Search

This paper addresses a Korean-English machine translation system for scientific papers. The MT system is supported by CL (Controlled Language)-guided source language rewriting. After analyzing the translation errors of the system, we defined Korean rewriting rules to avoid the linguistic obstacles that may affect the translation accuracy. To support this, a Korean CL-checker was implemented. We showed that this CL-guided MT system can improve the translation accuracy by about 13% by adopting CL rewriting rules. However, this improvement is still not enough for various purposes, because most of the users of the MT system may want to submit the translated texts to a conference or an academic journal. As the MT output contains erroneous expressions, a language model module was added to the pattern-based MT engine. The system automatically detects expressions with low frequency and asks the authors to examine the translation. By adopting CL rewriting rules and language model module to the existing MT engine, almost "professional" translations can be obtained. [ABSTRACT FROM AUTHOR]

This paper presents a novel application of a semantic annotation system, named Cerno, to analyze research publications in electronic format. Specifically, we address the problem of providing automatic support for authors who need to deal with large volumes of research documents. To this end, we have developed Biblio, a user-friendly tool based on Cerno. The tool directs the user's attention to the most important elements of the papers and provides assistance by generating automatically a list of references and an annotated bibliography given a collection of published research articles. The tool performance has been evaluated on a set of papers and preliminary evaluation results are promising. The backend of Biblio uses a standard relational database to store the results. [ABSTRACT FROM AUTHOR]

Researchers from the same lab often spend a considerable amount of time searching for published articles relevant to their current project. Despite having similar interests, they conduct independent, time consuming searches. While they may share the results afterwards, they are unable to leverage previous search results during the search process. We propose a research paper recommender system that avoids such time consuming searches by augmenting existing search engines with recommendations based on previous searches performed by others in the lab. Most existing recommender systems were developed for commercial domains with millions of users. The research paper domain has relatively few users compared to the large number of online research papers. The two major challenges with this type of data are the large number of dimensions and the sparseness of the data. The novel contribution of the paper is a scalable subspace clustering algorithm (SCuBASCuBA: Subspace Clustering Based Analysis.) that tackles these problems. Both synthetic and benchmark datasets are used to evaluate the clustering algorithm and to demonstrate that it performs better than the traditional collaborative filtering approaches when recommending research papers. [ABSTRACT FROM AUTHOR]

Office workers tend to produce paper piles of documents to read or to process sometime later. The information contained in these piles is often lost if it is not transferred to electronic format and connected to knowledge structures. Information that is not part of the knowledge worker's electronic information space is frequently overlooked because it is not proactively provided during actual processes or tasks he is involved in. This paper presents a novel prototype for an intelligent office appliance, which results from an integration of three state-of-the-art office applications/appliances: a workflow system, a document classification system, and a multi-functional peripheral. The resulting system allows for leveraging an office worker's papers to her personal knowledge space in order to realize a pro-active and context-sensitive information support within knowledge-intensive tasks and processes. [ABSTRACT FROM AUTHOR]

To facilitate the transition from paper-based patient record (PPR) to computer-based patient record (CPR), engineers should try to improve the usability of CPR system. From the point of view of a physician, we reviewed PPRs written by 8 Japanese physicians. We revealed the characteristics of PPR to find out about the barrier to transition from PPR to CPR. Our findings may be helpful to the engineers who are aiming to develop a CPR system. [ABSTRACT FROM AUTHOR]

In this paper we describe the design of a hybrid search that combines simple metadata search with a traditional keyword search over unstructured context data. This paradigm provides the inquirer additional options to narrow the search with some semantic aspects through the XML metadata query. We demonstrate a paper search for a case study of the hybrid search, and describe a data integration hub to integrate those data dispersed on the Net. [ABSTRACT FROM AUTHOR]

Privacy-preserving classification mining is one of the fast-growing sub-areas of data mining. How to perturb original data and then build a decision tree based on perturbed data is the key research challenge. By applying transition probability matrix this paper proposes a novel privacy-preserving classification mining algorithm which suits all data types, arbitrary probability distribution of original data, and perturbing all attributes (including label attribute). Experimental results demonstrate that decision tree built using this algorithm on perturbed data has comparable classifying accuracy to decision tree built using un-privacy-preserving algorithm on original data. [ABSTRACT FROM AUTHOR]

