ICAART 2009 Abstracts


Area 1 - Artificial Intelligence

Full Papers
Paper Nr: 8
Title:

AGENT-BASED SIMULATION OF SOCIAL LEARNING IN CRIMINOLOGY

Authors:

Charlotte Gerritsen, Michel C. A. Klein and Tibor Bosse

Abstract: Criminal behaviour exists in many variations, each with its own cause. A large group of offenders only shows criminal behaviour during adolescence. This kind of behaviour is largely influenced by the interaction with others, through social learning. This paper contributes a dynamical agent-based approach to simulate social learning of adolescence-limited criminal behaviour, illustrated for a small school class. The model is designed in such a way that it can be compared with data resulting from a large scale empirical study.

Paper Nr: 33
Title:

HOW DO EMOTIONAL STIMULI INFLUENCE THE LEARNER’S BRAIN ACTIVITY? - Tracking the Brainwave Frequency Bands Amplitudes

Authors:

Alicia Heraz and Claude Frasson

Abstract: In this paper we discuss how learner’s electrical brain activity can be influenced by emotional stimuli. We conducted an experimentation in which we exposed a group of 17 learners to a series of pictures from the International Affective Picture System (IAPS) while their electrical brain activity was recorded. We got 33.106 recordings. In an exploratory study we examined the influence of 24 picture categories from the IAPS on the amplitude variations of the 4 brainwaves frequency bands: δ, φ, α and β. We used machine learning techniques to track the amplitudes in order to predict the dominant frequency band which inform about the learner mental and emotional states. Correlation and regression analyses show a significant impact of the emotional stimuli on the amplitudes of the brainwave frequency bands. Standard classification techniques were used to assess the reliability of the automatic prediction of the dominant frequency band. The reached accuracy was 90%. We discuss the prospects of extending our actual Brainwave-Sensing Multi Agent System to be integrated to an intelligent tutoring system (ITS) in the future.

Paper Nr: 40
Title:

SPECIFYING MULTIAGENT ENVIRONMENTS IN THE GAME DESCRIPTION LANGUAGE

Authors:

Michael Thielscher and Stephan Schiffel

Abstract: The Game Description Language (GDL) has been developed for the purpose of formalizing game rules. It serves as the input language for general game players, which are systems that learn to play previously unknown games without human intervention. In this paper, we show that GDL can be readily used as a specification language for a large class of multiagent environments. The resulting specifications are declarative, compact, and easy to understand and maintain. At the same time they can be fully automatically understood and used by autonomous agents who intend to participate in these environments. Our main result is a formal characterization of the class of multiagent environments that can be described in GDL.

Paper Nr: 44
Title:

RELATING KNOWLEDGE SPECIFICATIONS BY REDUCTION MAPPINGS

Authors:

Alexei Sharpanskykh and Jan Treur

Abstract: Knowledge can be specified at different levels of conceptualisation or abstraction. In this paper, lessons learned on the philosophical foundations of cognitive science are discussed, with a focus on how the relationships of cognitive theories with specific underlying (physical/biological) makeups can be dealt with. It is discussed how these results can be applied to relate different types of knowledge specifications. More specifically, it is shown how different knowledge specifications can be related by means of reduction relations, similar to how specifications of cognitive theories can be related to specifications within physical or biological contexts. By the example of a specific reduction approach, it is shown how the process of reduction can be automated, including mapping of specifications of different types and checking the fulfilment of reduction conditions.

Paper Nr: 54
Title:

AN INTELLIGENT TUTORING SYSTEM FOR OPERATORS’ TRAINING IN POWER SYSTEM CONTROL CENTRES

Authors:

Albino Marques, António Silva, Carlos Ramos, Luiz Faria and Zita Vale

Abstract: The activity of Control Center operators is important to guarantee the effective performance of Power Systems. Operators’ actions are crucial to deal with incidents, especially severe faults, like blackouts. In this paper we present an Intelligent Tutoring approach for training Portuguese Control Centre operators in tasks like incident analysis and diagnosis, and service restoration of Power Systems. Intelligent Tutoring System (ITS) approach is used in the training of the operators, taking into account context awareness and the unobtrusive integration in the working environment.

Paper Nr: 77
Title:

STATE AGGREGATION FOR REINFORCEMENT LEARNING USING NEUROEVOLUTION

Authors:

Nathaniel Gemelli and Robert Wright

Abstract: In this paper, we present a new machine learning algorithm, RL-SANE, which uses a combination of neuroevolution (NE) and traditional reinforcement learning (RL) techniques to improve learning performace. RL-SANE is an innovative combination of the neuroevolutionary algorithm NEAT(Stanley, 2004) and the RL algorithm Sarsa(l)(Sutton and Barto, 1998). It uses the special ability of NEAT to generate and train customized neural networks that provide a means for reducing the size of the state space through state aggregation. Reducing the size of the state space through aggregation enables Sarsa(l) to be applied to much more difficult problems than standard tabular based approaches. Previous similar work in this area, such as in Whiteson and Stone (Whiteson and Stone, 2006) and Stanley and Miikkulainen (Stanley and Miikkulainen, 2001), have shown positive and promising results. This paper gives a brief overview of neuroevolutionary methods, introduces the RL-SANE algorithm, presents a comparative analysis of RL-SANE to other neuroevolutionary algorithms, and concludes with a discussion of enhancements that need to be made to RL-SANE.

Paper Nr: 85
Title:

GOAL-BASED ADVERSARIAL SEARCH - Searching Game Trees in Complex Domains using Goal-based Heuristic

Authors:

Branislav Bošanský, Michal Jakob, Michal Pěchouček and Viliam Lisý

Abstract: We present a novel approach to reducing adversarial search space by using background knowledge represented in the form of higher-level goals that players tend to pursue in the game. The algorithm is derived from a simultaneous-move modification of the maxn algorithm by only searching the branches of the game tree that are consistent with pursuing player’s goals. The algorithm has been tested on a real-world-based scenario modelled as a large-scale asymmetric game. The experimental results obtained indicate the ability of the goalbased heuristic to reduce the search space to a manageable level even in complex domains while maintaining the high quality of resulting strategies.

Paper Nr: 92
Title:

NEW CONFIDENCE MEASURES FOR STATISTICAL MACHINE TRANSLATION

Authors:

Caroline Lavecchia, David Langlois, Kamel Smaïli and Sylvain Raybaud

Abstract: A confidence measure is able to estimate the reliability of an hypothesis provided by a machine translation system. The problem of confidence measure can be seen as a process of testing: we want to decide whether the most probable sequence of words provided by the machine translation system is correct or not. In the following we describe several original word-level confidence measures for machine translation, based on mutual information, n-gram language model and lexical features language model. We evaluate how well they perform individually or together, and show that using a combination of confidence measures based on mutual information yields a classification error rate as low as 25.1% with an F-measure of 0.708.

Paper Nr: 93
Title:

DATAZAPPER: GENERATING INCOMPLETE DATASETS

Authors:

Ann E. Nicholson, Kevin B. Korb and Yingying Wen

Abstract: Evaluating the relative performance of machine learners on incomplete data is important because one common problem with real data is that the data is often incomplete, which means that some values in the data are not present. DataZapper is a tool for uncreating data: given a dataset containing joint samples over variables, DataZapper will make a specified percentage of observed values disappear, replaced by an indication that the measurement failed. Since the causal mechanisms of measurement that result in failed measurements may depend in arbitrary ways upon the system under study, it is important to be able to produce incomplete data sets which allow for such arbitrary dependencies. DataZapper is the only tool that allows any kind of dependence, and any degree of dependence, in its generation of missing data. We illustrate its use in a machine learning experiment and offer it to the data mining and machine learning communities.

Paper Nr: 103
Title:

A BATCH LEARNING VECTOR QUANTIZATION ALGORITHM FOR CATEGORICAL DATA

Authors:

Ning Chen and Nuno C. Marques

Abstract: Learning vector quantization (LVQ) is a supervised learning algorithm for data classification. Since LVQ is based on prototype vectors, it is a neural network approach particularly applicable in non-linear separation problems. Existing LVQ algorithms are mostly focused on numerical data. This paper presents a batch type LVQ algorithm used for mixed numerical and categorical data. Experiments on various data sets demonstrate the proposed algorithm is effective to improve the capability of standard LVQ to deal with categorical data.

Paper Nr: 110
Title:

HYPERTREE DECOMPOSITION FOR SOLVING CONSTRAINT SATISFACTION PROBLEMS

Authors:

Abdelmalek Ait-Amokhtar, Kamal Amroun and Zineb Habbas

Abstract: This paper deals with the structural decomposition methods and their use for solving Constraint Satisfaction problems (CSP). mong the numerous structural decomposition methods, hypertree decomposition has been shown to be the most general CSP decomposition. However so far the exact methods are not able to find optimal decomposition of realistic instances in a reasonable CPU time. We present Alea, a new heuristic to compute hypertree decomposition. Some experiments on a serial of benchmarks coming from the literature or the industry permit us to observe that Alea is in general better or comparable to BE (Bucket Elimination), the best well known heuristic, while it generally outperforms DBE (Dual Bucket Elimination), another successful heuristic. We also experiment an algorithm (acyclic solving algorithm) for solving an acyclic CSP obtained by using the heuristic Alea. The experimental results we obtain are promising comparing to those obtained by solving CSP using an enumerative search algorithm.

