Similarity Measures Based on Imperfect Domain Theories
نویسنده
چکیده
Inspired by recent psychological findings on human similarity assessment, this paper introduces two methods to increase the classification accuracy and flexibility of similarity measures in CBR systems. Similarity measures are enhanced by imperfect domain theories. Attribute weights are inferred analytically from their relations to the classification goal, and additional virtual attributes are derived. We aim at combining imperfect domain-theories and CBR in order to achieve better classification accuracies than when using the two approaches alone. Furthermore, it is shown how similarity measure can be adapted to classification goals.
منابع مشابه
Similarity-based Opponent Modelling using Imperfect Domain Theories
This paper proposes a similarity-based approach for opponent modelling in multi-agent games. The classification accuracy is increased by adding derived attributes from imperfect domain theories to the similarity measure. The main contributions are to show how different forms of domain knowledge can be incorporated into similarity measures for opponent modelling, and to show that the situation s...
متن کاملPartial, Vague Knowledge for Similarity Measures
This paper proposes to enhance similarity-based classification by virtual attributes from imperfect domain theories. We analyze how properties of the domain theory, such as partialness and vagueness, influence classification accuracy. Experiments in a simple domain suggest that partial knowledge is more useful than vague knowledge. However, for data sets from the UCI Machine Learning Repository...
متن کاملPartial and Vague Knowledge for Similarity Measures
This paper proposes to enhance similarity-based classification by virtual attributes from imperfect domain theories. We analyze how properties of the domain theory, such as partialness and vagueness, influence classification accuracy. Experiments in a simple domain suggest that partial knowledge is more useful than vague knowledge. However, for data sets from the UCI Machine Learning Repository...
متن کاملVirtual Attributes from Imperfect Domain Theories
This paper proposes to enhance similarity-based classification by virtual attributes from imperfect domain theories. We analyze how properties of the domain theory, such as partialness and vagueness, influence classification accuracy. Experiments in a simple domain suggest that partial knowledge is more useful than vague knowledge. However, for data sets from the UCI Machine Learning repository...
متن کاملEnhancing Similarity Measures with Imperfect Rule-based Background Knowledge
Classification is a general framework that can be applied to various tasks such as object recognition, prediction, diagnosis or learning. There exist at least two different approaches for classification, namely rule-based and similaritybased classification. The two approaches have different strengths and weaknesses. The former requires a domain theory in order to make inferences from the test i...
متن کامل