: The application of machine learning (ML) to solve practical problems is complex. Only recently, due to the increased promise of ML in solving real problems and the experienced difficulty of their use, has this issue started to attract attention. This difficulty arises from the complexity of learning problems and the large variety of available techniques. In order to understand this complexity and begin to overcome it, it is important to construct a characterization of learning situations. Building on previous work that dealt with the practical use of ML, a set of dimensions is developed, contrasted with another recent proposal, and illustrated with a project on the development of a decision-support system for marine propeller design. The general research opportunities that emerge from the development of the dimensions are discussed. Leading toward working systems, a simple model is presented for setting priorities in research and in selecting learning tasks within large projects. Cen...

Design is an information intensive process. Designers base design decisions by gathering, synthesizing and analyzing information from various sources such as memos from colleagues or documented case histories. Translating design needs into information requests or queries aimed at finding the most useful information to help make design decisions represents a critical step in this process. Unfortunately, in the process of constructing information requests in the form of queries, designers must deal with several uncertainties, such as not being cognizant about the information available in the document database and/or not knowing how to express the needs in the query. This usually reduces the efficacy of the designers for finding the information most useful to their needs during the search process. Most information retrieval research has focused on retrieval techniques given a query rather than augmenting or re-writing queries to direct the search. Given that the information retrieval proc...

Abstract. The realization of the potential of the World Wide Web as a source of information as well as a platform for collaboration in engineering design calls for developing a new generation of design tools. We provide an overview of the Concept Database (Cdb)- a prototype framework for Web-based design information resources management. The implementation of the Cdb proposes an agent architecture for the coordination and delegation of tasks related to the support of the design process. The level of delegation of design process support from designer to agent is suggested as a measure of agent intelligence. Research directions with potential for enhanced agent effectiveness in engineering design tasks are presented. 1.

Design is the evolutionary process of transforming informal requirements into a product. Whether this product is real or virtual, mass produced or made to order, the information development that produces this transformation is generic. The task we focus on here is that of making textual information more useful throughout the design process. Design information can cover a range of different activities within the design process, from conceptual design to implementation. We focus on information captured in electronic notebooks. The informal information found in these notebooks is of particular interest because it is captured as it is generated, in effect, capturing the design process. In this paper, we examine techniques for improving access to such informal design information using hierarchical thesauri overlaid on generic information retrieval tools. We examine several approaches to creating thesauri, using both manual and data mining techniques, and compare the tradeoffs of each strate...

In this paper, we introduce ontology-centric knowledge organization approach to realize design knowledge base system for sharing and reuse of knowledge. Since ontology is used here as an intermediate level of information representation between the model and media level of information, it can work to bridge multiple models and multiple users. DesignersAmplifier is a workbench for designers where they can store, organize their information resources, and also can communicate to other designers based on the ontology-centric knowledge organization. DesignersAmplifier helps designers to organize documents with ontology. For example, it can re-build documents as hypertexts of which hyper-links are linked to concepts in ontology. It can help designers to expand search words by ontology or by collocation data in documents. DesignersAmplifier can help communication among designers by exchanging ontologies. We realized exchanging ontologies by mobile agent architecture. Keywords ontology, coope...

This paper presents a methodology to generate an XML (eXtensible Markup Language) document that expresses the information needs of a design engineer. XML documents and their underlying Document Type Definition (DTD) offer an efficient structure for the organization of design information [5] and representation of information needs. Through declarations of XML entities and the inherent structural hierarchy of XML documents, XML documents can express the designer's information needs while framing the design's structural hierarchies. For example, an element in the DTD may permit the design engineer to express a preference for formal company documents of past designs (e.g., technical memos) rather than informal design notes. The data in the XML document may be drawn from a repository of semi-structured or unstructured text documents that the design engineer has retrieved and placed into a personal information store by using an information retrieval system. Our methodology draws from the co