Paper Nr: 111
Title:

AUTOMATED ACQUISITION OF ACTION KNOWLEDGE

Authors:

M. M. West, N. E. Richardson, S. N. Cresswell and T. L. McCluskey

Abstract: AI planning engines require detailed specifications of dynamic knowledge of the domain in which they are to operate, before they can function. Further, they require domain-specific heuristics before they can function efficiently. The problem of formulating domain models containing dynamic knowledge regarding actions is a barrier to the widespread uptake of AI planning, because of the difficulty in acquiring and maintaining them. Here we postulate a method which inputs a partial domain model (one without knowledge of domain actions) and training solution sequences to planning tasks, and outputs the full domain model, including heuristics that can be used to make plan generation more efficient. To do this we extend GIPO’s Opmaker system (Simpson et al., 2007) so that it can induce representations of actions from training sequences without intermediate state information and without requiring large numbers of examples. This method shows the potential for considerably reducing the burden of knowledge engineering, in that it would be possible to embed the method into an autonomous program (agent) which is required to do planning. We illustrate the algorithm as part of an overall method to acquire a planning domain model, and detail results that show the efficacy of the induced model.

Paper Nr: 119
Title:

QUALITY OF KNOWLEDGE IN GROUP DECISION SUPPORT SYSTEMS

Authors:

Cesar Analide, José Neves, José Bulas Cruz, Luís Lima, Paulo Novais and Ricardo Costa

Abstract: In this work it is addressed the problem of knowledge evaluation in a VirtualECare Group Decision Supporting System (GDSS), in terms of an Multi-valued Extended Logic Programming language, which is aimed at sustaining online healthcare services. Indeed, reasoning with incomplete and uncertain knowledge have to be dealt with, due to the particular nature of the healthcare services, where the awful consequences of bad decisions, or lack of timely ones, demand for a responsible answer.

Paper Nr: 122
Title:

LEARNING USER INTENTIONS IN SPOKEN DIALOGUE SYSTEMS

Authors:

Hamid R. Chinaei, Brahim Chaib-draa and Luc Lamontagne

Abstract: A common problem in spoken dialogue systems is finding the intention of the user. This problem deals with obtaining one or several topics for each transcribed, possibly noisy, sentence of the user. In this work, we apply the recent unsupervised learning method, Hidden Topic Markov Models (HTMM), for finding the intention of the user in dialogues. This technique combines two methods of Latent Dirichlet Allocation (LDA) and Hidden Markov Model (HMM) in order to learn topics of documents. We show that HTMM can be also used for obtaining intentions for the noisy transcribed sentences of the user in spoken dialogue systems. We argue that in this way we can learn possible states in a speech domain which can be used in the design stage of its spoken dialogue system. Furthermore, we discuss that the learned model can be augmented and used in a POMDP (Partially Observable Markov Decision Process) dialogue manager of the spoken dialogue system.

Paper Nr: 123
Title:

GOSSIP GALORE - A Conversational Web Agent for Collecting and Sharing Pop Trivia

Authors:

Feiyu Xu, Hans Uszkoreit, Hong Li, Peter Adolphs and Xiwen Cheng

Abstract: This paper presents a novel approach to a self-learning agent who collects and learns new knowledge from the web and exchanges her knowledge via dialogues with the users. The application domain is gossip about celebrities in the music world. The agent can inform herself and update the acquired knowledge by observing the web. Fans of musicians can ask for gossip information about stars, bands or people and groups related to them. This agent is built on top of information extraction, web mining, question answering and dialogue system technologies. The minimally supervised machine learning method for relation extraction gives the agent the capability to learn and update knowledge constantly from the web. The extracted relations are structured and linked with each other. Data mining is applied to the learned data to induce the social network among the artists and related people. The knowledge-intensive question answering technology enhanced by domain-specific inference and active memory allows the agent to have vivid and interactive conversations with users by utilizing natural language processing. Users can freely formulate their questions within the gossip data domain and access the answers in different ways: textual response, graph-based visualization of the related concepts and speech output.

Paper Nr: 144
Title:

WORD SEGMENTATION BASED ON HIDDEN MARKOV MODEL USING MARKOV CHAIN MONTE CARLO METHOD

Authors:

Takao Miura and Takuya Fukuda

Abstract: It is well-known that Japanese has no word boundary, so that we should think about how to separate each sentence into words by means of morphological analysis or some other word segmentation analysis. It is said, however, that the separation depends on domain specific rules. The author have proposed a sophisticated word separation method based on Conditional Random Fields (CRF). Unfortunately we need a huge amount of test corpus in application domains as well as computation time for learning. In this investigation, we propose a new approach to obtain test corpus based on Markov Chain Monte Carlo (MCMC) method, by which we can obtan efficient Markov model for segmentation.

Paper Nr: 148
Title:

DETERMINATION OF DRIVER’S HYPOVIGILANCE FROM BIOSIGNALS

Authors:

Dave Edwards, David Sommer, Martin Golz and Udo Trutschel

Abstract: Robust and reliable determination of hypovigilance is required in many areas, particularly transportation. Here, new products of Fatigue Monitoring Technologies (FMT) emerge. Their development and assessment requires an independent reference standard of driver’s hypovigilance. Until recently most approaches utilized electrooculography (EOG) and electroencephalography (EEG) combined to descriptive statistics of a few time or spectral domain features, like e.g. power spectral densities (PSD) averaged in four to six spectral bands. Here we present a more general approach of data fusion of many features utilizing computational intelligence methods, like e.g. Support-Vector Machines (SVM). For simplicity, two classes were discriminated: slight and strong hypovigilance. Validation was performed by independent class labels which were assessed from Karolinska Sleepiness Scale (KSS) and from variation of lane deviation (VLD). The first is a measure of subjectively self-experienced hypovigilance, whereas the second is an objective measure of performance decrements. 16 young volunteers participated in overnight experiments in our real car driving simulation lab. Results were compared with PERCLOS (percentage of eye closure), an oculomotoric variable utilized in several FMT systems. We conclude that EEG and EOG biosignals are substantially more suited to assess driver’s hypovigilance than the PERCLOS biosignal. In addition, computational intelligence performed better when objective class labels were used instead of subjective class labels.

Short Papers
Paper Nr: 11
Title:

A KNOWLEDGE-BASED SYSTEM FOR RISKS EVALUATION ON SOFTWARE PROJECTS VIABILITY

Authors:

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

Abstract: In software development, an adequate risks management increases the quality of the final product. However, the importance of this activity is not always acknowledged, and since it requires a high level of experience, it is often not carried out. This article presents a Knowledge-Based System that allows software developers and, or, project managers to evaluate the viability of a project on the basis of its risks: it offers an initial estimation of the risks that must be taken into account and of their impact on the software development project. The proposed system was designed according to the CommonKADS methodology and implemented by means of the Clips tool.

Paper Nr: 15
Title:

FACE RECOGNITION USING ENSEMBLE OF NEURAL NETWORKS

Authors:

A. Glazs and M. Alekseichevs

Abstract: Authors describe a novel approach for human faces recognition using ensembles (or committee) of artificial neural networks. In the task of human faces recognition there are several problems that should be considered: 1) overlapping of different sets (classes), for example, when distinguishing faces of twins; 2) the training time of neural networks can be limited. In this case it is not possible to reach correct recognition of training set during neural networks training. Therefore, the two-level hierarchical structure is used to recognize objects of examination (testing) set. As a result of neural networks training at the lower level a decisions set is formed. On the basis of the decisions set the final committee solution is constructed at the upper level. A special algorithm of weighted voting is proposed to form the committee decision. The experimental results show that the proposed algorithm is more effective in comparison with other known committee methods, when number of training iterations is limited.

Paper Nr: 16
Title:

BANKRUPTCY PREDICTION BASED ON INDEPENDENT COMPONENT ANALYSIS

Authors:

Armando Vieira and Ning Chen

Abstract: Bankruptcy prediction is of great importance in financial statement analysis to minimize the risk of decision strategies. It attempts to separate distress companies from healthy ones according to some financial indicators. Since the real data usually contains irrelevant, redundant and correlated variables, it is necessary to reduce the dimensionality before performing the prediction. In this paper, a hybrid bankruptcy prediction algorithm is proposed based on independent component analysis and learning vector quantization. Experiments show the algorithm is effective for high dimensional bankruptcy data and therefore improve the capability of prediction.

Paper Nr: 18
Title:

COMPARATIVE STUDY OF ARABIC AND FRENCH STATISTICAL LANGUAGE MODELS

Authors:

Kamel Smaili, Karima Meftouh and Mohamed Tayeb Laskri

Abstract: In this paper, we propose a comparative study of statistical language models of Arabic and French. The objective of this study is to understand how to better model both Arabic and French. Several experiments using different smoothing techniques have been carried out. For French, trigram models are most appropriate whatever the smoothing technique used. For Arabic, the n-gram models of higher order smoothed with Witten Bell method are more efficient. Tests are achieved with comparable corpora and vocabularies in terms of size.

