Agent and Multi-Agent Systems: Technologies and Applications [recurso electrónico] : 4th KES International Symposium, KES-AMSTA 2010, Gdynia, Poland, June 23-25, 2010, Proceedings. Part II / edited by Piotr Jedrzejowicz, Ngoc Thanh Nguyen, Robert J. Howlet, Lakhmi C. Jain.

Management and e-Business -- Agent-Based Decision Making in the Electronic Marketplace: Interactive Negotiation -- Modeling and Verifying Business Interactions via Commitments and Dialogue Actions -- Personalized Support for Management of Financial Instruments by Means of Software Agents -- MAS Approach to Business Models Simulations: Supply Chain Management Case Study -- Analysing Bidder Performance in Randomised and Fixed-Deadline Automated Auctions -- Mobile Agents and Robots -- cljRobust - Clojure Programming API for Lego Mindstorms NXT -- Agent-Enabled Collaborative Downloading: Towards Energy-Efficient Provisioning of Group-Oriented Services -- Lifespan-Aware Routing for Wireless Sensor Networks -- Machine Learning -- A Machine Learning Approach to Speech Act Classification Using Function Words -- Neural Networks for Solving the Superposition Problem Using Approximation Method and Adaptive Learning Rate -- Distributed Data Mining System Based on Multi-agent Communication Mechanism -- Biologically Inspired Agent System Based on Spiking Neural Network -- Agent-Based Optimization (ABO2010) -- Cooperative Optimization in Cellular Automata - Based Multiagent Systems with Spatio-temporally Generalized Prisoner’s Dilemma Model -- An Agent-Based Simulated Annealing Algorithm for Data Reduction -- Feature Set Reduction by Evolutionary Selection and Construction -- Iterative Method for Improving Consistency of Multi-attribute Object Judgments Performed by Teams of Decision Makers -- Experimental Investigation of the Synergetic Effect Produced by Agents Solving Together Instances of the Euclidean Planar Travelling Salesman Problem -- Multidimentional Self-organization for Online Time-Constrained Vehicle Routing Problems -- Cooperative Solution to the Vehicle Routing Problem -- AdQL – Anomaly Detection Q-Learning in Control Multi-queue Systems with QoS Constraints -- Two Ensemble Classifiers Constructed from GEP-Induced Expression Trees -- Experimental Evaluation of the A-Team Solving Instances of the RCPSP/max Problem -- Agent-Enabled Social Computing (AESC2010) -- Early Warning of Cardiac Problems in a Crowd -- Symmetry Approach to Evacuation Scenarios -- Development of a Cognitive-Emotional Model for Driver Behavior -- Modelling Dynamic Forgetting in Distributed Information Systems -- Integrated Modeling of Cognitive Agents in Socio-technical Systems -- Digital Economy (DE2010) -- Aggregated Information Representation for Technical Analysis on Stock Market with Csiszár Divergence -- Implementation of Network Oriented Manufacturing Structures -- Supply Chain Arrangements in Recovery Network -- A Study of Stock Market Trading Behavior and Social Interactions through a Multi Agent Based Simulation -- e-Sourcing Cluster Strategies: Empathy vs. Egoism -- Application of Economic Order Value for Creation of Time-Defined Transactions in Web-Based Open Sourcing System -- Using Intelligent Systems for Information Technology Assessment (ISITA2010) -- Ontology as a Tool for the IT Management Standards Support -- Methods of Incomplete and Uncertain Knowledge Acquisition in the Knowledge Processing Environment -- An Approach to Agent-Based Supporting System for IT Projects -- Doctoral Track -- ACO-GA Approach to Paper-Reviewer Assignment Problem in CMS -- Updatable Multi-agent OSGi Architecture for Smart Home System -- An Approach to Evaluate the Impact of Web Traffic in Web Positioning -- Agent System for Managing Distributed Mobile Interactive Documents -- Multiagent Means of Bandwidth Allocation for Telecommunication Market.

Presented experiments show that usage ofevolutionary approach to feature - duction is justi?ed.Feature selection as well as construction gives goodresults. It is noticeable that attribute construction’s best results assign higher classi?- tion accuracy than feature selection alone.That is why, carrying out selection before construction to decrease searchingspace isagoodsolution. Because of indeterministicbehavior of neuralnetworks,it was di?cultto - ducefeaturesetincaseofusingthemto evaluatecandidateresults.Forexample, aneuralnetworklearntverywellondatathatwasdescribedbyfullattributeset, but when thisset was decreased it had huge problems to do this duringrequired number ofepochs.That suggests that usingC4.5 ismuchmore preferred. Numerous experiments havebeen performed and observed.Analysis ofabove results allowsto put the hypothesisthat it is worth to use Construction module as the feature set reduction. But experiments show that Constructormodule does not work sowell whenitusesthe whole initial set offeatures – the search space istoo large.Soit is worth to use ?rstly Selectorand nextConstructor. The second important issue isthatConstructor destructs the semanticmeaning of the features.New constructed features are notunderstandableforusers.In some real-liveproblems measuring offeature values isquite expensive, forsuch problems selector seems to be more suitable because itdiminishes a number of realfeatures.To constructonefeaturesa number ofreal(measured)featurescan be required. Obtainedresults haveencouragedus to extendour system,especiallythe c- structormodule.Weplan to developenlarged set offunctionsFwhich allowsto use the system with data containingdi?erenttype offeatures,not only nume- cal. Such system will be veri?ed usingagreater number ofbenchmark data sets as well as real data. Acknowledgments. This work ispartially ?nanced fromthe Ministryof S- ence and Higher Education Republic of Polandresources in 2008–2010 years as a Poland–Singapore joint research project 65/N-SINGAPORE/2007/0.

19