Search

This is a summary of the papers presented at the Active Conceptual Modeling of Learning (ACM-L) Workshop, November 8, 2006, Tucson, Arizona, USA, and several invited papers. [ABSTRACT FROM AUTHOR]

Active Learning in the classroom domain presents an interesting case for integrating physical and digital affordances. Traditional physical handouts and transparencies are giving way to new digital slides and PCs, but the fully digital systems still lag behind the physical artifacts in many aspects such as readability and tangibility. To better understand the interplay between physical and digital affordances in this domain, we developed PaperCP, a paper-based interface for a Tablet PC-based classroom interaction system (Classroom Presenter), and deployed it in an actual university course. This paper reports on an exploratory experiment studying the use of the system in a real-world scenario. The experiment confirms the feasibility of the paper interface in supporting student-instructor communication for Active Learning. We also discuss the challenges associated with creating a physical interface such as print layout, the use of pen gestures, and logistical issues. [ABSTRACT FROM AUTHOR]

Collaborative tagging has grown on the Internet as a new paradigm for web information discovering, filtering and retrieval. In the physical world, we use visual tags: labels readable by smartphones with cameras. While visual tags are usually related to a web site address, collaborative tagging, instead, provides updated, recommended information contributed and shared by users. In this paper we investigate the combination of collaborative tagging systems with visual tags. We present a prototype of a semiautomatic system generating visual tags which gather information from collaborative tagging. The user can interact with a list of relevant tags (built by clustering closely related tags) that can be further encoded in a visual tag, according to user's preferences. The user experience is enriched by retrieving multimedia content linked to the selected tags, present on the web. We finally show a case study illustrating our approach. [ABSTRACT FROM AUTHOR]

The regulation of multiagent systems may be approached from different stand-points. In this paper I will take the perspective of using a certain type of devices, electronic institutions, to regulate agent interactions. Furthermore, in this paper I am concerned with the tasks of design and construction of actual electronic institutions and I will explore some of the empirical aspects that one may encounter in such activities. More specifically, I will focus on those empirical aspects that are characteristic of electronic institutions rather than those that may be typical of multi-agent systems development in general or other types of software engineering. I use three examples of actual electronic institutions that show different and complementary features in order to motivate a number of distinctions that may be used to treat empirical features in a systematic way. [ABSTRACT FROM AUTHOR]

Changes and adaptations are always necessary after the deployment of a multiagent system (MAS), as well as of any other type of software systems. Some of these changes may be simply perfective and have local impact only. However, adaptive changes to meet changed situations in the operational environment of the MAS may have global impact on the overall design. In this paper, we analyze the issue of continuous design change/adaptation in a MAS organization, and the specific problem of how to properly model/design a MAS so as to make it ready to adaptation. Following, the paper focuses on the Gaia methodology and analyzes - also with the help of an illustrative example - its suitability in supporting and facilitating adaptive changes in MASs organizations, and its advantages and limitations with this regard over a number of different agent-oriented methodologies. Keywords: Agent Oriented Methodologies, Design for Change, Adaptive Organizations, Methodologies Evaluation. [ABSTRACT FROM AUTHOR]

Spatial structure supporting applications offer an abstract level of what can be found in the real world. However, in many systems, objects are aligned straight, rotation is not possible, they can be resized easily and can hold more text than is visible on the screen. Paper and structures created with paper seem to be more limited: Straight alignment is not possible without spending much time; paper can hardly be resized without damaging it; and piles may fall down if they become too tall. However, a closer look shows that paper structures offer much more attributes and dependencies than any current spatial structure supporting application. In this article, we compare paper structures to a selection of computer applications. We argue that the observed small additions with paper carry information which improves finding and organizing. [ABSTRACT FROM AUTHOR]

Generally, it is difficult to find constant patterns on identifiers in a container image, since the identifiers are not normalized in color, size, and position, etc. and their shapes are damaged by external environmental factors. This paper distinguishes identifier areas from background noises and removes noises by using an ART2-based quantization method and general morphological information on the identifiers such as color, size, ratio of height to width, and a distance from other identifiers. Individual identifier is extracted by applying the 8-directional contour tracking method to each identifier area. This paper proposes a refined ART2-based RBF network and applies it to the recognition of identifiers. Through experiments with 300 container images, the proposed algorithm showed more improved accuracy of recognizing container identifiers than the others proposed previously, in spite of using shorter training time. [ABSTRACT FROM AUTHOR]