Paper Nr: 23
Title:

SEMANTICS-PROVIDED ENVIRONMENT VIEWS FOR NORMALITY ANALYSIS-BASED INTELLIGENT SURVEILLANCE

Authors:

Javier Albusac, José Jesús Castro-Schez, Lorenzo M. López-López and Luis Jiménez-Linares

Abstract: Nowadays, the design and development of intelligent surveillance systems is a hot research topic thanks to the recent advances in related fields such as computer perception, artificial intelligence, and distributed devices infrastructures. These systems are gradually going from the classic CCTV passive surveillance systems towards systems which are capable of offering automatic interpretation of the events occurred in a monitored environment and decision support information based on the data obtained from a number of heterogeneous perception devices. In this work, we introduce the formal definition of an intermediate layer in the architecture of an intelligent surveillance system, of which purpose is to provide the components responsible for performing the reasoning processes with the data from the environment they need. Such data is provided by means of environment views, which are data objects that contain not only data from different sensors, but also associated semantics which depends on the particular context in which the analysis of the normality of a concept is performed.

Paper Nr: 25
Title:

HOW TO EASILY DESIGN REUSABLE BEHAVIOURS FOR SITUATED CHARACTERS?

Authors:

Jean-Christophe Routier and Tony Dujardin

Abstract: Since the action selection mechanism chooses the next fired action, we claim that it is the place where the character’s behaviour is defined. We propose an ASM wich is able to produce believable and reusable behaviours for situated cognitive characters. It is defined as a combination of several motivations. It is modular and robust to evolutions of the environment, hence the designer task of building behaviour is made easier. The design of NPC in MMORPG can particularly derive benefit from this ASM.

Paper Nr: 26
Title:

CLASSIFIER AGGREGATION USING LOCAL CLASSIFICATION CONFIDENCE

Authors:

David Štefka and Martin Holeňa

Abstract: Classifier aggregation is a method for improving quality of classification. Instead of using just one classifier, a team of classifiers is created, and the outputs of the individual classifiers are aggregated into the final prediction. In this paper, we study the potential of using measures of local classification confidence in classifier aggregation methods. We introduce four measures of local classification confidence and study their suitability for classifier aggregation. We develop two novel classifier aggregation methods which utilize local classification confidence and we compare them to two commonly used methods for classifier aggregation. The results on four artificial and five real-world benchmark datasets show that by incorporating local classification confidence into classifier aggregation methods, significant improvement in classification quality can be obtained.

Paper Nr: 29
Title:

A USEFUL LOGICAL SEMANTICS OF UML FOR QUERYING AND CHECKING UML CLASS DIAGRAM

Authors:

David Genest, Stéphane Loiseau and Thomas Raimbault

Abstract: In Knowledge Engineering, UML class diagram is the defacto standard for modeling object oriented systems. We propose a way for logical reasoning on UML class diagram, concerning querying and checking class diagram. First, we define an original logical semantics to UML class diagram. Our approach differs from other existing works, because we use a same set of predicates to translate any class diagram instead of other “ad hoc” approaches. Second, we extend UML, especially with variable and bicoloration, to express query and constraint into the visual environment of (extended-)UML.

Paper Nr: 32
Title:

DOMAIN ONTOLOGY EVOLUTION BY VERSIONING

Authors:

Danielle Boulanger and Guilaine Talens

Abstract: To solve the semantic conflicts in the cooperation of heterogenous databases, we propose a multi-agent system which contains domain ontologies. When a local source is added by an expert, ontology is dynamically created by the system. The expert can also completed it. It evolves with the update of the local base but also when an user performs a query. A process examines the query and creates temporary semantic links. These must be validated or not by the user. The result validation implies the version creation from temporary links. The modification and deletion of database elements by the expert perform the ontology evolution. Our research work treats evolution by the version concept.

Paper Nr: 45
Title:

BELIEFS ON INDIVIDUAL VARIABLES FROM A SINGLE SOURCE TO BELIEFS ON THE JOINT SPACE UNDER DEMPSTER-SHAFER THEORY - An Algorithm

Authors:

Kenneth O. Cogger and Rajendra P. Srivastava

Abstract: It is quite common in real world situations to form beliefs under Dempster-Shafer (DS) theory on various variables from a single source. This is true, in particular, in auditing. Also, the judgment about these beliefs is easily made in terms of simple support functions on individual variables. However, for propagating beliefs in a network of variables, one needs to convert these beliefs on individual variables to beliefs on the joint space of the variables pertaining to the single source of evidence. Although there are many possible solutions to the above problem that will yield beliefs on the joint space with the desired marginal beliefs, there is no method that will guarantee that the beliefs are derived from the same source, fully dependent evidence. In this article, we describe such a procedure based on a maximal order decomposition algorithm. The procedure is computationally efficient and is supported by objective chi-square and entropy criteria. While such assignments are not unique, alternative procedures that have been suggested, such as linear programming, are more computationally intensive and result in similar m-value determinations. It should be noted that our maximal order decomposition (i.e., minimum entropy) approach provides m-values on the joint space for fully dependent items of evidence.

Paper Nr: 49
Title:

DISTRIBUTED LEARNING ALGORITHM BASED ON DATA REDUCTION

Authors:

Ireneusz Czarnowski and Piotr Jędrzejowicz

Abstract: The paper presents an approach to learning classifiers from distributed data, based on a data reduction at a local level. In such case, the aim of data reduction is to obtain a compact representation of distributed data repositories, that include non-redundant information in the form of so-called prototypes. In the paper data reduction is carried out by simultaneously selecting instances and features, finally producing prototypes which do not have to be homogenous and can include different sets of features. From these prototypes the global classifier based on a feature voting is constructed. To evaluate and compare the proposed approach computational experiment was carried out. The experiment results indicate that data reduction at the local level and next merger of prototypes into the global classifier can produce very good classification results.

Paper Nr: 56
Title:

ANT COLONY SYSTEM ALGORITHM FOR EXTRACTING MATHEMATICAL RELATIONS FROM DATABASE

Authors:

L. H. A. Monteiro and R. F. Marques

Abstract: An algorithm, inspired on the strategy employed by ant colonies for seeking food, was developed in order to extract mathematical formulas from data. This algorithm, called Formula Miner, is applied in a breast cancer diagnosis database and its performance is compared to the performances of some well-known data mining algorithms.

Paper Nr: 66
Title:

COMPONENT-BASED FRAMEWORK FOR MOBILE DATA MINING WITH SUPPORT FOR REAL-TIME SENSORS

Authors:

Juha Röning, Perttu Laurinen and Taneli Rautio

Abstract: The increasing use of various mobile devices has shown that there is a need for mobile data mining applications. While many existing data mining frameworks can be modified to handle data streams generated in real time, they are usually too complex and inflexible to be used in mobile devices. This paper presents Mobile Smart Archive, a component-based framework for data stream mining in mobile devices. The framework takes care of generic data mining operations, allowing the application developer to concentrate on implementing only application-specific functionalities. This reduces implementation time and generates fewer errors, since the underlying framework of the application is tested and robust. The presented framework is written in C++ and it extends the existing Smart Archive framework with support for mobile systems and real-time sensors. The benefits of framework-based applications in the mobile world are presented by building and testing a demonstration program in different computer architectures. In this paper we show that the MSA framework is suitable for building data stream mining applications for the hardware-oriented mobile environment.

Paper Nr: 67
Title:

ARGUING OVER MOTIVATIONS WITHIN THE V3A-ARCHITECTURE FOR SELF-ADAPTATION

Authors:

Kostas Stathis, Laurent Vercouter and Maxime Morge

Abstract: The Vowel Agent Argumentation Architecture (V3A) is an abstract model by means of which an autonomous agent argues with itself to manage its motivations and arbitrate its possible internal conflicts. We propose an argumentation technique which specifies the internal dialectical process and a dialogue-game amongst internal components which can dynamically join/leave the game, thus having the potential to support the development of self-adaptive agents. We exemplify this dialectical representation of the V3A model with a scenario, whereby components of the agent's mind called facets can be automatically downloaded to argue an agent's motivation.

Paper Nr: 72
Title:

DATA MINING DRIVEN DECISION MAKING

Authors:

Antonio Fernández-Caballero and Marina V. Sokolova

Abstract: This paper introduces the details of the design of an agent-based decision support system (ADSS) for environmental impact assessment upon human health. We discuss the structure and the data mining methods of the designed ADSS. The intelligent ADSS described here provides a platform for integration of related knowledge coming from external heterogeneous sources, and supports its transformation into an understandable set of models and analytical dependencies, with the global aim of assisting a manager with a set of decision support tools.

Paper Nr: 73
Title:

USING EXPANDED MARKOV PROCESS AND JOINT DISTRIBUTION FEATURES FOR JPEG STEGANALYSIS

Authors:

Andrew H. Sung, Bernardete M. Ribeiro, Mengyu Qiao and Qingzhong Liu

Abstract: In this paper, we propose a scheme for detecting the information-hiding in multi-class JPEG images by combining expanded Markov process and joint distribution features. First, the features of the condition and joint distributions in the transform domains are extracted (including the Discrete Cosine Transform or DCT, the Discrete Wavelet Transform or DWT); next, the same features from the calibrated version of the testing images are extracted. A Support Vector Machine (SVM) is applied to the differences of the features extracted from the testing image and from the calibrated version. Experimental results show that this approach delivers good performance in identifying several hiding systems in JPEG images.

