecting (self-*) properties. It examines component & service, and agent technologies, and shows how to build a component & service-based framework with agent-like autonomous features. This paper illustrates the design of one such framework, Self-OSGi, built over Java technology from the Open Service Gateway Initiative (OSGi). The use of the new framework is illustrated and tested with a simulated robotic application and with a dynamic service-selection example.

Short Papers
Paper Nr: 28
Title:

EXPLORING THE POTENTIAL FOR USING ARTIFICIAL INTELLIGENCE TECHNIQUES IN POLICE REPORT ANALYSIS - A Design Research Approach

Authors:

Fredrik Bengtsson, Amadeus Hein and Carl Magnus Olsson

Abstract: Storing digital data is increasingly affordable and attractive for many organizations, thus allowing longitudinal postum analysis of events and for identifying trends that may hold interest for predicting future scenarios. Results of manual data analysis suffer from high time consumption and human error due to the complexity or volume of data. Responding to this, our study explores advances in artificial intelligence techniques by presenting experiences from the iterative development of a prototype that assists intelligence officers in identifying trends in serial crimes. This study contributes by illustrating the first steps that may be taken towards diffusing advances in artificial intelligence into a practice area serving the general public.

Paper Nr: 31
Title:

EVALUATION OF DATABASE TECHNOLOGIES FOR USAGE IN DYNAMIC DATA MODELS - A Comparison of Relational, Document Oriented and Graph Oriented Data Models

Authors:

Alexander Wendt, Benjamin Dönz, Stephan Mantler, Dietmar Bruckner and Alexander Mikula

Abstract: Database technologies are evaluated in respect to their performance in model extension, data integration, data access, querying and distributed data management. The structure of the data sources is partially unknown. Additional value is gained combination of data sources. Data models for a relational, a document and a graph oriented database are compared showing strengths and weaknesses of each data model.

Paper Nr: 33
Title:

TOWARDS AVERAGE-CASE ALGORITHMS FOR ABSTRACT ARGUMENTATION

Authors:

Samer Nofal, Paul Dunne and Katie Atkinson

Abstract: Algorithms for abstract argumentation are created without extensive consideration of average-case analysis. Likewise, thorough empirical studies have been rarely implemented to analyze these algorithms. This paper presents average-case methods in the context of value-based argumentation frameworks. These methods solve decision problems related to arguments’ acceptability. Experiments have shown indications of an improved average-case behavior in comparison to the naive ones.

Paper Nr: 34
Title:

CATEGORIZATION OF SIMILAR OBJECTS USING BAG OF VISUAL WORDS AND SUPPORT VECTOR MACHINES

Authors:

Przemysław Górecki, Piotr Artiemjew, Paweł Drozda and Krzysztof Sopyła

Abstract: This paper studies the problem of visual subcategorization of objects within a larger category. Such categorization seems more challenging than categorization of objects from visually distinctive categories, previously presented in the literature. The proposed methodology is based on ”Bag of Visual Words” using Scale-Invariant Feature Transform (SIFT) descriptors and Support Vector Machines (SVM). We present the results of the experimental session, both for categorization of visually similar and visually distinctive objects. In addition, we attempt to empirically identify the most effective visual dictionary size and the feature vector normalization scheme.

Paper Nr: 41
Title:

A RECONSTRUCTION OF ABSTRACT ARGUMENTATION ADMISSIBLE SEMANTICS INTO DEFAULTS AND ANSWER SETS PROGRAMMING

Authors:

Farid Nouioua and Vincent Risch

Abstract: Given a default theory, we first show that the justified extensions of this theory characterize the maximal conflict-free sets of the corresponding abstract argumentation framework such as defined by Dung. We then show how to specialize justified extensions in order to represent admissible (and hence preferred and stable) extensions inside default theories. Relying on the correspondance of justified extensions with i-answer sets on one hand, on the semi-monotonic character of justified extensions on the other hand, we then show that any admissible (or preferred) set of arguments of the initial argumentation framework can be directly computed from the i-answer sets of the equivalent logic program. Eventually, this allows us to consider the addition of integrity constraints with whom the admissible sets are filtered from each i-answer set.

Paper Nr: 50
Title:

A FRAMEWORK FOR QUALITATIVE MULTI-CRITERIA PREFERENCES

Authors:

Wietske Visser, Reyhan Aydoğan, Koen V. Hindriks and Catholijn M. Jonker

Abstract: A key challenge in the representation of qualitative, multi-criteria preferences is to find a compact and expressive representation. Various frameworks have been introduced, each of which with its own distinguishing features. In this paper we introduce a new representation framework called qualitative preference systems (QPS), which combines priority, cardinality and conditional preferences. Moreover, the framework incorporates knowledge that serves two purposes: to impose (hard) constraints, but also to define new (abstract) concepts. In short, QPS offers a rich and practical representation for qualitative, multi-criteria preferences.

Paper Nr: 57
Title:

A NOVEL STRUCTURE FOR REALIZING GOAL-DIRECTED BEHAVIOR

Authors:

Cem Yucelgen, Yusuf Kuyumcu and N. Serap Sengor

Abstract: Intelligent organisms complete goal-directed behaviour by accomplishing a series of cognitive process. Inspired from these cognitive processes, in this work, a novel structure composed of Adaptive Resonance Theory and an Action Selection module is introduced. This novel structure is capable of recognizing task relevant patterns and choosing task relevant actions to complete goal-directed behavior. In order to construct these task relevant choices the parameters of the system are modified by Reinforcement Learning. Thus the proposed structure is capable of modifying its choices and evaluates the outcome of these choices. In order to show the efficiency of the proposed structure word hunting task is solved.

Paper Nr: 58
Title:

EFFICIENT TOLERANT PATTERN MATCHING WITH CONSTRAINT ABSTRACTIONS IN DESCRIPTION LOGIC

Authors:

Carsten Elfers, Stefan Edelkamp and Otthein Herzog

Abstract: In this paper we consider efficiently matching logical constraint compositions called patterns by introducing a degree of satisfaction. The major advantage of our approach to other soft pattern matching methods is to exploit existing domain knowledge represented in Description Logic to handle imprecision in the data and to overcome the problem of an insufficient number of patterns. The matching is defined in a probabilistic framework to support post-processing with probabilistic models. Additionally, we propose an efficient complete algorithm for this kind of pattern matching, which reduces the number of inference calls to the reasoner. We analyze its worst-case complexity and compare it to a simple and to a theoretical optimal algorithm.

Paper Nr: 64
Title:

PROBABILISTIC ESTIMATION OF VAPNIK-CHERVONENKIS DIMENSION

Authors:

Przemyslaw Klesk

Abstract: We present an idea of probabilistic estimation of Vapnik-Chervonenkis dimension given a set of indicator functions. The idea is embedded in two algorithms we propose --- named A and A. Both algorithms are based on an approach that can be described as 'expand or divide and conquer'. Also, algorithms are parametrized by probabilistic constraints expressed in a form of (epsilon, delta)-precision. The precision implies how often and by how much the estimate can deviate from the true VC-dimension. Analysis of convergence and computational complexity for proposed algorithms is also presented.

Paper Nr: 72
Title:

ARTIFICIAL NEURAL NETWORKS APPLIED TO AN AGENT ACTING IN CDA AUCTIONS IN TAC

Authors:

Robson G. F. Feitosa, Dalmo D. J. Andrade, Enyo J. T. Gonçalves, Yuri A. Lacerda, Gustavo A. L. de Campos and Jerffeson T. de Souza

Abstract: This paper describes an approach based on Artificial Neural Networks to estimate the trading price of bids in CDA auctions in the TAC Classic scenario. To validate the approach, we used some methods to validate the performances of both the ANN and an agent which uses the approach. By analyzing the results of the experiments we could prove that such estimation helps improving the agent's performance.

Paper Nr: 78
Title:

EVALUATING RERANKING METHODS BASED ON LINK CO-OCCURRENCE AND CATEGORY IN WIKIPEDIA

Authors:

Yuichi Takiguchi, Koji Kurakado, Tetsuya Oishi, Miyuki Koshimura, Hiroshi Fujita and Ryuzo Hasegawa

Abstract: We often use search engines in order to find appropriate documents on the Web. However, it is often the case that we cannot find desired information easily by giving a single query. In this paper, we present a method to extract related words for the query by using the various features of Wikipedia and rank learning. We aim at developing a system to assist the user in retrieving Web pages by reranking search results.

Paper Nr: 81
Title:

CONSENSUAL DYNAMICS AND CHOQUET INTEGRAL IN AN ATTACK TREE-BASED FRAUD DETECTION SYSTEM

Authors:

Alessandro Buoni and Mario Fedrizzi

Abstract: In this paper we extend two modules of the multi-agent system FIDES (Fraud Interactive Detection Expert System) previously introduced in Buoni et al. (2011), and involving the attack tree representation of fraudulent attacks. First, assuming that the opinions of experts involved in the design of the attack tree are represented by fuzzy preference relations, we introduce a dynamical consensus model aiming at finding a shared representation of the attack tree. Second, assuming that the leaf nodes of the attack tree are attribute fuzzy numbers valued and that the attributes are interdependent, we show how to propagate the values up the tree through an aggregation process based on Choquet integral.

Paper Nr: 85
Title:

A REALIZATION OF GOAL-DIRECTED BEHAVIOR - Implementing a Robot Model Based on Cortico-Striato-Thalamic Circuits

Authors:

Berat Denizdurduran and Neslihan Serap Sengor

Abstract: Computational models of cognitive processes based on neural substrates clarify our understanding of the ongoing mechanisms during these high order processes. These models also inspire new approaches and techniques for implementing intelligent systems. Here, an implementation of goal-directed behaviour on Khepera II mobile robot will be presented. The main point of this work is to show the potential use of robot models for tasks requiring high order processes like goal-directed behaviour.

Paper Nr: 86
Title:

HIGH THROUGHPUT COMPUTING DUE TO NEAR-OPTIMAL EMERGENT MULTIAGENT COALITIONS FOR LOAD SHARING

Authors:

Leland Hovey and Mina Jung

Abstract: Grid CPU load-sharing is a subclass of computational grid resource management. Its purpose is to improve grid throughput – High Throughput Computing (HTC). The problem is load-sharing optimization state-space can be quite large. This is because of two factors: the load-sharing optimization problem is NP-complete, and a large volume of CPU-intensive loads can require thousands of Internet connected CPUs. Approximate models can find near-optimal solutions to NP-complete problems. Multiagent coalition formation (MCF) is a particular approximate game theoretic approach for these problems. We propose a new distributed MCF (DMCF) model for Grid CPU load-sharing, DMCF grouping genetic algorithm (DMCF-GGA). This paper presents the model in detail. It also compares this model with our existing model, DMCF-spatial. The comparison consists of a discussion of the models’ similarities and differences, and a comprehensive empirical evalution. The results of this study are the following: The optimization search cost of DMCF-GGA is significantly less than DMCF-spatial. DMCF-GGA has a linear relation between coalition size and search cost (for high throughput). We have found preliminary lower and upper bound estimates for the effective coalition size. We have also found the average job sizes required for the run time of DMCF-GGA to be 1% of the job execution time.

Paper Nr: 91
Title:

GENERATING PHONEMES FROM WRITTEN THAI USING LEXICAL ANALYSIS BASED ON REGULAR EXPRESSIONS

Authors:

Leo van Moergestel and John-Jules Meyer

Abstract: This document describes the approach and techniques used in software that has been developed to generate phonemes from written Thai. This software has been used to generate the phonetic transcription of Thai words in a Thai-Dutch dictionary. The most important part of this software is a lexical analyzer based on regular expressions for matching patterns in the Thai writing system. Because most software tools that use regular expressions are still based on the 7-bit ASCII set, a mapping of Thai characters to ASCII-characters has been used.

