nach oben

2011 | Buch

Kapitel lesen Erstes Kapitel lesen

Combinations of Intelligent Methods and Applications

Proceedings of the 2nd International Workshop, CIMA 2010, France, October 2010

herausgegeben von: Ioannis Hatzilygeroudis, Jim Prentzas

Verlag: Springer Berlin Heidelberg

Buchreihe : Smart Innovation, Systems and Technologies

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten

Über dieses Buch

The combination of different intelligent methods is a very active research area in Artificial Intelligence (AI). The aim is to create integrated or hybrid methods that benefit from each of their components. Some of the existing efforts combine soft computing methods either among themselves or with more traditional AI methods such as logic and rules. Another stream of efforts integrates machine learning with soft-computing or traditional AI methods. Yet another integrates agent-based approaches with logic and also non-symbolic approaches. Some of the combinations have been quite important and more extensively used, like neuro-symbolic methods, neuro-fuzzy methods and methods combining rule-based and case-based reasoning. However, there are other combinations that are still under investigation, such as those related to the Semantic Web.

The 2nd Workshop on “Combinations of Intelligent Methods and Applications” (CIMA 2010) was intended to become a forum for exchanging experience and ideas among researchers and practitioners who are dealing with combining intelligent methods either based on first principles or in the context of specific applications. CIMA 2010 was held in conjunction with the 22nd IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2010). Also, a special track was organized in ICTAI 2010, under the same title.

This volume includes revised versions of the papers presented in CIMA 2010 and one of the short papers presented in the corresponding ICTAI 2010 special track. It also includes a paper of the editors as invited.

Inhaltsverzeichnis

Frontmatter

Defeasible Planning through Multi-agent Argumentation

Abstract

The work reported here introduces DefPlanner, an argumentation-based partial-order planner where different agents that have a partial, and possibly contradictory, knowledge of the world articulate arguments for and against supporting preconditions of the actions to be included in a plan. In this paper, we introduce an extension to multiple agents of the defeasible argumentation formalism that has been proposed to address the task of planning in a single agent environment.

Sergio Pajares, Eva Onaindia

Operator Behavior Modelling in a Submarine

Abstract

Simulations of naval action estimate the operational performance of warships or submarines for a given scenario. In common models, the operator’s reactions are predefined. This is not realistic: the operator’s decision can produce unexpected reactions.

This paper presents a method to model operator decision in simulations. This method allows to reason about incomplete, revisable and uncertain information: an operator has partial information about his environment only and must revise his decisions. Our method uses a nonmonotonic logic: the rules of behavior are formalized with default logic, to which we added a consideration of time. Our method uses preferences to manage choice between different rules, with simple probabilistic techniques.

This method has been implemented in Prolog, interfaced to DCNS simulator framework and applied to a scenario involving two adverse submarines.

Isabelle Toulgoat, Pierre Siegel, Yves Lacroix

Automatic Wrapper Adaptation by Tree Edit Distance Matching

Abstract

Information distributed through the Web keeps growing faster day by day, and for this reason, several techniques for extracting Web data have been suggested during last years. Often, extraction tasks are performed through so called wrappers, procedures extracting information from Web pages, e.g. implementing logic-based techniques. Many fields of application today require a strong degree of robustness of wrappers, in order not to compromise assets of information or reliability of data extracted.

Unfortunately, wrappers may fail in the task of extracting data from a Web page, if its structure changes, sometimes even slightly, thus requiring the exploiting of new techniques to be automatically held so as to adapt the wrapper to the new structure of the page, in case of failure. In this work we present a novel approach of automatic wrapper adaptation based on the measurement of similarity of trees through improved tree edit distance matching techniques.

Emilio Ferrara, Robert Baumgartner

Representing Temporal Knowledge in the Semantic Web: The Extended 4D Fluents Approach

Abstract

Representing information that evolves in time in ontologies, as well as reasoning over static and dynamic ontologies are the areas of interest in this work. Building upon well established standards of the semantic Web and the 4D-fluents approach for representing the evolution of temporal information in ontologies, this work demonstrates how qualitative temporal relations that are common in natural language expressions (i.e., relations between time intervals like “before”, “after”, etc.) are represented in ontologies. Existing approaches allow for representations of temporal information, but do not support representation of qualitative relations and reasoning.

Sotiris Batsakis, Euripides G. M. Petrakis

Combining a Multi-Document Update Summarization System –CBSEAS– with a Genetic Algorithm

Abstract

In this paper, we present a combination of a multi-document summarization system with a genetic algorithm. We first introduce a novel approach for automatic summarization. CBSEAS, the system which implements this approach, integrates a new method to detect redundancy at its very core in order to produce summaries with a good informational diversity. However, the evaluation of our system at TAC 2008—Text Analysis Conference—revealed that system adaptation to a specific domain is fundamental to obtain summaries of an acceptable quality.

