Dissertations / Theses on the topic 'Web-Intelligent-System'

COORDENAÇÃO DE APERFEIÇOAMENTO DO PESSOAL DE ENSINO SUPERIOR
Esta dissertação investigou a aplicação dos processos de KDD (Knowledge Discovery in Databases) e técnicas de inteligência artificial para a criação de uma ferramenta de avaliação de textos da WEB de acordo com um determinado perfil. O trabalho, na área de sistemas de computação, teve como objetivo o desenvolvimento de técnicas que em conjunto com técnicas de inteligência computacional podem automatizar a avaliação de textos através de uma ferramenta, bem como a construção de um protótipo desta ferramenta. As técnicas inéditas desenvolvidas nesta dissertação tiveram como objetivo avaliar automaticamente textos independente da língua utilizada nestes e sem o uso de técnicas de PLN (Processador de Linguagem Natural). Outro objetivo foi desenvolver este trabalho baseado em alguns conceitos, ferramentas, formas de documentação considerados em trabalhos anteriores como forma de dra continuidade ao desenvolvimento científico. O protótipo, SITEX - Sistema Inteligente para Textos WEB - foi desenvolvido e módulos que permitem utilizar a ferramenta que melhor se enquadre na solução de um problema. Um outro objetivo no desenvolvimento do protótipo foi a utilização da linguagem C++, a qual é largamente utilizada e conhecida entre os desenvolvedores de técnicas de inteligência artificial, permitindo com isso a integração e o desenvolvimento de outros módulos. As técnicas foram desenvolvidas tendo também como objetivo o tratamento de padrões da WEB, como o Protocolo TCP/IP, as linguagens HTML, DHTML, Javascript, VBscript, entre outros, o que permite a utilização destas na Internet, Extranet ou localmente. Os estudos de casos foram realizados com textos fornecidos pela WEB através de inscrições em jornais on-line e avaliados de acordo com três tipos de perfis. Os perfis utilizados nos estudos de casos foram: economia, esportes e informática. Os resultados dos estudos de casos comprovam a validade das técnicas descobertas e implementadas neste trabalho. A comparação dos resultados do SITEX com os resultados do TextAnalyst, produto de mercado para análise de texto da Web baseado em inteligência computacional, comprovam a qualidade das técnicas apresentadas nesta dissertação.
This dissertation investigated the application of KDD´s process and artificial intelligence techniques for the development of a WEB text evaluation tool according to a specific interest. The work, in computing systems area, had as objective the development of techniques together with computing intelligence techniques to automate the texts evaluation by a tool, as well the development of a prototype of this tool. The techniques developed in this dissertation had as objective evaluate taext automatically with independence of the language used and without using NLP (natural Language Processing) techniques. Another onjective was develop this work based on others works as a way to continue the scientific development. The prototype, SITEX - Intelligent System for WEB Texts - was developed by modules which provides the condition to choose the best tool to solve a problem. Another objectiv on the development of the prototype was to use the C++ language, which is largely used and well known by artificial intelligence techniques developers, providing in this way facilities for development and integration of others modules. The techniques was also developed with the objective for WWB standards treatment, as the TCP/IP protocol, lamguages as HTML, DHTML, javascript, Vbscript, and others, which provides the usage of theses techniques in the Internet, intranets, Extranets and locally. The case studies werw based on WEB texts provided by on- line newsletters subscriptions and evaluated according to three types of interests. The interests used in these case studies were: ecoonomy, sports and computing. The results found in this case studies shows the validity of the techniques developed in this work. The results os SITEX compared to the result of TextAnalyst, a well known product in the market for Web text analysis based on artificial intelligence, shows the quality of the techniques discovered in this dissertation.

Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Civil and Environmental Engineering, 2001.
Includes bibliographical references (p. [63]-64).
With the globalization of world economics, more and more globally located teams are involved in the procedure of engineering design. The teams have members working on the same project but living around the world in different time zones and thus having different working hours. The collaborations among the team members are intensive and important to the success of the project. Traditional collaboration methods, such as mail, telephone and so on, cannot fulfill the requirements of fast and efficient collaborations among the team. Virtual Engineering Initiative is an intelligent web collaboration system, which is designed to meet the collaboration needs of such teams. This thesis discusses the design and implementation of Virtual Engineering Initiative. Virtual Engineering Initiative has ten main components, which can be further classified into four functional groups: video conferencing, information publishing, instant messaging, and meeting scheduling. Video conferencing enable users to collaborate in a virtual conference room. Database backed web publishing enables users to publish information published before, in and after. Web Based Discussion Boards, Email, News Group, BBS and Public Folder enable users share their information when offline. Instant Messaging allows users to send messages to others in real time. By integrating commercialized systems from different vendors, Virtual Engineering Initiative achieves high efficiency and stability. Virtual Engineering Initiative provides Meeting Scheduler to save team members from the burden of time-consuming meeting scheduling. Virtual Engineering Initiative chooses the distributed system as its meeting scheduling system structure and implements it as a software agent system. Meeting Scheduler adds an intelligent feature into the system by automating the procedure of meeting scheduling. Virtual Engineering Initiative has been successfully used by the 42V Consortium as their collaboration platform in the design procedure of a new electronic architecture.
by Fuxin Sun.
S.M.

Considering the redundancy and the irrelevancy of current search engines in the World Wide Web (WWW), this thesis explores an alternative web-based method of Internet search and retrieval of information via an Intelligent Agent. The Intelligent Agent retrieves the information back to users and it inserts this information automatically into the users' database. There are three components in this system: (1) Multiple User Dungeon (MUD) as a front end, (2) dynamic database management system, and (3) Intelligent Agent as a back end. The front end is a web site open to all the users of this system. It allows different users to access the system simultaneously from different PCs inside the same Intranet. The DBMS database system is designed using Microsoft Access. It is the reservoir of all the data. It provides information to the front end when the users query the database. Intelligent agent (back-end) is implemented using Visual C++ 6.0. It takes advantage of the technique of Open Database Connectivity (ODBC) to connect to the DBMS. The Intelligent Agent searches the Internet through the search engine of Google and then inserts the records into the database based on the user preference. The Intelligent Agent can also update the database by deleting the obsolete records automatically. In order to test and implement this application system, it is applied two business cases: (1) Fisheries Resource Conservation Council (FRCC) and (2) Sport Utility Vehicle (SUV) database system. DBMS and back-end are transparent to users. Users simply need to manipulate the front end interface that links the user to all database review and modification functions, as well as to the search and automatic retrieval options. Results of the implementation of the applications are presented and future research applications for Internet information search and retrieval processes are discussed.

Collaboration among teachers in some shape or form is becoming increasing popular among the educational system. The goal of this thesis is to determine whether teachers find value in collaboratively working in a Web environment and if we can use collaboration to improve educational content. We took a Web-based intelligent tutoring system, called ASSISTments, and incorporated a collaboration feature allowing teachers from around the Web to work together to create content for their students. The previous ASSISTments model did not allow for any form of collaboration; teachers using ASSISTments were not able to modify each other's content. By creating the opportunity for teachers to work together, we hypothesized that the educational content within ASSISTments would improve. To help improve education content among ASSISTments, we also deemed it necessary to improve the tool that teachers used to create problems for their students. Using surveys and interviews, we obtained feedback from teachers supporting our changes of the ASSISTments system and validating our claims that they found value in collaboratively working in a Web-based environment.

ASSISTments is a web-based intelligent tutoring system that can provide students with immediate feedback when they are doing math homework. Until now, ASSISTments required internet access in order to do nightly homework. Without ASSISTments, students do their work on paper and are not told if they are correct or given help for wrong answers until the next morning at best. We've developed a component that supports 'offline-mode', enabling students without internet access at home to still receive immediate feedback on their responses. Students with laptops download their assignments at school, and then run ASSISTments at home in offline mode, utilizing the browser's application cache and Web Storage API. To evaluate the benefit of having the offline feature, we ran a randomized controlled study that tests the effect of immediate feedback on student learning. Intuition would suggest that providing a student with tutoring and feedback immediately after they submit an answer would lead to better understanding of the material than having them wait until the next day. The results of the study confirmed our hypothesis, and validated the need for 'offline mode.'