Paper Nr: 95
Title:

A CONVERSATIONAL AGENT FOR INFORMATION RETRIEVAL BASED ON A STUDY OF HUMAN DIALOGUES

Authors:

A. Loisel, G. Dubuisson Duplessis, N. Chaignaud, J-Ph. Kotowicz and A. Pauchet

Abstract: This study strives to improve medical information search in the CISMEF system by including a conversational agent to interact with the user in natural language. Experimentation has been set up to obtain human dialogues between a user dealing with medical information search and a CISMEF expert refining the request. We extend the GODIS dialogue system with dialogue strategies in order to support system digressions. A model of an artificial agent has been implemented.

Paper Nr: 101
Title:

PREDICTION OF IMMINENT SPECIES’ EXTINCTION IN EcoSim

Authors:

Meisam Hosseini Sedehi, Robin Gras and Md Sina

Abstract: The process of evolution involves the emergence and disappearance of species. Many factors affect on the survival of species. Real study of factors’ influence is particularly difficult due to the complex interaction between them. An individual-based model (IBM) can assist in the analysis of effective factors. In this study, using an IBM called EcoSim, we have examined the impact of some factors on the prediction of the imminent extinction. By applying some machine learning’s techniques for feature selection and classification, we have shown that demographic and genetic factors have a critical role for the prediction. Especially, paying attention to both factors can highly improve the accuracy of the species’ prediction.

Paper Nr: 105
Title:

A SAMPLING APPROXIMATION FOR LARGE-SCALE K-MEANS

Authors:

Piyaphol Phoungphol

Abstract: In data mining field, K-means clustering is an efficient method in the process of small dataset, but the time performance of K-means Clustering cannot be satisfied for the large-scale dataset due to its expensive computation and storage cost. One idea is to reduce the size of the dataset by using sampling technique. However, finding a sample data that can ideally represent entire dataset is challenging. In this paper, we propose a systematic way to find the most effective sample size for clustering problem by using techniques from statistics. The experimental results on several real-world datasets show that sampling with effective size makes clustering much faster, in which up to 96% of the running time was saved, while still yielding excellent clustering results.

Paper Nr: 118
Title:

INTERACTIVE EVOLVING RECURRENT NEURAL NETWORKS ARE SUPER-TURING

Authors:

Jérémie Cabessa

Abstract: We consider a model of evolving recurrent neural networks where the synaptic weights can change over time, and we study the computational power of such networks in a basic context of interactive computation. In this framework, we prove that both models of rational- and real-weighted interactive evolving neural networks are computationally equivalent to interactive Turing machines with advice, and hence capable of super-Turing capabilities. These results support the idea that some intrinsic feature of biological intelligence might be beyond the scope of the current state of artificial intelligence, and that the concept of evolution might be strongly involved in the computational capabilities of biological neural networks. It also shows that the computational power of interactive evolving neural networks is by no means influenced by nature of their synaptic weights.

Paper Nr: 132
Title:

A GRAPH-SEARCH APPROACH ON RESOURCE-CONSTRAINED SCHEDULING PROBLEMS AND ITS APPLICATION TO ADVANCED DRIVER ASSISTANCE SYSTEMS

Authors:

Christoph Endres and Christian Müller

Abstract: In this paper we present a problem which is a variation of the resource-constrained project scheduling problem and a graph-based approach to solve it. The problem is defined as resource-constrained scheduling problem (RCSP). Particularly, we apply the approach to the problem of scheduling a large number of driver warnings based on car-to-car communication (also known as cooperative vehicles). Data is presented from the project SIMTD , a large-scale field test in the area of the Hessian city of Frankfurt, where 120 cars participate in a number of controlled tests in three main scenarios: the rural road scenario (basic complexity), the motorway scenario (intermediate complexity), and the urban road scenario (high complexity). We argue that, due to its run-time behaviour, our graph-based approach is suitable for the particular application domain at hand. Results are presented in terms of quality of the solution (conflict resolution), runtime behavior and pruning effects to the size of the search tree. In addition to the scenarios derived from the actual field test, a hyper-real stress test is presented to demonstrate the performance of our solution.

Paper Nr: 150
Title:

HANDLING PREFERENCES IN ARGUMENTATION FRAMEWORKS WITH NECESSITIES

Authors:

Imane Boudhar, Farid Nouioua and Vincent Risch

Abstract: Argumentation theory is a promising reasoning model which is more and more used to solve various key problems in artificial intelligence. Most of the developments in this domain are based on extended versions of Dung argumentation frameworks (AFs). In this paper, we propose an argumentation model that extends Dung AFs by two additional aspects : a necessity relation that represents a particular positive interaction between arguments and a preference relation that allows to represent arguments that do not have the same strength.

Paper Nr: 165
Title:

ON COMPLEXITY OF VERIFYING NESTED WORKFLOWS WITH EXTRA CONSTRAINTS

Authors:

Roman Barták

Abstract: Workflow is a formal description of a process or processes. There exist tools for interactive and visual editing of workflows such as the FlowOpt Workflow Editor. During manual editing of workflows, it is common to introduce flaws such as cycles of activities. Hence one of the required features of workflow management tools is verification of workflows, which is a problem of deciding whether the workflow describes processes that can be realized in practice. In this paper we deal with the theoretical complexity of verifying workflows with a nested structure and with extra constraints. The nested structure forces users to create valid workflows but as we shall show, introduction of extra causal, precedence, and temporal synchronization constraints makes the problem of deciding whether the workflow represents a realizable process hard. In particular, we will show that this problem is NP-complete.

Paper Nr: 188
Title:

CLASSIFICATION OF DEFORMABLE GEOMETRIC SHAPES - Using Radial-Basis Function Networks and Ring-wedge Energy Features

Authors:

El-Sayed M. El-Alfy

Abstract: This paper describes a system for automatic classification of geometric shapes based on radial-basis function (RBF) neural networks even in the existence of shape deformation. The RBF network model is built using ring-wedge energy features extracted from the Fourier transform of the spatial images of geometric shapes. Using a benchmark dataset, we empirically evaluated and compared the performance of the proposed approach with two other standard classifiers: multi-layer perceptron neural networks and decision trees. The adopted dataset has four geometric shapes (ellipse, triangle, quadrilateral, and pentagon) which may have deformations including rotation, scaling and translation. The empirical results showed that the proposed approach significantly outperforms the other two classification methods with classification error rate around 3.75% on the testing dataset using 5-fold stratified cross validation.

Paper Nr: 193
Title:

INCIDENT AND PROBLEM MANAGEMENT USING A SEMANTIC WIKI-ENABLED ITSM PLATFORM

Authors:

Frank Kleiner, Andreas Abecker and Marco Mauritczat

Abstract: IT Service Management (ITSM) is concerned with providing IT services to customers. In order to improve the provision of services, ITSM frameworks (e.g., ITIL) mandate the storage of all IT-relevant information in a central Configuration Management System (CMS). This paper describes our Semantic Incident and Problem Analyzer, which builds on a SemanticWiki-based Configuration Management System. The Semantic Incident and Problem Analyzer assists IT-support personnel in tracking down the causes of incidents and problems in complex IT landscapes. It covers two use cases: (1) by analyzing the similarities between two or more system configurations with problems, it suggests possible locations of the problem; (2) by analyzing changes over time of a component with a problem, possible configuration changes are reported which might have led to the problem.

Paper Nr: 196
Title:

TRAINING RADIAL BASIS FUNCTION NETWORKS BY GENETIC ALGORITHMS

Authors:

Juliano F. da Mota, Paulo H. Siqueira, Luzia V. de Souza and Adriano Vitor

Abstract: One of the issues of modeling a RBFNN - Radial Basis Function Neural Network consists of determining the weights of the output layer, usually represented by a rectangular matrix. The inconvenient characteristic at this stage it’s the calculation of the pseudo-inverse of the activation values matrix. This operation may become computationally expensive and cause rounding errors when the amount of variables is large or the activation values form an ill-conditioned matrix so that the model can misclassify the patterns. In our research, Genetic Algorithms for continuous variables determines the weights of the output layer of a RBNN and we’ve made a comparsion with the traditional method of pseudo-inversion. The proposed approach generates matrices of random normally distributed weights which are individuals of the population and applies the Michalewicz’s genetic operators until some stopping criteria is reached. We’ve tested four classification patterns databases and an overall mean accuracy lies in the range 91–98%, in the best case and 58–63%, in the worse case.

Paper Nr: 199
Title:

WHEN YOU SAY (DCOP) PRIVACY, WHAT DO YOU MEAN? - Categorization of DCOP Privacy and Insights on Internal Constraint Privacy

Authors:

Tal Grinshpoun

Abstract: Privacy preservation is a main motivation for using the DCOP model and as such, it has been the subject of comprehensive research. The present paper provides for the first time a categorization of all possible DCOP privacy types. The paper focuses on a specific type, internal constraint privacy, which is highly relevant for models that enable asymmetric payoffs (PEAV-DCOP and ADCOP). An analysis of the run of two algorithms, one for ADCOP and one for PEAV, reveals that both models lose some internal constraint privacy.

Paper Nr: 206
Title:

BLUEPRINTS FOR SUCCESS - Guidelines for Building Multidisciplinary Collaboration Teams

Authors:

Sidath Gunawardena and Rosina O. Weber

Abstract: Finding collaborators to engage in academic research is a challenging task, especially when the collaboration is multidisciplinary in nature and collaborators are needed from different disciplines. This paper uses evidence of successful multidisciplinary collaborations, funded proposals, in a novel way: as an input for a method of recommendation of multidisciplinary collaboration teams. We attempt to answer two questions posed by a collaboration seeker: what disciplines provide collaboration opportunities and what combinations of characteristics of collaborators have been successful in the past? We describe a two-step recommendation framework where the first step recommends potential disciplines with collaboration potential based on current trends in funding. The second step recommends characteristics for a collaboration team that are consistent with past instances of successful collaborations. We examine how this information source can be used in a case-based recommender system and present a preliminary validation of the system using statistical methods.

Paper Nr: 215
Title:

FEATURE VECTOR APPROXIMATION BASED ON WAVELET NETWORK

Authors:

Mouna Dammak, Mahmoud Mejdoub, Mourad Zaied and Chokri Ben Amar

Abstract: Image classification is an important task in computer vision. In this paper, we propose a new image representation based on local feature vectors approximation by the wavelet networks. To extract an approximation of the feature vectors space, a Wavelet Network algorithm based on fast Wavelet is suggested. Then, the K-nearest neighbor (K-NN) classification algorithm is applied on the approximated feature vectors. The approximation of the feature space ameliorates the feature vector classification accuracy.

Paper Nr: 219
Title:

OPTIMIZED DELIVERY OF ON-LINE ADVERTISEMENTS - A Linear Programming Approach to the Delivery of On-line Advertisements

Authors:

Fabrizio Caruso and Giovanni Giuffrida

Abstract: We find an optimal strategy for displaying advertisements in given locations at given times under some realistic dynamic constraints. Our goal is to maximize the total profit produced by the impressions, which depends on profit-generating events such as the impressions themselves and the ensuing clicks. We must take into account the possibility that the constraints could change over time in a way that cannot always be foreseen.