Paper Nr: 74
Title:

EMOTION-BASED MULTIMEDIA RETRIEVAL AND DELIVERY THROUGH ONLINE USER BIOSIGNALS - Multichannel Online Biosignals Towards Adaptative GUI and Content Delivery

Authors:

Eugénio Oliveira, Luís Paulo Reis and Vasco Vinhas

Abstract: Affective computing and multichannel multimedia distribution have gathered the time and investment of industry and academics. The proposed system merges such domains so that ubiquitous system can be enhanced through online user emotion assessment based on user’s biosignals. It was used IAPS as a emotional library for controlled visual stimuli and biosignals were collected in real-time - heartbeat rate and skin conductance - in order to online assess the user's emotional state through Russell’s Circumplex Model of Affect. In order to improve usability and session setup, a distributed architecture was used so that software models might be physically detached. The conducted experimental sessions and the validation interviews supported the system's efficiency not only in real-time discrete emotional state assessment but also considering the emotion inducing process. The next logic step consists in replicating the achieved success in multi-format multimedia contents without the need of pre-defined restricted emotional metadata.

Paper Nr: 76
Title:

SEMI-AUTONOMOUS RULE ACQUISITION FRAMEWORK USING CONTROLLED LANGUAGE AND ONTOLOGY

Authors:

Mye M. Sohn and Yungyu Choi

Abstract: This paper presents a framework for rule extraction from unstructured web documents. To do so, we adopted the controlled language technique to reduce the burden as well as error of a domain expert and suggest a rule extraction framework that uses ontology, to solve the problem of missing variable and value that may be caused by incomplete natural language. Here, it is referred to as NEXUCE (New rule EXtraction Using ontology and Controlled natural languagE). To evaluate the performance of the NEXUCE framework, the natural language statements were collected from the websites of Internet bookstores and the rule extraction capability was analyzed. As a result, it was proven that NEXUCE can have more than 70% of rule extraction from unstructured web documents.

Paper Nr: 83
Title:

A KNOWLEDGE-RICH APPROACH TO THE RAPID ENUMERATION OF QUASI-MAGIC SUDOKU SEARCH SPACES

Authors:

I. J. Grimstead, P. A. Roach, S. Perkins and S. K. Jones

Abstract: The popular logic puzzle, Sudoku, consists of placing the digits 1, …, 9 into a 9 x 9 grid, such that each digit appears only once in each row, column, and subdivided ‘mini-grid’ of size 3 x 3. Uniqueness of solution of a puzzle is ensured by the positioning of a number of given values. Quasi-Magic Sudoku adds the further constraint that within each mini-grid, every row, column and diagonal must sum to 15±∆, where ∆ is chosen to take a value between 2 and 8. Recently Sudoku has been shown to have potential for the generation of erasure correction codes. The additional quasi-magic constraint results in far fewer given values being required to ensure uniqueness of solution, raising the prospect of improved usefulness in code generation. Recent work has highlighted useful domain knowledge concerning cell interrelationships in Quasi-Magic Sudoku for the case ∆ = 2, providing pruning conditions to reduce the size of search space that need be examined to ensure uniqueness of solution. This paper examines the usefulness of the identified rich knowledge in restricting search space size. The knowledge is implemented as pruning conditions in a backtracking implementation of a Quasi-Magic Sudoku solver, with a further cell ordering heuristic. Analysis of the improvement in processing time, and thereby of the potential usefulness of Quasi-Magic Sudoku for code generation, is provided.

Paper Nr: 88
Title:

DOCUMENT RELATION ANALYSIS BASED ON COMPRESSIBILITY VECTOR

Authors:

Daisuke Matsuzaki, Hisashi Koga, Nuo Zhang and Toshinori Watanabe

Abstract: Nowadays, there are a great deal of e-documents can be easily accessed. It will be beneficial if a method can evaluate documents and abstract significant content. Similarity analysis and topic extraction are widely used as document relation analysis techniques. Most of the methods are based on dictionary-base morphological analysis. They cannot meet the requirement when the Internet grows fast and new terms appear but dictionary cannot be automatically updated fast enough. In this study, we propose a novel document relation analysis (topic extraction) method based on a compressibility vector. Our proposal does not require morphological analysis, and it can automatically evaluate input documents. We will examine the proposal with using model document and Reuters-21578 dataset, for relation analysis and topic extraction. The effectiveness of the proposed method will be shown in simulations.

Paper Nr: 108
Title:

NEW EXTENDED AND QUANTIFIED CONSTRAINTS IN XML SCHEMA

Authors:

A. Duffoux, B. Duval and S. Loiseau

Abstract: In this paper, we present a new model to represent complex constraints in XML schema. Due to its flexibility and its capacity to describe all kinds of data, XML has become a widely used exchange format during the last years. Hence, such data have been integrated in several information systems. However these systems need strengthness and coherence that XML in its primary form can not provide. We thus propose to extend classical XML schema in order to integrate a quantification of constraints and to allow conditional constraints on several elements. Thanks to this extension, XML applications can have a richer and stronger framework. To illustrate the use of this new model, we present a case study concerning XML curriculum vitae treatment.

Paper Nr: 109
Title:

UPDATING A LOGISTIC DISCRIMINATION RULE - Comparing Some Logistic Submodels in Credit-scoring

Authors:

Christophe Biernacki and Farid Beninel

Abstract: Often a discriminant rule to predict individuals from a certain subpopulation is given, but the individuals to predict belong to another subpopulation. Two distinct approaches are usually implemented. The first approach is to apply the same discriminant rule for the two subpopulations. The second approach is to estimate a new rule for the second subpopulation. The first classical approach does not take into account differences between subpopulations. The second approach is not reliable in cases of few available individuals from the second subpopulation. In this paper we develop an intermediate approach: we get a rule to predict in the second population combining the experienced rule of the first population and the available learning sample from the second. Different models combining the first rule and the labeled sample from the second population are estimated and tested.

Paper Nr: 115
Title:

SYROTEK - On an e-Learning System for Mobile Robotics and Artificial Intelligence

Authors:

Jan Chudoba, Jan Faigl, Karel Košnar, Libor Přeučil and Miroslav Kulich

Abstract: The paper deals with motivations and design leading to succeeding development of a system for remote learning of mobile robotics topics. Specifically, the designed SyRoTek system comprises a team of 12 tele-operated mobile robots acting in 24/7 maintenance-free environment equipped with charging docks and reconfigurable system of obstacles, all being observable and accessible via Internet. The SyRoTek system together with an attached e-learning environment it is aimed to provide the features real data gathering and real robot motion execution. The whole set-up is targeted on training purposes in basic and advanced courses in the field of Intelligent and Mobile Robotics and Collective Robotics as well as for test/verification purposes in a research domain.

Paper Nr: 125
Title:

WEB PAGE SUMMARIZATION BY USING CONCEPT HIERARCHIES

Authors:

Ben Choi and Xiaomei Huang

Abstract: To address the problem of information overload and to make effective use of information contained on the Web, we created a summarization system that can abstract key concepts and can extract key sentences to summarize text documents including Web pages. Our proposed system is the first summarization system that uses a knowledge base to generate new abstract concepts to summarize documents. To generate abstract concepts, our system first maps words contained in a document to concepts contained in the knowledge base called ResearchCyc, which organized concepts into hierarchies forming an ontology in the domain of human consensus reality. Then, it increases the weights of the mapped concepts to determine the importance, and propagates the weights upward in the concept hierarchies, which provides a method for generalization. To extract key sentences, our system weights each sentence in the document based on the concept weights associated with the sentence, and extracts the sentences with some of the highest weights to summarize the document. Moreover, we created a word sense disambiguation method based on the concept hierarchies to select the most appropriate concepts. Test results show that our approach is viable and applicable for knowledge discovery and semantic Web.

Paper Nr: 127
Title:

AGENT APPROACH TO SITUATION ASSESSMENT

Authors:

Daniele Nardi, Giuseppe Paolo Settembre and Roberta Pigliacampo

Abstract: The Situation Assessment process is evolving from signal-analysis based centralized models to high-level reasoning based net-centric models, according to new paradigms of information fusion proposed by recent research. In this paper we propose a knowledge-based approach to Situation Assessment, and we apply it to maritime surveillance. A symbolic model of the world is given to an agent based framework, that use Description Logics based automatic reasoning to devise on estimate of the situation. The described approach potentially allows distributed Situation Assessment through agent collaboration. The goal is to support the understanding of the situation by relying on automatic interpretation processes, in order to provide the human operators with a synthetic vision, pointing out which are the elements on the scenario that require human intervention. The success of high level reasoning techniques is shown through experiments in a real maritime scenario, in which our approach is compared to the performances of human operators which monitor the situation without any support of an automatic reasoning system.

Paper Nr: 134
Title:

THE DARMSTADT CHALLENGE - The Turing Test Revisited

Authors:

Carlos Ramos, D. Cook, F. Flentge, G. Marreiros, J. C. Augusto, M. Bohlen, Weijun Qin and Yue Suo

Abstract: Significant work has been done in the areas of Pervcomp/Ubicomp/Smart Environments with advances on making proactive systems, but those advances have not made these type of systems accurately proactive. On the other hand a great deal is needed to make systems more sensible/sensitive and trustable (both in terms of reliability and privacy). We put forward the thesis that a more integral and social-aware sort of intelligence is needed to effectively interact, decide and act on behalf of people’s interest and that a way to test how effective systems are achieving these desirable behaviour is needed as a consequence. We support our thesis by providing examples on how to measure effectiveness in variety of different environments.