Titled Documents (TD) are short text documents that are segmented into two parts: Heading Part and Excerpt Part. With the development of the Internet, TDs are widely used as papers, news, messages, etc. In this paper we discuss the problem of automatic TDs categorization. Unlike traditional text documents, TDs have short headings which have less useless words comparing to their excerpts. Though headings are usually short, their words are more important than other words. Based on this observation we propose a titled document classification framework using the widely used MNB classifier. This framework puts higher weight on the heading words at the cost of some excerpt words. By this means heading words play more important roles in classification than the traditional method. According to our experiments on four datasets that cover three types of documents, the performance of the classifier is improved by our approach. [ABSTRACT FROM AUTHOR]

In Mizar, unlike in most other proof assistants, the types are not part of the foundations of the system. Mizar is based on untyped set theory, which means that in Mizar expressions are typed but the values of those expressions are not. In this paper we present the Mizar type system as a collection of type inference rules. We will interpret Mizar types as soft types, by translating Mizar's type judgments into sequents of untyped first order predicate logic. We will then prove that the Mizar type system is correct with respect to this translation in the sense that each derivable type judgment translates to a provable sequent. [ABSTRACT FROM AUTHOR]

This paper deals with the problem of global stability for a class of neural networks with time-varying delays. A new sufficient condition for global stability is proposed by using some slack matrix variables to express the relationship between the system matrices. The restriction on the derivative of the delay function to be less than unit is removed. A numerical example shows that the result obtained in this paper improves the upper bound of the delay over some existing ones. [ABSTRACT FROM AUTHOR]

Engineering component interactions is a major challenge in the development of large-scale, open systems. In the realm of multiagent system research, organizational abstractions have been proposed to overcome the complexity of this task. However, the gap between these modeling abstractions, and the constructs provided by todays agent-oriented software frameworks is still rather big. This paper reports on the multiagent programming framework, which provides executable constructs for each of the organizational, ACL-based modeling abstractions of the theory. Setting out from a components and connectors perspective on the elements of the metamodel, their executions semantics is defined and instrumented on top of the JADE platform. Moreover, a systematic reuse approach to the engineering of interactions is put forward. [ABSTRACT FROM AUTHOR]

This paper discusses the AgentAssebly architecture and specifically the agent framework platform component of the architecture. An introduction is given to the work covered in the paper and previous work (see [1]) this paper is based upon. Then an in-depth discussion is rendered on the agent framework platform provided by the AgentAssembly architecture. The paper concludes with some remarks on the research presented and future aims of the ongoing research project. Keywords: Agent programming languages, frameworks, and toolkits meta-modeling and meta reasoning. [ABSTRACT FROM AUTHOR]

The traveling salesman problem (TSP) is a very hard optimization problem in the field of operations research. It has been shown to be NP-hard, and is an often-used benchmark for new optimization techniques. This paper pro- poses an improved multi-agent approach for solving large TSP. This proposed approach mainly includes three kinds of agents with different function. The first kind of agent is conformation agent and its function is generating the new solution continuously. The second kind of agent is optimization agent and its function is optimizing the current solutions group. The third kind of agent is refining agent and its function is refining the best solution from the beginning of the trial. At same time, there are many sub-agents in each kind of agent. These sub-agents accomplish the task of its superior agent cooperatively. At the end of this paper, the experimental results have shown that the proposed hybrid approach has good performance with respect to the quality of solution and the speed of computation. [ABSTRACT FROM AUTHOR]

A great deal of research has been devoted in recent years to the designing Fuzzy-Neural Networks (FNN) from input-output data. And some works were also done to analyze the performance of some methods from a rigorous mathematical point of view. In this paper, a new approximation bound for the clustering method, which is employed to design the FNN with the Gaussian Membership Function, is established. It is an improvement of the previous result in which the related approximation bound was somewhat complex. The detailed formulas of the error bound between the nonlinear function to be approximated and the FNN system designed based on the input-output data are derived. [ABSTRACT FROM AUTHOR]