Paper Nr: 222
Title:

TOWARDS AN INTELLIGENT QUESTION-ANSWERING SYSTEM - State-of-the-art in the Artificial Mind

Authors:

Andrej Gardoň and Aleš Horák

Abstract: This paper discusses three up-to-date Artificial Intelligence (AI) projects focusing on the question-answering problem – Watson, Aura and True Knowledge. Besides a quick introduction to the architecture of systems, we show examples revealing their shortages. The goal of the discussion is the necessity of a module that acquires knowledge in a meaningful way and isolation of the Mind from natural language. We introduce an idea of the GuessME! system that, by a playing simple game, deepens its own knowledge and brings new light to the question-answering problem.

Paper Nr: 227
Title:

HUMANS DIFFER: SO SHOULD MODELS - Systematic Differences Call for Per-subject Modeling

Authors:

Wolfgang Heidl, Stefan Thumfart and Christian Eitzinger

Abstract: While machine learning is most often learning from humans, training data is still considered to originate from a uniform black box. Under this paradigm systematic differences in training provided by multiple subjects are translated into unavoidable modeling error. When trained on a per-subject basis those differences indeed translate to systematic differences in the resulting model structure. We feel that the goal of creating humanlike capabilities or behavior in artificial systems can only be achieved if the diversity of humans is adequately considered.

Paper Nr: 232
Title:

LEARNING HIGH-LEVEL BEHAVIORS FROM DEMONSTRATION THROUGH SEMANTIC NETWORKS

Authors:

Benjamin Fonooni, Thomas Hellström and Lars-Erik Janlert

Abstract: In this paper we present an approach for high-level behavior recognition and selection integrated with a low-level controller to help the robot to learn new skills from demonstrations. By means of Semantic Network as the core of the method, the robot gains the ability to model the world with concepts and relate them to low-level sensory-motor states. We also show how the generalization ability of Semantic Networks can be used to extend learned skills to new situations.

Paper Nr: 237
Title:

USING MOBILE DEVICES FOR TOPOLOGICAL INFERENCE OF INDOOR ENVIRONMENTS

Authors:

Marco Paiva, Marcelo Petry and Rosaldo J. F. Rossetti

Abstract: Nowadays location systems are used within a large variety of applications. The application of these systems within indoor environments is already provided by several solutions. However, the need for high accuracy within these environments to pursue such purpose implies the use of specific infrastructures designed towards it. Our project tries to meet the requirements for a simple, low-cost, and scalable location system through different approaches. The main idea of it is to re-construct topological maps of indoor spaces through location estimation, i.e. using off-the-shelf technologies. We try to perform location estimations and then re-create the indoor maps as topological maps as a means of reducing the precision requirements other systems have, and develop a scalable and highly applicable system using sensors featuring mobile devices.

Paper Nr: 238
Title:

TOWARD SOPHISTICATED AGENT-BASED UNIVERSES - Statements to Introduce some Realistic Features into Classic AI/RL Problems

Authors:

Filipo Studzinski Perotto

Abstract: In this paper we analyze some common simplifications present in the traditional AI / RL problems. We argue that only facing particular conditions, often avoided in the classic statements, will allow the overcoming of the actual limits of the science, and the achievement of new advances in respect to realistic scenarios. This paper does not propose any paradigmatic revolution, but it presents a compilation of several different elements proposed more or less separately in recent AI research, unifying them by some theoretical reflections, experiments and computational solutions. Broadly, we are talking about scenarios where AI needs to deal with true situatedness agency, providing some kind of anticipatory learning mechanism to the agent in order to allow it to adapt itself to the environment.

Paper Nr: 244
Title:

DATA ACCESS THROUGH A DYNAMIC DATA MODEL - A Concept for Accessing Heterogenic Data Structures in RDF Databases

Authors:

Alexander Wendt, Benjamin Dönz and Dietmar Bruckner

Abstract: This paper introduces an alternative method for using ontologies to create a dynamic data model for RDF databases or other schema-less databases. The main challenge is how to continuously adapt the data model and its queries to new data, which may be imported with any given structure.

Paper Nr: 245
Title:

KNOWLEDGE-DRIVEN HARMONIZATION MODEL FOR TONAL MUSIC

Authors:

Mariusz Rybnik and Władysław Homenda

Abstract: The paper proposes an approach to an automatic harmonization of musical work, and is based on the knowledge of music theory. It may be described as knowledge-based, being in contrast to a data-driven approach, that extracts relationships from examples. Our approach emphasizes universality, understood as the possibility of direct model modifications in order to obtain varied harmony characteristics (as for example a complicated and unusual harmony, or a simple harmony using only a small subset of harmonic functions and few modifiers). Therefore it is configurable by changing the internal parameters of harmonization mechanisms (among others: harmonic functions excitements with note pitches, note importance regarding among others horizontal position in measure and vertical position in voices structure, successions of neighboring harmonic functions), as well as importance weights attached to each of these mechanisms.

Paper Nr: 246
Title:

ALLOPHONE GROUP SELECTION FACTORS FOR POLISH SPEECH SYNTHESIS

Authors:

Bożena Kozłowska, Janusz Rafałko and Mariusz Rybnik

Abstract: The article concerns selection of allophone groups for Polish speech synthesis. It describes factors to be taken into consideration while dividing allophones into certain groups. Thus, the presentation includes classification suggested by the authors. Although the described factors regard Polish language, they may facilitate any study on similar division concerning any other language. Each language has determined specificity pronounces, therefore should choose suitable allophonic groups for the language. However precise description on what elements we should special attention give, where later problems can appear in pronunciation e.g. certainty will make easier work to persons making similar division in different languages.

Posters
Paper Nr: 12
Title:

DEVELOPING A KNOWLEDGE PROCESS QUALITY MODEL EVALUATION SYSTEM USING COMMONKADS

Authors:

Javier Andrade, Juan Ares, Rafael García, Santiago Rodríguez and Sonia Suárez

Abstract: Several knowledge management maturity models have been proposed in the last years. These models are used to evaluate the quality of knowledge management practices in the organizations. One of these models is the Knowledge Process Quality Model, which has five maturity levels. The acquisition of a high maturity level is usually expensive due to the evaluations and improvement processes that are often required for a positive final decision. With the aim of minimizing these costs, this paper proposes a Knowledge-Based System that tries to check if the company currently stands in compliance with a given KPQM maturity level. The actual evaluation process starts only if the system output is positive. This approach implies an important cost reduction by avoiding negative evaluations. The design of the system is based on the CommonKADS methodology, and its implementation was carried out with the Clips tool.

Paper Nr: 15
Title:

COMPLEX EXPONENT MOMENTS FFT ALGORITHM AND ITS APPLICATION

Authors:

ZiLiang Ping and YongJing Jiang

Abstract: A fast and accurate algorithm for computation of multi-distorted invariant Complex Exponent Moments (CEMs) is presented in the paper. An image function in polar coordinate system, , was divided into 2-D discrete image matrix in which the radial variables on lines and angle variables on columns. 2-D Fast Fourier Transform (FFT) was excuted for the matrix and the Complex Exponent Moments (CEMs) can be obtained. The multi-distorted invariance and the excellent performance of Complex Exponent Moments (CEMs) were demonstrated. The Complex Exponent Moments (CEMs) were applied in human face recognition.

Paper Nr: 17
Title:

HYBRIDIZING ANT COLONY SYSTEMS AND TABU SEARCH FOR A VEHICLE ROUTING PROBLEM WITH TIME WINDOWS

Authors:

Juan Carlos Figueroa D., M. Angélica Pinninghoff J. and Ricardo Contreras A.

Abstract: This paper describes a new approach for solving the vehicle routing problem that considers time windows (VRPTW). The proposal presents a hybrid approach that takes into account an ant colony system ACS and the meta-heuristic Tabu Search. Hybridizing meta-heuristics is one of the alternatives used for solving VRPTWs. Authors believe that a hybrid approach, with ACS providing good initial solutions for the Tabu Search heuristic can help to get acceptable final solutions. Tabu Search plays the role of keeping diversity in the population considered while searching a solution. The proposal was implemented and tested, and results obtained are discussed in the final part of this presentation.

Paper Nr: 32
Title:

AN AUTOMATIC APPROACH TO FEATURE EXTRACTION

Authors:

Manuela Angioni and Franco Tuveri

Abstract: The pervasive diffusion of social networks as common way to communicate and share information is becoming a valuable resource for analysts and decision makers. Reviews are used every day by common people or by companies who need to make decisions. It is evident that even the opinion monitoring is essential for listening to and taking advantage of the conversations of possible customers in a decision making process. Opinion Mining is a way to analyse opinions related to specific topics: products, services, tourist locations, etc. In this paper we propose an automatic approach to the extraction of feature terms, applying our experience in the semantic analysis of textual resources to Opinion Mining task and performing a contextualisation by means of semantic categorisation, and by a set of qualities associated to the sense expressed by adjectives and adverbs.

Paper Nr: 48
Title:

RECOGNIZING EMOTIONS IN SHORT TEXTS

Authors:

Ovidiu Şerban, Alexandre Pauchet and Horia F. Pop

Abstract: Affective Computing is one of the fields used by computer scientists to transfer the knowledge from psychology to the Human-Machine Interaction research field, while offering a better understanding on Human to Human Interaction. Several approaches have been tried in the area, like text and voice techniques to discover emotions. Since the classification problem is not typical, the difficulty is increased by the fuzziness of the data sets. Our paper proposes a method that aims at a better recognition rate of human emotions. Our model is based on the Self-Organizing Maps algorithm and it can be applied on short texts with a high degree of affective content. It is designed to be integrated into an Embodied Conversational Agent.

Paper Nr: 49
Title:

TOWARD A GOAL-BASED MISSION PLANNING CAPABILITY - Using PDDL Based Automated Planners

Authors:

John Bookless and Glenn Callow

Abstract: This paper proposes a generic goal-based mission planning framework which provides an integration environment to support evaluation of existing planning and task assignment technologies. The framework facilitates planning across a team of heterogeneous assets with a distributed capability for generating plans to collaboratively achieve goals. A human operator assigns a team with a top-level goal which the framework then decomposes into a list of tasks that can either be tackled by an individual asset or collectively by a sub-team of assets with the appropriate capabilities. Each asset can generate individual plans with knowledge of the current world state and a goal state. A selection of candidate planners are investigated using the framework including a Hierarchical Task Network (HTN) Planner for goal decomposition and a Partial Ordered PDDL (Planning Domain Definition Language) Planner for action-based plan generation. The developed framework is applied to a search-and-rescue scenario requiring a team of UAVs (Unmanned Aerial Vehicle) to search a specified area of operation.

Paper Nr: 52
Title:

VULNERAPEDIA: SECURITY KNOWLEDGE MANAGEMENT WITH AN ONTOLOGY

Authors:

Francisco J. Blanco, José Ignacio Fernández-Villamor and Carlos A. Iglesias

Abstract: Ontological engineering can do an efficient management of the security data, generating security knowledge. We use a step methodology defining a main ontology in the web application security domain. Next, extraction and integration processes translate unstructured data in quality security knowledge. Thus, we check the ontology can perform management processes involved. A social tool is implemented to wrap the knowledge in an accessible way. It opens the security knowledge to encourage people to collaboratively use and extend it.

Paper Nr: 94
Title:

INTERNALLY DRIVEN Q-LEARNING - Convergence and Generalization Results

Authors:

Eduardo Alonso, Esther Mondragón and Niclas Kjäll-Ohlsson

Abstract: We present an approach to solving the reinforcement learning problem in which agents are provided with internal drives against which they evaluate the value of the states according to a similarity function. We extend Q-learning by substituting internally driven values for ad hoc rewards. The resulting algorithm, Internally Driven Q-learning (IDQ-learning), is experimentally proved to convergence to optimality and to generalize well. These results are preliminary yet encouraging: IDQ-learning is more psychologically plausible than Q-learning, and it devolves control and thus autonomy to agents that are otherwise at the mercy of the environment (i.e., of the designer).