Paper Nr: 136
Title:

THE RE-USE OF EXPERIENCE THROUGH THE USE OF CBR IN INFORMATION SYSTEMS MODELLING

Authors:

Ernesto Costa, Luís Amaral and Paulo Tomé

Abstract: Information Systems Development (ISD) is an important organization activity. IT professionals develop models that describe specific organizational aspects. The IT professionals experience plays an important role in the development of a model. Generally, IT professionals apply past experience acquired in the previous ISD processes. This paper describes a Case-Based-Reasoning (CBR) tool that enables the use of experience in the model development in the context of ISD process.

Paper Nr: 149
Title:

APPLYING Q-LEARNING TO NON-MARKOVIAN ENVIRONMENTS

Authors:

Arkady Borisov and Jurij Chizhov

Abstract: This paper considers the problem of intelligent agent functioning in non-Markovian environments. We advice to divide the problem into two subproblems: just finding non-Markovian states in the environment and building an internal representation of original environment by the agent. The internal representation is free from non Markovian states because insufficient number of additional dynamically created states and transitions are provided. Then, the obtained environment might be used in classical reinforcement learning algorithms (like SARSA(λ)) which guarantee the convergence by Bellman equation. A great difficulty is to recognize different “copies” of the same states. The paper contains a theoretical introduction, ideas and problem description, and, finally, an illustration of results and conclusions.

Paper Nr: 158
Title:

COORDINATION OF SELF-OPTIMIZING MECHATRONIC SYSTEMS - A New Application for Multi-Agent Planning

Authors:

Benjamin Klöpper and Wilhelm Dangelmaier

Abstract: The paradigm of self-optimization introduces flexible and highly adaptive mechatronic systems. During the exploiation of this flexibility, new problems arise. One of these problems is the coordination of mechatronics systems and subsystems. This paper introduces the application area self-optimizing mechatronic systems and identifies the arising coordination problems. Two main scenarios are identified: coordination of autonomous mechatronic systems and coordination of several subsystems within an autonomous mechatronic system. We will show that multi-agent technology and in particular multi-agent planning can be applied to solve both coordination scenarios.

Paper Nr: 160
Title:

EQUATION DISCOVERY FOR MACROECONOMIC MODELLING

Authors:

Dimitar Kazakov and Tsvetomira Tsenova

Abstract: This article describes a machine learning based approach applied to acquiring empirical forecasting models. The approach makes use of the LAGRAMGE equation discovery tool to define a potentially very wide range of equations to be considered for the model. Importantly, the equations can vary in the number of terms and types of functors linking the variables. The parameters of each competing equation are automatically fitted to allow the tool to compare the models. The analysts using the tool can exercise their judgement twice, once when defining the equation syntax, restricting in such a way the search to a space known to contain several types of models that are based on theoretical arguments. In addition, one can use the same theoretical arguments to choose among the list of best fitting models, as these can be structurally very different while providing similar fits on the data. Here we describe experiments with macroeconomic data from the Euro area for the period 1971–2007 in which the parameters of hundreds of thousands of structurally different equations are fitted and the equations compared to produce the best models for the individual cases considered. The results show the approach is able to produce complex non-linear models with several equations showing high fidelity.

Posters
Paper Nr: 10
Title:

INTEGRATED SYNTACTIC AND SEMANTIC DATA STRUCTURING - An Abstraction of Intelligent Man-machine Communication

Authors:

Wladyslaw Homenda

Abstract: The paper discusses an approach to intelligent man-machine communication which is a fundamental topic of intelligent interface of any software. The approach presented in the paper is based on integration of syntactic and semantic approximations of information structure. In most cases of communication automatic revealing of the structure of information subjected to communication is not possible due to its complexity. Proposed solution of this problem is based on raw, approximated descriptions of information entities and relations between them. This approach reveals parallel syntactic and semantic attempts to so called languages of natural communication. Duality of both attempts automatically exposes structure of information and allows a machine for information maintenance and processing in human-like way. The attempt is reflected in the domain of music information taking music notation as the language of natural communication.

Paper Nr: 78
Title:

DATA TYPE MANAGEMENT IN A DATA MINING APPLICATION FRAMEWORK

Authors:

Juha Röning, Lauri Tuovinen and Perttu Laurinen

Abstract: Building application frameworks is one of the major approaches to code and design reuse in object-oriented software engineering. Some frameworks target a particular application domain, adopting a number of domain-specific problems to be addressed by the framework in such a fashion that there is no need for application developers to devise solutions of their own to those problems. When the target domain is data mining, one interesting domain-specific problem is management of the data types of model parameters and data variables. This is not trivial because the framework must be able to convert parameter and variable values between different representations, and it would be preferable to have these conversions take place transparently, without involving the application programmer. This is not difficult to achieve if the framework restricts the programmer to a predefined set of allowed data types, but if such a restriction is undesirable, the framework needs an extension mechanism in its type management subsystem. Smart Archive, a framework for developing data mining applications in Java or C++, includes such a mechanism, based on a type dictionary document and a type renderer programming interface. These make it possible to handle even highly complex values such as collections of instances of programmer-defined classes in a variety of platform-independent representation formats. The benefits of this approach can be seen in how the framework interfaces with databases through data sinks and in how it exports and imports application configurations.

Paper Nr: 89
Title:

A COMPUTATIONAL MODEL FOR VISUAL METAPHORS - Interpreting Creative Visual Advertisements

Authors:

Amitash Ojha, Angela Schwering, Bipin Indurkhya, Helmar Gust, Kai-Uwe Küehnberger, Tonio Wandmacher and Ulf Krumnack

Abstract: Coming up with new and creative advertisements is a sophisticated task for humans, because creativity requires breaking conventional associations to create new juxtaposition of familiar objects. Using objects in an uncommon context attracts the viewer’s attention and is an effective way to communicate a message in advertisements. Perceptual similarity seems to be a major source for creativity in the domain of visual metaphors, e.g. replacing objects by perceptually similar, but conceptually different objects is a technique to create new and unconventional interpretations. In this paper, we analyze the role of perceptual similarity in advertisements and propose an extension of Heuristic-Driven Theory Projection, a computational theory for analogy making that can be used to automatically compute interpretations of visual metaphors.

Paper Nr: 113
Title:

HUMAN-MACHINE INTERFACE TO CONTROL A ROBOT WITH THE NINTENDO WII REMOTE

Authors:

Armando Sousa, Daniel Coutinho and Luís Paulo Reis

Abstract: This paper intends to demonstrate the development of and easy-to-use local human-machine interface that would allow any user to control all kinds of service robots intuitively. This interface is based on the Nintedo Wii remote controller and consists of three operating modes: a steering wheel, an infra-red monitor and a movement identifier. These modes were tested on a cleaning robot and they led to very satisfactory results, proving that the Wiimote is an inexpensive and interesting way of making this kind of interfaces.

Paper Nr: 137
Title:

ADAPTATIVE MULTIMODAL ARCHITECTURES MANAGING SOFTWARE QUALITIES

Authors:

Amar Ramdane-Cherif, Hicham Djenidi and Nicole Lévy

Abstract: Multimodal interfaces for natural human-computer interaction involve complex architectures that should facilitate the process of matching IT to people. These architectures should react to events occurring simultaneously, and possibly redundantly, from different input media. In this paper, intelligent expert agent-based architecture for multimedia multimodal dialog protocols are proposed. The generic components of the multimodal architecture are monitored by an expert agent, which can perform dynamic changes in reconfiguration, adaptation and evolution at the architectural level. Software performance and usability are maintained by the expert agent via a scenario-based methodology. The expert agent’s behavior modeled by Petri nets permits a software quality tradeoff between attributes of usability and other software attributes like system’s performance.

Paper Nr: 138
Title:

SOFTWARE ARCHITECTURE EVALUATION APPROACH

Authors:

Amar Ramdane-Cherif, Nicole Lévy and Olfa Lamouchi

Abstract: This paper describes our approach for software architecture quality evaluation. The mechanics of this evaluation is based on quality model, metric model and a set of evaluation methods. These models are considered as a hierarchy properties structured set. The final properties need to be measured using metrics. For this purpose a metric measurement-based framework is linked to the defined quality model. In this evaluation approach an indication of overall quality can be determined using a Fuzzy engine.

Paper Nr: 154
Title:

AUTOMATIC MULTILINGUAL LEXICON GENERATION USING WIKIPEDIA AS A RESOURCE

Authors:

Ahmad R. Shahid and Dimitar Kazakov

Abstract: This paper proposes a method for creating a multilingual dictionary by taking the titles of Wikipedia pages in English and then finding the titles of the corresponding articles in other languages. The creation of such multilingual dictionaries has become possible as a result of exponential increase in the size of multilingual information on the web. Wikipedia is a prime example of such multilingual source of information on any conceivable topic in the world, which is edited by the readers. Here, a web crawler has been used to traverse Wikipedia following the links on a given page. The crawler takes out the title along with the titles of the corresponding pages in other targeted languages. The result is a set of words and phrases that are translations of each other. For efficiency, the URLs are organized using hash tables. A lexicon has been constructed which contains 7-tuples corresponding to 7 different languages, namely: English, German, French, Polish, Bulgarian, Greek and Chinese.