Abstract The use of agent systems has increased enormously, especially in the field of mobile services. Intelligent services have also increased rapidly in the web. In this thesis, the utilization of software agent technology in mobile services and decentralized intelligent services in the multimedia business is introduced and described. Both Genie Agent Architecture (GAA) and Decentralized International and Intelligent Software Architecture (DIISA) are described. The common problems in decentralized software systems are lack of intelligence, communication of software modules and system learning. Another problem is the personalization of users and services. A third problem is the matching of users and service characteristics in web application level in a non-linear way. In this case it means that web services follow human steps and are capable of learning from human inputs and their characteristics in an intelligent way. This third problem is addressed in this thesis and solutions are presented with two intelligent software architectures and services. The solutions of the thesis are based on a combination of neural network and agent technology. To be more specific, solutions are based on an intelligent agent which uses certain black box information like Self-Organized Map (SOM). This process is as follows; information agents collect information from different sources like the web, databases, users, other software agents and the environment. Information is filtered and adapted for input vectors. Maps are created from a data entry of an SOM. Using maps is very simple, input forms are completed by users (automatically or manually) or user agents. Input vectors are formed again and sent to a certain map. The map gives several outputs which are passed through specific algorithms. This information is passed to an intelligent agent. The needs for web intelligence and knowledge representation serving users is a current issue in many business solutions. The main goal is to enable this by means of autonomous agents which communicate with each other using an agent communication language and with users using their native languages via several communication channels.

The Semantic Web is the vision of the future Web. Its aim is to enable machines to process Web documents in a way that makes it possible for the computer software to "understand" the meaning of the document contents. Each document on the Semantic Web is to be enriched with meta-data that express the semantics of its contents. Many infrastructures, technologies and standards have been developed and have proven their theoretical use for the Semantic Web, yet very few applications have been created. Most of the current Semantic Web applications were developed for research purposes. This project investigates the major factors restricting the wide spread of Semantic Web applications. We identify the two most important requirements for a successful implementation as the automatic production of the semantically annotated document, and the creation and maintenance of semantic based knowledge base. This research proposes a framework for Semantic Web implementation based on context-oriented controlled automatic Annotation; for short, we called the framework the Semantic Web Implementation Framework (SWIF) and the system that implements this framework the Semantic Web Implementation System (SWIS). The proposed architecture provides for a Semantic Web implementation of stand-alone websites that automatically annotates Web pages before being uploaded to the Intranet or Internet, and maintains persistent storage of Resource Description Framework (RDF) data for both the domain memory, denoted by Control Knowledge, and the meta-data of the Web site's pages. We believe that the presented implementation of the major parts of SWIS introduce a competitive system with current state of art Annotation tools and knowledge management systems; this is because it handles input documents in the ii context in which they are created in addition to the automatic learning and verification of knowledge using only the available computerized corporate databases. In this work, we introduce the concept of Control Knowledge (CK) that represents the application's domain memory and use it to verify the extracted knowledge. Learning is based on the number of occurrences of the same piece of information in different documents. We introduce the concept of Verifiability in the context of Annotation by comparing the extracted text's meaning with the information in the CK and the use of the proposed database table Verifiability_Tab. We use the linguistic concept Thematic Role in investigating and identifying the correct meaning of words in text documents, this helps correct relation extraction. The verb lexicon used contains the argument structure of each verb together with the thematic structure of the arguments. We also introduce a new method to chunk conjoined statements and identify the missing subject of the produced clauses. We use the semantic class of verbs that relates a list of verbs to a single property in the ontology, which helps in disambiguating the verb in the input text to enable better information extraction and Annotation. Consequently we propose the following definition for the annotated document or what is sometimes called the 'Intelligent Document' 'The Intelligent Document is the document that clearly expresses its syntax and semantics for human use and software automation'. This work introduces a promising improvement to the quality of the automatically generated annotated document and the quality of the automatically extracted information in the knowledge base. Our approach in the area of using Semantic Web iii technology opens new opportunities for diverse areas of applications. E-Learning applications can be greatly improved and become more effective.

This thesis focuses on analysis, definition and description of mobile personal assistants as a phenomenon emerging in past few years. Mobile personal assistants are first mentioned in the context of computational linguistics and information needs, which is one of the motivations to use them. Main interest of this thesis is an introduction of the core technologies for the natural language communication between the assistant and its user, followed by an introduction of host environments and possible usage. The thesis also presents the limitations and risks resulting from using them, which are in some ways affecting their usability. Beside the analysis the main focus is on the design and implementation of the natural language understanding (NLU) system, which can be used in particular personal assistant application. This system is implemented as a web service and consists of an annotation scheme with a set of components. The results show that the system architecture and tools used are suitable solution for the construction of a basic NLU system, which has been created and which is in the compliance with the requested parameters. It is still difficult task to achieve high precision, which depends on many factors including the amount of training data, which was very small in this case. However, the resulting application is a solid starting point for its further development and extensions.

For researches in the field of the data mining and machine learning the necessary condition is an availability of various input data set. Now researchers create the databases of such sets. Examples of the following systems are: The UCI Machine Learning Repository, Data Envelopment Analysis Dataset Repository, XMLData Repository, Frequent Itemset Mining Dataset Repository. Along with above specified statistical repositories, the whole pleiad from simple filestores to specialized repositories can be used by researchers during solution of applied tasks, researches of own algorithms and scientific problems. It would seem, a single complexity for the user will be search and direct understanding of structure of so separated storages of the information. However detailed research of such repositories leads us to comprehension of deeper problems existing in usage of data. In particular a complete mismatch and rigidity of data files structure with SDMX - Statistical Data and Metadata Exchange - standard and structure used by many European organizations, impossibility of preliminary data origination to the concrete applied task, lack of data usage history for those or other scientific and applied tasks.

Now there are lots of methods of data miming, as well as quantities of data stored in various repositories. In repositories there are no methods of DM (data miming) and moreover, methods are not linked to application areas. An essential problem is subject domain link (problem domain), methods of DM and datasets for an appropriate method. Therefore in this work we consider the building problem of ontological models of DM methods, interaction description of methods of data corresponding to them from repositories and intelligent agents allowing the statistical repository user to choose the appropriate method and data corresponding to the solved task. In this work the system structure is offered, the intelligent search agent on ontological model of DM methods considering the personal inquiries of the user is realized.

For implementation of an intelligent data and metadata exchange repository the agent oriented approach has been selected. The model uses the service oriented architecture. Here is used the cross platform programming language Java, multi-agent platform Jadex, database server Oracle Spatial 10g, and also the development environment for ontological models - Protégé Version 3.4.

The ASSISTment system is a web-based tutor that is currently being used as an eighth and tenth-grade mathematics in both Massachusetts and Pennsylvania. This system represents its tutors as state-based "pseudo-tutors" which mimic a more complex cognitive tutor based on a set of production rules. It has been shown that building pseudo-tutors significantly decreases the time spent authoring content. This is an advantage for authoring systems such as the ASSITment builder, though it sacrifices greater expressive power and flexibility. A cognitive tutor models a student's behavior with general logical rules. Through model-tracing of a cognitive tutor's rule space, a system can find the reasons behind a student action and give better tutoring. In addition, these cognitive rules are general and can be used for many different tutors. It is the goal of this thesis to provide the architecture for using cognitive rule-based tutors in the ASSITment system. A final requirement is that running these computationally intensive model-tracing tutors do not slow down students using the pseudo-tutors, which represents the majority of ASSISTment usage. This can be achieved with remote computation, realized with SOAP web services. The system was further extended to allow the creation and implementation of user-level experiments within the system. These experiments allow the testing of pedagogical choices. We implemented a hint dissuasion experiment to test this experimental framework and provide those results.