This paper presents the advantage that knowledge-intensive activities, such as Scientific Conference Management, can take by the exploitation of expert components in the key tasks. Typically, in this domain the task of scheduling the activities and resources or the assignment of reviewers to papers is performed manually leading therefore to time-consuming procedures with high degree of inconsistency due to many parameters and constraints to be considered. The proposed systems, evaluated on real conference datasets, show good results compared to manual scheduling and assignment, in terms of both accuracy and reduction of runtime. [ABSTRACT FROM AUTHOR]

In this chapter, we proudly introduce eight awarded papers, selected from the papers presented in the 20th annual conference of Japan Society for Artificial Intelligence (JSAI2006). The conference was held at Tower Hall Funabori located in the east part of Tokyo from June 7 until June 9, 2006. 276 papers were presented in about 60 sessions and over 500 people participated in the conference. Sessions vary from the fundamental issues to the state-of-the-art applications. Session for regular papers are as follows; Logic and learning, Reinforcement learning and agent learning, Agent theory, Auction/Game/Economics, Agent learning, Agent planning, Agent simulation and interaction, Genetic algorithm, Image processing, Information extraction and classification, Clustering/self-organization, Classifi- cation learning, Text mining, Graph mining, Mining algorithm, Web mining, Pre- and post-processing for data mining, Practices of data mining, Cognitive modeling, Language processing and dialogue, Robot/sensor network, Web information system, Semantic Web, Knowledge modeling and knowledge sharing, Support of knowledge management, knowledge modeling/ontology,Web service, Human interface and communication support, Education support, Learning support environment, and Musical and auditory information processing. [ABSTRACT FROM AUTHOR]

Organic computing is an upcoming research area with strong relationships to the ideas and concepts of agent-based systems. In this paper, we therefore will have a closer look at agent systems, organic computing systems (as well as autonomic computing systems) and state commonalities and divergences between them. We then propose a common view on these technologies and show, how they can benefit from each other with regard to software engineering. [ABSTRACT FROM AUTHOR]

In this chapter, we introduce five awarded papers, selected from the 19th annual conference of JSAI (Japan Society for Artificial Intelligence) 2005. These five papers are truly excellent, for they were selected out of over 290 papers, the rate of which was less than 2%, voted by the total number of approximately seventy reviewers. As has been often mentioned, the research of artificial intelligence branches to many fields; among them, we could observe such tendency that empirical methods were rather prevalent compared with theoretical issues. However, we contend that the following five papers were both sound in theory and practical in feasibility. We show the synopses of the five papers, adding short comments for the award for each. [ABSTRACT FROM AUTHOR]

In this paper, we discuss importance and usefulness of interpersonal network in a community support system. We built a scheduling support system for an academic conference. Our system supports information exchange among participants and information discovery with generating participants' interpersonal network. This system was used in an academic conference called JSAI2003 involving 276 active users. The analysis of the networks reveals that interpersonal networks can promote information exchange among people by indicating existence of people to the others, and that it can also support information discovery by recommendation. [ABSTRACT FROM AUTHOR]

On behalf of the program committee (PC) of JSAI 2003, I would like to thank all the chair persons, discussants, and attentive audience who contributed to select these awarded papers. [ABSTRACT FROM AUTHOR]

The research community plays a very important role in helping researchers undertake new research topics. The authors propose a community mining system that helps to find communities of researchers by using bibliography data. The basic concept of this system is to provide interactive visualization of communities both local and global communities. We implemented this concept using actual bibliography data and present a case study using the proposed system. [ABSTRACT FROM AUTHOR]

