Genetic algorithms in logic tree decision modeling |
| |
| Institution: | 1. Department of Information Systems, College of Business Administration, San Francisco State University, 1600 Holloway Avenue, San Francisco, CA 94132, USA;2. Owen Graduate School of Management, Vanderbilt University, Nashville, TN 37203, USA;3. Department of Accounting and Business Information Systems, The University of Melbourne, Victoria, 3010 Australia;1. Graduate School of Engineering Science, Osaka University, Japan;2. Department of Biomedical Statistics and Bioinformatics, Kyoto University Graduate School of Medicine, Japan;1. Department of Neurology, The First Hospital Affiliated to the Chinese PLA General Hospital, 51 Fucheng Avenue, Haidian District, Beijing 100048, China;2. Oasi Institute for Research on Mental Retardation and Brain Aging (IRCCS), Via Conte Ruggero 73, 94018 Troina (EN), Italy;1. Universidad de Castilla-La Mancha, Facultad de Educación de Toledo, Campus Fábrica de Armas, Avda. Carlos III, s/n, 45071, Toledo, Spain;2. Universidad Complutense de Madrid, Facultad de Psicología, Campus de Somosaguas, 28223, Pozuelo de Alarcón, Madrid, Spain;1. Department of Animal Science, Universidade Federal de Viçosa, Av. P.H. Holfs, 36570-000 Viçosa, Brazil;2. Department of General Biology, Universidade Federal de Viçosa, Av. P.H. Holfs, 36570-000 Viçosa, Brazil;3. Laboratory of Animal Science, Universidade Estadual do Norte Fluminense, 28013-602 Campos dos Goytacazes, Brazil;4. Embrapa Florestas/UFV, Estrada da Ribeira, km 111, 83411-000 Colombo, Brazil |
| |
| Abstract: | An important approach to decision modeling is the induction of knowledge structures—such as rules, trees, and graphs—from empirical data describing previous conditions and the resulting decisions. We examine here a specific knowledge structure, a logic tree, in which the conditions are leaves, the decision is the root, and the intermediate nodes are logical operators. We then use genetic algorithms (GAs) to construct logic trees that best represent the correspondence between conditions and decisions described by the empirical data. We also investigate an important characteristic of the GA search, the fitness distance correlation. Finally, we comment on the usefulness of GAs in knowledge modeling. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