En esta tesis se propone el uso de agentes inteligentes en entornos de aprendizaje en línea con el fin de mejorar la asistencia y motivación del estudiante a través de contenidos personalizados que tienen en cuenta el estilo de aprendizaje del estudiante y su nivel de conocimiento. Los agentes propuestos se desempeñan como asistentes personales que ayudan al estudiante a llevar a cabo las actividades de aprendizaje midiendo su progreso y motivación.
El entorno de agentes se construye a través de una arquitectura multiagente llamada MASPLANG diseñada para dar soporte adaptativo (presentación y navegación adaptativa) a un sistema hipermedia educativo desarrollado en la Universitat de Girona para impartir educación virtual a través del web.
Un aspecto importante de esta propuesta es la habilidad de construir un modelo de estudiante híbrido que comienza con un modelo estereotípico del estudiante basado en estilos de aprendizaje y se modifica gradualmente a medida que el estudiante interactúa con el sistema (gustos subjetivos).
Dentro del contexto de esta tesis, el aprendizaje se define como el proceso interno que, bajo factores de cambio resulta en la adquisición de la representación interna de un conocimiento o de una actitud. Este proceso interno no se puede medir directamente sino a través de demostraciones observables externas que constituyen el comportamiento relacionado con el objeto de conocimiento. Finalmente, este cambio es el resultado de la experiencia o entrenamiento y tiene una durabilidad que depende de factores como la motivación y el compromiso.
El MASPLANG está compuesto por dos niveles de agentes: los intermediarios llamados IA (agentes de información) que están en el nivel inferior y los de Interfaz llamados PDA (agentes asistentes) que están en el nivel superior. Los agentes asistentes atienden a los estudiantes cuando trabajan con el material didáctico de un curso o una lección de aprendizaje. Esta asistencia consiste en la recolección y análisis de las acciones de los estudiantes para ofrecer contenidos personalizados y en la motivación del estudiante durante el aprendizaje mediante el ofrecimiento de contenidos de retroalimentación, ejercicios adaptados al nivel de conocimiento y mensajes, a través de interfaces de usuario animadas y atractivas. Los agentes de información se encargan del mantenimiento de los modelos pedagógico y del dominio y son los que están en completa interacción con las bases de datos del sistema (compendio de actividades del estudiante y modelo del dominio).
El escenario de funcionamiento del MASPLANG está definido por el tipo de usuarios y el tipo de contenidos que ofrece. Como su entorno es un sistema hipermedia educativo, los usuarios se clasifican en profesores quienes definen y preparan los contenidos para el aprendizaje adaptativo, y los estudiantes quienes llevan a cabo las actividades de aprendizaje de forma personalizada. El perfil de aprendizaje inicial del estudiante se captura a través de la evaluación del cuestionario ILS (herramienta de diagnóstico del modelo FSLSM de estilos de aprendizaje adoptado para este estudio) que se asigna al estudiante en su primera interacción con el sistema. Este cuestionario consiste en un conjunto de preguntas de naturaleza sicológica cuyo objetivo es determinar los deseos, hábitos y reacciones del estudiante que orientarán la personalización de los contenidos y del entorno de aprendizaje. El modelo del estudiante se construye entonces teniendo en cuenta este perfil de aprendizaje y el nivel de conocimiento obtenido mediante el análisis de las acciones del estudiante en el entorno.

My doctoral thesis deals with use of the sophisticated methods for the selection of technical and economic solution of electrical wiring. This solution is based not only on a price but also on many other criteria such as a comfort, service, durability etc. The focus of the work is a treatise on wiring systems from a global perspective, where it is impossible to use a conventional approach for objective evaluation and selection of the appropriate electrical wiring system (because of the complexity of such systems and their interdependencies). In the four chapter are given information of an energy consumption (the total consumption and household consumption). In this chapter is given also a consumption prediction – especially for households. Following is an overview of possible measures for reducing electricity consumption in households. In the next part of this thesis are solved the knowledge, respectively expert systems for use in an electrical engineering – especially for a suitable tool for the selection and evaluation of households wiring electrical system. The result of this work provides a possible solution for a selection of wiring electrical system for households (focusing on the intelligent wiring) – from a technical and economic point of view and with using an innovative approach. The main contribution of this work is a proposal of the main part of the knowledge base. This base could be as a basis for knowledge, respectively for an evaluating technical and economical solution of an electrical wiring system – the expert system includes also a feedback function of an effectiveness solution, use value, price etc., which would also serve as a knowledge base.

La présente thèse de doctorat en informatique propose un modèle pour une recherche d'information intelligente possibiliste des documents Web et son implémentation. Ce modèle est à base de deux Réseaux Petits Mondes Hiérarchiques (RPMH) et d'un Réseau Possibiliste (RP) : Le premier RPMH consiste à structurer les documents retrouvés en zones denses de pages Web thématiquement liées les unes aux autres. Nous faisons ainsi apparaître des nuages denses de pages qui traitent d'un sujet et des sujets connexes (assez similaires sémantiquement) et qui répondent toutes fortement à une requête. Le second RPMH est celui qui consiste à ne pas prendre les mots-clés tels quels mais à considérer une requête comme multiple en ce sens qu'on ne cherche pas seulement le mot-clé dans les pages Web mais aussi les substantifs qui lui sont sémantiquement proches. Les Réseaux Possibilistes combinent les deux RPMH afin d'organiser les documents recherchés selon les préférences de l'utilisateur. En effet, l'originalité du modèle proposé se décline selon les trois volets suivants qui synthétisent nos contributions. Le premier volet s'intéresse au processus itératif de la reformulation sémantique de requêtes. Cette technique est à base de relations de dépendance entre les termes de la requête. Nous évaluons notamment les proximités des mots du dictionnaire français « Le Grand Robert » par rapport aux termes de la requête. Ces proximités sont calculées par le biais de notre approche de recherche des composantes de sens dans un RPMH de dictionnaire de mots par application d'une méthode basée sur le dénombrement des circuits dans le réseau. En fait, l'utilisateur du système proposé choisit le nombre de mots sémantiquement proches qu'il désire ajouter à chaque terme de sa requête originelle pour construire sa requête reformulée sémantiquement. Cette dernière représente la première partie de son profil qu'il propose au système. La seconde partie de son profil est constituée des choix des coefficients de pertinence possibilistes affectés aux entités logiques des documents de la collection. Ainsi, notre système tient compte des profils dynamiques des utilisateurs au fur et à mesure que ces derniers utilisent le système. Ce dernier est caractérisé par son intelligence, son adaptativité, sa flexibilité et sa dynamicité. Le second volet consiste à proposer des relations de dépendance entre les documents recherchés dans un cadre ordinal. Ces relations de dépendance entre ces documents traduisent les liens sémantiques ou statistiques évaluant les distributions des termes communs à des paires ou ensembles de documents. Afin de quantifier ces relations, nous nous sommes basés sur les calculs des proximités entres ces documents par application d'une méthode de dénombrement de circuits dans le RPMH de pages Web. En effet, les documents peuvent ainsi être regroupés dans des classes communes (groupes de documents thématiquement proches). Le troisième volet concerne la définition des relations de dépendance, entre les termes de la requête et les documents recherchés, dans un cadre qualitatif. Les valeurs affectées à ces relations traduisent des ordres partiels de préférence. En fait, la théorie des possibilités offre deux cadres de travail : le cadre qualitatif ou ordinal et le cadre quantitatif. Nous avons proposé notre modèle dans un cadre ordinal. Ainsi, des préférences entre les termes de la requête se sont ajoutées à notre modèle de base. Ces préférences permettent de restituer des documents classés par préférence de pertinence. Nous avons mesuré aussi l'apport de ces facteurs de préférence dans l'augmentation des scores de pertinence des documents contenant ces termes dans le but de pénaliser les scores de pertinence des documents ne les contenant pas. Pour la mise en place de ce modèle nous avons choisi les systèmes multi-agents. L'avantage de l'architecture que nous proposons est qu'elle offre un cadre pour une collaboration entre les différents acteurs et la mise en œuvre de toutes les fonctionnalités du système de recherche d'information (SRI). L'architecture s'accorde parfaitement avec le caractère intelligent possibiliste et permet de bénéficier des capacités de synergie inhérente entre les différentes composantes du modèle proposé. Dans le présent travail, nous avons donc pu mettre en exergue à travers les expérimentations effectuées l'intérêt de faire combiner les deux RPMH via un réseau possibiliste dans un SRI, ce qui permet d'enrichir le niveau d'exploration d'une collection. Ce dernier n'est pas limité aux documents mais l'étend en considérant les requêtes. En effet, la phase de reformulation sémantique de requête permet à l'utilisateur de profiter des autres documents correspondants aux termes sémantiquement proches des termes de la requête originelle. Ces documents peuvent exister dans d'autres classes des thèmes. En conséquence, une reclassification proposée par le système s'avère pertinente afin d'adapter les résultats d'une requête aux nouveaux besoins des utilisateurs.

This study is a qualitative research project classified as practical and participatory action research designs, which has as its aim the creation of an instructional design, used as a learning metric for Domus Software - Procel Edification, which integrates concept maps and the revised Bloom taxonomy into an intelligent web assessment system. This metric aligns curriculum concept maps along with conceptual and procedural knowledge of the Domus software - Procel edifies the retaining cognitive processes, provides understanding and application, through offering a model of instructional design, which assigns weights to those cognitive processes attained by students and identifies principles to be used in its applicability for the evaluation of distance learning. The authors also present the results for alignment, inferring weights as well as an outline of the logical sequence along with steps for the implementation of the intelligent system through the association of some exemplification slides.
O presente trabalho é uma pesquisa qualitativa e classificada como practical and participatory action research designs (desenho de pesquisa de prática e ação participativa), que tem como intuito criar um desenho instrucional para uma métrica da aprendizagem do Software Domus Procel Edifica, integrando mapas conceituais à taxonomia revisada de Bloom em um sistema inteligente de avaliação na Web. Essa métrica alinha mapas conceituais curriculares, conhecimentos procedimentais e conceituais do software Domus − Procel Edifica aos processos cognitivos de retenção, entendimento e aplicação, oferecendo um modelo de desenho instrucional, que atribui pesos aos processos cognitivos alcançados pelos estudantes e identifica alguns princípios para sua aplicabilidade na avaliação da aprendizagem a distância. Apresenta-se ainda, resultados de alinhamento, inferência de pesos e um esboço da sequência lógica e etapas de execução do sistema inteligente, associando-se algumas telas de exemplificação.
Mestre em Educação

