No description available.

No description available.

No description available.

No description available.

No description available.

Critical to semantic integration of heterogeneous data sources, determining the semantic correspondences among the data sources is a very complex and resource-consuming task and demands automated support. In this dissertation, we propose a comprehensive approach to detecting both schema-level and instance-level semantic correspondences from heterogeneous data sources. Semantic correspondences on the two levels are identified alternately and incrementally in an iterative procedure. Statistical cluster analysis methods and the Self-Organizing Map (SOM) neural network method are used first to identify similar schema elements (i.e., relations and attributes). Based on the identified schema-level correspondences, classification techniques drawn from statistical pattern recognition, machine learning, and artificial neural networks are then used to identify matching tuples. Multiple classifiers are combined in various ways, such as bagging, boosting, concatenating, and stacking, to improve classification accuracy. Statistical analysis techniques, such as correlation and regression, are then applied to a preliminary integrated data set to evaluate the relationships among schema elements more accurately. Improved schema-level correspondences are fed back into the identification of instance-level correspondences, resulting in a loop in the overall procedure. Empirical evaluation using real-world and simulated data that has been performed is described to demonstrate the utility of the proposed multi-level, multi-technique approach to detecting semantic correspondences from heterogeneous data sources.

With the rapid growth of the Web, users are often faced with the problem of information overload and find it difficult to search for relevant and useful information on the Web. Besides general-purpose search engines, there exist some alternative approaches that can help users perform searches on the Web more effectively and efficiently. Personalized search agents and specialized search engines are two such approaches. The goal of this dissertation is to study how machine learning and artificial intelligence techniques can be used to improve these approaches. A system development research process was adopted as the methodology in this dissertation. In the first part of the dissertation, five different personalized search agents, namely CI Spider, Meta Spider, Cancer Spider, Nano Spider, and Collaborative Spider, were developed. These spiders combine Web searching with various techniques such as noun phrasing, text clustering, and multi-agent technologies to help satisfy users' information needs in different domains and different contexts. Individual experiments were designed and conducted to evaluate the proposed approach and the experimental results showed that the prototype systems performed better than or comparable to traditional search methods. The second part of the dissertation aims to investigate how artificial intelligence techniques can be used to facilitate the development of specialized search engines. A Hopfield Net spider was proposed to locate from the Web URLs that are relevant to a given domain. A feature-based machine-learning text classifier also was proposed to perform filtering on Web pages. A prototype system was built for each approach. Both systems were evaluated and the results demonstrated that they both outperformed traditional approaches. This dissertation has two main contributions. Firstly, it demonstrated how machine learning and artificial intelligence techniques can be used to improve and enhance the development of personalized search agents and specialized search engines. Secondly, it provided a set of tools that can facilitate users in their Web searching and Web mining activities in various contexts.

This dissertation aims to discover synergistic combinations of top-down (ontologies), interactive (relevance feedback), and bottom-up (machine learning) knowledge encoding techniques for text mining. The strength of machine learning techniques lies in their coverage and efficiency because they can discover new knowledge without human intervention. The output, however, is often imprecise and irrelevant. Human knowledge, top-down or interactively encoded, may remedy this. The research question addressed is if knowledge discovery can become more precise and relevant with hybrid systems. Three different combinations are evaluated. The first study investigates an ontology, the Unified Medical Language System (UMLS), combined with an automatically created thesaurus to dynamically adjust the thesaurus' output. The augmented thesaurus was added to a medical, meta-search portal as a keyword suggester and compared with the unmodified thesaurus and UMLS. Users preferred the hybrid approach. Thus, the combination of the ontology with the thesaurus was better than the components separately. The second study investigates implicit relevance feedback combined with genetic algorithms designed to adjust user queries for online searching. These were compared with pure relevance feedback algorithms. Users were divided into groups based on their overall performance. The genetic algorithm significantly helped low achievers, but hindered high achievers. Thus, the interactively elicited knowledge from relevance feedback was judged insufficient to guide machine learning for all users. The final study investigates ontologies combined with two natural language processing techniques: a shallow parser and an automatically created thesaurus. Both capture relations between phrases in biomedical text. Qualified researchers found all terms to be precise; however, terms that belonged to ontologies were more relevant. Parser relations were all precise. Thesaurus relations were less precise, but precision improved for relations that had their terms represented in ontologies. Thus, this integration of ontologies with natural language processing provided good results. In general, it was concluded that top-down encoded knowledge could be effectively integrated with bottom-up encoded knowledge for knowledge discovery in text. This is particularly relevant to business fields, which are text and knowledge intensive. In the future, it will be worthwhile to extend the parser and also to test similar hybrid approaches for data mining.

As the role of computer-assisted instruction (CAI) rapidly expands in the educational and training efforts of all types of organizations, the need for well-designed, learner-centered CAI continues to grow. The CAI design principles and methodology proposed herein provide systems designers with a framework for designing effective, learner-centered CAI systems that support learning with information technologies. Implementing the framework should lead to CAI that better supports learners in the development of their mental schemas, and ultimately, in achieving their learning objectives. The primary goals of this research are two-fold. First, derive a theoretically and empirically-based set of CAI design principles directed at purposefully exploiting the unique capabilities of information technology to help learners develop their mental schemas. Second, codify a methodology for implementing these principles in the systems analysis and design process. Both goals are accomplished as follows. First, a literature review was undertaken to uncover features important for designing CAI to improve learning. Concurrently, the design features and functionality of several existing CAI were reviewed. A field study of one distinctive CAI was conducted to investigate and substantiate its effectiveness. Results indicated that learners using the CAI improved their achievement significantly more than learners who did not use the CAI. Moreover, learners attributed their improved performance to using the CAI. Based on the literature review, review of existing CAI, and the results of the field study, a set of principles and a methodology for designing CAI were derived. The design principles and methodology focus the CAI design process on supporting learners' development of their mental schemas. Finally, we designed, developed and implemented a prototype web based, multimedia training system in accordance with the proposed CAI design principles. As a partial instantiation of the proposed principles and methodology, this prototype CAI provides a proof-of-concept. The design and effectiveness of the prototype CAI has been tested in a series of experiments. The corroborating evidence from these studies indicates that the prototype CAI is well-designed, usable, and an effective training tool. The demonstrated success of the prototype provides evidence of the merits of the proposed principles and methodology.

In this dissertation the dynamics of trust between anonymous agents playing iterated trust dilemmas are examined. Two separate experimental institutions are used. The first institution is a three-player Centipede Game. The second is a novel institution called the Real Time Trust Game. Both games have structures with diametrically opposed Pareto optimal outcomes and Nash equilibrium. Mutually anonymous individuals play the games for real pecuniary rewards. A variety of experimental manipulations are employed to determine their relative effects on individuals' decisions, as well as the changes in population dynamics. General findings confirm the fragility of trust in these barren institutions, the institutions used here are barren in the sense that the normal social mechanisms that typically facilitate trust (credible communication, reputation, potential retaliation) are unavailable to players. As a consequence, most of the results display a slow breakdown of trust between players, with the rate of decay being subject to experimental manipulation. Nonetheless, individual differences are substantial and a handful of players resist playing narrowly rational strategies, exhibiting "hard-core" cooperative tendencies.