Paper Nr: 106
Title:

PLANNING FOR THE CONVOY MOVEMENT PROBLEM

Authors:

Anand Kumar, I. Murugeswari, Deepak Khemani and N. S. Narayanaswamy

Abstract: Convoy movement problem has significant practical applications. The problem has been attempted in many styles with varying results. We address it as an AI Search and Planning and Scheduling problem. The work focuses on modeling the convoy movement problem using PDDL and attempting a solution using existing planning methods and planners. Initial results indicated problems of scalability. To address this we propose a two stage planning process.

Paper Nr: 153
Title:

PROPOSING A SIMILARITY MEASURE IN CASE BASED REASONING FOR PRODUCTS SELECTION - An Experimental Evidence

Authors:

Fadi Amroush

Abstract: This paper presents a novel similarity measure to design a Decision Support System for products selection using Case Based Reasoning "CBR". The presented approach combines a novel local similarity measure with Nearest Neighbour Matching Function which is used as a typical evaluation function to compute the nearest-neighbour matching case in CBR. This paper suggests using this similarity measure in CBR in order design our model in products selection to help users to find the optimal product according to their preferences. The nature of this local similarity measure is to give more reality measure used by people in selecting products instead of the traditional one proposed by (Xiao-tai et al., 2004). We illustrate the significance of our proposed measure experimentally. The paper shows that our approach has been followed by about 80% of subjects.

Paper Nr: 167
Title:

CONCEPTS EXTRACTION BASED ON HTML DOCUMENTS STRUCTURE

Authors:

Rim Zarrad, Narjes Doggaz and Ezzeddine Zagrouba

Abstract: The traditional methods to acquire automatically the ontology concepts from a textual corpus often privilege the analysis of the text itself, whether they are based on a statistical or linguistic approach. In this paper, we extend these methods by considering the document structure which provides interesting information on the significances contained in the texts. Our approach focuses on the structure of the HTML documents in order to extract the most relevant concepts of a given field. The candidate terms are extracted and filtered by analyzing their occurrences in the titles and in the links belonging to the documents and by considering the used styles.

Paper Nr: 172
Title:

SMART AND INTERACTIVE FUTURE HOMES - Integration of Autonomic Computing and New HCI Methods

Authors:

Rafael Del-Hoyo, Luis Miguel Sanagustín, Carolina Benito, Isabelle Hupont and David Abadía

Abstract: Nowadays, huge R&D efforts are running on the re-invention of the Internet so that it is able to cope with future challenges, like the viral growth of the number of connected users, devices, services and user-generated contents. Today’s houses are slowly turning into a complex electronic net of devices. The increasing complexity of systems and the need for these systems to remain simple, accessible and transparent for the user, makes it necessary to research technologies that enable intelligent and autonomous computing and new ways of interacting with future home. Autonomic computing systems are those which can manage themselves given high level objectives. If we integrate autonomic computing and new interactive user mechanisms like virtual agents, we obtain the future smart homes. These houses would detect the people inside, and self-configure by personalizing the services for each user and detecting new devices plugged to the house: would self-optimize by disconnecting lights or closing doors if people aren’t present: would self-heal by controlling sensors to prevent problems related to physical and software elements; and would self-protect by identifying the current users at home, and preventing external attacks.

Paper Nr: 182
Title:

OPERATIONS ON CONVERSATIONAL MIND-GRAPHS

Authors:

Jayanta Poray and Christoph Schommer

Abstract: Mind-graphs define an associative-adaptive concept of managing information streams, like for example words within a conversation. Being composed of vertices (or cells; representing external stimuli like words) and undirected edges (or connections), mind-graphs adaptively reflect the strength of simultaneously occurring stimuli and allow a self-regulation through the interplay of an artificial ‘fever’ and ‘coldness’ (capacity problem). With respect to this, an interesting application scenario is the merge of information streams that derive from a conversation of k conversing partners. In such a case, each conversational partner has an own knowledge and a knowledge that (s)he shares with other. Merging the own (inside) and the other’s (outside) knowledge leads to a situation, where things like e.g. trust can be decided. In this paper, we extend this concept by proposing extended mind-graph operations, dealing with the merge of sub-mind-graphs and the extraction of mind-graph skeletons.

Paper Nr: 220
Title:

PLANNING GRAPH HEURISTICS FOR SOLVING CONTINGENT PLANNING PROBLEMS

Authors:

Incheol Kim and Hyunsik Kim

Abstract: In order to extract domain-independent heuristics from the specification of a planning problem, it is necessary to relax the given problem and then solve the relaxed one. In this paper, we present a new planning graph, Merged Planning Graph(MPG), and GD heuristics for solving contingent planning problems including both uncertainty about the initial state and non-deterministic action effects. MPG is a new version of the relaxed planning graph for solving the contingent planning problems. In addition to the traditional delete relaxations of deterministic actions, MPG makes the effect-merge relaxations of both sensing and non-deterministic actions. Parallel to the forward expansion of MPG, the computation of GD heuristics proceeds with analysis of interactions among goals and/or subgoals. GD heuristics estimate the minimal reachability cost to achieve the given goal set by excluding redundant action costs. Through experiments in several problem domains, we show that GD heuristics are more informative than the traditional max and additive heuristics. Moreover, in comparison to the overlap heuristics, GD heuristics require much less computational effort for extraction.

Paper Nr: 248
Title:

INTERACTIVE QUESTIONNAIRES

Authors:

Yann Veilleroy, Frédéric Hoogstoel and Luigi Lancieri

Abstract: The use of online interactive questionnaires is an interesting example of human-computer interactions mediatizing human interactions to support the emergence of collective intelligence. To better understand these interactions and their various effects, we propose to investigate the operating mode of interactive questionnaires. First, we recall what the questionnaires are made of in order to know their anatomy. Then we give two examples of interactive questionnaires: e-Brainstorming from the Orange Labs and the Real-Time Delphi, one computerization of the Delphi method.

Paper Nr: 249
Title:

COGNITIVELY MOTIVATED EPISODIC MEMORY FOR A VIRTUAL GUIDE

Authors:

Felix Rabe and Ipke Wachsmuth

Abstract: This paper describes how the guiding capabilities of a virtual agent with a belief – desire – intention cognitive architecture can be enhanced by adding an episodic memory. We describe how the theories of episodic memory and event segmentation can be applied to the architecture of our virtual agent Max, and how to create an index according to the event indexing model. Having memories of past experiences will enable our agent to have improved plans how to react in future interaction.

Paper Nr: 250
Title:

THREE DIFFERENTIAL EMOTION CLASSIFICATION BY MACHINE LEARNING ALGORITHMS USING PHYSIOLOGICAL SIGNALS - Discriminantion of Emotions by Machine Learning Algorithms

Authors:

Eun-Hye Jang, Byoung-Jun Park, Sang-Hyeob Kim and Jin-Hun Sohn

Abstract: In HCI researches, human emotion classification has done by machine learning algorithms based on physiological signals. The aim of this study is to classify three different emotional states (boredom, pain, and surprise) by 5 machine learning algorithms using features extracted from physiological signals. 200 college students participated in this experiment. The audio-visual film clips were used to provoke emotions and were tested their appropriateness and effectiveness. EDA, ECG, PPG, and SKT as physiological signals were acquired for 1 minute before each emotional state as baseline and for 1-1.5 minutes during emotional state and were analyzed for 30 seconds from the baseline and the emotional state. 23 parameters were extracted from these signals: SCL, NSCR, mean SCR, mean SKT, maximum SKT, sum of negative SKT, and sum of positive SKT, mean PPG, mean RR interval, standard deviation RR interval, mean BPM, RMSSD, NN50, percenet of NN50, SD1, SD2, CSI, CVI, LF, HF, nLF, nHF, and LF/HF ratio. For emotion classification, the difference values of each feature subtracting baseline from the emotional state were used for analysis using 5 machine learning algorithms. The result showed that an accuracy of emotion classification by SOM was lowest and SVM was highest. This could help emotion recognition studies lead to better chance to recognize various human emotions by using physiological signals. Also, it is able to be applied on human-computer interaction system for emotion detection.

Paper Nr: 252
Title:

AMBIGUOUS LEXICAL RESOURCES FOR COMPUTATIONAL HUMOR GENERATION

Authors:

Alessandro Valitutti

Abstract: The ongoing work presented here is aimed to investigate to what extent it is possible to perform a feasible use of ambiguous texts in computational humor generation. The first core of a lexical database was developed in order to collect ambiguous terms in the English lexicon. Then an exploratory use of the resource for computational humor generation was performed. Finally, three existing prototypes of humor generator were simulated in order to generate different form of humorous messages from the same lexical resource.

Area 2 - Agents

Full Papers
Paper Nr: 26
Title:

AN IDIOTYPIC NETWORK APPROACH TO TASK ALLOCATION IN THE MULTI-ROBOT DOMAIN - Use of an Artificial Immune System to Moderate the Greedy Solution

Authors:

Amanda Whitbrook, Gabriel Gainham and Wen-Hua Chen

Abstract: This paper presents and explains a set of equations for governing simultaneous task allocation in multi-robot systems and describes how they are used to construct a novel algorithm - the Idiotypic Task Allocation Algorithm (ITAA); the equations are based on Farmer's model of an idiotypic immune network but are adapted to include 2-dimensional stimulation and suppression and the use of affinity rather than concentration levels to select antibodies. This novel approach is taken to render the model suitable for simultaneous task allocation where robots must act individually; other idiotypic algorithms have only been applicable to problems where many robots are required to perform one task at a time using swarming behaviours. The paper describes the analogy between idiotypic network theory and the problem of task allocation and shows how the former can be used to increase the fitness of solutions to the latter, also discussing the types of Multi-Robot Task Allocation (MRTA) problem that might benefit from this approach. The results of applying ITTA to a number of simulated mine-clearance problems (with increasing numbers of robots and mines) are presented, and clear advantage over the greedy solution in both simple and more complex scenarios is demonstrated.

Paper Nr: 36
Title:

A NEW VARIANT OF THE MINORITY GAME - Asset Value Game and Its Extension

Authors:

Jun Kiniwa, Takeshi Koide and Hiroaki Sandoh

Abstract: A minority game (MG) is a non-cooperative iterated game with an odd population of agents who make bids whether to buy or sell. Based on the framework of MG, several kinds of games have been proposed. However, the common disadvantage in their characteristics is to neglect past actions. So we present a new variant of the MG, called an asset value game (AG), in which every agent aims to decrease a mean asset value, that is, an acquisition cost averaged through the past actions. The AG, however, is too simple to reproduce the complete market dynamics. So we further consider an improvement of AG, called an extended asset value game (ExAG), and investigate their features and obtain some results by simulation.

Paper Nr: 74
Title:

EFFICIENCY IN PERSUASION DIALOGUES

Authors:

Katie Atkinson, Priscilla Bench-Capon and Trevor Bench-Capon

Abstract: Inquiry, Persuasion and Deliberation Dialogues are all designed to transfer information between agents so that their beliefs and opinions may be revised in the light of the new information, and all make use of a similar set of speech acts. These dialogues also have significant differences. We define success conditions for some different dialogue types in this family and note the pragmatic implications of the speech acts they employ. Focusing on persuasion we consider how successful persuasion dialogues can be conducted efficiently, in terms of minimising the expected transfer of information. We observe that a strategy for efficient persuasion can be developed by considering the pragmatic implications. We present results showing that our strategy is an optimal strategy in a range of representative persuasion scenarios.