Paper Nr: 162
Title:

TASK MANAGEMENT AND ITINERARY PLANNING - An Integrated View based on Multi-Agent Systems

Authors:

Fábio L. Correia, Rosaldo J. F. Rossetti and Rui F. S. Amaro

Abstract: The main objective of this paper is to describe the framework of an agent-based agenda manager. The technology herein presented is intended to be able to assist a user in his/hers every day’s life, supporting all aspects of activities to be carried out in different places and times. Differently from other tools with the same ability, our agenda agent goes beyond the simple task of managing activities and their common attributes, such as date, time and place at which an activity is to be performed. Profiting from all potentials offered by mobile communication and portable devices, activities must now be assisted throughout their whole lifecycle, meaning the user will be able to optimize his/hers daily agenda including journeys he/she must make between places of two consecutive activities. This paper reports on the first steps towards the specification of the whole multi-agent architecture for an agenda management system, accounting for real-time and geographical distribution constraints that are inherent in this kind of systems.

Area 2 - Agents

Full Papers
Paper Nr: 2
Title:

TIERED LOGIC FOR AGENTS

Authors:

John Newsome Crossley and Rosalito Perez Cruz

Abstract: We introduce a new kind of logic for agents in different localities, which works in tiers or layers. At the base are local worlds with their own logic. Above them is a global logic that takes statements from the local worlds and combines them. This allows communications between the different localities. We give a basic example using first order logic as the local logic and propositional calculus at the global level. As a more sophisticated example we use the algebraic specification language CASL and take the locations as specificationsm. Moreover we then permit the combination of such specifications according to the architectural specifications of CASL. Although we only consider two layers in the present paper, we see no reason why the approach should not be extended to any finite number of tiers. We prove soundness and completeness proofs for our logics.

Paper Nr: 14
Title:

AN AGENT-BASED APPLICATION FOR HOME INTELLIGENCE

Authors:

Ambra Molesini, Andrea Omicini and Enrico Denti

Abstract: Ambient Intelligence is an interesting research application area for Multi-Agent Systems. In this paper, we focus on the methodological support that the agent-oriented methodologies can provide to such kind of systems: in particular we present HomeManager, an application for the control of an intelligent home designed through SODA—an agent-oriented methodology. In this vision, the house is seen as an intelligent environment made of independent and distributed devices, each equipped with an agent to support the user’s goals and tasks.

Paper Nr: 57
Title:

USING AGENTS’ ATTITUDES AND ASSESSMENTS IN AUTOMATED FUZZY BIDDING STRATEGY

Authors:

Jun Ma and Madhu Lata Goyal

Abstract: To be successful in multi-attribute auction, agents must be capable of adapting to continuous changing bidding price. This paper presents a novel fuzzy attitude based bidding strategy (FA-Bid), which employs dual assessment technique i.e. assessment of multiple attributes of the goods as well as assessment of agents attitude (eagerness) to procure an item in automated auction. The assessment of attributes adapts the fuzzy sets technique to handle uncertainty of the bidding process as well use heuristic rules to determine attitude of bidding agents in simulated auctions to procure goods. The overall assessment is used to determine a price range based on current bid, which finally selects the best one as the new bid.

Paper Nr: 71
Title:

TOWARDS AN INTEGRATIVE METHODOLOGY FOR DEVELOPING MULTI-AGENT SYSTEMS

Authors:

Antonio Fernández-Caballero and José M. Gascueña

Abstract: A great number of methodologies to develop MAS systems have been proposed in the last few years. But, a perfect methodology that satisfies all the developer necessities can not be found. This is the reason why different methodologies are studied to create a new one. In this article, a methodology that includes all steps from the capture of requirements to the implementation and deployment of an agent-based application is proposed. In first place, an Analysis Overview Diagram is created to obtain an initial sketch of the application. Afterwards, the model obtained - by following the two first stages proposed by Prometheus methodology - is integrated into INGENIAS through UML-AT language. Next, the modelling goes on with INGENIAS. Finally, code is generated for the ICARO-T platform.

Paper Nr: 79
Title:

APPROXIMATED WINNER DETERMINATION FOR A SERIES OF COMBINATORIAL AUCTIONS

Authors:

Naoki Fukuta and Takayuki Ito

Abstract: In this paper, we propose approximated winner determination algorithms for iteratively conducted combinatorial auctions. Our algorithms are designed to effectively reuse last-cycle solutions to speed up the initial approximation performance on the next cycle. Experimental results show that our proposed algorithms outperform existing algorithms when a large number of similar bids are contained through iterations. Also, we propose an enhanced algorithm that effectively avoids the undesirable reuse of the last solutions in the algorithm without serious computational overheads.

Paper Nr: 80
Title:

PERSONALIZATION OF A TRUST NETWORK

Authors:

Laurent Lacomme, Valérie Camps and Yves Demazeau

Abstract: Trust and personalization are two important notions in social network that have been intensively developed in multi-agent systems during the last years. But there is few works about integrating these notions in the same network of agents. In this paper, we present a way to integrate trust and personalization in an agent network by adding a new dimension to the calculus of trust in the model of Falcone and Castelfranchi, which we will call a similarity degree. We first present the fundamental notions and models we use, then the model of integration we developed and finally the experiments we made to validate our model.

Paper Nr: 82
Title:

AGENT BASED MODELING AND SYSTEM DYNAMICS IN HEALTHCARE - Modeling Two Stage Preventive Medical Checkup Systems

Authors:

Andreas Martischnig, Gerhard Stark and Siegfried Voessner

Abstract: Modeling preventive medical checkup systems (PMCS) is an important part of predicting future healthcare coverage. In this paper we show how to model a two stage interdependent System as it applies to basic cancer prevention. Starting with a short introduction of the two used modeling techniques we show the basic principle of the preventive cancer checkup process (PCCP) and how it was modeled with these opposing approaches. We then extract the key benefits from each technique and also their shortcomings when applying it onto the PCCP. Furthermore we show at what level of detail which method should be used to gain the most valuable insight into those complex checkup systems.

Paper Nr: 90
Title:

FROM REACTIVE MULTI-AGENTS MODELS TO CELLULAR AUTOMATA - Illustration on a Diffusion-Limited Aggregation Model

Authors:

Antoine Spicher, Nazim Fatès and Olivier Simonin

Abstract: This paper deals with the synchronous implementation of situated Multi-Agent Systems (MAS) in order to have no execution bias and to allow their programming on massively parallel computing devices. For this purpose we investigate the translation of discrete MAS into Cellular Automata (CA). Contrarily to the sequential scheduling generally used in MAS simulations, CA are a model for massively parallel computing where the updating of the components is synchronous. However, CA expressiveness is limited and not always adapted to build models where independent entities move and act on neighbor cells. After illustrating these issues on a simple example, we propose a generic method to translate a discrete MAS into a CA, called a transactional CA. Our approach consists in using the influence-reaction model to perform this translation.

Paper Nr: 106
Title:

A UNIFIED APPROACH FOR RECONCILING CHARACTERS AND STORY IN THE REALM OF AGENCY

Authors:

Rossana Damiano and Vincenzo Lombardo

Abstract: In the last decade, a number of computational systems for entertainment and communication have appeared, that share a set of common features, including the use of artificial characters and the reference to drama and storytelling. Systems for interactive storytelling and drama rely on agent theories to model characters, and adopt planning techniques to cope with non-determinism at the story level, combining them according to sophisticate architectural designs. However, a consolidated approach has not emerged yet, that fully reconciles these two dimensions. In this paper, we propose a unifying framework to accommodate the tension between story control and character behavior and we claim that the accurate modeling of agency is a prerequisite to the success of attempts to solve this tension. By using this framework to analyze practical systems we point out that the importance of agency is acknowledged by successful systems, although only implicitly in most cases.

Short Papers
Paper Nr: 6
Title:

A NEW PERFORMATIVE FOR HANDLING LACK OF ANSWERS OF AUTONOMOUS AGENTS

Authors:

Amal El Fallah Seghrouchni, Katia Potiron and Patrick Taillibert

Abstract: An agent can send a message and never receive a response, this is what we name the ”empty mailbox problem” this paper is concerned with. The causes of the problem can lie in low level layer as, for instance, in communication links, but also in the behavior of the autonomous entity the agent is interacting with, which can choose not to respond. The task is not easy, for the agents developer, to find what is to do in such cases. The proposed solution consists in a performative and the associated meta-protocol. This results into a generic method to handle the empty mailbox problem in the case of temporary faults. Some prospects are given to handle permanent faults.

Paper Nr: 34
Title:

JAMOCHAAGENT - A Rule-based Programmable Agent

Authors:

Alexander Wilden, Karl-Heinz Krempels and Uta Christoph

Abstract: Agent programming in compliance with standardized interaction mechanisms is a challenging task in agent based application development. This results from standard-compliant agent development frameworks that provide support for the interaction mechanisms on one hand and non-standardized high level programming inference machines for knowledge processing on the other hand. We propose an approach to automated speech act consumption and production within MAS by mapping agent behaviour onto a rule-based system. We show how speech acts have to be transformed, resolved and retransformed into the appropriate reply act to comply with predefined/given interaction protocols. This shift of behaviour definition onto a rule-based system allows for a convenient adaptation of agent behavior at runtime without the necessity of time consuming recompilation.