The major purpose of the design of distributed databases is to improve system performance and to increase system reliability. Fragmentation and allocation play important roles in the development of a cost-efficient system. This paper addresses the problem of fragmentation in the context of complex value databases, which cover the common aspects of object-oriented databases, object-relational databases and XML. In this paper, we present a cost-based approach for horizontal and vertical fragmentation. Our approach is based on a cost model that takes the structure of complex value databases into account. [ABSTRACT FROM AUTHOR]

The SPAWAR Systems Center (SSC San Diego) of the U.S. Navy hosted two workshops on Active Conceptual Modeling of Learning (ACM-L). The first workshop was held at SSC San Diego on May 10-12, 2006 to introduce the Science &Technology (S&T) Initiative and identify a Research and Development agenda for the technology development investigation. Eleven invited researchers in Conceptual Modeling presented position papers on the proposed S&T Initiative. The second workshop was held on November 8, 2006 at the 25th International Conference on Conceptual Modeling, ER 2006, 6-9 November 2006, in Tucson, Arizona. Complementary to the May Workshop, the November workshop was a forum for the international researchers and practitioners to present their papers as a result of a call for papers and to exchange ideas from various perspectives of the subject. This paper describes research issues identified by participants from the two ACM-L workshops. [ABSTRACT FROM AUTHOR]

This paper discusses the mechanical design and simulation of a novel omnidirectional wheel based on Reuleaux-triangles. The main feature of our omniwheel is that the point of contact of the wheel with the floor is always kept at the same distance from the center of rotation by mechanical means. This produces smooth translational movement on a flat surface, even when the profile of the complete wheel assembly has gaps between the passive rollers. The grip of the wheel with the floor is also improved. The design described in this paper is ideal for hard surfaces, and can be scaled to fit small or large vehicles. This is the first design for an omnidirectional wheel without circular profile, yet capable of rolling smoothly on a hard surface. [ABSTRACT FROM AUTHOR]

During the early stages of architectural training, tangibility plays an important role in developing spatial awareness. In such contexts, tangible user interfaces are believed to provide a significant advantage as they combine the affordances of both the physical and the digital world. We introduce CubeExplorer, a hybrid 3D conceptual aid that combines physical interaction and digital modeling in an effort to complement conventional architectural space-training tools (such as physical materials and digital CAD programs). Using a digital pen as an input mechanism, CubeExplorer lets users perform subtractive 3D geometric operations on a simple paper based cube model while observing the resulting model on a display. The tangibility of the model simplifies navigation and command execution, while the digital interface makes it easy for users to explore multiple alternative designs. To evaluate the potential of such an approach, we conducted a user study in a normal classroom environment where students were provided with physical (wooden block), hybrid (CubeExplorer), and virtual (FormZ) interfaces to complete the same assignment. Our evaluation showed that CubeExplorer combined the advantages of both digital and tangible media. The advantages of CubeExplorer over digital media were substantiated in a follow-up study comparing CubeExplorer and SketchUp in a similar building task. [ABSTRACT FROM AUTHOR]

Ubiquitous interaction places the user in the centre of dynamic configurations of technology, where work not necessarily is performed through a single personal computer, but supported by a multiplicity of technologies and physical devices. This paper presents an activity-theoretically based framework for analyzing ubiquitous substitution, i.e. a set of mediators that are or can be continuously substituted with the purpose of highlighting expected and indented uses, and the conflicts encountered when attempting substitution between them. The paper develops a four-leveled analysis of such mediators, and point towards a minimalist approach to design of ubiquitous interaction. [ABSTRACT FROM AUTHOR]