碩士
東海大學
資訊工程與科學系
90
This thesis introduces a human-friendly Internet naming service called Intelligent Naming System (INS). It provides a mechanism to map a name to its corresponding Internet address or a web URL. The name used in INS can be any human understandable string in natural language. It is not for computers or networks to understand, and therefore it is not necessary to follow the same syntax similar to Internet address, domain name or URL. The goal of this thesis is to improve the usage of Internet naming, or web browsing, as easy as possible by automatically binding conceptually equivalent names to the target address or URL. This solution is especially useful for non-English language users since the names can be in any natural language. The architecture of INS is a directory-enable solution. There are three major components in INS. The first component is the directory that is used to store dictionary and the metadata of the naming knowledge. The second component is a quick matching service which is responsible for resolving the mapping between names and their addresses managed in the cache. The third component is called intelligent matching service which is used to resolve the mapping required the support of additional knowledge. After the mapping result set is obtained, a rule-based filter is applied to generate the final mapping. The Intelligent Naming System has been implemented and freely accessed on Internet for about eight months. After analyzing the logged information collected in this period, it shows that the mapping resolved by INS is over 80% correct. Also, from this study, we can identify some valuable user behaviors when using human-friendly naming service instead of using traditional Internet addressing or a web URL. INS is totally developed in Java and its performance is quite good especially when using in the Internet world.

碩士
中原大學
資訊工程研究所
90
UDDI（Universal Description, Discovery and Integration) is one of the key technologies of web services. UDDI is used to recognize web services and build web service catalogs, so that a user can search related information on line. But it is not easy to search the desired web services on Internet. It is also inconvenient to build the client-side applications for a web service after receiving the service specification. In this thesis, we designed and implemented a system for web services classification and search. A graphic user interface is also provided. Since, WSDL（Web Service Description Language）is described in XML and thus inherits the characteristics of XML, which is in structural form and can be used to define new tags. We build the classification tree according to the properties of web services, and then extend WSDL tags in terms of the classification tree. To search a service, the WSDL document was parsed by an XML DOM（Document Object Model）parser, to find the web services specified. Breadth-first search is used to look for answers which are compared with the query using string comparison. A user-friendly GUI is provided for client-side applications, which are packed as listeners. These listeners will invoke web services after receiving client requests. One advantage of using listener is the separation of graphic user interface from client-side applications. This will result in more extensible and more reusable code. Finally, we use a travel agent as an example to implement a sample web service search system. By using a simple and explicit classification, the system is able to retrieve the correct web services. And the graphical interface can help a user to invoke a web service more directly and conveniently.

博士
國立成功大學
工程科學系碩博士班
95
The purpose of this dissertation is concerning the applications of artificial intelligence in e-Learning domain. The majority of e-Learning research is putting such web learning system into practice, or standardizing a SCORM conformable learning system environment. However, different from those researches, this study focuses attention on applying artificial intelligence technique to facilitate learners and lecturers simplifying their works and enhancing learning effects. This dissertation may consider the subject under the following heads: (1) applying Dynamic Fuzzy Petri Net to an e-learning system; (2) Standardized Course Generation Process using Dynamic Fuzzy Petri Nets; (3) an intelligent human-expert forum system based on fuzzy information retrieval technique; (4) a method of cross-level frequent pattern mining for web-based instruction. This research in Chapter 3 provides an authoring tool, which is model by DFPN (Dynamic Fuzzy Petri Net), and LMS (Learning Management System) to provide lecturers mapping out their course learning map. Therefore, the learners can study the whole concept of a certain course based on the course learning map and their learning result. The lecturer needs to arrange some auxiliary learning materials to assist learners when they get into trouble. However, there are too many SCOs (Sharable Content Objects) in the system, and the lecturer cannot easily find out the interrelations between each learning material. Therefore, the research in Chapter 4 extends the above research and provides lecturer finding out the relevant auxiliary learning materials automatically. Furthermore, a SCGP (Standardized Course Generation Process) is also introduced in Chapter 4. By means of this automatic process, standardized courses not only correspond to the SCORM standard but also arrange adaptive auxiliary materials dynamically. The generated multimedia course is interoperable, reusable, and standardized. Recently, there are more and more online forum systems for problem solving and discussion. The most important benefit of these forum systems is users can receive the tailored answers from peers by formulating the problem with natural language. Especially in e-Learning field, learners often announce their problems on the forum system and communicate their comments subjectively. Therefore, the research in Chapter 5 introduces a human-expert oriented forum system for collaborative learning. The system uses fuzzy information retrieval techniques to discover important discussion knowledge and actively invites human-experts who may answer the question to participate the discussion. Following that, learners can indicate the crux of the problem by the human-experts’ advisements. Hence, they can precisely search their needs in LMS (Learning Management System). The research in Chapter 6 introduces a cross-level frequent pattern mining methodology for further study. It collects all of users’ learning access data which connote a hierarchical scheme to provide cross-level learning suggestions for the next learning course. With this system, a learner can get multiple levels of abstract suggestions instead of merely single level frequent pattern mining results.

碩士
東海大學
工業工程學系
87
Abstract International competition has forced revolutionary changes in the marketing process to occur in the past decade. Traditional paradigms were changed and the supply chain concept has been developed. Marketing policies such as quick response and total customer satisfaction have become critical issues. In the meantime, the development of information technology (IT) such as Internet and client-server database design tools have made electronic commerce (EC) possible. But most of the EC applications available now can only provide the basic product information such as the specification and the price of the product for customers. Questions like what the best product combination is to order or what the reasonable price is and when customers should place their order could not be answered by the existing EC systems. Therefore the purpose of this research is to build an intelligent EC prototype system in which an expert system is embedded. A real time database will be designed to connect the fuzzy expert system and the price prediction model to the EC web site and help customers to optimize their purchase plan.

碩士
南台科技大學
資訊工程系
94
Recently, mobile devices become more and more popular and lots of functions are added into. Because the capability of internet access on mobile device is common today, the limit of internet coverage is unrestricted now. Through wireless mobile devices, users could get the information all they need. However, the screen of mobile devices are so small that it is difficult to browse the web pages; moreover, while users are accessing internet through wireless networks, file transmission is often unstable. In this paper, we propose a scheme to provide intelligent download suggestions for mobile learning contents using artificial intelligence. To deliver learning content via mobile devices, including PDA's, cell phones, pocket PCs, or other mobile devices, the file size must be considered. The success of downloading a large file depends on the Internet traffic at the moment. According to the induced decision tree, we can predict whether the downloading would be successful. If not, the server would suggest the user not to download the large file at the moment or to download an alternative file. There are a lot of resources on the web. Through this system, we can browse these materials on each mobile device normally. Cooperate with the download suggestions, users will observe the correct information on their mobile devices in a minute. In the future, the system will develop more corresponding functions. It not only makes the web pages simple and clear, but also let users browse any information on moblie device easily.

碩士
國防管理學院
國防資訊研究所
89
Since 1985, the operation of information system using Internet as core has become popular. How to use the Internet to promote entrepreneur’s advantages, to reduce cost, to increase customer’s satisfaction, and to create more profit is an important issue in nowadays business organization planning. As the Internet prevails, the way of people’s information conveyance and model of commercial trade changes. Traditional business trading behavior was replaced by electronic commerce. The improvement of information science and prosperity of cyber word makes life more vivacious, and source of information is getting more extensive for information searching. Today, collection of market information is not limited in newspaper and magazine for those who do market information work, and via the Internet and searching engine, people can get more abundant market information. However, the establishment of a complete market information database needs the collection of many-sided information and process of systematic analysis and classifying. Then the database can be gradually accumulated and formed during a long period. So that decision makers can get suitable reference anytime according to their demand. It has become future trend to implement inviting bidding of purchase through the Internet. This research provides the Internet based intelligence inviting-bidding decision support system to assist users doing purchase case in systematizing and unshading the examination of merchandises’ qualification. Via experts’ analysis and judgment method of AHP weighted value, this system can provide people doing inviting bidding work on the basis of qualification examination so as to expect that inviting-bidding process can reach the principles of fairness and justice.