Paper Nr: 115
Title:

GAPEX: AN AGENT-BASED FRAMEWORK FOR POWER EXCHANGE MODELING AND SIMULATION

Authors:

Silvano Cincotti and Giulia Gallo

Abstract: The paper presents an agent-based framework for modeling and simulating power exchanges, the Genoa Artificial Power Exchange (GAPEX). The framework is implemented in MATLAB using the OOP paradigm, which allows one to define classes using a Java/C++ like syntax. GAPEX allows creation of artificial power exchanges where what-if analysis can be performed. GAPEX also reproduces exactly the market clearing procedure (e.g. by calculating Locational Marginal Prices based on the Italian high-voltage transmission network with its zonal subdivision) and the generation plants modeled are in direct correspondence with the real ones. Moreover, the presence of affine total cost functions for the generation plants results in payoff either positive, negative and null. This has major implications as negative reward are not generally considered by reinforcement learning algorithms. In order to overcome such limitation, an enhanced version of the Roth-Erev algorithm (i.e., that takes into account also negative payoffs) is presented and discussed. Results point out effectiveness of the proposed enhanced learning algorithm. Moreover, computational experiments performed within GAPEX point out a close agreement with historical real market data during both peak- and off-peak load hours thus confirming the direct applicability of GAPEX to model and to simulate power exchanges.

Paper Nr: 122
Title:

A SEARCH-BASED APPROACH TO ANNEXATION AND MERGING IN WEIGHTED VOTING GAMES

Authors:

Ramoni O. Lasisi and Vicki H. Allan

Abstract: Weighted voting games are classic cooperative games which provide a compact representation for coalition formation models in multiagent systems. We consider manipulation in weighted voting games via annexation and merging, which involves an agent or some agents misrepresenting their identities in anticipation of gaining more power at the expense of other agents in a game.We show that annexation and merging in weighted voting games can be more serious than as presented in the previous work. Specifically, using similar assumptions as employed in a previous work, we show that manipulators need to do only a polynomial amount of work to find a much improved power gain, and then present two search-based pseudo-polynomial algorithms that manipulators can use. We empirically evaluate our search-based method for annexation and merging. Our method is shown to achieve significant improvement in benefits for manipulating agents in several numerical experiments. While our search-based method achieves improvement in benefits of over 300% more than those of the previous work in annexation, the improvement in benefits is 28% to 45% more than those of the previous work in merging for all the weighted voting games we considered.

Paper Nr: 139
Title:

EXTENDING X-MACHINES TO SUPPORT REPRESENTATION OF SPATIAL 2-D AGENTS

Authors:

Isidora Petreska, Petros Kefalas, Marian Gheorghe and I. Stamatopoulou

Abstract: Starting with the notion of modelling biologically inspired agents, this paper focuses on their spatial characteristics. It will be demonstrated that one of the most prominent formalisms in modelling the behaviour of biological colonies, X-machines, cannot provide a neat and effective way to modelling spatial agents (i.e. agents distributed and move through a physical space). We introduce a X-machines variation that besides facilitating formal modelling, will provide grounds towards visual animation of these systems. This approach resulted into a novel progression, Spatial X-machines, without retracting the legacy characteristics of X-machines such as testing and verification strategies. Unlike other formalisms that go behind the concept of treating the agent’s behaviour as one uniform component, Spatial X-machines tend to draw a separation between different types of agent’s behaviour.

Paper Nr: 148
Title:

LET’S TALK TOPICALLY WITH ARTIFICIAL AGENTS! - Providing Agents with Humanlike Topic Awareness in Everyday Dialog Situations

Authors:

Alexa Breuing and Ipke Wachsmuth

Abstract: Spoken interactions between humans are characterized by coherent sequences of utterances assigning a thematical structure to the whole conversation. Such coherence and the success of a meaningful and flexible dialog are based on the cognitive ability to be aware of the ongoing conversational topic. This paper presents how to enable such topically coherent conversations between humans and interactive systems by emulating humanlike topic awareness in artificial agents. Therefore, we firstly automated human topic awareness on the basis of preprocessed Wikipedia knowledge and secondly transferred such computer-based awareness to a virtual agent. As a result, we contribute to improve human-agent dialogs by enabling topical talk between human and artificial conversation partners.

Paper Nr: 210
Title:

STRATEGIES FOR CHALLENGING TWO-PLAYER GAMES - Some Lessons from Iterated Traveler’s Dilemma

Authors:

Predrag T. Tošić and Philip C. Dasler

Abstract: We study the iterated version of the Traveler’s Dilemma (TD). TD is a two-player, non-zero sum game that offers plenty of incentives for cooperation. Our goal is to gain deeper understanding of iterated two-player games whose structures are far from zero-sum. Our experimental study and analysis of Iterated TD is based on a round-robin tournament we have recently designed, implemented and analyzed. This tournament involves 38 distinct participating strategies, and is motivated by the seminal work by Axelrod et al. on Iterated Prisoners Dilemma. We first motivate and define the strategies competing in our tournament, followed by a summary of the tournament results with respect to individual strategies. We then extend the performance comparisonand- contrast of individual strategies in the tournament, and carefully analyze how groups of closely related strategies perform when each such group is viewed as a “team”. We draw some interesting lessons from the analyzes of individual and team performances, and outline some promising directions for future work.

Short Papers
Paper Nr: 13
Title:

A MULTI-AGENT MODEL BASED ON RESIDUAL RESOURCES

Authors:

Gaël Hette, Sylvia Estivie, Emmanuel Adam and René Mandiau

Abstract: We propose a model to solve the disturbances which could occur during the execution of agents task schedules in a dynamic multi-agent system. Our model is based on pooling residual resources to reallocate tasks in case of incoming tasks or disturbances during the execution of the system. In our context, initial task schedules of agents are defined such that, during some given time windows, agents can perform additional tasks with their residual resources. In this paper, we propose a model for this problem. In order to validate this model, we also propose a first resolution method attempt and an experimental study of this framework.

Paper Nr: 25
Title:

STRATEGIC DOMINANCE AND DYNAMIC PROGRAMMING FOR MULTI-AGENT PLANNING - Application to the Multi-Robot Box-pushing Problem

Authors:

Mohamed Amine Hamila, Emmanuelle Grislin-Le Strugeon, René Mandiau and Abdel-Illah Mouaddib

Abstract: This paper presents a planning approach for a multi-agent coordination problem in a dynamic environment. We introduce the algorithm SGInfiniteVI, allowing to apply some theories related to the engineering of multi-agent systems and designed to solve stochastic games. In order to limit the decision complexity and so decreasing the used resources (memory and processor-time), our approach relies on reducing the number of joint-action at each step decision. A scenario of multi-robot Box-pushing is used as a platform to evaluate and validate our approach. We show that only weakly dominated actions can improve the resolution process, despite a slight deterioration of the solution quality due to information loss.

Paper Nr: 29
Title:

WHO ARE YOU? - On the Acquisition of Information about People for an Agent that Remembers

Authors:

Nikita Mattar and Ipke Wachsmuth

Abstract: Humans make extensive use of specialized representations to remember people they interacted with. While current research on embodied conversational agents focuses on the relationship between agent and interlocutor, the representation of the latter is mostly neglected. But information about others are inevitable for an agent to adapt to its interlocutors and to establish long-term relationships with them. In this work, we present a model of Person Memory for virtual agents. We discuss what kinds of information have to be stored about people. Furthermore, we stress the importance of social categories. In our scenario, we focus on first encounters between our agent and people. We show how the agent is able to exploit his Person Memory to acquire information about others during Small Talk and guide the conversation.

Paper Nr: 43
Title:

FORECASTING DEMAND FOR CLOUD COMPUTING RESOURCES - An Agent-based Simulation of a Two Tiered Approach

Authors:

Owen Rogers and Dave Cliff

Abstract: As cloud computing grows in popularity and usage, providers of cloud services are facing challenges of scale and complexity; how can they ensure they are most efficiently using their existing infrastructure, and when should they invest in new infrastructure to meet demand? We propose a two-period model which utilises a third party called the Coordinator, who interacts with a population of resource-buyers. The Coordinator uses two mechanisms to aid the provider in future capacity planning. Firstly, the Coordinator extracts probabilities from the buyers through an options market to determine their likely usage in the next period, which can subsequently be used to schedule workloads. Secondly, the Coordinator uses previous market demand to predict if cost can be reduced by investing in a reservation over a longer period. This upfront investment contributes to the provider’s capital expenditure in new capability and implies that Coordinator intends to further utilise such an investment. We implement the model in an agent-based simulation using actual UK market data where a pool of users submit different probabilities based on previous market demand. We show that the Coordinator can make a profit when faced with different market conditions, and that profit can be maximised by considering the utilisation of previously purchased reservations.

Paper Nr: 45
Title:

A QUOTA-BASED MULTI-AGENT NEGOTIATION PROTOCOL FOR COMPLEX CONTRACTS

Authors:

Fabian Lang and Andreas Fink

Abstract: Automated negotiation is regarded as an essential method for the coordination of software agents. However, without adequate protocols, negotiations are susceptible to malicious and strategic behavior of the agents – especially when interdependencies of contract items lead to complex contract spaces. In this study, we propose a mediator-based protocol employing acceptance quotas to ensure cooperative behavior in inter-organizational systems. Furthermore, we evaluate three potential extensions to the basic protocol. We have conducted simulation experiments for evaluation which show that the proposed protocol can ensure an effective welfare performance and that the proposed extensions can result in a further improvement of the basic protocol.

Paper Nr: 46
Title:

TOWARDS COGNITIVE STEERING BEHAVIOURS FOR TWO-WHEELED ROBOTS

Authors:

François Gaillard, Cédric Dinont, Michaël Soulignac and Philippe Mathieu

Abstract: We present a two-layer architecture for two-wheeled robots trajectory planning. This architecture can be used to describe steering behaviours and to generate candidate trajectories that will be evaluated by a higher-level layer before choosing which one will be followed. The higher layer uses a TÆMS tree to describe the current robot goal and its decomposition into alternative steering behaviours. The lower layer uses the DKP trajectory planner to grow a tree of spline trajectories that respect the kinematic constraints of the problem, such as linear/angular speed limits or obstacle avoidance. The two layers closely interact, allowing the two trees to grow simultaneously: the TÆMS tree nodes contain steering parameters used by DKP to generate its branches, and points reached in DKP tree nodes are used to trigger events that generate new subtrees in the TÆMS tree. We give two illustrative examples: (1) generation and evaluation of trajectories on a Voronoi-based roadmap and (2) overtaking behaviour in a road-like environment.

Paper Nr: 59
Title:

TOO FAST TOO FURIOUS - Faster Financial-market Trading Agents Can Give Less Efficient Markets

Authors:

John Cartlidge, Charlotte Szostek, Marco De Luca and Dave Cliff

Abstract: For many of the world's major financial markets, the proportion of market activity that is due to the actions of "automated trading" software agents is rising: in Europe and the USA, major exchanges are reporting that 30%-75% of all transactions currently involve automated traders. This is a major application area for artificial intelligence and autonomous agents, yet there have been very few controlled laboratory experiments studying the interactions between human and software-agent traders. In this paper we report on results from new human-agent experiments using the OpEx experimental economics system first introduced at ICAART-2011. Experiments explore the extent to which the performance of the traders, and of the market overall, is dependent on the speed at which the agents operate. Surprisingly, we found that slowing down the agents increased the market’s overall ability to settle to a competitive equilibrium, and that slow-agent markets were more efficient.