Paper Nr: 43
Title:

LANE CHANGING MODEL WITH EARLY COMMUNICATION OF INTENTIONS

Authors:

Kazuko Takahashi and Tomoki Takasago

Abstract: This paper describes the modeling and simulation of traffic flow with lane changing based on inter-vehicle communications. We regard vehicles as autonomous agents, and construct a simple traffic model in which some agents change lanes. We propose a new method for an agent to change lanes in which it tells the neighboring agents its intention beforehand, shares information with them, and determines the lane change time in cooperation with the other agents. The result of simulating this model showed that the early communication of intentions is effective in avoiding traffic jams and supporting smooth transportation.

Paper Nr: 59
Title:

UPDATING TECHNIQUE FOR PARTICLE SWARM OPTIMIZATION IN NONLINEAR DYNAMIC SYSTEMS

Authors:

Syahrulanuar Ngah, Takaaki Baba and Zhu Hui

Abstract: Dealing with searching and tracking an optimal solution in dynamic environment becomes more frequently nowadays. For dealing with this matter, Particle Swarm Optimization – Random Times Variable Inertia Weight and Acceleration Coefficient (PSO-RTVIWAC) concept, motivated by Particle Swarm Optimization-Time Variable Acceleration Coefficient (PSO-TVAC) and Particle Swarm Optimization-Random Inertia Weight (PSO-RANDIW) was introduced. PSO-RTVIWAC can accomplish an acceptable accuracy in detecting the target with the small number of particle and iteration. This paper will discuss about modifying the fitness value in the update mechanism for determining the local best and global best to improve the accuracy of detecting the target. By adding a constant value to the current stored fitness value, it will give the opportunity to the next fitness value to be the best fitness value. The result from this modifying technique then will be compared with PSO-RTVIWAC to evaluate the performance.

Paper Nr: 64
Title:

AGENT COALITION FORMATION VIA INDUCING TRUST RATIO

Authors:

Ahmed Rafea, Osama Ismail, Reem Bahgat and Samhaa R. El-Beltagy

Abstract: This work presents a model for assigning trust values to agents operating within a collaborative multi-agent system. The model enables agents to assess the trustworthiness of their peers, and thus, to be able to select reliable ones for cooperation and coalition formation. In this work, the performance of a group of agents – a team – that collaborate to achieve a shared goal where the individual contribution of each agent is unknown, is evaluated. The work thus aims to present a reliable method for calculating a trust value for agents involved in teamwork. More specifically, this research presents a model – called Inducing the Trust Ratio Model - for evaluating the individual trustworthiness of a group of agents. Toward this end, the model makes use of genetic algorithms to induce the trust ratio of each coalition member. Empirical analysis is undertaken to evaluate the effectiveness of this model.

Paper Nr: 68
Title:

FORMAL SPECIFICATION AND VERIFICATION OF MULTI-AGENT ROBOTICS SOFTWARE SYSTEMS - A Case Study

Authors:

Flavio Oquendo, Nadeem Akhtar and Yann Le Guyadec

Abstract: One of the most challenging task in software specifications engineering for robotics multi-agent systems is to ensure correctness. As these systems have high concurrency, often have dynamic and distributed environments, the formal specification and verification of these systems along with step-wise refinement from abstract to concrete concepts play major role in system correctness. Our objectives are the formal specification, analysis with respect to functional as well as non-functional properties by step-wise refinement from abstract to concrete specifications and then formal verification of these specifications. Multi-agent robotics systems are concurrent systems with processes working in parallel with synchronization between them. We have worked on Gaia multi-agent method along with finite state process based finite automata techniques and as a result we have defined the formal specifications of our system, checked the correctness and verified all possible flow of concurrent executions of these specifications. Our contribution consists in transforming Gaia organizational abstractions into executable FSP specifications that can be verified using LTS. We have considered a case study of our multi-agent robotics system to exemplify formal specifications and verification.

Paper Nr: 70
Title:

A CONFLICT-DIRECTED COORDINATION MECHANISM FOR TRAFFIC LIGHT CONTROL IN A SIMULATED ENVIRONMENT

Authors:

Jesús H. Domínguez, José L. Aguirre and Ramón Brena

Abstract: Car traffic control is a big issue nowadays, because of increasing time spent in traffic jams. A common mechanism that allows control of car flow is the use of traffic lights. Beyond static traffic lights' time assignments, we think it is possible to make traffic lights adjust the green time based on the current traffic conditions and coordinating by themselves. This paper presents a multi-agent based coordination mechanism followed by traffic lights in a simulated traffic intersection aiming to reduce the average car waiting time, compared to a traditional mechanism of static green time assignation. We call the mechanism ``conflict-directed'' since it is based on a conflict resolution strategy. The proposed mechanism has been tested with different cases on one and two independent intersections in a simulated environment. An evaluation of the conflict-directed mechanism performance is given.

Paper Nr: 84
Title:

MAGENTA MULTI-AGENT SYSTEMS FOR DYNAMIC SCHEDULING

Authors:

Andrey Glashchenko, Anton Ivashchenko, George Rzevski, Petr Skobelev, Petr Shveykin, Sergey Inozemtsev and Vyacheslav Andreev

Abstract: The document presents an overview of Magenta multi-agent solutions for real time scheduling and optimization of mobile resources. Brief survey on traditional scheduling methods, main principles of multi-agent approach, system architecture, functionality, industrial applications and perspectives are described. The multi-agent approach for dynamic scheduling gives opportunity to solve complex problems, react on events in real time, improve resource utilization and provide a number of other benefits.

Paper Nr: 91
Title:

APPLICATION OF AGENT’S PARADIGM TO MANAGE THE URBAN WASTEWATER SYSTEM

Authors:

M. Verdaguer, M. Poch, Montse Aulinas and P. Escribano

Abstract: Urban Wastewater Systems (UWS) are complex and their management is a challenging issue. Each one of the three principal elements that compose the UWS (i.e. sewer system, urban wastewater treatment plant and the receiving water) has particular goals to reach. However, the elements of the UWS should be ideally considered together to perform an integrated management of the UWS. Nevertheless, this approximation, which seems to be necessary, is not easy. Each one of these elements is in practice managed by a different entity, which has specific strategies and functions to optimize that sometimes are opposed. In this communication, a well known agent-oriented methodology –GAIA– is used to model the relations that take place in the UWS. A prototype is implemented in Java using Repast in order to evaluate the possibilities of agent-oriented methodologies to model this kind of complex systems.

Paper Nr: 96
Title:

THE MAR&A METHODOLOGY TO DEVELOP AGENT SYSTEMS

Authors:

Giacomo Cabri, Letizia Leonardi and Mariachiara Puviani

Abstract: In this paper we present a new agent methodology called MAR&A. Its aim is to better connect agent methodologies and agent infrastructures, since in the agent development we can find a ``gap'' between them. Our approach was not to build a new agent methodology \emph{from scratch}, but to reuse ``fragments'' of existing methodologies. Besides presenting the methodology, we propose its use in a case study, to help readers understand the exploitation of this methodology and to sketch the connections with agent infrastructures.

Paper Nr: 100
Title:

MODELLING AND FORMAL SPECIFICATION OF A MULTIAGENT TELEMEDICINE SYSTEM FOR DIABETES CARE

Authors:

Enrique J. Gómez, Gema García-Sáez, Hong Zhu, Iñaki Martinez-Sarriegui, Lijun Shan and M. Elena Hernando

Abstract: This paper presents the modelling and formal specification of a telemedicine system for diabetes care. In such scenario, the multiagent technology supports the distributed autonomy of several Personal Assistants; the communications between them and the hospital´s agents; the control of the system´s access and multitask functionality; scalability; adaptability; robustness; and the provision to the physicians with the necessary automatic processing tools for the analysis of the large amounts of data generated by patients. We evaluated the AOIS meta-model and the CAMLE’s modelling environment concluding that this methodology is adequate to represent a complex medical system like the one presented. The model and the formal specification provide a more complete view of the system and contain very useful information to cope with the future system evolution.

Paper Nr: 104
Title:

INTELLIGENT TILES - Putting Situated Multi-Agents Models in Real World

Authors:

François Charpillet, Nicolas Pépin and Olivier Simonin

Abstract: In this paper we propose to pave indoor floors with ``communicating'' tiles in order to extend perception and communication of mobile agents and more generally to implement environment-based multi-agent models. Each tile supports a real-time process which ensures communication with its neighbours and any agent laid on it. We details algorithms required for tiles to interact with mobile agents and to carry out distributed processes. Then we apply our approach to a behavior-based model, by splitting the model into the tiles and a simple agent. We show this new version is equivalent to the original one and so discuss its advantages.