碩士
聖約翰科技大學
資訊工程系碩士班
102
In this paper, in order to improve and enhance the service quality of the restaurant, we have designed an ordering system which used the Web Services technology. The proposed system can be divided into four man-machine interface: 1) Customer interface, 2) Waiter interface, 3) Kitchen interface, 4) Counter interface. The waiter interface allows a waiter to book, ordering, modify the number of customers, and check all of the meals service. The kitchen interface provides a cook to view meals case and to update the information of meals. On the other hand, the customer interface let users to replace table numbers, and to view the status of individual meals services. The counter interface provides us a set of checkout functions such as checkout for a single or checkout for a table number. In this paper, Microsoft SQL Server is used for our backend database. We wrote 42 Web Services API services to access the database. And these APIs is used to design the mentioned four operating interface. The waiter and the customer interface are android APP which designed using the Java and the proposed Web Services APIs. Meanwhile, the kitchen interface and checkout interface are desktop applications which are designed using the Visual Basic 2010 and the proposed Web Services APIs. Hence, in this paper, we have designed a system which has the code reuse and cross-platform merits. It can be developed and maintained easily. And it provides us a nice restaurant industry ordering systems.

碩士
國立雲林科技大學
資訊管理系碩士班
92
As the Internet is getting more popular, the enterprises have to face the challenge of building new business models and to promote their competition on the Internet. Many technologies for developing Internet application will be thought to provide services and transmit information on the Internet, but these technologies hardly communicate with each other and result in integration problems. Therefore, WS-I proposes Web Service to solve these problems. The needs for seeking appropriate web service become more and more necessary and interesting, and bring the enterprise the new business model of selling self-developed web services. As the consequence, how to find the proper web service you want is getting more attention. Our research intends to bring up an intelligent search mechanism for acquiring appropriate web services. This intelligent search mechanism uses ontology and information classification techniques to support fast and accurate search.

碩士
國立交通大學
資訊管理學程碩士班
91
Customer service is a very important aspect of Customer Relationship Management (CRM), and after-service constitutes a link in the customer service chain. RMA(Return Merchandise Authorization) is a kind of behavioral norm for the repair of international merchandise transaction; hence the ability to shorten merchandise repair time and increase customer satisfaction could become one’s competitive edge in business. The paper delves into the deficiencies of the traditional RMA service system of a notebook computer manufacturer and analyzes the customer service behavior of its customer relationship management. The paper uses a global web-based framework and Java for development tool for the establishment of this system. Data compilation procedure, with the help of the pro system case-based deduction technique, provided the system with an automatic analytical capacity, thereby further enhancing the capacity of this web-based intelligent RMA repair and maintenance system. The system allowed an interaction with the customers. The intelligent repair and maintenance system allowed us to improve repair and maintenance efficiency by 26%, strongly boosting degree of customer satisfaction. Moreover, in terms of global inventory management, it also enabled us to reduce global inventory by 12%; a boon that not only reduced the interest payments for inventory, but also eased up the company revolving fund cycle. The system allowed us to institute a more flexible part supply system, as well as enabled the Quality Assurance and R&D departments to understand the trouble-causing factors of the products that the company has sold. As a result, product AFR(Annual Failure Rate) dropped by around 85%. Finally, we also used the repair and maintenance information that the system has accumulated to train new repair and maintenance engineers. This saved us some training time. Hence, it may be said that this study has designed an innovative and practical IT (CRM) system.

碩士
輔仁大學
資訊工程學系
92
Web service is a term that covers a collection of operations that are network-accessible through standardized XML messaging. Many mobile commerce systems try to take the advantages of web services for providing ubiquitous services. However, the limited processing and displaying capability of the mobile devices limits the display of business information. The specifications of the mobile devices, platforms, different system interface of the operation environment, and different transmission protocol of the communication networks may also limit information usability for users. Furthermore, the geographical location, business behavior of users, and consumer interest may affect the successful of the mobile commerce drastically. This work proposes an intelligent mobile electronic commerce management system for doing the electronic commerce in the web services. The system contains four modules, namely, the information repository, interface manager, transaction manager and information analyzer. The information repository contains the mobile device model, m-commerce workflow model, web service model, and the user profiles. The mobile device model records the information of the different mobile devices and contains the device type, display capability, operation platform, and browsing specification. The m-commerce workflow model manages the business tasks of m-commerce. The web service model records web services information. Moreover, its user profile records the behavior, interest, and transaction history of users. The interface manager provides an interface generation for generating HTML or CHTML documents and collecting consumer business information. This manager provides the transaction assistant for the user during the business process. Moreover, it uses the mobile commerce markup language (MCML) for describing the business information. The transaction manager collects information regarding user operation behaviors from the transaction information and handles transaction processes according to the m-commerce workflow model and the user’s operation behaviors. This manager also assists the user in completing the incomplete business transaction. Finally, it translates transaction information into MCML for describing the consumer’s transaction information. The information analyzer dispatches different information agents to collect business information from the service provider. Moreover, it filters for personalized information according to user profiles.

博士
國立臺灣科技大學
電子工程系
94
This thesis describes the result of our research in developing FAQ-master as an intelligent Web information system. The system is developed to perform intelligent discovery, retrieval, filtering, proxy, ranking and presentation of Web information to provide high-quality FAQ solutions to meet user information request. By a high quality answer we mean an answer that is profound, up-to-date, and relevant to the user’s question. We summarized problems into: how to faithfully capture user intention, how to effectively discover and aggregate Web information, how to present the relevant result to the user, and how to provide efficient proxy mechanism to help speed up the turn around time. We propose the following techniques to tackle the above issues: ontology, user models, website models, and data aggregation and proxy mechanisms. Based upon the techniques, FAQ-master was developed to contain four agents, namely, Interface Agent, Proxy Agent, Answerer Agent, and Search Agent, which can effectively and efficiently improve the search result from the following three aspects of the Web search activity, namely, user intention, document processing, and website search. The Interface Agent was developed to work as an assistant between the user and FAQ system for capturing true user’s intention. Based on user modeling, template-based and ontology-supported techniques, the agent can support natural language query, enhanced by the pattern-match and template-based technique; assistance and guidance for human-machine interaction; and better personalized information services. It also handles user feedback on the suitability of the proposed responses. The Proxy Agent was developed to work as a two-tier mediator between the Interface Agent and backend Answerer Agent. It employs an ontology-enhanced intelligent proxy mechanism to effectively alleviate the overloading problem usually associated with a backend server. The Answerer Agent was developed to help clean, retrieve, and transform FAQ information collected from a heterogeneous environment, such as the Web, and stores it in an ontological database. It works as a back end process to perform ontology-directed information aggregation, supported by the wrapper technique, from the webpages collected by the Search Agent. Finally, the Search Agent was developed to work as an both user-oriented and domain-related Web information retrieval with the help of ontology-supported website models. This approach provides a semantic level solution for the Search Agent so that it can provide domain-specific, focused Web information discovery toward a high degree of user satisfaction. Our first contribution is on the techniques of user modeling and query processing involved in the development of Interface Agent, which features ontology-supported, template-based user modeling technique and query processing. Our preliminary experimentation demonstrates that user intention and focus of up to eighty percent of the user queries can be correctly understood by the system. In addition, from the experiments we verify the robustness of the linguistic pattern match technique by demonstrating its effectiveness in analyzing users’ query intention and focus. The second contribution is on the techniques of query prediction in Proxy Agent. The agent features following interesting points. First, it performs fast user-oriented mining and prediction by discovering frequent queries and predicted queries from user query history. The improved sequential pattern mining algorithm is made more efficient by the techniques of perfect hashing and database decomposition. Second, it performs ontology-directed case-based reasoning. The semantics of PC ontology, in particular the VRelationships, are used in determining similar cases, performing case adaptation, and case retaining. Our experiments show that the agent can share up to 70% of the query loading from the backend process, which helps a lot on the overall query performance. The third contribution is on the techniques of organizing and processing unstructured Web information in Answerer Agent. The agent employs ontology as the key technique, supported by the wrapper techniques to help clean, retrieve, and transform unstructured FAQ information collected from a heterogeneous environment, and stores it in an ontological database, which reflects the ontological structure. When it comes to the retrieval of FAQs, the agent trims irrelevant query keywords, employs either full keywords or partial keywords to retrieve FAQs, and removes conflicting FAQs before turning the final results to the user, all of which are supported by ontology. In addition, to producing a more effective presentation of the search results, the agent employs an enhanced ranking technique, which includes Appearance Probability, Satisfaction Value, Compatibility Value, and Statistic Similarity Value as four measures with proper weights to rank the FAQs. Our experiments show the Agent does improve the precision rate and produces better ranking results. The final contribution is on the techniques of reflecting both user-oriented and domain-focused aspects in web search in Search Agent. The agent features an ontology-supported website modeling technique to provide a semantic level solution for a search engine so that it can provide fast, precise and stable search results with a high degree of user satisfaction. The website modeling technique closely connected to the domain ontology, which supports the following functions in both website model construction and application: query expansion, webpage annotation, webpage/website classification, and focused collection of domain-related and user-interested Web resources. The agent features the following interesting characteristics. 1) Ontology-supported construction of website models. By this, we attribute domain semantics into the Web resources collected and stored in the local database. One important contribution here is the new Ontology-supported OntoClassifier which can do very accurate and stable classification on webpages to support more correct annotation of domain semantics. Our experiments show that Ontoclassifier performs very well in obtaining accurate and stable webpages classification. 2) Website models-supported web resource discovery. By this, we take into account both user interests and domain specificity. The contribution here is the new Focused Crawler which employs progressive strategies to do user query-driven webpage expansion, autonomous website expansion, and query results exploitation to effectively expand the website models. 3) Website models-supported Webpage Retrieval. By this, we leverage the power of ontology features as a fast index structure to locate most-wanted webpages for the user.