Recent advances in data and knowledge engineering have emphasized the need for formal concept analysis (fca) tools taking into account structured data. There are a few adaptations of the classical fca methodology for handling contexts holding on complex data formats, e.g. graph-based or relational data. In this paper, relational concept analysis (rca) is proposed, as an adaptation of fca for analyzing objects described both by binary and relational attributes. The rca process takes as input a collection of contexts and of inter-context relations, and yields a set of lattices, one per context, whose concepts are linked by relations. Moreover, a way of representing the concepts and relations extracted with rca is proposed in the framework of a description logic. The rca process has been implemented within the Galicia platform, offering new and efficient tools for knowledge and software engineering. [ABSTRACT FROM AUTHOR]

Despite numerous studies have applied various forecasting models to tourism demand analysis, data mining techniques have been largely overlooked by academic researchers in tourism forecasting prior to 1999. Based on our review of published articles in tourism journals that applied data mining techniques to tourism demand forecasting, we find that the application of data mining techniques are still at their infancy. This paper concludes with practical implications and future research areas. [ABSTRACT FROM AUTHOR]

Support vector regression (SVR) is a new technique for pattern classification , function approximation and so on. In this paper we propose an new constructing approach of classification rules based on support vector regression and its derivative characteristics for the classification task of data mining. a new measure for determining the importance level of the attributes based on the trained SVR is proposed. Based on this new measure, a new approach for clas-sification rule construction using trained SVR is proposed. The performance of the new approach is demonstrated by several computing cases. The experimen-tal results prove that the approach proposed can improve the validity of the ex-tracted classification rules remarkably compared with other constructing rule approaches, especially for the complicated classification problems. [ABSTRACT FROM AUTHOR]

Pattern recognition and classification problems are most popular issue in machine learning, and it seem that they meet their second golden age with bioinformatics. However, the dataset of bioinformatics has several distinctive characteristics compared to the data set in classical pattern recognition and classification research area. One of the most difficulties using this theory in bioinformatics is that raw data of DNA or protein sequences cannot be directly used as input data for machine learning because every sequence has different length of its own code sequences. Therefore, this paper introduces one of the methods to overcome this difficulty, and also argues that the capability of generalization in this method is very poor as showing simple experiments. Finally, this paper suggests different approach to select the fixed number of effective features by using Support Vector Machine, and noise whitening method. This paper also defines the criteria of this suggested method and shows that this method improves the precision of diagnosing abnormal protein sequences with experiment of classifying ovarian cancer data set. [ABSTRACT FROM AUTHOR]

To improve the safety of drivers and walkers in a city, several traffic monitors are usually set on lanes. These traffic monitors can also improve the security of communities. In this paper, we integrate the so-called linear/circular consecutive-k-out-of-n:F systems into our proposed traffic-monitor system. The objective is to find the optimal design of monitors under limited budget for the system. The main purposes of this paper are : (1) to propose a new traffic-monitor system, (2) to present an immune algorithm (IA) for the optimal design of traffic monitors, and (3) to report numerical results of various parameters by the proposed algorithm. It is shown that the proposed immune algorithm performs well for all test problems. [ABSTRACT FROM AUTHOR]

Medical Data Mining is a very active and challenging research area in Data Mining community. However researchers entering Medical Data Mining should be aware that in core clinical, dentistry and nursing, data mining is not welcomed as much as we believe and publication of results in these journals based on Data Mining algorithms is not easily possible. In this paper, in addition to presenting one of our "successful" KDD projects in Urology that did not get to anywhere, we back up our belief based on designed searches on PubMed and review literature based on these searches. Our findings suggest that few Data Mining algorithms made their ways into core clinical journals. The paper concludes by reasons we have collected through our experiences. [ABSTRACT FROM AUTHOR]

In this paper, we introduce a new type of reducts called the λ-Fuzzy-Reduct, where the fuzzy similarity relation is constructed by means of cosine-distances of decision vectors and the parameter λ is used to tune the similarity precision level. The λ-Fuzzy-Reduct can eliminate harsh requirements of the distribution reduct, and it is more flexible than the maximum distribution reduct, the traditional reduct, and the generalized decision reduct. Furthermore, we prove that the distribution reduct, the maximum distribution reduct, and the generalized decision reduct can be converted into the traditional reduct. Thus in practice the implementations of knowledge reductions for the three types of reducts can be unified into efficient heuristic algorithms for the traditional reduct. We illustrate concepts and methods proposed in this paper by an example. [ABSTRACT FROM AUTHOR]