Paper Nr: 107
Title:

RELAXATION OF SOCIAL COMMITMENTS IN MULTI-AGENT DYNAMIC ENVIRONMENT

Authors:

Antonín Komenda, Jiří Vokřínek and Michal Pěchouček

Abstract: The role of social commitments in distributed, multi-agent planning and plan execution will be discussed in this article. We argue agents' capability to reason about the actions in the form of social commitments directly improving robustness of the plans in dynamic, multi-actor environment. We focused on relaxation decommitment strategy, targeted specifically to the time interval in which the agent agrees to accomplish the commitment. We will discuss how changes of this interval affect the plan execution and how the potential changes of this interval can be represented in the commitment itself. The value of the use of social commitments in planning in dynamic, multi-actor environment has been documented on a series of empirical experiments.

Paper Nr: 112
Title:

CONCEPTS IN ACTION: PERFORMANCE STUDY OF AGENTS LEARNING ONTOLOGY CONCEPTS FROM PEER AGENTS

Authors:

Behrouz H. Far, Leila Safari and Mohsen Afsharchi

Abstract: The ability to share knowledge is a necessity for agents in order to achieve both group and individual goals. To grant this ability many researchers have assumed to not only establish a common language among agents but a complete common understanding of all the concepts the agents communicate about. But these assumptions are often too strong or unrealistic. In this paper we present a comprehensive study of performance of agents learning ontology concepts from peer agents. Our methodology allows agents that are not sharing a common ontology to establish common grounds on concepts known only to some of them, when these common grounds are needed by learning the concepts. Although the concepts learned by an agent are only compromises among the views of the other agents, the method nevertheless enhances the autonomy of agents using it substantially. The experimental evaluation shows that the learner agent performs better than or close to teacher agents when it is tested against the objects from the whole world.

Paper Nr: 120
Title:

DYNAMIC SERVICE RECONFIGURATION AND ENACTMENT USING AN OPEN MATCHING ARCHITECTURE

Authors:

Frances Brazier, Julian Padget, Omar Rana and Sander van Splunter

Abstract: An architecture for dynamic reconfiguration of complex services, in which the enactment is automated, and the matching of services is not limited to a pre-determined set of matchers and repositories, is presented. The proposed architecture consists of three, previously developed, components: the CoWS template-based reconfiguration service, the Knoogle MatchMaker service, and the Triana workflow enactment engine. This architecture has the following innovative aspects: 1) automated adaptation of complex services, which is more flexible than existing approaches based on replacing failing instances of services within a workflow, 2) use of heterogeneous components that may be both local and distributed, and 3) dynamic selection of matchers and repositories.

Paper Nr: 121
Title:

MODELING OF OPEN NORMATIVE MULTIAGENT SYSTEMS

Authors:

Carlos José Pereira de Lucena, Carolina Howard Felicíssimo and Jean-Pierre Briot

Abstract: A major challenge in the research of multiagent systems (MAS) is the design and implementation of open MAS in which norms can be effectively applied to their agents and easily managed. These tasks are arduous because norms are usually written for general purposes, hindering a more precise regulation. The motivation for this research came forth from the need to resolve this challenge, providing an approach applicable in open systems. In such systems, heterogeneity and autonomy rule out any assumption concerning the way third-party entities are implemented and behaved. This paper summarizes the result of a study done on solutions for the modeling of MAS. That study motivates the development of our DynaCROM approach.

Paper Nr: 150
Title:

INTEGRATION OF AN EMOTION MODEL TO THE BOARD GAME "INTRIGE"

Authors:

Andreas D. Lattner, Gabriela Lindemann, Ingo J. Timm and Jan-Marc Ehrmann

Abstract: One important issue in gaming design is to let the player's opponents appear as humanlike as possible. The underlying assumption of our work is that integrating artificial emotions to computer players will lead to a higher diversity of game situations and thus, to more interesting and joyful games. In this paper, we integrated an emotion model to agents playing the board game ``Intrige''. The current emotional state influences the behavior of the agent. In experiments we have shown that success of agents depends on the used emotional states and the varying constellations of opponents lead to different distributions of emotional states.

Paper Nr: 155
Title:

PARTICIPATORY SIMULATION AS A TOOL FOR AGENT-BASED SIMULATION

Authors:

Matthew Berland and William Rand

Abstract: Participatory simulation, as described by Wilensky & Stroup (1999c), is a form of agent-based simulation in which multiple humans control or design individual agents in the simulation. For instance, in a participatory simulation of an ecosystem, fifty participants might each control the intake and output of one agent, such that the food web emerges from the interactions of the human-controlled agents. We argue that participatory simulation has been under-utilized outside of strictly educational contexts, and that it provides myriad benefits to designers of traditional agent-based simulations. These benefits include increased robustness of the model, increased comprehensibility of the findings, and simpler design of individual agent behaviors. To make this argument, we look to recent research such as that from crowdsourcing (von Ahn, 2005) and the reinforcement learning of autonomous agent behavior (Abbeel, 2008).

Paper Nr: 156
Title:

AUTOMATIC CONFIGURATION OF SERVICE DIRECTORIES IN MULTIAGENT SYSTEMS

Authors:

Christoph Terwelp, Janno von Stülpnagel, Karl-Heinz Krempels and Martin Krebs

Abstract: Service directories provide basic functionalities for service discovery and service announcement in Multiagent Systems (MAS). A manual configuration of distributed MAS and their service directories is a time consuming and complex task and thus an automatic mechanism is highly desirable. Furthermore, the requirement for a fast response and processing time for agent queries still remains. Existing approaches do not fulfill these requirements in a satisfactory way. Thus, a new approach based on multicast DNS and DNS Service Discovery (DNS-SD) was developed and implemented for the multiagent framework JADE (Java Agent DEvelopment Framework). The architecture enables the automatic configuration of agent platforms in dynamic local networks as well as the later federation of the service directories which is necessary for a distributed service discovery operation.

Paper Nr: 161
Title:

SEE EMERGENCE AS A METAKNOWLEDGE - A Way to Reify Emergent Phenomena in Multiagent Simulations?

Authors:

Daniel David and Rémy Courdier

Abstract: Emergence is a fascinating concept for most scientists, and multiagent simulations are known to allow and facilitate its representation. Research in this area yield to several definitions and classifications of emergent phenomena, but only a few of them offers a solution for a concrete reification of emergence in simulation. This paper deals with this important notion of emergence reification that, as we know, does not have yet formal mathematic definition, if any could be expressed. We need to progress on the conceptual meaning, leading to more global definitions but allowing to give a general conceptual framework that makes possible the reification of emergent phenomena in multiagent simulations. We define emergence as being a metaknowledge and we present a conceptual framework in which emergent phenomena can be detected and injected into simulation systems and be handled like other entities.

Paper Nr: 164
Title:

SIMPATROL - Towards the Establishment of Multi-agent Patrolling as a Benchmark for Multi-agent Systems

Authors:

Daniel Moreira, Geber Ramalho and Patrícia Tedesco

Abstract: This paper discusses the establishment of multi-agent patrolling (MAP) as a benchmark for multi-agent systems (MAS). It argues that MAP can be a good benchmark for MAS, and points out what is lacking in order for this to happen. From the identified lacuna of not having a testbed, it presents SimPatrol, a simulator of MAS constructed strictly for the patrolling task. With such testbed, new results of performance are obtained for some of the previously proposed patrolling strategies.

Posters
Paper Nr: 13
Title:

MULTI-AGENTS FOR ENERGY EFFICIENT COMFORT - Agents for the Energy Infrastructure of the Built Environment: Flexergy

Authors:

Gert Boxem, Henk Broekhuizen, Jan-Fokko Haan, Joep van der Velden, Maarten Hommelberg, Paul Noom, Rene Kamhuis, Rinus van Houten, Willem Wortel and Wim Zeiler

Abstract: Synergy between end-user, building and the built environment is the ultimate in the intelligent comfort process control concept. This new comfort control technology is based on the use of agent technology and can further reduce energy consumption of buildings while at the same time improve individual comfort. The TU/e (Technische Universiteit Eindhoven) together with Kropman and ECN (Energy research Centre Netherlands) work together in the research for user based preference indoor climate control technology. Central in this approach is the whole building design process including the energy infrastructure which makes it possible to reduce energy consumption by tuning demand and supply of the energy needed to fulfil the comfort demand of the occupants of not just one building but a set of physical or virtual connected buildings.

Paper Nr: 17
Title:

TOWARDS A FRAMEWORK FOR MANAGEMENT OF STRATEGIC INTERACTION

Authors:

Rustam Tagiew

Abstract: Our research aim is to construct a software framework and associated language for definition, providing and recording of strategic interactions between real-world agents, human and artificial respectively. In this paper we present an example of such interaction, which is used to show designed and partially implemented concepts. We use FIPA based framework for our multi-agent system. The investigated scenario is a repeated two player zero sum symmetric matrix game. We also conducted a study and analyzed the data.

Paper Nr: 145
Title:

CONTEXT-AWARE AGENTS - The 6Ws Architecture

Authors:

John O'Donoghue and Juan Carlos Augusto

Abstract: Software agents have been designed and implemented to function within limited context-aware capabilities. For an agent to function correctly and efficiently it should contain sufficient knowledge and reasoning resources enabling them to process large quantities of implicit information conveyed through an explicit description. Presented in this position paper is an introduction of the 6Ws agent-based architecture which encompasses key reasoning capabilities which are not adequately supported by existing BDI frameworks but have been recognized as highly relevant for the development of Ambient Intelligent systems.