Capturing and understanding mathematics from print form is an important task in translating written mathematical knowledge into electronic form. While the problem of syntactically recognising mathematical formulas from scanned images has received attention, very little work has been done on semantic validation and correction of recognised formulas. We present a first step towards such an integrated system by combining the Infty system with a semantic analyser for matrix expressions. We applied the combined system in experiments on the semantic analysis of matrix images scanned from textbooks. While the first results are encouraging, they also demonstrate many ambiguities one has to deal with when analysing matrix expressions in different contexts. We give a detailed overview of the problems we encountered that motivate further research into semantic validation of mathematical formula recognition. [ABSTRACT FROM AUTHOR]

Today the proliferation of the availability of the information of scientific events on the Web has created the necessity to offer a quickly access to up-to-date information about the quality of these events. This requirement demands for (semi) automatic tools to speedily provide this information. The human-performed activity of the information quality evaluation is extremely time consuming and easily leads to failures. The application OntoQualis here described was motivated to support the quality evaluation of Scientific Conferences, in the Computer Science area, based on the graduated programs evaluation protocol of the Brazilian agency CAPES. The evaluation mechanism is specified in the QUALIS document specifically designed to assess journals and conferences ranking. This paper presents a brief vision of the ongoing process of domain analysis and ontology prototyping aiming to classify Scientific Conferences: the OntoQualis project. Some results of OntoQualis preliminary evaluation have shown a satisfactory classification level in comparison with CAPES-QUALIS ranking. [ABSTRACT FROM AUTHOR]

Real-world data often involves objects that exhibit multiple relationships; for example, ‘papers' and ‘authors' exhibit both paper-author interactions and paper-paper citation relationships. A typical learning problem requires one to make inferences about a subclass of objects (e.g. ‘papers'), while using the remaining objects and relations to provide relevant information. We present a simple, unified mechanism for incorporating information from multiple object types and relations when learning on a targeted subset. In this scheme, all sources of relevant information are marginalized onto the target subclass via random walks. We show that marginalized random walks can be used as a general technique for combining multiple sources of information in relational data. With this approach, we formulate new algorithms for transduction and ranking in relational data, and quantify the performance of new schemes on real world data—achieving good results in many problems. [ABSTRACT FROM AUTHOR]

Nowadays amount of information on Internet is dramatically increasing. The ability of facilitating users to achieve useful information is more and more important for search field. CDSE, a model for the domain-based intelligent search engine is proposed in this paper. The model can help users to retrieve what they need by combining text classification with keywords extraction. Several algorithms that use key technologies are proposed, such as statistics, data mining and agents. Then a new criterion named ranking error is contributed to solve the problem of evaluation ranking inefficiency in traditional performance evaluation methodologies. The experimental results indicate that the proposed model can effectively improve retrieval precision and solve the problem of relevant document ranking behind in current search engine. [ABSTRACT FROM AUTHOR]

In order to discover services in business-driven Web service composition conveniently, accurately, and efficiently, this paper proposes a business process-oriented service discovery approach. In order to link business property with services, this paper proposes a business related description model of operations. Based on the business related relation model proposed in this paper, a relation-driven discovering algorithm for business process-oriented service discovery is presented. Compared with other discovering approach, the proposed discovering approach considers the business relation between operations and can solve the problem of discovering services with meaningful business relation. The experimentation shows the better performance of this algorithm. [ABSTRACT FROM AUTHOR]

In this paper, we suggest a postal RFID application model that can be used for real time trace and tracking system implementation of parcel processing and pallet management. This paper also shows the tag recognition performance of parcels by speed and mounting tag material such as thin cans, water bottles, and paper using an implemented postal RFID system to find the best solution for RFID adaptation in postal logistics. [ABSTRACT FROM AUTHOR]

This paper introduces the invited session of "Intelligent Agents and their Applications" being presented at the 10th International Conference on Knowledge-Based and Intelligent Information and Engineering Systems. This session concentrates on discussing Intelligent Agents and uses some applications to demonstrate the theories reported. An update on last years session [1] is included to report on several key advances in technology that further enable the ongoing development of multi-agent systems. A brief summary of the impediments presented to researchers is also provided to highlight why innovation must be used to sustain the evolution of Artificial Intelligence. This year a variety of challenges and concepts are presented, together with a collection of thoughts about the direction and vision of Intelligent Agents ands their Applciations. [ABSTRACT FROM AUTHOR]

