Learning nonlinear multiregression networks based on evolutionary computation

Kwong-Sak Leung1, Man-Leung Wong2, Wai Lam3, Zhenyuan Wang4, Kebin Xu1
1Department of Computer Science and Engineering, Chinese University of Hong Kong, New Territories, Hong Kong, China
2Department of Information Systems, Lingnan University, Hong Kong, China
3Department of Systems Engineering and Engineering Management, Chinese University of Hong Kong, New Territories, Hong Kong, China
4Department of Mathematics, University of Nebraska, Omaha, NE, USA

Tóm tắt

This paper describes a novel knowledge discovery and data mining framework dealing with nonlinear interactions among domain attributes. Our network-based model provides an effective and efficient reasoning procedure to perform prediction and decision making. Unlike many existing paradigms based on linear models, the attribute relationship in our framework is represented by nonlinear nonnegative multiregressions based on the Choquet integral. This kind of multiregression is able to model a rich set of nonlinear interactions directly. Our framework involves two layers. The outer layer is a network structure consisting of network elements as its components, while the inner layer is concerned with a particular network element modeled by Choquet integrals. We develop a fast double optimization algorithm (FDOA) for learning the multiregression coefficients of a single network element. Using this local learning component and multiregression-residual-cost evolutionary programming (MRCEP), we propose a global learning algorithm, called MRCEP-FDOA, for discovering the network structures and their elements from databases. We have conducted a series of experiments to assess the effectiveness of our algorithm and investigate the performance under different parameter combinations, as well as sizes of the training data sets. The empirical results demonstrate that our framework can successfully discover the target network structure and the regression coefficients.

Từ khóa

#Evolutionary computation #Data mining #Genetic programming #Predictive models #Decision making #Databases #Training data #Problem-solving #Terrorism #Councils

Tài liệu tham khảo

wang, 1998, a new nonlinear regression model used for multisource–multisensor data fusion: an application of nonlinear integrals and genetic algorithms, Proc Fusion, 299 10.1016/S0888-613X(00)00048-7 10.1007/BFb0069178 10.1887/0750306645/b877c10 pearl, 1988, Probabilistic Reasoning in Intelligent Systems Networks of Plausible Inference 10.1016/0165-0114(89)90194-2 10.1016/S0165-0114(98)00220-6 10.1016/S0888-613X(96)00078-3 10.1007/978-1-4757-5303-5 schewefel, 1981, Numerical Optimization of Computer Models fogel, 1966, Artificial Intelligence Through Simulated Evolution friedman, 2000, gaussian process networks, Proc 16th CUAI, 211 10.1109/34.748825 10.1080/01621459.1981.10477729 goldberg, 1989, Genetic Algorithms in Search Optimization and Machine Learning 10.1109/FUZZY.1995.409673 10.1016/S0165-0114(97)00168-1 10.1007/s001820050125 halmos, 1967, Measure Theory holland, 1992, Adaptations in Natural and Artificial Systems, 10.7551/mitpress/1090.001.0001 jensen, 1996, An Introduction to Bayesian Networks 10.1016/0165-0114(94)90008-6 10.1109/4235.585888 bäck back, 1996, Evolutionary Algorithms in Theory and Practice Evolution Strategies Evolutionary Programming Genetic Algorithms, 10.1093/oso/9780195099713.001.0001 mori, 1989, an analysis of evaluation model using fuzzy measure and the choquet integral, Proc 5th Fuzzy Syst Symp, 207 fayyad, 1996, Advances in Knowledge Discovery and Data Mining cormen, 1990, Introduction to Algorithms 10.1016/0022-247X(91)90213-J 10.1109/72.265956 fogel, 2000, Evolutionary Computation Toward a New Philosophy of Machine Intelligence angeline, 1994, genetic programming and emergent intelligent, Advances in Genetic Programming, 75 fogel, 1998, revisiting evolutionary programming, Proc AeroSense Aerospace/Defense Sensing and Controls angeline, 1993, Evolutionary algorithms and emergent intelligence kwon, 2000, a hierarchical subjective evaluation model using nonmonotonic measures and the choquet integral, Fuzzy Measures and Integrals Theory and Applications, 375 koza, 1994, Genetic Programming II Automatic Discovery of Reusable Programs koza, 1992, Genetic Programming On the Programming of Computers by Means of Natural Selection 10.1109/34.667882 xu, 1998, using a new type of nonlinear integral for multiregression: an application of evolutionary algorithms in data mining, Proc IEEE ICSMC, 2326 koza, 1999, Genetic Programming III Darwinian Invention and Problem Solving 10.1137/S1064827595296574 10.1109/34.537345