The second part of this paper is dedicated to a genetic algorithm which aims to adapt our system to specific domains. We present its evaluation by TAC 2009 on a newswire articles summarization task and show that this optimization is having a great influence on both human and automatic evaluations.

Aurélien Bossard, Christophe Rodrigues

Extraction of Essential Events with Application to Damage Evaluation on Fuel Cells

Abstract

Although sudden changes of the event phase in complex system may indicate underlying essential forces, such events are not frequent. In the present paper, we propose an essential event extractor (E³) scheme to extract relatively rare but co-occurring event sequences in event phase transitions. In E³, the self-organizing map (SOM) is used as vector quantization (VQ) to encode non-symbolic events and KeyGraph as a co-occurrence graph. Afterwards, event transitions on the co-occurrence graph can be obtained by referring to an occurrence density estimation on the topology map of VQ. We demonstrate the E³ using an acoustic emission (AE) event sequence observed during a damage test of fuel cells and obtain reasonable and essential co-occurring damage sequences that exhibit mechanical effects.

Teppei Kitagawa, Ken-ichi Fukui, Kazuhisa Sato, Junichiro Mizusaki, Masayuki Numao

Detecting Car Accidents Based on Traffic Flow Measurements Using Machine Learning Techniques

Abstract

This paper deals with the problem of detecting the occurrence of a car accident in an urban environment. Firstly, a model based on Cellular Automata is designed to simulate the traffic flow with its main features such as: multiple lanes, cars, traffic lights, buses and bus stops. Afterwards, machine learning techniques are trained with the traffic flow measurements considering both the normal and the situation in which the accident caused a partial closure of the lanes. Several machine learning techniques results are presented to several car breaking scenarios.

L. D. Tavares, G. R. L. Silva, D. A. G. Vieira, R. R. Saldanha, W. M. Caminhas

Next Generation Environments for Context-Aware Learning Design

Abstract

Next generation Learning Design tools and applications have similar design requirements as intelligent applications that create, share and re-use content through the use of data specifications or formal models. In this paper, we present an approach that combines ontologies and autonomic computing principles to design and build next generation learning design environments that possess context-aware features. Our approach builds on the features of self-management and organisation of autonomic computing but uses self-configuration as a means to extend a knowledgebased inference through the design of meta-level inference. This leads to the design and implementation of a next generation learning design tool that is context-aware supporting both knowledge push and knowledge pull to enable appropriate use of theory and practice when creating learning designs for use in higher education.

Patricia Charlton, George D. Magoulas

Neurules-A Type of Neuro-symbolic Rules: An Overview

Abstract

Neurules are a kind of integrated rules integrating neurocomputing and production rules. Each neurule is represented as an adaline unit. Thus, the corresponding neurule base consists of a number of autonomous adaline units (neurules). Due to this fact, a modular and natural knowledge base is constructed, in contrast to existing connectionist knowledge bases. In this paper, we present an overview of our main work involving neurules. We focus on aspects concerning construction of neurules, efficient updates of neurule bases, neurule-based inference and combination of neurules with case-based reasoning. Neurules may be constructed from either symbolic rule bases or empirical data in the form of training examples. Due to the fact that the source knowledge of neurules may change with time, efficient updates of corresponding neurule bases to reflect such changes are performed. Furthermore, the neurule-based inference mechanism is interactive and more efficient than the inference mechanism used in connectionist expert systems. Finally, neurules can be naturally combined with case-based reasoning to provide a more effective representation scheme that exploits multiple knowledge sources and provides enhanced reasoning capabilities.

Jim Prentzas, Ioannis Hatzilygeroudis

Backmatter

Titel: Combinations of Intelligent Methods and Applications
herausgegeben von: Ioannis Hatzilygeroudis
Jim Prentzas
Verlag: Springer Berlin Heidelberg
Electronic ISBN: 978-3-642-19618-8
Print ISBN: 978-3-642-19617-1
DOI: https://doi.org/10.1007/978-3-642-19618-8

Springer Professional

Über dieses Buch

Inhaltsverzeichnis

Frontmatter

Defeasible Planning through Multi-agent Argumentation

Operator Behavior Modelling in a Submarine

Automatic Wrapper Adaptation by Tree Edit Distance Matching

Representing Temporal Knowledge in the Semantic Web: The Extended 4D Fluents Approach

Combining a Multi-Document Update Summarization System –CBSEAS– with a Genetic Algorithm

Extraction of Essential Events with Application to Damage Evaluation on Fuel Cells

Detecting Car Accidents Based on Traffic Flow Measurements Using Machine Learning Techniques

Next Generation Environments for Context-Aware Learning Design

Neurules-A Type of Neuro-symbolic Rules: An Overview

Backmatter

Premium Partner