Yaochu Jin Libri

Biological systems are inherently stochastic and uncertain. Thus, research in bioinformatics, biomedical engineering and computational biology has to deal with a large amount of uncertainties. Fuzzy logic has shown to be a powerful tool in capturing different uncertainties in engineering systems. In recent years, fuzzy logic based modeling and analysis approaches are also becoming popular in analyzing biological data and modeling biological systems. Numerous research and application results have been reported that demonstrated the effectiveness of fuzzy logic in solving a wide range of biological problems found in bioinformatics, biomedical engineering, and computational biology. Contributed by leading experts world-wide, this edited book contains 16 chapters presenting representative research results on the application of fuzzy systems to genome sequence assembly, gene expression analysis, promoter analysis, cis -regulation logic analysis and synthesis, reconstruction of genetic and cellular networks, as well as biomedical problems, such as medical image processing, electrocardiogram data classification and anesthesia monitoring and control. This volume is a valuable reference for researchers, practitioners, as well as graduate students working in the field of bioinformatics, biomedical engineering and computational biology.

This carefully edited book presents recent advances in knowledge incorporation within evolutionary computation, offering a unified framework. It provides a comprehensive, self-contained overview, including a concise introduction to evolutionary algorithms and knowledge representation methods. This resource is invaluable for researchers, students, and professionals in engineering and computer science, particularly in artificial intelligence, soft computing, natural computing, and evolutionary computation. The contents are organized into several parts: Part I introduces evolutionary computation; Part II discusses knowledge incorporation in initialization, recombination, and mutation, featuring topics like collective memory in genetic programming and cultural algorithms for job shop scheduling. Part III focuses on knowledge incorporation in selection and reproduction, including learning probabilistic models to enhance evolutionary computation and linkage learning in forest management. Part IV addresses knowledge incorporation in fitness evaluations, highlighting neural networks for fitness approximation. Part V explores lifetime learning and human-computer interactions, while Part VI examines preference incorporation in multi-objective evolutionary computation, integrating user preferences into evolutionary multi-objective optimization.

Fuzzy rule systems have found a wide range of applications in many fields of science and technology. Traditionally, fuzzy rules are generated from human expert knowledge or human heuristics for relatively simple systems. In the last few years, data-driven fuzzy rule generation has been very active. Compared to heuristic fuzzy rules, fuzzy rules generated from data are able to extract more profound knowledge for more complex systems. This book presents a number of approaches to the generation of fuzzy rules from data, ranging from the direct fuzzy inference based to neural net­ works and evolutionary algorithms based fuzzy rule generation. Besides the approximation accuracy, special attention has been paid to the interpretabil­ ity of the extracted fuzzy rules. In other words, the fuzzy rules generated from data are supposed to be as comprehensible to human beings as those generated from human heuristics. To this end, many aspects of interpretabil­ ity of fuzzy systems have been discussed, which must be taken into account in the data-driven fuzzy rule generation. In this way, fuzzy rules generated from data are intelligible to human users and therefore, knowledge about unknown systems can be extracted.

Recently, increasing interest has been shown in applying the concept of Pareto-optimality to machine learning, particularly inspired by the successful developments in evolutionary multi-objective optimization. It has been shown that the multi-objective approach to machine learning is particularly successful to improve the performance of the traditional single objective machine learning methods, to generate highly diverse multiple Pareto-optimal models for constructing ensembles models and, and to achieve a desired trade-off between accuracy and interpretability of neural networks or fuzzy systems. This monograph presents a selected collection of research work on multi-objective approach to machine learning, including multi-objective feature selection, multi-objective model selection in training multi-layer perceptrons, radial-basis-function networks, support vector machines, decision trees, and intelligent systems.