碩士
國立臺灣科技大學
工程技術研究所
97
Patient usually waits a long time in the waiting room before the doctor can receive them for consultation. This situation makes patient hesitate to consult the doctor because they might think it is a waste of time, and we all now that the earlier the illness is identify the better result the treatment can provide. Besides during this period patients are exposed to other illness that the risk of infection is high. Thinking of improving healthcare system must start with a better admission procedure and so on improve the waiting time and waiting condition. This system also suffers of a correlative information lake as a result he can not provide to patient or healthcare professional a waiting schedule. According to the scientific literature, we consider only one problematic situation which is the waiting time and then we come out by using technology and methodology based on the "waiting theory". This research uses Wireless Sensor Networks (WSN) with active push technology using ZigBee wireless transmit chip to communicate the Queue Management System (QMS). Using this technology a Real-Time DataBase (RDB) including room number, patient number, dates, times, can be maintain through the wireless connection. Using a one year History DataBase (HDB) correlated to the RDB will be processed by a Forecast Optimal Waiting Time Algorithm (FOWA) can calculate and predict an approximate time of consultation. This system will provide an internet access for patient allowing them to get precise information on the waiting time. By displaying this kind of system the waiting time can see his management having an important IV gain of efficiency and the condition of patient care will as a result be improved.

碩士
國立暨南國際大學
資訊工程學系
98
As the exponential growth of the Web, users are familiar to find solutions of problems from the Web through search engines. However, users often obtain too much information returned from search engines, so that they have to spend time to click-and-click for finding useful information. Therefore, we design an intelligent QA system to provide automatic and interactive chatting services for solving users’ problems progressively. In the thesis, we focus on the problem of trouble-shooting for the campus network. We integrate techniques of Web mining, information extraction, search engine and ontology into the system. Web mining and search engine techniques are applied to aggregate related information from the Web, then information extraction methods are employed to extract metadata for the domain problem. By extracting key concepts, calculating relations among concepts, constructing the hierarchy of concepts, we build the domain ontology. Based on the knowledge representation of AIML language, we develop a MSN robot that chats with users automatically for solving their problems, based on the inference of AIML.

碩士
清雲科技大學
電子工程研究所
94
We present an article about a machine of water electrolysis which can be controlled through Internet. Our design have the advantage of higher conversion efficiency and more variable output power modulation by using a switching power instead of a traditional power. We use the FPGA embedded system platform with web server for Internet control. With Common Gateway Interface, users can use a browser to remote internal settings to adjust the PH value setting of water electrolysis.

Tutoring is one of the most effective instruction methods. Computer as an Intelligent Tutor is an area of research since many decades. Technology advancement in Information and Communication Technology (ICT) can be used in developing Web – based Intelligent Tutoring System (WITS), which provides individualized tutoring at the same time to large number of students geographically distributed. Intelligent Tutoring System requires knowledge representation of expert, student and instructional strategy. While web technology promises many attractive features to build web based ITS, it would still be a challenge to represent knowledge objects that are scalable, reusable and platform independent. It is required to derive generalized knowledge representation framework which can be used in developing WITS for many courses. This research work proposes an instruction System Design (ISD) model based framework in development of WITS for Control Systems. ADDIE model is selected in development of WITS. Front end analysis is conducted to identify the learning goals of a course. Proposed research work presents a Bloom - Vincenti framework for preparing learning objectives for engineering courses. Problem Based Learning (PBL) is selected as instruction strategy. Then it presents an ontology based knowledge representation framework for expert module, tutoring module, and student module. Ontology for expert module is proposed on the course structure, instruction system, instruction material ontology, and Bloom – Vincenti Taxonomy. Ontology for student module is also proposed on course structure and Bloom – Vincenti Taxonomy. Tutoring module consists of ontology about the facts of the instruction material and rule base based on the categories of engineering knowledge (Vincenti) and cognitive skill (Bloom’s Taxonomy). Proposed way of knowledge representation supports scalability, and reusability. Prototype Web – based Intelligent Tutoring System for first level course on Control Systems is developed. JAVA technology used in development of Web – based Intelligent Tutoring System (WITS), makes WITS platform independent. Web – based Intelligent Tutoring System for Control Systems is deployed at laboratory level and its efficacy is tested for first two modules of a course.

碩士
南華大學
資訊管理學系碩士班
90
Due to the improvement of Information Technology (IT), all enterprises are facing the globalization of competitive marketplaces. Electronic Commerce (EC) is the utilization of network providing the enterprises services, marketing, sales and post-sale services. There is no doubt that EC is booming within recent years. How to accurately and effectively handle the Global Logistics Management (GLM) is the Critical Success Factors (CSFs) regarding the survival of an enterprise in this globalization of competitive marketplaces. Since the deployment of National Health Insurance, medical resources have been accidentally abused due to the redundancies of prescription or examination. Those kinds of activities are the waste of social welfares. The purpose of the research is to exploit the core competency of an Intelligent Agent (IA) being applied to the medical resource system on a web-based environment. Therefore, the integration of intelligent agent into the arena of medical resource management can provide the most valuable and accurate medical resources for emergency team in a proactive manner in saving people’s lives. In additions, not only does the research provide the multiple intelligent agent for the functionalities for each distinct subsystems, but also incorporate the communication and cooperation mechanism into the system in order to get the most efficient medical resource and information support. The research provides both spirits concerning the analysis of the operation of emergency team in the theoretical manner and the vision of the integration of IC card and Electronic Patient Record (EPR) for the construction of the database for national health records.

碩士
大同大學
資訊工程研究所
89
Electronic commerce rises sharply because of the growth of IT (Information Technology) and Internet. Customer oriented product and selling become a major tendency of commercial affairs little by little. In electronic commerce many behaviors of commerce can be done by a website. But the behavior model of electronic commerce is more passive than the behavior module of traditional commerce. If we can apply an intelligent system to web then it can increase active property to thrive trade. WWW is an important information medium on Internet which can offer much useful information. Web sites also include all kinds of information. How to provide a convenient user interface to various users and how the web site is used by user are all very important to system administrator. Traditional website does not give CRM (Customer Relationship Management) service to users. This results in user can not fast find information that he/she wants to get and is interested. In accordance with various users we want to use a technique of neural network to automatically get user cluster and combine the technology of data mining to analyze different users’ glance customs and users access patterns. Analyzing by such a technology we can get the data of interests from any kind of users or the characteristic rules of using websites. The result can dynamically offer users to view related pages on the website by ASP or PHP, which is the website program processing on server that can provide users about their interests content and products. Further, we can actively offer users the service of CRM, or we can recommend users their interesting products to create business opportunities and to let them find what they want faster. In this thesis, we present a method to filter log file and get the believable data to be training data in our system. In a large website can have many kinds of users, first we apply SOM network to cluster users, then analyze ever user cluster’s path pattern. In the last step, we add a tendency concept to the original algorithm for mining user path patterns.

碩士
國立高雄師範大學
資訊教育研究所
91
The purpose of this study is to explore on issues of an adaptive system that based on intelligent agent and 3D/VR web technology. An adaptive system is a kind of objectives in terms of user interface because it can satisfies the needs of different users. Based on agent technology which providing human-like Application Program Interface (API) and Information Richness Theory (IRT) , this study implements an “Intelligent Agent for Merchandise Recommendation System“(IA4MRS). The IA4MRS consists of recommending cars by user preferences and 3D/VR presentation. The implementation of the IA4MRS consists of three key stages. Firstly, JADE (Java Agent DEvelopment Framework) has been adopted as platform for distributed system that connects scattered information by agents’ communication. In addition, the OOA/D is applied in software construction process. Secondly, an online survey is designed for adaptive car recommendation system, and the system provides two adaptive guiding mechanisms: (a).Natural language query with thesaurus, and (b). An automatic recommendation by this system provided by gender factor as a user model. Finally, a semi-structured interview with intent sampling has been conducted for checking performance and guiding improvement of the system. The results of this study show three folds: (a).Intelligent agent technology that offers human-like API, communication protocol, and knowledge sharing greatly reduces the complexity of software development. (b).The 3D/VR presentation has been popularly recognized as sense-making for product since 3D/VR provides an animated environment；(c).Although most users confirm the online survey as a comprehensive base for car purchasing recommendation, they doubt the credit of recommendation, prefer further verification and hope that the quantity of 3D model information could be increased. Summarily, some recommendations for future research are included. It is hoped that the experience can be applied to educational adaptive system by analyzing students’ behaviors while intelligent technology and 3D/VR lay the foundation for an adaptive system. More related technology such as voice and virtual pedagogical agent, and higher credit for recommendation quality in an adaptive educational system should be integrated.