Paper Nr: 61
Title:

TOWARDS MORE FLEXIBLE BDI AGENTS

Authors:

Saadi Adel, Maamri Ramdane and Zaïdi Sahnoun

Abstract: BDI agents are among the most popular models for the development of intelligent agents. The practical reasoning within the most of BDI models and architectures rely, in the best case, on three kinds of attributes: The utility associated with a goal, the cost of a plan and the uncertainty associated with the action’s effects. Based on a richer set of practical reasoning’s attributes, we propose a BDI architecture which aims to provide a step towards more flexible BDI agents.

Paper Nr: 71
Title:

SIMULATING PEDESTRIAN ROUTE SELECTION WITH IMPERFECT KNOWLEDGE

Authors:

Kyle Feuz and Vicki Allan

Abstract: Heuristic evaluation of possible route choices allows pedestrians to make decisions in a timely and efficient manner. The heuristic function used to evaluate the route and the subsequent route selection has a large impact on the egress time of the pedestrian. We implement several common heuristic functions using the PLEASE simulation model and allow these heuristics to be combined using weighted factors. When the total distance of a route is unknown, using a greedy strategy of selecting the shortest-leg first route is shown to be a poor choice. When combined with other heuristic estimates however, including shortest-leg first costs can help to decrease egress times. We show that for a variety of building layouts using a heuristic function based upon width, distance, signage and congestion levels leads to better egress times.

Paper Nr: 73
Title:

SICAEN: A NEW METHOD TO DETERMINE THE IMPACT OF SEVERE NETWORK FAULTS ON BASIC TELECOMMUNICATION SERVICES

Authors:

Andrés Cancer, Cristina del Campo and Carlos Gascón

Abstract: Despite the effort that has been carried out in the last two decades, there is still a huge gap between the information that network management systems can provide to identify and solve network problems, and the information they offer to determine the actual impact of these problems on basic telecommunication services. This paper presents a new method (called SICAEN) to identify and characterize service impact incidents using network resource unavailability information as an input. Most of the previously done work tries to identify the root cause of a failure, while SICAEN is concerned with the actual impact of the failure, from a user (service) perspective. The method performs impact evaluation in a per-service basis and has been successfully applied in real world in the context of Telefonica’s IMPACTA project, whose goal is to determine the impact of severe network faults on mobile basic services for the Spanish biggest mobile operator.

Paper Nr: 80
Title:

EMOTION AS AN ENABLER OF CO-OPERATION

Authors:

Martyn Lloyd-Kelly, Katie Atkinson and Trevor Bench-Capon

Abstract: We investigate the emergence of co-operation through emotions. We use agents playing an iterated Prisoner’s Dilemma game, and show how the emotions of gratitude and anger enable co-operation to emerge as a response to the emotional state of the agents without reference to payoffs or history. We investigate the effect of different thresholds for these emotions to change behaviour on individual performance and system scores.

Paper Nr: 83
Title:

ENVIRONMENT UPDATING AND AGENT SCHEDULING POLICIES IN AGENT-BASED SIMULATORS

Authors:

Philippe Mathieu and Yann Secq

Abstract: Since Schelling’s segregation model, the ability to represent individual behaviours and to execute them to produce emergent collective behaviour has enabled interesting studies in diverse domains, like artificial financial markets, crowd simulation or biological simulations. Nevertheless, the description of such experiments are focused on the agents behaviours, and seldom clarify the exact process used to execute the simulation. In other words, little details are known on the assumptions, the choices and the design that have been done on the simulator on fundamental notions like time, simultaneity, agent scheduling or sequential/parallel execution. Though, these choices are crucial because they impact simulation results. This paper is focused on parameter sensitivity of agent-based simulators implementations, specifically on environment updating and agent scheduling policies. We highlight concepts that simulator designers have to define and presents several possible implementations and their impact.

Paper Nr: 92
Title:

CONCEPTUAL-BASED REASONING IN MOBILE WEB 2.0 BY MEANS MULTIAGENT SYSTEMS - Knowledge Engineering Notes

Authors:

Gonzalo A. Aranda-Corral, Joaquín Borrego-Díaz and Jesús Giráldez-Cru

Abstract: Increasingly, users connect to the Internet by mobile devices and they are generating massive content through them. The lead-off projects in Mobile Web 2.0 offer the opportunity to add semantics in order to obtain structured knowledge. In this paper, we present specific challenges for tagging reasoning, into the SinNet project. SinNet is based on user generated content (UGC) by mobile devices, as well as how to solve them by means of combining multi-agent systems and formal concepts analysis.

Paper Nr: 98
Title:

EXPLORING FIRMS FINANCIAL DECISIONS BY HUMAN AND ARTIFICIAL AGENTS - Towards an Assessment of Minsky’s Financial Instability Hypothesis

Authors:

Gianfranco Giulioni, Edgardo Bucciarelli and Marcello Silvestri

Abstract: In this paper we take the first step of a project aimed at assessing Minsky’s Financial Instability Hypothesis. Differently from a number of existing studies, our aim is to tackle the issue by combining two approaches: experimental and computational economics. The main goal of this paper is in fact to build artificial agents whose behavior mimic that of experimental agents. Two are the results worth to be mentioned. First, the heuristic approach could provide for a valid alternative micro-foundation for the financial decisions of entrepreneurs. Secondly, financial behaviors could mainly depend on the volatility of demand and on the accuracy of demand forecasts instead of depending on the business cycle phases as usually pointed out by models inspired by Minsky’s economic thought.

Paper Nr: 130
Title:

IMPROVING THE PRE-NOTIFICATION PROTOCOL OF THE CONTAINERS PICK-UP PROCEDURE - An Agent-based Approach

Authors:

Meditya Wasesa, Pim Nijdam, Ismail Habib Muhammad and Eric van Heck

Abstract: As the global container traffic flow is consequently increasing, the maritime container terminals (CTs) are seeking new ways to improve their service. Taking the container import pick-up context as a test case, we show that operational service can be improved by re-evaluating the information protocol. In this study, we analyze and propose measures to improve the existing pre-notification approval protocol, the procedure that bridges the CT and the incoming drayage trucks (DTs) in the container pick-up process. We put the emphasis on the importance of considering the containers’ exact location in the pre-notification approval request. The proposal is assessed by conducting agent based simulation experimentations. The results reveal the opportunities to improve the CT’s performance in terms of the reshuffling frequency, the truck turn-around time, and the average queue length at the CT’s gate-in, in favour of the proposal.

Paper Nr: 134
Title:

TOWARDS CONTEXTUAL GOAL-ORIENTED PERCEPTION FOR PEDESTRIAN SIMULATION

Authors:

Laure Bourgois, Julien Saunier and Jean-Michel Auberlet

Abstract: Perception is often seen in multiagent systems and in robotics from a passive point of view. The sensors of the agent collect information on its environment; however the potentially important number of percepts is not realistic and may decrease the agents efficiency. In this article, we introduce a contextual goal-oriented perception filtering. Besides the lack of plausibility of omniscient agents, it addresses the problem of transmitting too much information to the agents. This goal-oriented perception module is evaluated model in terms of validity of the resulting behavior and of time complexity.

Paper Nr: 163
Title:

DEVELOPMENT OF A MULTI-AGENT PLATFORM FOR SUPPLY CHAIN-WIDE ORDER FULFILMENT

Authors:

Roberto Domínguez Cañizares and Jose M. Framiñán

Abstract: In this paper we describe an agent-based framework for modelling and simulating different processes taking place in supply networks, resulting in a supply chain simulator called SCOPE (Sistemas COoperativos para la Programación y Ejecución de pedidos). The framework is composed of reusable elements (agents and objects) allowing easy modelling of real-scale supply chains, with different companies and products. Each company in the model can use different policies and parameters for the different business functions. The framework is implemented using Swarm. Furthermore, its generic and modular structure allows to easily adding new and more complex functions for the agents. The final aim of SCOPE is to serve as a testbed to implement and analyse the effects of different management decisions related to order fulfilment over real-scale supply chains. SCOPE has been validated using different supply chains described in the literature.

Paper Nr: 174
Title:

PREDICTIVE CONTROL FOR TRAJECTORY TRACKING AND DECENTRALIZED NAVIGATION OF MULTI-AGENT FORMATIONS

Authors:

Ionela Prodan, Sorin Olaru, Cristina Stoica and Silviu-Iulian Niculescu

Abstract: This paper addresses a predictive control strategy for multi-agent formations with a time-varying topology. The goal is to guarantee a trajectory tracking, where a reference trajectory is specified for an agent designed as the leader. Then, a predictive control strategy combined with the Potential Field method is used in order to derive a control action based only on local information within the group of agents. The main concern is that the interconnections between the agents are time-varying, affecting the neighborhood around each agent. The proposed method exhibits effective performance validated through some illustrative examples.

Paper Nr: 183
Title:

TASK-BASED REORGANIZATION IN MULTI-AGENT SYSTEMS - Exploring Performance Characteristics

Authors:

Maryamossadat Mahani and Arvin Agah

Abstract: Important to the effective performance of organizations in multi-agent systems, is the ability to reorganize to a more effective organization. Due to the costs associated with reorganization, it becomes necessary to find a balance in how often or when a reorganization is performed. In this work, we study performance tradeoffs of a task-based reorganization model. A pursuit game simulation is used as a sample distributed problem solving application. Two different models of organizational structure and a reorganization model are implemented using the S-MOISE+ organizational modeling framework. These organizational models are applied to the simulation model, and their performance is evaluated by considering the success rate and the total cost associated with each. The results demonstrate potential benefits of the reorganization once the complexity of the system increases.

Paper Nr: 184
Title:

ON A PRICED RESOURCE-BOUNDED ALTERNATING μ-CALCULUS

Authors:

Dario Della Monica and Giacomo Lenzi

Abstract: Much attention has been devoted in artificial intelligence to the verification of multi-agent systems and different logical formalisms have been proposed, such as Alternating-time Temporal Logic (ATL), Alternating μ-calculus (AMC), and Coalition Logic (CL). Recently, logics able to express bounds on resources have been introduced, such as RB-ATL and PRB-ATL, both of them based on ATL. The main contribution of this paper is the introduction and the study of a new formalism for dealing with bounded resources, based on μ-calculus. Such a formalism, called Priced Resource-Bounded Alternating μ-calculus (PRB-AMC), is an extension of both PRB-ATL and AMC. In analogy with PRB-ATL, we introduce a price for each resource. By considering that the resources have each a price (which may vary during the game) and that agents can buy them only if they have enough money, several real world scenarios can be adequately described. First, we show that the model checking problem for PRB-AMC is in EXPTIME and has a PSPACE lower bound. Then, we solve the problem of determining the minimal cost coalition of agents. Finally, we show that the satisfiability problem of PRB-AMC is undecidable, when the game is played on arenas with only one state.

Paper Nr: 189
Title:

ANALYSIS FOR DISTRIBUTED COOPERATION BASED ON LINEAR PROGRAMMING METHOD

Authors:

Toshihiro Matsui and Hiroshi Matsuo

Abstract: Distributed cooperative systems have optimization problems in their tasks. Supporting the collaborations of users, or sharing communications/observations/energy resources, are formalized as optimization problems. Therefore, distributed optimization methods are important as the basis of distributed cooperation. In particular, to handle problems whose variables have continuous domains, solvers based on numerical calculation techniques are important. In a related work, a linear programming method, in which each agent locally performs the simplex method and exchanges the sets of bases, has been proposed. On the other hand, there is another interest in the cooperative algorithm based on a linear programming method whose steps of processing are more distributed among agents. In this work, we study the framework of distributed cooperation based on a distributed linear programming method.