In this paper, a music information retrieval system in real mobile environment is proposed. In order to alleviate distortions due to the mobile noise, a noise reduction algorithm is applied and then a feature extraction using Multi-Feature Clustering is implemented to improve the system performance. The proposed system shows quite successful performance with real world cellular phone data. [ABSTRACT FROM AUTHOR]

Incrementally maintaining association rules based on two or more classes of frequent item sets may reduce the costs of scanning the original database remarkably. However, it was considered as a method of saving time with more storage spaces. It is suggested in this paper that all frequent item sets of several minimal supports can be stored in a table with a little additional storage, and a representation model is given. Based on this model, the paper systematically discusses the problem of incremental maintenance based on discovered association rules of several minimal supports. Theoretical analysis and experiments show that the approach makes full use of the previous results and reduces the complexity of incremental maintenance algorithms. [ABSTRACT FROM AUTHOR]

This paper describes a class of random additively decomposable problems (rADPs) with and without interactions between the subproblems. The paper then tests the hierarchical Bayesian optimization algorithm (hBOA) and other evolutionary algorithms on a large number of random instances of the proposed class of problems. The results show that hBOA can scalably solve rADPs and that it significantly outperforms all other methods included in the comparison. Furthermore, the results provide a number of interesting insights into both the difficulty of a broad class of decomposable problems as well as the sensitivity of various evolutionary algorithms to different sources of problem difficulty. rADPs can be used to test other optimization algorithms. [ABSTRACT FROM AUTHOR]

In UML 2.0 sequence diagrams have been considerably extended and are now fundamentally better structured. Interactions in sequence diagrams can be structured using so-called interaction fragments, including alt (alternative behaviour), par (parallel behaviour), neg (forbidden behaviour), assert (mandatory behaviour) and ref (reference another diagram). The operator ref in particular greatly improves the way diagrams can be decomposed. In previous work we have given a semantics to a subset of sequence diagrams using labelled event structures, a true-concurrent model that naturally captures alternative and parallel behaviour. In this paper, we expand that work to address refinement and show how to obtain a refined model by means of a powerful categorical construction over two categories of labelled event structures. The underlying motivation for this work is reasoning and verification of complex scenario-based inter-object behavioural models. We conclude the paper with a discussion on future work. [ABSTRACT FROM AUTHOR]

This paper describes how to refine a Gaia design by applying agent-oriented extensions of UML. First, we show how the Gaia Interaction model can be improved by applying the first two layers of the Agent Interaction Protocol (AIP) of AUML. Second, Gaia Agent and Service models are refined by applying the AIP's third layer combined with Extended UML Class Diagrams. Third, Gaia Organisational Structure is enriched by applying the Aalaadin model. The final aim of the whole process is to obtain a more concrete design closer to implementation. We demonstrate how the refinement process can be applied to the development of an agent-based system for conference management. [ABSTRACT FROM AUTHOR]

In order to enable the intelligent agents to be aware of the dynamic business requirements and strategies, and cooperate with other agents in a stable and explicit way, a policy and contract extended BDI logic (called BGIPDC logic) has been proposed, by integrating contracts and policies into traditional BDI model. On the basis of BGIPDC logic, this paper proposes a model of agent architecture as a concrete realization of it, called PDC-agent. PDC-agent is an extension of traditional BDI agent, by adding a policy engine, a contract engine and a goal maintenance component into agent's interpreter. Besides, PDC-agent has two characteristics. First, the operation of PDC-agent is based on an event-driven mechanism. Various events drive the components of the interpreter. Second, the representation of PDC-agent is on the basis of ontology. [ABSTRACT FROM AUTHOR]

Driven by the issue of geo-spatial data mining under grid computing environment, a new representation method called spatial information multi-grid (SIMG) for depicting spatial data and spatial information is presented in this paper. A strategy of dividing the globe with multi-level spatial grid is proposed. And through further studying on the precision of description on feature of detail, this paper tries to divide the globe with SIMG and constructs the framework of SIMG in China. Based on SIMG this paper tries to realize data mining of different thematic information on the same geographical position, data mining of dynamic spatial-temporal information of the same thematic content, data mining and transforming of different coordinate systems and to make SIMG a fundamental research work for further developing spatial information sharing and data mining. [ABSTRACT FROM AUTHOR]