碩士
國立屏東科技大學
資訊管理系所
104
The Internet of Things (Internet of Things, IoT) concept gradually be concerned about. And in part of agricultural production, farmers are dependent on the weather, crop production, environmental state is very important. Along with sensor networks (Sensor Web) development, build sensors in the agriculture environment. But the manchine can’t understand the information form sensor. In view of this, this paper proposes a " Design of an Intelligent IoT Agriculture Knowledge Management System Based on Semantic Web", Using Semantic Web of the technology that give matadate for the collected data. So that computer can understand the information. And building agricultural knowledge ontology, make the rules. We use Multiple Regression Analysis to predict the future agriculture enviroment’s state. Finally, giving farmer corps planted, early warning, plant diseases and insect pests and environment knowledge based on crops planted knowledge.

碩士
佛光大學
資訊學系
96
Nursing resources usually covers 30% to 40% of total labor cost in a hospital. Thus, properly arrange the human resource has become one of the important tasks for hospital administrators. The work force system of nursing staff need to take several factors into the consideration when you manage and allocate the human resource since it covers not only manpower allocation, day-off arrangement, personal physiology and psychology, group fairness, reasonableness, and so on. Therefore, the more nursing resources in the hospital the more variation exists in the management system. Even though heuristic inference model is currently one of the most optimized and popular mechanisms for most hospital to manage their faculties, shifting rules in the decision tree and relationship among those elements are too many, and complicated to properly meet with more and more unexpected requests from end users of information system. The objective of this research is to collects and analysis information which are classifications, rules and policy of shift job completely. All design is based on the Service-Oriented Architecture (SOA) principle, and coordinated with Particle Swarm Optimization (PSO) algorithm to come out with an optimized kernel of model. Faculties gain several advantages by using shift-scheduling information system. For instance, schedulers and the other nursing staff can be easily satisfied with the schedule planned by computer system, meanwhile, it can compensate for the imperfection caused by human manual scheduling, such as lacking of consideration comprehensively, or lacking of fairness for some personal issues. In addition, it can reduce the argument among staff, and increase the appreciation for the flexibility of scheduling, and reservation for taking day-off. Moreover, scheduling system can make plenty of combination to meet variety of demand from people in different department by providing the scheduling service on the web. Finally, rule must be modified accordingly to enhance the flexibility of the system and reduce the problem caused by the system integration due to the policy change by management level.

碩士
逢甲大學
交通工程與管理研究所
89
Recently, it takes about one month to key in the road traffic accidents data into the data files. In the same time, these data files are only authorized using by the official departments such as Department of Police Administration (DPA), the Ministry of Communication and Transportation (MOCT), And Institute of Transportation (IOT) for the internal applications. Since the technology innovation and the World Wide Web (WWW) are widely used in the world, it is very convenient to utilize the function of WWW to key in, analyze, search, and utilize these road traffic data. Through the innovation of WWW, it will save the time to key in data, and users update the data much more friendly. Moreover, The web database system can be download, search for the scholars who want to extend the further analysis and research. Besides, the user also can search the related traffic accident information. This study use the methodology of the statistical analysis of the digital road traffic accidents data from 1999 to 2000 provided by Taichung City Police Bureau(TCPB) and analytic results can be utilized by the related departments or the scholars for the further analysis and research. Finally, the advanced search function can identify the accident-prone locations based on accident frequencies and ETAN index. In 2000, there are 13,030 digital road traffic accidents data of TCPB are used to develop the accident frequencies programs. Then obtaining empirical result of the rank of top 10 accident-prone intersections and accuracy results show about 98.89﹪. Meanwhile, the intelligent improving system for traffic engineering based on the expert system method have found the effective methods to avoid the car accidents at the accident-prone intersections.

碩士
聖約翰科技大學
電子工程系碩士班
99
This paper focuses on developing a Cloud intelligent interface agent with Web services. Not only does it explore related technologies to establish Web service platforms, but it also investigates the construction of Cloud interactive diagrams using Web service techniques for extensively and seamlessly integrating backend information systems on the Internet. This system contains two main portions, including information processing platform and Cloud information interface. The former is composed of three sub-systems: Receiver\Transmitter, Decision Maker, and WSI. The latter is showed in a lot of sub-webpages, including real-time information browsing, historical information query, dynamically decision-making process, WIAS’ service interface, and system homepage. Notably, this work provides an example of an energy-saving information system and produces results regarding the feasibility of the proposed architecture, and then verifies a lot of system designs on flexibility, adaptation, and real-time and dynamic feedback learning based on Web service techniques. The system verifications and comparisons can not only present the uniqueness of functions on on-line browsing, information query, user guiding, dynamically decision-making process, intelligent decision-making, and feedback controlling, but also show that the decision-making precision, system reliability and system validity yield excellent system qualities. The contributions obtained in the system development and application are: 1) the system possesses most powerful extensibility and easy to maintain and developing further; 2) the system platform can not only have deserved properties of agent, but also completely possess important friendly to users during the interface communication; 3) the system architecture can go through re-assembling and composing individual sub-system objects and correspondingly put in use of various domains for truly reaching the best application significance of cross-platform and program code reuse. Keywords: Web Service, Cloud Interface Agents, Energy-saving Information Systems.

碩士
國立屏東科技大學
資訊管理系所
98
With the change of diet habit and lifestyle in Taiwan, the quantity of chronic disease patients is becoming more and more, especially of hypertension, hyperglycemia and hyperlipemia patients. However, the Food Service Recommendation (FSR) mechanism based on user’s vital data and health records has not been investigated. In this paper, we propose the Intelligent Personalization Food Service Recommendation System (IPFSRS) which contains Vital Sensor Web Layer (VSWL), Semantic Medical Web Layer (SMWL), and Medical Service Present Layer (MSPL). The vital sensors in VSWL can sense and transfer user’s vital data based on Sensor Web Enablement (SWE). The SMWL uses Rule-Based Reasoning (RBR) and Domain Ontologies (DO) based on Semantic Web (SW) to infer user’s health state according to user’s vital data from VSWL. Furthermore, we use Bayesian Classification (BC) to predict the future user’s health state. Finally, the FSR is generated according to current and future user’s health state and showed in MSPL for healthcare.