Name disambiguation can occur when one is seeking a list of publications of an author who has used different name variations and when there are multiple other authors with the same name. We present an efficient integrative framework for solving the name disambiguation problem: a blocking method retrieves candidate classes of authors with similar names and a clustering method, DBSCAN, clusters papers by author. The distance metric between papers used in DBSCAN is calculated by an online active selection support vector machine algorithm (LASVM), yielding a simpler model, lower test errors and faster prediction time than a standard SVM. We prove that by recasting transitivity as density reachability in DBSCAN, transitivity is guaranteed for core points. For evaluation, we manually annotated 3,355 papers yielding 490 authors and achieved 90.6% pairwise-F1. For scalability, authors in the entire CiteSeer dataset, over 700,000 papers, were readily disambiguated. [ABSTRACT FROM AUTHOR]

It is well known that connectivity analysis of linked documents provides significant information about the structure of the document space for unsupervised learning tasks. However, the ability to identify distinct clusters of documents based on link graph analysis is proportional to the density of the graph and depends on the availability of the linking and/or linked documents in the collection. In this paper, we present an information theoretic approach towards measuring the significance of individual words based on the underlying link structure of the document collection. This enables us to generate a non-uniform weight distribution of the feature space which is used to augment the original corpus-based document similarities. The experimental results on the collection of scientific literature show that our method achieves better separation of distinct groups of documents, yielding improved clustering solutions. [ABSTRACT FROM AUTHOR]

Object-level vertical search engine has been the research focus recently where the resource collecting problem is still an open area. It is difficult to adapt the traditional link-based web crawler for this task because of the sparse linkage and data-centered webpage of the relevant resources. In this paper, we propose a meta-search based method enhanced with auxiliary crawling to address the problem caused by sparse linkage of the relevant resources. And to retrieve the data-centered webpages efficiently, domain schema is defined to describe the target resource, and representative data instances are selected for meta-search query composing. Moreover, evaluation criteria for the domain resource survey are also proposed as the guideline for query composing and auxiliary crawling, which enable the resource discovery to be automatically performed by computers. Experiment results on real-world data show that our method is effective and efficient. [ABSTRACT FROM AUTHOR]

This paper gives a survey of the current state of ARTIC - the modern Czech concatenative corpus-based text-to-speech system. All stages of the system design are described in the paper, including the acoustic unit inventory building process, text processing and speech production issues. Two versions of the system are presented: the single unit instance system with the moderate output speech quality, suitable for low-resource devices, and the multiple unit instance system with a dynamic unit instance selection scheme, yielding the output speech of a high quality. Both versions make use of the automatically designed acoustic unit inventories. In order to assure the desired prosodic characteristics of the output speech, system-version-specific prosody generation issues are discussed here too. Although the system was primarily designed for synthesis of Czech speech, ARTIC can now speak three languages: Czech (both female and male voices are available), Slovak and German. [ABSTRACT FROM AUTHOR]

Performance on a statistical language processing task relies upon accurate information being found in a corpus. However, it is known (and this paper will confirm) that many perfectly valid word sequences do not appear in training corpora. The percentage of n-grams in a test document which are seen in a training corpus is defined as n-gram coverage, and work in the speech processing community [7] has shown that there is a correlation between n-gram coverage and word error rate (WER) on a speech recognition task. Other work (e.g. [1]) has shown that increasing training data consistently improves performance of a language processing task. This paper extends that work by examining n-gram coverage for far larger corpora, considering a range of document types which vary in their similarity to the training corpora, and experimenting with a broader range of pruning techniques. The paper shows that large portions of language will not be represented within even very large corpora. It confirms that more data is always better, but how much better is dependent upon a range of factors: the source of that additional data, the source of the test documents, and how the language model is pruned to account for sampling errors and make computation reasonable. [ABSTRACT FROM AUTHOR]

