Tsunenori Mine

Agent Community Based Peer-to-Peer Information Retrieval

This paper proposes an Agent Community based Peer-to-Peer information retrieval method called ACP2P method, which uses agent communities to manage and look up information related to users. An agent works as a delegate of its user and searches for information that the user wants by communicating with other agents. The communication between agents is carried out in a peer-to-peer computing architecture. In order to retrieve information related to a user query, an agent uses a content file, which consists of retrieved documents, and two histories : a query/retrieved document history(Q/RDH) and a query/sender agent history(Q/SAH). We implemented this method with Multi-Agents Kodama[1], and conducted preliminary experiments to test the hypothesis. The empirical results showed that the method was much more efficient than a naive method employing ýmulticastý techniques only to look up a target agent.

A Predictive Model to Evaluate Student Performance

In this paper we propose a new approach based on text mining techniques for predicting student performance using LSA (latent semantic analysis) and K-means clustering methods. The present study uses free-style comments written by students after each lesson. Since the potentials of these comments can reflect student learning attitudes, understanding of subjects and difficulties of the lessons, they enable teachers to grasp the tendencies of student learning activities. To improve our basic approach using LSA and k-means, overlap and similarity measuring methods are proposed. We conducted experiments to validate our proposed methods. The experimental results reported a model of student academic performance predictors by analyzing their comments data as variables of predictors. Our proposed methods achieved an average 66.4% prediction accuracy after applying the k-means clustering method and those were 73.6% and 78.5% by adding the overlap method and the similarity measuring method, respectively.

Adaptive exploiting user profile and interpretation policy for searching and browsing the Web on KODAMA system

The main thrust of the KODAMA research project is an investigation into novel ways of agentifying the Web based on the pre-existing hyper-link structure, and how this community of agents can automatically achieve and update its interpretation policies and cooperate with other agents to retrieve online distributed relevant information on the Web. The paper focuses on the use of the user interface agents in the KODAMA system for personalized information filtering and adapting, and discusses the method to update a user profile and interpretation policies adaptively for the user. This is an ideal and challenging environment for interface agents. The proposed idea is to employ an adaptive autonomous user interface agent that works for satisfying a users information needs cooperatively with other agents in the KODAMA system, Web page agents and server agents.

An architecture for personal semantic web information retrieval system

The semantic Web and Web service technologies have provided both new possibilities and challenges to automatic information processing. There are a lot of researches on applying these new technologies into current personal Web information retrieval systems, but no research addresses the semantic issues from the whole life cycle and architecture point of view. Web services provide a new way for accessing Web resources, but until now, they have been managed separately from traditional Web contents resources. In this poster, we propose a conceptual architecture for a personal semantic Web information retrieval system. It incorporates semantic Web, Web services and multi-agent technologies to enable not only precise location of Web resources but also the automatic or semi-automatic integration of hybrid Web contents and Web services.

Open distributed autonomous multi-agent coordination on the Web

Agent technology is becoming more prevalent as the availability of network access, and the demand for the end uses of agents becomes greater. Intelligent agents for information filtering and retrieval applications and tools are being employed in a variety of ways on the Web. A centralized agent for information discovery has usually limited capabilities for finding diverse and distributed information online. The main thrust of the paper is to present a framework that allows distributed adaptive information KODAMA agents to work together to browse and retrieve distributed information based on the preexisting hyperlink structure on the Web and how this community of agents can automatically extract meta-information and cooperate to retrieve online distributed relevant information. We have developed the software architecture, and a working prototype showing the benefits to the Web of interactive architectures based on the coordination of the hyperlink structure on the network. The authors summarize the current results of the project, and discuss some ideas on future work.

