Search

This paper presents a complete inductive learning system that aims to produce comprehensible theories for XML document classifications. The knowledge representation method is based on a higher-order logic formalism which is particularly suitable for structured-data learning systems. A systematic way of generating predicates is also given. The learning algorithm of the system is a modified standard decision-tree learning algorithm driven by predicate/recall breakeven point. Experimental results on XML version of Reuters dataset show that this system is able to produce comprehensible theories with high precision/recall breakeven point values. [ABSTRACT FROM AUTHOR]

A fast local pattern matching method for fingerprints with less than two singulars is proposed in this paper. The method has three steps: pre-processing, minutia extraction, and matching based on local pattern. In pre-processing, a twice smoothing method is used to get a high qualification orientation image. In minutia extraction, the number of go-throughs is used for later matching. In matching, a local pattern method is proposed which include the structure information. The result shows that the local pattern matching is an effective method. [ABSTRACT FROM AUTHOR]

A synthetic method for wafer character recognition is discussed in this paper. The pre-processing of image, stroke detection and segmentation specially to wafer image are discussed. The special structure matching method is proposed. Finally, combined SOM tree classifier with structure matching method, a synthetic method is proposed which is superior to any single one. [ABSTRACT FROM AUTHOR]