A Review of Kernel Methods Based Approaches to Classification and Clustering of Sequential Patterns, Part II: Sequences of Discrete Symbols

Abstract

Pattern analysis tasks on sequences of discrete symbols are important for pattern discovery in bioinformatics, text analysis, speech processing, and handwritten character recognition. Discrete symbols may correspond to amino acids or nucleotides in biological sequence analysis, characters in text analysis, and codebook indices in processing of speech and handwritten character data. The main issues in kernel methods based approaches to pattern analysis tasks on discrete symbol sequences are related to defining a measure of similarity between sequences of discrete symbols, and handling the varying length nature of sequences. We present a review of methods to design dynamic kernels for sequences of discrete symbols. We then present a review of approaches to classification and clustering of sequences of discrete symbols using the dynamic kernel based methods.