Paper Nr: 201
Title:

LANDMARK-BASED CAR NAVIGATION WITH OVERTAKE CAPABILITY IN MULTI-AGENT ENVIRONMENTS

Authors:

Sirvan Khalighi, Somayeh Maabi, Mercedeh Sanjabi and Ali Jahanian

Abstract: Intelligent car navigation systems are planned to assist humans and route them automatically in the roads with sufficient security and correctness. Landmark-based car navigation is a widely used technique in automotive and robot navigation. In this paper, we improved a wireless landmark-based car navigation (WLCN) algorithm to operate in multi-agent (MA) environments. The extended navigation algorithm allows the cars to overtake in uni-directional real roads. Overtaking is based on the information which the cars send to each other in the road. According to this information and using a related algorithm, cars traverse each other. Analysis of accuracy and efficiency in various states, real-time RISC-based embedded system especially for high speed movements in real roads show that, the cars are navigated easily and reliable in multi-agent environments and they can successfully do overtake. In addition to reliable navigating, calculation cost of the algorithm is acceptable for real world scenarios.

Paper Nr: 207
Title:

SEEKING AND AVOIDING COLLISIONS - A Biologically Plausible Approach

Authors:

M. A. J. Bourassa and N. Abdellaoui

Abstract: The success of an agent model that incorporates a hierarchical structure of needs, required that the needs trigger human-like actions such as collision avoidance. This paper demonstrates a minimalist, “rule-of-thumb” collision avoidance approach that performs well in dynamic, obstacle-cluttered domains. The algorithm relies only on the range, range rate, bearing, and bearing rate of a target perceived by an agent. Computation is minimal and the approach yields a natural behaviour suitable for robotic or computer generated agents in games.

Paper Nr: 212
Title:

SIMULATING KNOWLEDGE AND INFORMATION IN PEDESTRIAN EGRESS

Authors:

Kyle Feuz and Vicki Allan

Abstract: Accurate pedestrian simulation is a difficult yet important task. One of the main challenges with pedestrian simulation is providing the simulated pedestrians with appropriate amounts of route knowledge to be used in the route selection algorithm. In this paper, we propose a novel use of reinforcement learning as a means to represent different amounts of route knowledge. Using this techniques we show the impact learning about route distances and average route congestion levels has upon the egress time of pedestrians. We also look at the effect that dynamic congestion information has upon the efficiency of pedestrian egress.

Paper Nr: 226
Title:

MULTI-AGENT BASED MODELING OF THE TUNISIAN PASTORAL DYNAMIC - Multi-level Organization

Authors:

Islem Henane, Sameh Hadouaj and Khaled Ghedira

Abstract: Pastoral systems in arid and semi arid areas are characterized by a continued deterioration. This degradation is the result of the mismanagement of resources in response to natural, economic and social mutations. These systems are considered as complex systems, given the large number of stakeholders in interaction and levels of granularity. To address this situation, analytical and systemic approaches are no longer adequate. In this paper, we propose a multi-agent based model of Tunisian pastoral dynamics taking into account the interaction dynamics of the different stakeholders and the different levels of granularity. The completion of this work is within the scope of the development of the Intelligent Decision Support System PASDES (Pastoral Strategies Definition System). PASDES aims to support pastoral strategic decision making in short and long terms.

Paper Nr: 228
Title:

EMPHASIZING ON THE TIMING AND TYPE - Enhancing the Backchannel Performance of Virtual Agent

Authors:

Xia Mao, Na Luo and Yuli Xue

Abstract: Addressing backchannel feedbacks to virtual agent listener gives the agent human-like conversation skills and creates rapport in Human-Computer Interaction. We argue the limitations of current approaches in predicting and generating backchannel. Following two hypotheses emphasizing on the timing and type of backchannel, we introduce an improved system to enhance the agent listener’s performance. By using Newcastle Personality Assessor before parasocial consensus sampling and then neural networks, we can obtain the personality rules and select different backchannel timing thresholds for specific agent listener according to its own personality. After a context-free perceptual study, we will build two emotional backchannel lexicons showing positive affection and negative affection respectively. In accordance with the empathy strategy, the system will select one type of backchannel from the corresponding emotional backchannel lexicon. The improved system will be more suitable for different conversation occasions and greatly increase the naturalness between the human speaker and the virtual agent listener in the future.

Paper Nr: 229
Title:

MODELLING THERAPEUTIC EMPATHY IN A VIRTUAL AGENT TO SUPPORT THE REMOTE TREATMENT OF MAJOR DEPRESSION

Authors:

Juan Martínez-Miranda, Adrián Bresó and Juan Miguel García-Gómez

Abstract: The use of computer based psychotherapy has been one of the fields that have attracted the interest of practitioners and computer scientists in the last years given the initial and promising results. In particular the use of computerised cognitive behavioural therapy for the treatment of major depression has been supported the evidence that psychological therapies can be delivered effectively without face to face contact. However, the value of these tools for patients is limited by the difficulty of staying engaged during the long-time periods of the treatment. The use of Virtual Agents as enhanced human-computer interaction brings the opportunity to overcome this limitation by establishing effective long-term social relationships with patients. We introduce the main ideas behind the design of a cognitive-emotional model aimed to generate therapeutic empathic responses and support the remote treatment of major depression.

Paper Nr: 230
Title:

MODELLING MICROSCOPIC PEDESTRIAN MOBILITY USING BLUETOOTH

Authors:

Thomas Liebig and Armel Ulrich Kemloh Wagoum

Abstract: Emergence of Bluetooth tracking technology for event monitoring is currently applied to extract individual pathways, movement patterns or to rank popularity of locations by their visitor quantities. The next steps are to achieve short term movement predictions, to understand people’s motivations and to come up with microscopic traffic values. This work proposes a solution for these questions, namely, the combination of recorded values with a microsimulation. In our presented framework, simulated pedestrians move from one decision area to the next one in a navigation graph. The graph is automatically generated from the facility based on the inter-visibility of the exits. Intermediate areas are inserted if needed. With the data obtained from the Bluetooth scanners, individual pathways of pedestrians are determined. The routing algorithm will then use those information to adjust the pathways of the agents in the simulation. An accurate reproduction of pedestrian route choice in a complex facility is expected.

Paper Nr: 233
Title:

LEARNING BY OBSERVATION IN SOFTWARE AGENTS

Authors:

Paulo Costa and Luis Botelho

Abstract: In a society of similar agents, all of them using the same kind of knowledge representation, learning with others could be achieved through direct transfer of knowledge from experts to apprentices. However, not all agents use the same kind of representation methods, hence learning by direct communication of knowledge is not always possible. In such cases, learning by observation might be of key importance. This paper presents an agent architecture that provides software agents with learning by observation capabilities similar to those observed in superior mammals. The main contribution of our proposal is to let software agents learn by direct observation of the actions being performed by expert agents. This is possible because, using the proposed architecture, agents may see one another.

Paper Nr: 234
Title:

ARTIFICIAL CONVERSATIONAL COMPANIONS - A Requirements Analysis

Authors:

Sviatlana Danilava, Stephan Busemann and Christoph Schommer

Abstract: This work is based on several attempts to provide a definition and a design approach of Artificial Companions that can be found in the referenced literature. We focus on computer agents that simulate human language behaviour and are aimed to serve, to assist and to accompany their owner over a long period of time, that we call Artificial Conversational Companions. Although accepted by the research community, the visions set very high expectations of such agents, but they do not address the technical feasibility and the system limitations. This is the first approach to define a set of features that allow an artificial agent to be regarded as an Artificial Conversational Companion. We describe relationships between the components and identify systematic shortcomings of the current systems. We propose a scalable method for implementing the desired capabilities of an Artificial Conversational Companion in a generic framework with reusable, customizable and interdependent components.

Posters
Paper Nr: 8
Title:

AN ARTIFICIAL STOCK MARKET

Authors:

Martin Sewell

Abstract: To set the scene, fundamental analysis, technical analysis, behavioural finance and multiagent systems are introduced and discussed. The work utilizes behavioural finance; the evolved heuristics and biases exhibited by fundamental analysts and technical analysts, inducing underreaction and overreaction, are used to build an agent-based artificial stock market. Results showed that whether a fundamental analyst, or a technical analyst, it pays to be in a small majority of about 60 per cent, whilst being in a small minority is the least profitable position to be in. As the number of technical analysts increases, the standard deviation of returns decreases, whilst the skewness increases. Whilst kurtosis of market returns peaks with around 40 per cent technical analysts, and rapidly declines as the number of technical analysts exceeds 90 per cent. The autocorrelation of returns is close to zero with 100 per cent fundamental analysts, and approaches one as the proportion of technical analysts approaches 100 per cent. The artificial stock market replicates mean returns, the standard deviation of returns, the absolute returns correlation and the squared returns correlation of a real stock market, but failed to accurately replicate the skewness, kurtosis and autocorrelation of returns.

Paper Nr: 30
Title:

TraxBot - Assembling and Programming of a Mobile Robotic Platform

Authors:

André Araújo, David Portugal, Micael S. Couceiro, Carlos M. Figueiredo and Rui P. Rocha

Abstract: This work presents the TraxBot mobile robot design, a ground platform recently developed for applications in the mobile robotics field. The assembling of the robotic system, with description of its components as well as information about the microcontroller programming, development and testing are presented. The TraxBot is a multidisciplinary platform and is ideal for education, since it is easily programmed with open-source tools requiring basic knowledge of other areas beyond robotics, like mechanics, control or energy management. Although being released in a stable version, the robot is continually in development, with the ability to incorporate extensions to its design and new features.

Paper Nr: 42
Title:

EnvEdit - A GRAPHICAL ENVIRONMENT EDITOR - Approaches towards a Fast and Simple Way of Building Complex Environments in Multi Agent Simulations

Authors:

Christoph Schwarz, Jan Busch, Carsten Beth, Jürgen Sauer and Axel Hahn

Abstract: Multi Agent Simulations are well known and widely-used simulations which can simulate embodied agents in neighbourhoods or environments. The designing of such environments has, so far, mainly to be done by hard coding them directly in the simulation source code. In this paper we present EnvEdit, a graphical environment editor for MASON. EnvEdit leads to a less time consuming and less error-prone design of environments.

Paper Nr: 44
Title:

NORMATIVE APPROACH FOR SOCIO-PHYSICAL COMPUTING - An Application to Distributed Tangible Interaction

Authors:

Fabien Badeig, Catherine Garbay, Valentin Valls and Jean Caelen

Abstract: We present a normative multi-agent design for computer-supported collaboration in the framework of sociophysical computing. An example application (RISK game) in the context of the TangiSense platform supports the proposed approach. Our work is driven under four complementary views: a systemic view, according to which various designing levels, from the physical infrastructure to the social level of human coordination are integrated in a single modelling, a normative view, in which consistency and coordination of action is ensured with respect to individual as well as collective systems of norms, a trace-based view, in which traces reflecting human activity and its compliance to the norms are registered and an agent-oriented view, according to which agents are meant to process, interpret and communicate information across distant tables.