It is a challenging issue to analyze video content for video mining due to the difficulty in video representation. A hierarchical model of video representation is proposed with a schema for content-based analysis of news video in this paper. The research problem targeted in this paper is to mine a massive video database to retrieve specific clip based on content defined by users. This is frequently encountered in entertainment and video editing. A novel solution to this problem is developed in this paper, in which the consecutive news video is segmented into shots, scenes and news items using multimodal features based on the hierarchical model. To summarize the content of video, a video abstract is developed. The experimental evaluation demonstrates the effectiveness of the approaches discussed in this paper. [ABSTRACT FROM AUTHOR]

This paper discusses extending the Unified Modelling Language by means of a profile for modelling knowledge-based system in the context of Model Driven Architecture (MDA) framework. The profile is implemented using the eXecutable Modelling Framework (XMF) Mosaic tool. A case study from the health care domain demonstrates the practical use of this profile; with the prototype implemented in Java Expert System Shell (Jess). The paper also discusses the possible mapping of the profile elements to the platform specific model (PSM) of Jess and provides some discussion on the Production Rule Representation (PRR) standardisation work. [ABSTRACT FROM AUTHOR]

The goal of this article is to formalize Object Role Modeling (ORM) using the $\mathcal{DLR}$ description logic. This would enable automated reasoning on the formal properties of ORM diagrams, such as detecting constraint contradictions and implications. In addition, the expressive, methodological, and graphical capabilities of ORM make it a good candidate for use as a graphical notation for most description logic languages. In this way, industrial experts who are not IT savvy will still be able to build and view axiomatized theories (such as ontologies, business rules, etc.) without needing to know the logic or reasoning foundations underpinning them. Our formalization in this paper is structured as 29 formalization rules, that map all ORM primitives and constraints into $\mathcal{DLR}$, and 2 exceptions of complex cases. To this end, we illustrate the implementation of our formalization as an extension to DogmaModeler, which automatically maps ORM into DIG and uses Racer as a background reasoning engine to reason about ORM diagrams. [ABSTRACT FROM AUTHOR]

This paper presents a methodology to derive views over a relational database by applying a sequence of appropriately defined operations to the global schema. Such tailoring and composition process aims at offering personalized views over the database schema, so as to improve its ability to support the new needs of customers, support evolutionary software development, and fix existing legacy database design problems. The process is driven by the designer's knowledge of the possible operational contexts, in terms of the various dimensions that contribute to determine which portions of the global schema are relevant with respect to the different actors and situations. We formally introduce some operators, defined on sets of relations, which tailor the schema and combine the intermediate views to derive different final views, suitable for the different envisioned situations. The application to a case study is also presented, to better clarify the proposed approach. [ABSTRACT FROM AUTHOR]

This paper presents a set of components that support psychotherapy processes on mobile and office settings. One provides patients the required access to psychotherapy artefacts, enabling an adequate and tailored aid and motivation for fulfilment of common therapy tasks. Another offers therapists the ability to define and refine the artefacts, in order to present, help and react to the patient according to his/her specific needs and therapy progress. Two other components allow the analysis and annotation of the aforementioned artefacts. All these components run on a PDA base. Evaluation results validated some of the design choices, and indicate future directions and improvements. [ABSTRACT FROM AUTHOR]

