Helder Coelho

A multi-agent intelligent environment for medical knowledge

AMPLIA is a multi-agent intelligent learning environment designed to support training of diagnostic reasoning and modelling of domains with complex and uncertain knowledge. AMPLIA focuses on the medical area. It is a system that deals with uncertainty under the Bayesian network approach, where learner-modelling tasks will consist of creating a Bayesian network for a problem the system will present. The construction of a network involves qualitative and quantitative aspects. The qualitative part concerns the network topology, that is, causal relations among the domain variables. After it is ready, the quantitative part is specified. It is composed of the distribution of conditional probability of the variables represented. A negotiation process (managed by an intelligent MediatorAgent) will treat the differences of topology and probability distribution between the model the learner built and the one built-in in the system. That negotiation process occurs between the agents that represent the expert knowledge domain (DomainAgent) and the agent that represents the learner knowledge (LearnerAgent).

BDI Models and Systems: Reducing the Gap

Beliefs-Desires-Intentions models (or BDI models) of agents have been around for quit a long time. The purpose of these models is to characterize agents using anthropomorphic notions, such as mental states and actions. However, despite the fact that many systems have been developed based on these models, it is a general concern that there is a gap between those powerful BDI logics and practical systems. The purpose of this paper is to present a BDI model that, besides being a formal model of agents, is also suitable to be used to implement agents. Instead of defining a new BDI logic or choosing an existing one, and extending it with an operational model, we define the notions of belief, desires and intentions using a logic formalismthat is both well-defined and computational.

Automated reasoning in geometry theorem proving with Prolog

This paper describes automated reasoning in a PROLOG Euclidean geometry theorem-prover. It brings into focus general topics in automated reasoning and the ability of Prolog in coping with them.

Mapping concurtasktrees into UML 2.0

ConcurTaskTrees (CTT) is one of the most widely used notations for task modeling, specifically tailored for user interface model-based design. The integration of CTT with a de facto standard modeling language was already identified as an important issue, but there is no consensus about the best approach to achieve this goal. The purpose of this paper is to examine the relative strengths and weaknesses of control and data flow specification in UML 2.0 Activity Diagrams to represent CTT semantics. The analysis is driven by the definition of pattern-based activities for the temporal operators in CTT. In this paper, we propose an extension of the UML 2.0 abstract syntax that fully supports the concepts behind CTTs and provides an adapted graphical notation for a UML-like representation.