Recommender algorithms have been quite successfully employed in a variety of scenarios from filtering applications to recommendations of movies and books at Amazon.com. However, all these algorithms focus on single item recommendations and do not consider any more complex recommendation structures. This paper explores how semantically rich complex recommendation structures, represented as RDF graphs, can be exchanged and shared in a distributed social network. After presenting a motivating scenario we define several annotation ontologies we use in order to describe context information on the user's desktop and show how our ranking algorithm can exploit this information. We discuss how social distributed networks and interest groups are specified using extended FOAF vocabulary, and how members of these interest groups share semantically rich recommendations in such a network. These recommendations transport shared context as well as ranking information, described in annotation ontologies. We propose an algorithm to compute these rankings which exploits available context information and show how rankings are influenced by the context received from other users as well as by the reputation of the members of the social network with whom the context is exchanged. [ABSTRACT FROM AUTHOR]

The paper reports on the development of the formal framework to design strategies for multi-issue non-symmetric meaning negotiations among software agents in a distributed information retrieval system. The advancements of the framework are the following. A resulting strategy compares the contexts of two background domain theories not concept by concept, but the whole context to the other context by accounting the relationships among concepts, the properties, the constraints over properties, and the available instances. It contains the mechanisms for measuring contextual similarity through assessing propositional substitutions and to provide argumentation through generating extra contexts. It uses presuppositions for choosing the best similarity hypotheses and to make the mutual concession to the common sense monotonic. It provides the means to evaluate the possible eagerness to concede through semantic commitments and related notions of knowledgeability and degree of reputation. [ABSTRACT FROM AUTHOR]

This edited volume contains the papers selected for presentation at the Second Workshop on Data Mining for Biomedical Applications (BioDM'07) held in Nanjing, China on 22nd of May 2007. The workshop was held in conjunction with the 11th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2007), a leading international conference in the areas of data mining and knowledge discovery. The aim of this workshop was to provide a forum for discussing research topics related to biomedical applications where data mining techniques were found to be necessary and/or useful. [ABSTRACT FROM AUTHOR]

This paper proposes a novel algorithm for nonnegative independent component analysis, which is based on minimizing the mutual information of the separated signals, and is truly insensitive to the particular underlying distribution of the source data. The unmixing system culminates to a novel neural network model. Compared with other algorithms for nonnegative ICA, the method proposed in this paper can work efficiently even in the case that the source signals are not well grounded, and that pre-whiting process is not needed. Finally, the experiments were performed on both simulating signals and mixtures of image data, the results indicate that the algorithm is efficient and effective. [ABSTRACT FROM AUTHOR]

This paper presents a multi-dependency language modeling approach to information retrieval. The approach extends the basic KL-divergence retrieval approach by introducing the hybrid dependency structure, which includes syntactic dependency, syntactic proximity dependency and co-occurrence dependency, to describe dependencies between terms. Term and dependency language models are constructed for both document and query. The relevant between a document and a query is then evaluated by using the KL-divergence between their corresponding models. The new dependency retrieval model has been compared with other traditional retrieval models. Experiment results indicate that it produces significant improvements in retrieval effectiveness. [ABSTRACT FROM AUTHOR]

We consider some problems about the computation time of evolutionary algorithms in this paper. First, some exact analytic expressions of the mean first hitting times of general evolutionary algorithms in finite search spaces are obtained theoretically by using the properties of Markov chain associated with evolutionary algorithms considered here. Then, by introducing drift analysis and applying Dynkin's Formula, the general upper and lower bounds of the mean first hitting times of evolutionary algorithms are estimated rigorously under some mild conditions listed in the paper. Those results in this paper are commonly useful. Also, the analytic techniques adopted in the paper are widely instructive for analyzing the computation time of evolutionary algorithms in a given search space as long as some specific mathematical arts are introduced accordingly. [ABSTRACT FROM AUTHOR]