Evaluation of effectiveness of time-series comments by using machine learning techniques

Understanding individual students more deeply in the class is the most vital role in educational situations. Using comment data written by students after each lesson helps in the understanding of their learning attitudes and situations. They can be a powerful source of data for all forms of assessment. The PCN method categorizes the comments into three items: P (Previous learning activity), C (Current learning activity), and N (Next learning activity plan). The objective of this paper is to investigate how the three time-series items: P, C, and N, and the difficulty of a subject affect the prediction results of final student grades using two types of machine learning techniques: Support Vector Machine (SVM) and Artificial Neural Network (ANN). The experiment results indicate that the students described their current activities (C-comment) in more detail than previous and next activities (Pand N-comments); this tendency is reflected in prediction accuracy and F-measure of their grades.

Adaptive user interface for personalized transportation guidance system

Public transportation guidance services, such as Yahoo, Jorudan and NAVITIME, are widely used nowadays and support our daily lives. Although they provide useful services, they have not fully been personalized yet. This paper presents a personalized transportation system called PATRASH: Personalized Autonomous TRAnsportation recommendation System considering user context and History. In particular, we discuss an Adaptive User Interface (AUI) of PATRASH. Before designing a personalized route recommendation function for PATRASH’s AUI, we investigated possibilities and effectiveness of the function. First, we collected and analyzed 10 subjects’ usage histories of public transportation. Through this investigation, we confirmed the possibilities and effectiveness of the personalized route recommendation function. Second, we investigated the effectiveness of the basic functions of PATRASH’s AUI by comparing with two major transportation guidance systems in Japan. We evaluated those systems from the point of view of usabilities: click costs and time costs. The experimental results illustrate the effectiveness of AUI of PATRASH.

Estimation of Student Performance by Considering Consecutive Lessons

Examining student learning behavior is one of the crucial educational issues. In this paper, we propose a new method to predict student performance by using comment data mining. A teacher just asks students after every lesson to freely describe and write about their learning situations, attitudes, tendencies, and behaviors. The method employs Latent Dirichlet Allocation (LDA) and Support Vector Machine (SVM) to predict student grades in each lesson. In order to obtain further improvement of prediction results, we apply a majority vote method to the predicted results obtained in consecutive lessons to keep track of each students learning situation. Also, we evaluate the reliability of the predicted student grades to know when we can rely prediction results of student grade during the period of the semester. The experiment results show that our proposed method continuously tracked student learning situation and improved prediction performance of final student grades compared to Probabilistic Latent Semantic Analysis (PLSA) and Latent Semantic Analysis (LSA) models. Also, considering the differences of prediction results in the two consecutive lessons helps to evaluate the reliability of the predicted results.

Design and Implementation of Security Mechanisms for a Hierarchical Community-Based Multi-Agent System

Recently, several community-based systems have been developed; however, almost all such systems have been developed as Web-server-based systems. Thus, server administrator can easily eavesdrop on user communications, since they have to send/receive information through the server. Therefore, we propose multi-agent-based peer-to-peer (P2P) system wherein each peer manages his/her information and exchanges it with other peers directly. This, thus, resolves the problems posed by Web-server-based systems; however, we have to consider attacks from malicious third parties. This study designs and implements security protocols/mechanisms for a hierarchical community-based multi-agent system. Furthermore, if we consider a practical use case, we should be able to demonstrate that the proposed system can be implemented by combining it with existing security techniques for more reliable and rapid deployment. Finally, we evaluate the performance of the proposed security system and present an example application.

Personalized Search Using ODP-based User Profiles Created from User Bookmark

When searching for intended pages on the Internet, users often have a hard time to find the pages because the pages do not always come at the higher rank of searched results. The Personalized Search is a promising approach to solve this problem. In the Personalized Search, User Profiles (UPs in short) that represent interests of the users, are well used and often created from personal documents of the users. This paper proposes (1) a method for making UPs based on Open Directory Project (ODP) and shows (2) a Personalized Search system using the UPs made from Book Marks. Some of experimental results illustrate the validity of our method for making the UPs, and show the precision enhancement of this system.