Paper Nr: 63
Title:

COOPERATIVE MULTI-ROBOT SYSTEM FOR INFRASTRUCTURE SECURITY TASKS

Authors:

Erik Hernandez, Antonio Barrientos, Claudio Rossi and Jaime del Cerro

Abstract: As a result of terrorist attacks in the last years, new efforts have raised trying to solve challenges related to security task automation using robotic platforms. In this paper we present the results of a cooperative multi-robot approach for infrastructure security applications at critical facilities. We formulate our problem using a Ms. Pac-Mac like environment. In this implementation, multiple robotic agents define policies with the objective to increase the number of explored states in a grid world. This is through the application of the off-policy learning algorithm from reinforcement learning area, known as Q-learning. We validate experimentally our approach with a group of agents learning a patrol task and we present results obtained in simulated environments.

Paper Nr: 82
Title:

SOCIAL BEHAVIOR INVESTIGATION OF AN INTELLIGENT VIRTUAL AGENT WITH THE HELP OF TYPICAL WORKING STUDENT’S LIFE SCENARIO MODELING

Authors:

Dilyana Budakova and Lyudmil Dakovski

Abstract: This paper investigates the social behaviour of an intelligent virtual agent (IVA) with PRE-ThINK architecture with the help of typical working student’s life scenario modeling. Тhe program system and the PRE-ThINK architecture, adapted for this scenario, are proposed, and their components are considered. The dynamics of the decision making process in problem situations caused by the implementation of this architecture is shown, when mixed emotions arise and the realization of what happened reflects on the agent’s temper. IVA’s social behavior is shown, during which in the process of communicating with the user the agent expresses learned from experience secondary emotions, which can be either in harmony or in conflict with the realized secondary emotions, resulting both from the agent’s generalized condition and the events. The investigated secondary emotions are: relief, confidence, prestige, uncertainty, confirmed fear, disappointment; and also the socially expressed secondary emotions such as refrained sadness, refrained anger, businesslike manners, politeness and authoritativeness.

Paper Nr: 117
Title:

TOWARDS FORMAL AND DEDUCTION-BASED ANALYSIS OF BUSINESS MODELS FOR SOA PROCESSES

Authors:

Radosław Klimek

Abstract: The paper concerns formal analysis and verification of business models expressed in BPMN as a visualization of SOA processes. This verification is based on deductive reasoning which is in a certain kind of opposition to the well-known approaches based on state exploration (model checking). Semantic tableaux are proposed as a method of inference. Both the logical specification and the desired system properties are expressed in the smallest linear temporal logic. Automatic transformations of business models (expressed as workflow patterns) to temporal logic formulas are proposed. These formulas constitute a logical specification of the analyzed model. An algorithm for generation of a logical specification is presented.

Paper Nr: 128
Title:

A LOCAL-GLOBAL MODEL FOR MULTIAGENT SYSTEMS - Sheaves on the Category MAS

Authors:

Thomas Soboll and Ulrike Golas

Abstract: In multiagent systems, each agent has its own local view of the environment. Nevertheless, agents try to cooperate to reach a common global goal. In this paper, we use a suitable Grothendieck topology and sheaves to model the agents’ local data and their communication.

Paper Nr: 137
Title:

HAND IN HAND - Maths and Storytelling together in an Educational Game

Authors:

Isabel Machado Alexandre, David Jardim and Pedro Faria Lopes

Abstract: In this paper, we describe a novel approach to teaching early mathematical concepts to young children. The approach aims to merge storytelling and Maths. Evidence show that through dramatic games and role-playing activities young children (aging from 5-7 years old) learn to master new knowledge, to fit in a new school setting and to socially relate with their peers. So taking this evidence into account, it is possible to devise an innovative learning scenario that teaches early mathematical concepts by telling and creating stories. To explore this idea, we first started by developing an application that provides children from 5 to 7 years old to learn simple maths concepts by interacting and playing in a game. Then, we take this project a step forward and explore the introduction of storytelling by devising an engaging approach of presenting the maths concepts through the use of a story.

Paper Nr: 144
Title:

MULTI-AGENT PLANNING FOR THE ROBOCUP RESCUE SIMULATION - Applying Clustering into Task Allocation and Coordination

Authors:

Amr Hussein, Carmen Gervet and Slim Abdennadher

Abstract: The RoboCup Rescue Simulation system provides a rich environment for developing novel techniques for multi-agent systems. The simulation provides a city map modeled as buildings and roads with civilians amongst them. A disaster scenario is simulated causing buildings to catch fire, roads to get blocked, and civilians to get injured and/or buried. The main goal is to use the available emergency services (rescue agents) to extinguish the fires, clear the roads, and rescue the civilians. This paper describes a new multi-agent planning approach applied to the RoboCup Rescue problem. The key novelty lies in the distributed approach for task allocation and coordination. It is done through clustering the map into several overlapping maps each with a different group of agents assigned to it. Our results showed that not only we could compete against the top teams in the 2011 RoboCup Rescue Agent Simulation Competition, but we ranked 3rd in this first participation of the GUC in the competition.

Paper Nr: 149
Title:

B2DI - A Bayesian BDI Agent Model with Causal Belief Updating based on MSBN

Authors:

Álvaro Carrera and Carlos A. Iglesias

Abstract: In this paper, we introduce B2DI model that extends BDI model to perform Bayesian inference under uncertainty. For scalability and flexibility purposes, Multiply Sectioned Bayesian Network (MSBN) technology has been selected and adapted to BDI agent reasoning. A belief update mechanism has been defined for agents, whose belief models are connected by public shared beliefs, and the certainty of these beliefs is updated based on MSBN. The classical BDI agent architecture has been extended in order to manage uncertainty using Bayesian reasoning. The resulting extended model, so-called B2DI, proposes a new control loop. The proposed B2DI model has been evaluated in a network fault diagnosis scenario. The evaluation has compared this model with two previously developed agent models. The evaluation has been carried out with a real testbed diagnosis scenario using JADEX. As a result, the proposed model exhibits significant improvements in the cost and time required to carry out a reliable diagnosis.

Paper Nr: 156
Title:

NEGOTIATION POLICIES FOR PROVISIONING OF CLOUD RESOURCES

Authors:

Salvatore Venticinque, Viorel Negru, Victor Ion Munteanu, Calin Sandru, Rocco Aversa and Massimiliano Rak

Abstract: Cloud represents today a computing market where users can buy resources according to a pay-per-use business model. Cloud providers offer different kind of services which can be characterized by different service levels. Negotiation of the best resource can be very difficult because there is a semantic gap between the different provider SLAs and the requirements of an user’s application. We address the negotiation issue within the research activity of the mOSAIC project by designing and developing an agents based service at platform level for provisioning of cloud resources. In order to allow the execution of the application and fulfill the developer’s requirements, the service uses a policy based approach that is able to choose, at infrastructure level, the best solution, in terms of a collection of cloud resources from different providers.

Paper Nr: 160
Title:

DATA TRAFFIC REDUCTION FOR MOBILE AGENT MIGRATION

Authors:

Masayuki Higashino, Kenichi Takahashi, Takao Kawamura and Kazunori Sugahara

Abstract: In this paper, we propose a method of reducing data traffic on mobile agent migration. Mobile agents are able to simplify network programming with autonomous process migration as compared with inter-process communication. However, mobile agents increase data traffic by transfer of program codes when migration. Therefore, many researchers have proposed for reducing data traffic on mobile agent system with agent behaviour. These methods complicate the algorithm of agent behaviour. On the other hand, we focus on a mechanism of mobile agent migration, and our method is fully independent from agent behaviour. Our method reduces program code traffic with cache on mobile agent runtime environment. We have implemented our technique on a mobile agent framework, and experimented on a practical mobile agent system. As a result, the system’s performance has improved to 52%.

Paper Nr: 170
Title:

A SURVEY ON AGENT-BASED ONTOLOGY ALIGNMENT

Authors:

Maxim Davidovsky, Vadim Ermolayev and Vyacheslav Tolok

Abstract: Ontologies today are increasingly used as consensual knowledge representations in many distributed applications. However, if a system of knowledge based nodes is decentralized, the ontologies at those nodes differ. Therefore the alignment of knowledge representations is required. One of the promising approaches to solve this heterogeneity is the use of agents for aligning knowledge representations. The paper presents a brief survey of the approaches to agent-based ontology alignment. The analysis of these approaches is grounded on the analysis of the requirements to ontology alignments by typical applications that address semantic heterogeneity in open and decentralized settings.

Paper Nr: 187
Title:

INTERBANK PAYMENT SYSTEM (RTGS) SIMULATION USING MULTI-AGENT APPROACH

Authors:

Hedjazi Badiâa, Ahmed-Nacer Mohamed, Aknine Samir and Benatchba Karima

Abstract: This work consists in simulating a real time interbank gross payment system (RTGS) through a multi-agent model, to analyze the evolution of the liquidity brought by the banks to the system. In this model, each bank chooses the amount of a daily liquidity provided in the system on the basis of costs minimization (costs of liquidity and delaying) by taking into account the liquidity brought by the other banks. Banks agents reasoning is based on a repeated aggregate game of over several payment days where each bank plays against the other banks. For adaptive behaviour we integrate into bank agents a learning classifier system. We carry out then several simulations to follow the system total liquidity evolution as that of each bank agent with varying costs coefficients. The question to be answered is: what are the cash amounts that banks must provide and under what constraints (costs of liquidity and delaying) the system beyond the lack of liquidity (illiquidity)? We find that liquidity evolution depends on costs coefficients.

Paper Nr: 190
Title:

SEMANTIC RESOURCE DISCOVERY IN GRID AND MULTI-AGENT ENVIRONMENT

Authors:

Muntasir Al-Asfoor and Maria Fasli

Abstract: Resources sharing has become an evolved field of study for the distributed systems communities. Enabling geographically diverse computational entities to share resource in a seamless way regardless of the hardware and software specifications has become a need by researchers communities. Resource discovery plays a vital role in the sharing lifetime. Resource sharing has been studied in this paper as a network activity. The effect of the locations where the semantic matching is done on the network performance has been investigated. An experiment has been designed to implement the proposed scenarios in a simulated environment. As part of this experiment a semantic matching algorithm based on reference ontology has been also implemented. The experimental results have demonstrated that doing a matching process in the requesters nodes is less network time consuming, giving that the requester has a copy of the neighbors resources descriptions.

Paper Nr: 204
Title:

A COMPARISON OF DIPLOMACY GAMEBOARD GRAPH SEARCH ALGORITHMS

Authors:

Daniel P. Stormont and Vicki H. Allan

Abstract: The boardgame Diplomacy has been used as a testbed for multiagent systems almost since the time of its introduction in 1959. The reason is that the game presents a number of interesting challenges to artificial intelligence researchers: a state space that is too large to be tackled by brute force searches, imperfect information due to simultaneous movement, no random elements, and non-binding negotiations between the seven players. This paper looks at just one aspect of creating an agent for playing Diplomacy – finding the fewest number of moves to achieve a victory in the game, if the player was unopposed. This planning function forms the basis for a more sophisticated move planner that also takes into account the game state and the other players. Three search algorithms are compared to determine which is the most effective (in terms of the number of map nodes expanded during the search).

Paper Nr: 208
Title:

TURTLES AS STATE MACHINES - Agent Programming in NetLogo using State Machines

Authors:

Ilias Sakellariou

Abstract: Agent based modelling has received significant attention in the recent years mainly due its wide adoption by scientists in a number of fields. Although agent simulation platforms have proven to be quite mature and expressive for modelling simple agents, little has been done regarding enhancing these platforms by higher level agent oriented programming facilities. This work aims at this direction, i.e. an add-on library to a well known simulation platform aiming at the specification of complex high level agents, using state machines.