Manual curation of biological databases is an expensive and labor-intensive process in Genomics and Systems Biology. We report the implem-entation of a state-of-the-art, rule-based Natural Language Processing system that creates computer-readable networks of regulatory interactions directly from abstracts and full-text papers. We evaluate its output against a manually-curated standard database, and test the possibilities and limitations of automatic and semi-automatic curation of the so-called biobibliome. We also propose a novel Regulatory Interaction Mining Markup Language suited for representing this data, useful both for biologists and for text-mining specialists. [ABSTRACT FROM AUTHOR]

This paper presents the integration of linguistic knowledge in learning semantic user profiles able to represent user interests in a more effective way with respect to classical keyword-based profilesThis research was partially funded by the EC under the 6th FP IST IP VIKEF No. 507173, Priority 2.3.1.7 Semantic Based Knowledge Systems (www.vikef.net) and under the DELOS NoE on Digital Libraries, Priority: Technology-enhanced Learning and Access to Cultural Heritage - Contract n. G038-507618 (www.delos.info). The work was supported also by the research project "Modelli avanzati di personalizzazione per biblioteche elettroniche", year 2005, funded by the University of Bari.. Semantic profiles are obtained by integrating a naïve Bayes approach for text categorization with a word sense disambiguation strategy based on the WordNet lexical database (Section 2). Semantic profiles are exploited by the "conference participant advisor" service in order to suggest papers to be read and talks to be attended by a conference participant. Experiments on a real dataset show the effectiveness of the service (Section 3). [ABSTRACT FROM AUTHOR]

In Service-Oriented Architectures (SOAs), software systems are decomposed into independent units, namely services, that interact with one another through message exchanges. To promote reuse and evolvability, these interactions are explicitly described right from the early phases of the development lifecycle. Up to now, emphasis has been placed on capturing structural aspects of service interactions. Gradually though, the description of behavioral dependencies between service interactions is gaining increasing attention as a means to push forward the SOA vision. This paper deals with the description of these behavioral dependencies during the analysis and design phases. The paper outlines a set of requirements that a language for modeling service interactions at this level should fulfill, and proposes a language whose design is driven by these requirements. [ABSTRACT FROM AUTHOR]

This paper proposes a method for sensitivity communication robots which infer their dialogist's emotion. The method is based on the Bayesian approach: by using a Bayesian modeling for prosodic features. In this research, we focus the elements of emotion included in dialogist's voice. Thus, as training datasets for learning Bayesian networks, we extract prosodic feature quantities from emotionally expressive voice data. Our method learns the dependence and its strength between dialogist's utterance and his emotion, by building Bayesian networks. Bayesian information criterion, one of the information theoretical model selection method, is used in the building Bayesian networks. The paper finally proposes a reasoner to infer dialogist's emotion by using a Bayesian network for prosodic features of the dialogist's voice. The paper also reports some empirical reasoning performance. [ABSTRACT FROM AUTHOR]

In this paper, we propose a state transition model using context based approach for gesture analysis. This method defines the analysis situation as five different states; NULL, OBJECT, POSTURE, LOCAL, and GLOBAL. We first infer the situation of the system by estimating the transition of the state model, and then apply different analysis algorithms according to the system state. Gestures are analyzed with the queue-based matching method which is newly proposed in the paper instead of general gesture spotting algorithms. In the algorithm, movement of feature points; face and both hands, is compared directly, so gesture can be recognized quickly without applying any constraints for real world application. The transition of the states can be interpreted as the context of motion and that is estimated with conditional probability between the states in the algorithm. [ABSTRACT FROM AUTHOR]

In WWW information integration, eliminating semantic hetero-geneity and implementing semantic combination is one of the key problems. This paper introduces classification ontology into WWW information integration to solve the semantic combination problem of heterogeneity classification architecture in Web information integration. However, there may be many kinds of ontology in a specific domain due to the structure of the websites, domain experts and different goals. So we have to combine all these kinds of ontology into logically unified integrated classification ontology in order to solve the problem of semantic heterogeneity commendably. This paper primarily discusses the method of building integrated classification ontology based on individual ontology, presents the definition of classification ontology, analyses the conceptual mapping and relational mapping between ontologies and solves the level conflict in the equivalent concepts. Keywords: Information integration, Classification ontology, Semantic, Similarity. [ABSTRACT FROM AUTHOR]