Advances in Artificial Intelligence - IBERAMIA-SBIA 2006

Invited Speakers.- Organizing Software Agents.- Learning, Logic, and Probability: A Unified View.- Reinventing Machine Learning with ROC Analysis.- Cocktail Party Processing.- AI in Education and Intelligent Tutoring Systems.- Diagnostic of Programs for Programming Learning Tools.- Intelligent Learning Objects: An Agent Approach to Create Reusable Intelligent Learning Environments with Learning Objects.- An Experimental Study of Effective Feedback Strategies for Intelligent Tutorial Systems for Foreign Language.- Autonomous Agents and Multiagent Systems.- Coordination with Collective and Individual Decisions.- Negotiator Agents for the Patrolling Task.- Running Agents in Mobile Devices.- A Multi Agent Based Simulator for Brazilian Wholesale Electricity Energy Market.- Using IDEF0 to Enhance Functional Analysis in OISE?+? Organizational Modeling.- Simulations Show That Shame Drives Social Cohesion.- SILENT AGENTS: From Observation to Tacit Communication.- Simulating Working Environments Through the Use of Personality-Based Agents.- GAPatrol: An Evolutionary Multiagent Approach for the Automatic Definition of Hotspots and Patrol Routes.- Learning by Knowledge Sharing in Autonomous Intelligent Systems.- Formal Analysis of a Probabilistic Knowledge Communication Framework.- Computer Vision and Pattern Recognition.- Color Image Segmentation Through Unsupervised Gaussian Mixture Models.- An Image Analysis Methodology Based on Deterministic Tourist Walks.- Feature Characterization in Iris Recognition with Stochastic Autoregressive Models.- Cryptographic Keys Generation Using FingerCodes.- Evolutionary Computation and Artificial Life.- Using Computational Intelligence and Parallelism to Solve an Industrial Design Problem.- Two-Phase GA-Based Model to Learn Generalized Hyper-heuristics for the 2D-Cutting Stock Problem.- Mirrored Traveling Tournament Problem: An Evolutionary Approach.- Pattern Sequencing Problems by Clustering Search.- Hybrid Systems (Fuzzy, Genetic, Neural, Symbolic).- Development of a Hybrid Intelligent System for Electrical Load Forecasting.- Extending a Hybrid CBR-ANN Model by Modeling Predictive Attributes Using Fuzzy Sets.- Development of a Neural Sensor for On-Line Prediction of Coagulant Dosage in a Potable Water Treatment Plant in the Way of Its Diagnosis.- Multi-objective Memetic Algorithm Applied to the Automated Synthesis of Analog Circuits.- A Hybrid Learning Strategy for Discovery of Policies of Action.- Knowledge Acquisition and Machine Learning.- A Fractal Dimension Based Filter Algorithm to Select Features for Supervised Learning.- Comparing Meta-learning Algorithms.- A New Linear Dimensionality Reduction Technique Based on Chernoff Distance.- A Machine Learning Approach to the Identification of Appositives.- Parameterized Imprecise Classification: Elicitation and Assessment.- Evolutionary Training of SVM for Multiple Category Classification Problems with Self-adaptive Parameters.- Time-Space Ensemble Strategies for Automatic Music Genre Classification.- Predictive and Descriptive Approaches to Learning Game Rules from Vision Data.- Knowledge Discovery and Data Mining.- Mining Intonation Corpora Using Knowledge Driven Sequential Clustering.- Using Common Sense to Recognize Cultural Differences.- Detection of Repetitive Patterns in Action Sequences with Noise in Programming by Demonstration.- Knowledge Engineering, Ontologies and Case Based Reasoning.- Supporting Ontology-Based Semantic Matching of Web Services in MoviLog.- Learning Similarity Metrics from Case Solution Similarity.- Knowledge Representation and Reasoning.- Epistemic Actions and Ontic Actions: A Unified Logical Framework.- Strings and Holes: An Exercise on Spatial Reasoning.- A Causal Perspective to Qualitative Spatial Reasoning in the Situation Calculus.- PFORTE: Revising Probabilistic FOL Theories.- Rule Schemata for Game Artificial Intelligence.- Neutral Language Processing.- Selecting a Feature Set to Summarize Texts in Brazilian Portuguese.- Word Sense Disambiguation Based on Word Sense Clustering.- Comparing Two Markov Methods for Part-of-Speech Tagging of Portuguese.- Shallow Parsing Based on Comma Values.- Planning and Scheduling.- Unifying Nondeterministic and Probabilistic Planning Through Imprecise Markov Decision Processes.- Achieving Conditional Plans Through the Use of Classical Planning Algorithms.- Assessing the Value of Future and Present Options in Real-Time Planning.- Reading PDDL, Writing an Object-Oriented Model.- Robotics.- A Reactive Lazy PRM Approach for Nonholonomic Motion Planning.- Negative Information in Cooperative Multirobot Localization.- Gait Control Generation for Physically Based Simulated Robots Using Genetic Algorithms.- Does Complex Learning Require Complex Connectivity?.- Theoretical and Logical Methods.- The Predicate-Minimizing Logic MIN.- Strong Negation in Well-Founded and Partial Stable Semantics for Logic Programs.- MAT Logic: A TemporalxModal Logic with Non-deterministic Operators to Deal with Interactive Systems in Communication Technologies.- Uncertainty.- Probabilistic Logic with Strong Independence.- Bayesian Model Combination and Its Application to Cervical Cancer Detection.

Requirements analysis of agent-based simulation platforms: state of the art and new prospects

In this paper we propose a preliminary reference model for the requirements specification of agent-based simulation platforms. We give the following contributions: (i) aid the identification of general principles to develop platforms; (ii) advance the analysis and prospection of technical-operational and high-level requirements; (iii) promote the identification of shared requirements, addressing them to the development of an integrated work. We present our reference model and make a comparative analysis between three well-known platforms, resulting in an unambiguous and schematic characterisation of computational systems for agent-based simulation.

