signal analysis on strings for immune-type pattern recognition信号分析免疫型号模式识别的字符串.pdfVIP

Comparative and Functional Genomics Comp Funct Genom 2004; 5: 69–74. Published online in Wiley InterScience (). DOI: 10.1002/cfg.367 Conference Review Signal analysis on strings for immune-type pattern recognition Nikolaos D. Atreas, Costas Karanikas* and Persefoni Polychronidou Department of Informatics, Aristotle University of Thessaloniki, Thessaloniki 54124, Greece *Correspondence to: Abstract Costas Karanikas, Department of Informatics, Aristotle University of We use wavelet-type discrete transforms for signal analysis on strings of finite length. Thessaloniki, Thessaloniki 54124, We apply these transforms for edge and hidden Markov process detection. We also Greece. present new approaches for string matching and for measures of the diversity of E-mail: karanika@csd.auth.gr chaotic strings. Copyright  2004 John Wiley Sons, Ltd. Keywords: immune-inspired computational systems; discrete tree transform; edge Received: 10 November 2003 detection; hidden Markov model; string matching Revised: 27 November 2003 Accepted: 28 November 2003 Introduction in Bisbas and Karanikas 1990 [6], and we present a novel string matching method based on analytic The immune system is one of the most effective number theory. pattern recognition systems. This system deals As Felix Browder, the President of the American with RNA strings on proteins and viruses and Mathematical Society, said in his Retiring Presi- is involved in several operations and recognition dential Address [4]: modes capable of: I