The use of an ontology in order to provide a mechanism to enable machine reasoning has continuously increased during the last few years. This paper proposed an automated method for document classification using an ontology, which expresses terminology information and vocabulary contained in Web documents by way of a hierarchical structure. Ontology-based document classification involves determining document features that represent the Web documents most accurately, and classifying them into the most appropriate categories after analyzing their contents by using at least two pre-defined categories per given document features. In this paper, Web documents are classified in real time not with experimental data or a learning process, but by similarity calculations between the terminology information extracted from Web documents and ontology categories. This results in a more accurate document classification since the meanings and relationships unique to each document are determined. [ABSTRACT FROM AUTHOR]

Research on e-learner community building has attracted much attention for its effectiveness in sharing the learning experience and resources among geographically dispersed e-learners. While collaborative filtering proves its success as one of the most efficient methods in finding similar users in e-commerce domain, it does meet special challenges in e-learning areas. In this paper, we incorporate multi-agent techniques into collaborative filtering and propose a novel community building scheme. By doing so, we manage to collect useful information from the learner behaviors and thus increase the scalability and flexibility of traditional collaborative filtering methods. The experiment on a standard benchmark shows that our scheme has reasonable community building quality and e-learners can make better recommendations to each other inside the community. [ABSTRACT FROM AUTHOR]

This chapter contains papers presented in the workshop on Text Mining and Applications (TeMA 2005), organized in the framework of the Portuguese Association for Artificial Intelligence conference (EPIA). This workshop is aimed at attracting quality papers and enhancing the knowledge in this area. 27 papers were submitted. From these, 9 papers were selected for publication in this Springer volume. These numbers show current importance of this field in AI and suggest that the organization of equivalent events in future EPIA editions should be pursued. First paper works on bilingual lexical acquisition from non parallel corpora, applicable in Machine Translation. Second paper describes work on Text Summarization. Third uses Transformation Based learning for NP Identification applied to Portuguese.Fourth uses linguistic knowledge for passage retrieval and question answering. Fifth describes the use of weakly supervised learning for extraction of semantic patterns. Sixth paper proposes a method for semantic indexing and evaluates it on traditional Information Retrieval tasks. Seventh works on unsupervised language independent extraction of multi-word terms, applicable in multiple domains and evaluates their results for Slovene and English. Eighth paper presents a variant of a known method for Anaphora resolution, adapted to Portuguese. Last paper proposes a stemmer for Brazilian Portuguese. [ABSTRACT FROM AUTHOR]

International workshop on Risk Mining (RM2006) was held in conjunction with the 20th Annual Conference of the Japanese Society for Artificial Intelligence(JSAI2005), Tokyo Japan, June 2005. The workshop aimed at sharing and comparing experiences on risk mining techniques applied to risk detection, risk clarification and risk utilization. In summary, the workshop gave a discussion forum for researchers working on both data mining and risk management where the attendees discussed various aspects on data mining based risk management. [ABSTRACT FROM AUTHOR]

This paper shows how multi-dimensional functions, describing the operation of complex equipment, can be learned. The functions are points in a shape space, each produced by morphing a prototypical function located at its origin. The prototypical function and the space's dimensions, which define morphological operations, are learned from a set of existing functions. New ones are generated by averaging the coordinates of similar functions and using these to morph the prototype appropriately. This paper discusses applying this approach to learning new functions for components of gas turbine engines. Experiments on a set of compressor maps, multi-dimensional functions relating the performance parameters of a compressor, show that it more accurately transforms old maps, into new ones, than existing methods. [ABSTRACT FROM AUTHOR]

A Personal Assistant (PA) agent is a software agent capable of helping people to handle tasks in their workplace. The paper proposes a memory mechanism for personal assistant agents in order to enhance agent intelligence while working with the user or with other agents. Inspired by a case memory model in the domain of Case-Based Reasoning (CBR), this paper endows PA agents with a case memory mechanism, which results in improved PA agents: MemoPAs. We present the memory mechanism of MemoPA in detail, and report a first implementation of the method. Finally, future work is outlined for improving the memory mechanism. [ABSTRACT FROM AUTHOR]