Central to the process of query optimization in all real-life modern-day Database Management Systems (DBMS) is the use of histograms. These have been used for decades in approximating query result sizes in the query optimizer, and methods such as the Equi-Width and Equi-Depth histograms have been incorporated in all real-life systems. This is because histograms are simple structures, and can be easily utilized in determining efficient Query Evaluation Plans (QEPs). This paper demonstrates how we can incorporate two recently-developed histogram methods into the ORACLE real-life DBMS. These two new histograms methods were introduced by Oommen and Thiyagarajah [1], and called the the Rectangular Attribute Cardinality Map (R-ACM), and the Trapezoidal Attribute Cardinality Map (T-ACM). The superiority of the R-ACM and the T-ACM in yielding more accurate query result size estimates has been well demonstrated, and the resulting superior QEPs for a theoretically-modeled database was shown in [2]. In this paper we make a "conceptual leap" and demonstrate how the ACMs can be incorporated into a real-life DBMS. This has been done by designing and implementing a prototype which sits on top of an ORACLE 9i system. The integration is achieved in C/C++ and PL/SQL, and serves as a prototype "plug-in" to the ORACLE system, since it is fully integrated and completely transparent to users. The superiority of utilizing the ACM histograms is rigorously validated by conducting an extensive set of experiments on the TPC-H benchmark data sets, and by testing on equi-select and equi-join queries. The entire set of experimental results obtained by integrating the underlying algorithms into the ORACLE query optimizer can be found in [3]. [ABSTRACT FROM AUTHOR]

This paper presents a context-aware text summarizer based on ontologies intended to be used for adapting information to mobile devices. The system generates summaries from texts according to the profile of the user and the context where he/she is at the moment. Context is determined by spatial and temporal localization. Ontologies are used to allow identifying which parts of the texts are related to the user's profile and to the context. Ontologies are structured as hierarchies of concepts and concepts are represented by keywords with a weight associated. [ABSTRACT FROM AUTHOR]

Run-time application environments are affected by the changes in mini-world or technology changes. Large number of applications are process driven. For robust applications that can evolve over time, there is a need for a methodology that implicitly handles changes at various levels from mini-world to run-time environment through a layers of models and systems. In this paper, we present ER* methodology for evolving applications. In the context of this paper, the role of two-way active behaviour and template driven development of applications is presented. This methodology facilitates capturing active behaviour from run-time transactions and provides a means of using this knowledge to guide subsequent application design and its evolution. [ABSTRACT FROM AUTHOR]

The perception and modeling of other robots has been a topic of minor regard in the Four-Legged League, because of the limited processing und sensing capabilities of the AIBO platform. Even the current world champion, the GermanTeam, abandoned the usage of a robot recognition. Nevertheless, accurate position estimates of other players will be needed in the future to accomplish tasks such as passing or applying adaptive tactics. This paper describes an approach for localizing other players in a robot's local environment by integrating different unreliable perceptions of robots and obstacles, which may be computed in a reasonable way. The approach is based on Gaussian distributions describing the models of the robots as well as the perceptions. The integration of information is realized by using Kalman filtering. [ABSTRACT FROM AUTHOR]

In the RoboCup small-size league, most teams calculate the robots' positions by means of a camera that is mounted above the field as well as different kinds of artificial intelligence methods that run on an additional PC. This processing loop induces various time delays, which require forecasting routines, if more accurate behaviors are desired. This paper shows that by utilizing a combination of a neural network and local sensors, the robot is able to estimates its actual position quite accurately. This paper furthermore shows that the learning procedure is also able to compensate for slip and friction effects that cannot be observed by the local sensors. [ABSTRACT FROM AUTHOR]

Learning automata act in a stochastic environment and are able to update their action probabilities considering the inputs from their environment, so optimizing their functionality as a result. In this paper, the goal is to investigate and evaluate the application of learning automata to cooperation in multi-agent systems, using soccer simulation server as a test bed. We have also evaluated our learning method in hard situations such as malfunctioning of some of the agents in the team and in situations that agents' sense/act abilities have a lot of noise involved. Our experiment results show that learning automata adapt well with these situations. [ABSTRACT FROM AUTHOR]

This paper describes a method for cooperative play among 3 robots in order to score a goal in the RoboCup Small Size League. In RoboCup 2005 Osaka, our team introduced a new attacking play, where one robot kicks a ball and the other receives and immediately shoots the ball on goal. However, due to the relatively slow kicking speed of the robot, top opponent teams could prevent successful passing between robots. This motivates the need for more complex play, such as passing around to several robots to avoid the opponents' passing defense. In this paper we propose a method to realize such a play, i.e. a combination play among 3 robots. We discuss the technical issues to achieve this combination play, especially for a pass-and-shoot combination play. Experimental results on real robots are provided. They indicate that the success rate of the play depends strongly on the arrangement of the robots, and ranges from 20 % to 90 % in tests with an opponent goalkeeper which stands still. [ABSTRACT FROM AUTHOR]