Machinery for artificial emotions

We present a preliminary definition and theory of artificial emotion viewed as a sequential process comprising the appraisal of the agent global state, the generation of an emotion-signal, and an emotion-response. This theory distinguishes cognitive from affective appraisal on an architecture-grounded basis. Affective appraisal is performed by the affective component of the architecture; cognitive appraisal is performed by its cognitive component. A scheme for emotion classification with seven dimensions is presented. Among them, we emphasize the roles played by emotions and the way these roles are fulfilled. It is shown how emotions are generated, represented, and used in the Salt & Pepper architecture for autonomous agents (Botelho, 1997). Salt & Pepper is a specific architecture comprising an affective engine, a cognitive and behavioral engine, and an interruption manager. Most properties of the cognitive and behavioral engine rely upon a hybrid associative, schema-based long-term memory. In Salt & Pepper, emotion-signals, represented by label, object of appraisal, urgency, and valence, are generated by the affective engine through the appraisal of the agents global state. For each emotion-signal there are several nodes stored and interconnected in long-term memory. Each of these nodes contains an emotion response that may be executed when an emotion-signal is generated. Emotion intensity relates to the activation of the node. It is shown that the Salt & Pepper architecture for autonomous agents exhibits several properties usually related to emotion: state and mood congruence, compound emotions, autonomic emotion-responses, and different emotion-responses to the same stimulus including the generation of different motives. The implementation of a concrete example is described.We present a preliminary definition and theory of artificial emotion viewed as a sequential process comprising the appraisal of the agent global state, the generation of an emotion-signal, and an emotion-response. This theory distinguishes cognitive from affective appraisal on an architecture-grounded basis. Affective appraisal is performed by the affective component of the architecture; cognitive appraisal is performed by its cognitive component. A scheme for emotion classification with seven dimensions is presented. Among them, we emphasize the roles played by emotions and the way these roles are fulfilled. It is shown how emotions are generated, represented, and used in the Salt & Pepper architecture for autonomous agents (Botelho, 1997). Salt & Pepper is a specific architecture comprising an affective engine, a cognitive and behavioral engine, and an interruption manager. Most properties of the cognitive and behavioral engine rely upon a hybrid associative, schema-based long-term memory. In Salt & Pep...

Improving Choice Mechanisms within the BVG Architecture

The BVG agent architecture relies on the use of values (multiple dimensions against which to evaluate a situation) to perform choice among a set of candidate goals. Choice is accomplished by using a calculus to collapse the several dimensions into a function that serialises candidates. In our previous experiments, we have faced decision problems only with perfect and complete information. In this paper we propose new experiments, where the agents will have to decide in the absence of all the needed and relevant information. In the BVG model, agents adjust their scale of values by feeding back evaluative information about the consequences of their decisions. We use the exact same measures to analyse the results of the experiments, thus providing a fair trial to the agents: they are judged with the same rules they can use for decision. Our method, based on values, is a novel approach for choice and an alternative to classical utilitarian theories.

Bilateral contracting in multi-agent electricity markets: Negotiation strategies and a case study

Electricity markets are systems for effecting the purchase and sale of electricity using supply and demand to set energy prices. Two major market models are often distinguished: pools and bilateral transactions. Pool prices tend to change quickly and variations are usually highly unpredictable. In this way, market participants can enter into bilateral contracts to hedge against pool price volatility. This article addresses the challenges of using software agents with negotiation competence to help manage the complexity of electricity markets, particularly the issues associated with the negotiation of bilateral contracts. Specifically, the purpose of this article is twofold: (i) to present the key features of a generic model for software agents that handles two-party and multi-issue negotiation, and (ii) to describe a case study on forward bilateral contracts.

Tactical exploration of tax compliance decisions in multi-agent based simulation

Tax compliance is a field that crosses over several research areas, from economics to machine learning, from sociology to artificial intelligence and multi-agent systems. The core of the problem is that the standing general theories cannot even explain why people comply as much as they do, much less make predictions or support prescriptions for the public entities. The compliance decision is a challenge posed to rational choice theory, and one that defies the current choice mechanisms in multi-agent systems. The key idea of this project is that by considering rationally-heterogeneous agents immersed in a highly social environment we can get hold of a better grasp of what is really involved in the individual decisions. Moreover, we aim at understanding how those decisions determine tendencies for the behaviour of the whole society, and how in turn those tendencies influence individual behaviour. This paper presents the results of some exploratory simulations carried out to uncover regularities, correlations and trends in the models that represent first and then expand the standard theories on the field. We conclude that forces like social imitation and local neighbourhood enforcement and reputation are far more important than individual perception of expected utility maximising, in what respects compliance decisions.