A top-down experimental procedure for defect type recognition of epoxy-resin transformers by Partial Discharge (PD) is proposed. Most of the PD detection methods could be performed only at the shutdown period of equipments. By using Acoustic Emission (AE), the real-time and online detection could be reachable. Therefore, this paper conducted high voltage test of pre-faulty transformers and measured those PD signals for recognition needed. Afterward, the selected features that proposed in this paper can be extracted from these collected PD signals. According to these features, effective identification of their faulty types can be done using the proposed particle swarm optimization combined with neural network. Finally, with a view to apply in field, this research adds different noise levels to distort the original data. These distorted data are entered for subsequent testing. Research shows encouraging results that with 30% noise per discharge count, an 80% successful recognition rate can be achieved. [ABSTRACT FROM AUTHOR]

Electromagnetism-like algorithm (EM) is a population-based meta-heuristic which has been proposed to solve continuous problems effectively. In this paper, we present a new meta-heuristic that uses the EM methodology to solve the single machine scheduling problem. Single machine scheduling is a combinatorial optimization problem. Schedule representation for our problem is based on random keys. Because there is little research in solving the combinatorial optimization problem (COP) by EM, the paper attempts to employ the random-key concept enabling EM to solve COP in single machine scheduling problem. We present a hybrid algorithm that combines the EM methodology and genetic operators to obtain the best/optimal schedule for this single machine scheduling problem, which attempts to achieve convergence and diversity effect when they iteratively solve the problem. The objective in our problem is minimization of the sum of earliness and tardiness. This hybrid algorithm was tested on a set of standard test problems available in the literature. The computational results show that this hybrid algorithm performs better than the standard genetic algorithm. [ABSTRACT FROM AUTHOR]

Upon close examination of a set of industrial data from a large scale power plant, time varying behavior are discovered. If a fixed model is applied to monitor this process, false alarms will be inevitable. This paper suggests the use of adaptive models to cope with such situation. A recently proposed technique, fast algorithm for Moving Window Principal Component Analysis (MWPCA) was employed because of its following strength: (i) the ability in adapting process changes, (ii) the conceptual simplicity, and (iii) its computational efficiency. Its advances in fault detection is demonstrated in the paper by comparing with the conventional PCA. In addition, this paper proposed to plot the scaled variables in conjunction with MWPCA for fault diagnosis, which is proved to be effective in this application. [ABSTRACT FROM AUTHOR]

PVM (Parallel virtual machine) library is a tool which used processes large amounts of data sets. This paper wants to achieve a high performance solution that exploits PVM library and parallel computers to solve ICA (Independent Component Analysis) problem. The paper presents parallel power ICA implementations to decomposition data sets. Power iteration (PI) is an algorithm for independent component analysis, which has some desired features. It has higher performance and data capacity than current sequential implementations. This paper, we show the power iteration algorithm which learning updating is in the form of matrix transformation . From power iteration algorithm, we develop parallel power iteration algorithm and implement parallel component decomposition solution. At last, experimental results, analysis and future plans are presented. [ABSTRACT FROM AUTHOR]

In this paper, global exponential stability of Cohen-Grossberg neural networks with reaction-diffusion and Dirichlet boundary conditions is considered by using an approach based on the delay differential inequality and the fixed-point theorem. Some sufficient conditions are obtained to guarantee that the reaction-diffusion Cohen-Grossberg neural networks are globally exponentially stable. The results presented in this paper are the improvement and extension of the existed ones in some existing works. [ABSTRACT FROM AUTHOR]

This paper analyzes global convergence and learning parameters of the back-propagation algorithm for quadratic functions. Some global convergence conditions of the steepest descent algorithm are obtained by directly analyzing the exact momentum equations for quadratic cost functions. In addition, in order to guarantee the convergence for a given learning task, the method is obtained to choose the proper learning parameters. The results presented in this paper are the improvement and extension of the existed ones in some existing works. [ABSTRACT FROM AUTHOR]