Μια από τις μεγαλύτερες προκλήσεις στις μέρες μας αποτελεί η εξαγωγή και η κατανόηση του πλήθους των πληροφοριών που βρίσκονται κρυμμένες στα βιολογικά δεδομένα. Ο καταιγισμός των πληροφοριών που προέρχονται από τη βιολογική έρευνα είναι τόσο σύνθετος που χρειάζεται να αναλυθεί με τη χρήση προηγμένων υπολογιστικών μεθόδων. Αυτό οδήγησε στη Βιοπληροφορική, έναν επαναστατικό επιστημονικό τομέα, ο οποίος εφαρμόζει στοιχεία της επιστήμης των υπολογιστών και της τεχνολογίας των πληροφοριών για τη διαχείριση των βιολογικών δεδομένων. Ο κλάδος της Βιοπληροφορικής σήμερα θεωρείται, παγκοσμίως, ένας από τους πλέον εξελισσόμενους, ενώ έχει ήδη επιδείξει σημαντικά επιτεύγματα και έχει συγκεντρώσει ιδιαίτερα σημαντικές διακρίσεις. Η εκπαίδευση εξειδικευμένων ατόμων σε θέματα Βιοπληροφορικής αποτελεί ιδιαίτερη πρόκληση, καθώς οι εκπαιδευόμενοι προέρχονται από τον τομέα της Βιολογίας ή της Πληροφορικής, παρουσιάζοντας γι' αυτόν τον λόγο μεγάλες διαφορές στο μαθησιακό τους υπόβαθρο. Επιπλέον, δημοσιεύονται συνεχώς καινούριες μέθοδοι επεξεργασίας βιολογικών δεδομένων, καθιστώντας το δύσκολο ακόμα και για κάποιον εκπαιδευτικό να παρακολουθεί την εξέλιξη και να ενημερώνει το εκπαιδευτικό περιεχόμενο των μαθημάτων του. Την ίδια στιγμή, η τεχνολογία της ηλεκτρονικής εκμάθησης έχει γίνει ένα εναλλακτικό μαθησιακό πρότυπο. Κατά τη διάρκεια του 20ού αιώνα, για τους περισσότερους από εμάς, η έννοια της μάθησης ήταν συνυφασμένη με τις παραδοσιακές αίθουσες διδασκαλίας. Όμως, από τον 21ο αιώνα άρχισε να κυριαρχεί μια νέα κουλτούρα μάθησης. Χάρη στην κατάλληλη χρήση των τεχνολογιών πληροφορίας, των δικτύων και των πολυμέσων, μαθητές και ερευνητές οι οποίοι διαχωρίζονται από την απόσταση, συνδέονται τεχνολογικά. Η γνώση γίνεται διαθέσιμη στο σύγχρονο ακαδημαϊκό και επαγγελματικό κόσμο, χωρίς χωρικούς ή χρονικούς περιορισμούς. Η συνεχώς αυξανόμενη υποδομή των ψηφιακών δικτύων ενισχύει την ικανότητα για πρόσβαση και χρήση απεριόριστων πηγών και εργαλείων. Επιπλέον, η ηλεκτρονική μάθηση εκτείνεται πέρα από την απλή πρόσβαση στην πληροφορία, αλλά βασίζεται στην επικοινωνία και στην αλληλεπίδραση των ατόμων που συμμετέχουν στη διαδικασία της μάθησης. Οι πλατφόρμες της ηλεκτρονικής εκμάθησης είναι ιδιαίτερα χρήσιμες και στην εκπαίδευση της Βιοπληροφορικής, καθώς μπορούν να βελτιώσουν την ποιότητα της διδασκαλίας και να μειώσουν τον χρόνο που απαιτείται για τη διαχείριση του εκπαιδευτικού υλικού. Πέραν τούτου, το αντικείμενο της Βιοπληροφορικής είναι πλήρως συνυφασμένο με τη χρήση του Διαδικτύου, καθώς μέσω αυτού μπορούν να βρεθούν πολλές πηγές δεδομένων και χρήσιμα εργαλεία. Στην παρούσα διπλωματική εργασία, προηγμένες διαδικασίες ηλεκτρονικής μάθησης έχουν αναπτυχθεί ώστε να εισαγάγουν ολοένα και περισσότερους μαθητές στην επαναστατική επιστήμη της Βιοπληροφορικής. Μια σύγχρονη διαδικτυακή εφαρμογή, η οποία όχι μόνο αποθηκεύει και διαχειρίζεται τον πλούτο της γνώσης και της εμπειρίας της ερευνητικής ομάδας «Υπολογιστικής Βιολογίας και Βιοπληροφορικής» του Πανεπιστημίου Πατρών, αλλά επιπλέον επιτρέπει στους χρήστες του συστήματος να προβάλλουν, οπουδήποτε και οποτεδήποτε, και να αλληλεπιδρούν με το πλούσιο μαθησιακό περιεχόμενο το οποίο παρουσιάζεται με τη μορφή κειμένων, υπερκειμένων,εικόνων, παρουσιάσεων και βίντεο. Δημοσιεύσεις σε συνέδρια και περιοδικά, ερευνητικά έργα, διπλωματικές εργασίες, παρουσιάσεις, εργαλεία και ανακοινώσεις είναι μόνο μερικά δείγματα της καθημερινής συνεισφοράς και της ανεκτίμητης προσπάθειας της ερευνητικής ομάδας. Πλήθος πληροφοριών, καλά οργανωμένων και δυναμικά ανανεώσιμων, είναι πάντα στη διάθεση μας. Σημαντικότατο στοιχείο του συστήματος ηλεκτρονικής εκμάθησης αποτελεί η ευφυΐα του, με άλλα λόγια η ικανότητα παροχής μιας εξατομικευμένης μαθησιακής πορείας στον κάθε εκπαιδευόμενο, με βάση το επίπεδο γνώσεων, τις μαθησιακές ανάγκες αλλά και την πρόοδο του. Επιπρόσθετα, η εν λόγω διαδικτυακή εφαρμογή εκμάθησης της Βιοπληροφορικής ευνοεί τη δημιουργία μαθησιακών κοινοτήτων οι οποίες ενισχύουν τη συνεργασία, την επικοινωνία αλλά και την αλληλεπίδραση μεταξύ εκπαιδευτών και εκπαιδευόμενων, όπως δηλαδή συμβαίνει σε μία παραδοσιακή αίθουσα διδασκαλίας. Όμως, μέσα από την ηλεκτρονική μάθηση, ο εκπαιδευόμενος αποτελεί πλέον το «κέντρο της μαθησιακής διαδικασίας», καθώς μετατρέπεται από παθητικό σε ενεργό δέκτη της μάθησης, επιλέγοντας το πώς και τι μαθαίνει.
One of the greatest challenges today is the extraction and comprehension of the huge mass of information hidden in biological data. The flood of information that comes from the biological research is so complex that needs to be analyzed by means of advanced computational methods. This has given rise to Bioinformatics, a revolutionary scientific field which applies elements of computer science and information technology to the management of this biological information. Bioinformatics is now considered, worldwide, as one of the most evolving fields since it has already demonstrated some very significant achievements and it has gathered really important distinctions. Training students in Bioinformatics is an important challenge as they have big academic differences and their learning background is either in Biology or in Informatics. Moreover, new methods for biological data processing are being published frequently and it is very hard even for professionals in the field of Bioinformatics to follow the new publications and renew the material of their courses. At the same time, the e-learning technology has become an alternative learning standard. During the 20th century, for most of us, the concept of learning was intertwined with the traditional classrooms. But, since the 21st century a new culture of learning has begun. Thanks to the proper use of modern information technologies, networks and multimedia, students and researches who are separated by distance, get technologically connected. Knowledge becomes available to the contemporary academic and professional world, without any geographical restrictions or time limits. The growing infrastructure of digital networks enhances the ability to access and use unlimited resources and tools. Furthermore, e-learning extends beyond simple access to information, but it is based on the communication and interaction of people involved in the learning process. The e-learning platforms are particularly useful in Bioinformatics education, as they can improve the quality of teaching and reduce the time required for the administration of educational material. Furthermore, the scientific field of Bioinformatics is completely interwoven with the use of the Internet due to the fact that many data sources and software tools are accessible through it. In this thesis, advanced e-learning processes have been developed in order to introduce more and more students to the revolutionary science of Bioinformatics. A modern web application which not only stores and manages the wealth of knowledge and experience provided by the Computational Biology and Bioinformatics group of the University of Patras, but also permits visitors to visualize, anywhere and anytime, and interact with this rich learning content which is presented in the form of text, hypertext, images, presentations and videos. Publications in conferences and journals, research projects, theses, presentations, tools, latest news and announcements are just some demonstrations of the daily contribution and the priceless effort spent by this group. A great deal of information, securely organized and dynamically updated, always at our disposal. The most important element of this e-learning application is its intelligence, in other words its ability to provide a personalized learning path to each student, based on his level of knowledge, his learning needs and the progress made in every step of the e-learning training. In addition, this Bioinformatics e-learning application, favors the creation of learning communities which enhance collaboration, communication and interaction between trainers and trainees, as that occurs in a traditional classroom. However, through e-learning, the trainee becomes the "center of the learning process", as he turns from a passive to an active receiver of learning, by choosing how and what he learns.

The Internet and world wide web (WWW) have in recent years, grown exponentially in size and in terms of the volume of information that is available on it. In order to effectively deal with the huge amount of information on the web, so called web search engines have been developed for the task of retrieving useful and relevant information for its users. Unfortunately, these web search engines have not kept pace with the boom growth and commercialization of the web. The main goal of this dissertation is the development of a model for a collaborative personalized meta-search agent (COPEMSA) system for the WWW. This model will enable the personalization of web search for users. Furthermore, the model aims to leverage on current search engines on the web as well as enable collaboration between users of the search system for the purposes of sharing useful resources between them. The model also employs the use of multiple intelligent agents and web content mining techniques. This enables the model to autonomously retrieve useful information for it’s user(s) and present this information in an effective manner. In order to achieve the above stated, the COPEMSA model employs the use of multiple intelligent agents. COPEMSA consists of five core components: a user agent, a query agent, a community agent, a content mining agent and a directed web spider. The user agent learns about the user in order to introduce personal preference into user queries. The query agent is a scaled down meta-search engine with the task of submitting the personalized queries it receives from the user agent to multiple search services on theWWW. The community agent enables the search system to communicate and leverage on the search experiences of a community of searchers. The content mining agent is responsible for analysis of the retrieved results from theWWWand the presentation of these results to the system user. Finally, a directed web spider is used by the content mining agent to retrieve the actual web pages it analyzes from the WWW. In this dissertation an additional model is also presented to deal with a specific problem all web spidering software must deal with namely content and link encapsulation.
Prof. E.M. Ehlers