Color segmentation is typically the first step of vision processing for a robot operating in a color-coded environment, such as RoboCup soccer, and many object recognition modules rely on that. Although many approaches to color segmentation have been proposed, in the official games of the RoboCup Four Legged League manual calibration is still preferred by most of the teams. In this paper we present a method for color segmentation that is based on an adaptive transformation of the color distribution of the image: the transformation is dynamically computed depending on the current image (i.e., it adapts to condition changes) and then it is used for color segmentation with static thresholds. The method requires the setting of only a few parameters and has been proved to be very robust to noise and light variations, allowing for setting parameters only once when arriving at a competition site. The approach has been implemented on AIBO robots, extensively tested in our laboratory, and successfully experimented in the some of the games of the Four Legged League in RoboCup 2005. [ABSTRACT FROM AUTHOR]

This paper shows that it is possible to retrieve all parameters of the parabolic flight trajectory of an object from a time stamped sequence of images captured by a single camera looking at the scene. Surprisingly, it is not necessary to use two cameras (stereo vision) in order to determine the coordinates of the moving object with respect to the floor. The technique described in this paper can thus be used to determine the three-dimensional trajectory of a ball kicked by a robot. The whole calculation can be done, at the limit, with just three measurements of the ball position captured in three consecutive frames. Therefore, this technique can be used to forecast the future motion of the ball a few milliseconds after the kick has taken place. The computation is fast and allows a robot goalie to move to the correct blocking position. Interestingly, this technique can also be used to self-calibrate stereo cameras. [ABSTRACT FROM AUTHOR]

A fast gait is an essential component of any successful team in the RoboCup 4-legged league. However, quickly moving quadruped robots, including those with learned gaits, often move in such a way so as to cause unsteady camera motions which degrade the robot's visual capabilities. This paper presents an implementation of the policy gradient machine learning algorithm that searches for a parameterized walk while optimizing for both speed and stability. To the best of our knowledge, previous learned walks have all focused exclusively on speed. Our method is fully implemented and tested on the Sony Aibo ERS-7 robot platform. The resulting gait is reasonably fast and considerably more stable compared to our previous fast gaits. We demonstrate that this stability can significantly improve the robot's visual object recognition. [ABSTRACT FROM AUTHOR]

When developing skills on a physical robot, it is appealing to turn to modern machine learning methods in order to automate the process. However, when no accurate simulator exists for the type of motion in question, all learning must occur on the physical robot itself. In such a case, there is a high premium on quick, efficient learning (specifically, learning with low sample complexity). Recent results in learning locomotion have demonstrated the feasibility of learning fast walks directly on quadrupedal robots. This paper demonstrates that it is also possible to learn a higher-level skill requiring more fine motor coordination, again with all learning occurring directly on the robot. In particular, the paper presents a learned ball-grasping skill on a commercially available Sony Aibo robot, with no human intervention other than battery changes. The learned skill significantly outperforms our best hand-tuned solution. As the learned grasping skill relies on a learned walk, we characterize our learning implementation within the layered learning formalism. To our knowledge, the two learned layers represent the first use of layered learning on a physical robot. [ABSTRACT FROM AUTHOR]

We propose a new multi-agent development method, named MDAD (Model Driven Agent Development). It is based on the MDA (Model Driven Architecture) paradigm. The aim of MDAD method is to reduce the cost of building MAS applications by starting from abstract specification of system thanks to MAS meta-models, and producing the final system by means of transformations of this specification into computational entities. We present in this paper the application of MDAD to the INAF framework. First we give an overview of MDA approach and its application to MAS. Thus, several abstraction levels are determined and a set of meta-models is introduced. Then, we give the transformation rules used to produce INAF compliant models. MDAD method is illustrated with the timetable management benchmark. [ABSTRACT FROM AUTHOR]