Reliable multiclass cancer classification of microarray gene expression profiles using an improved wavelet neural network |
| |
| Authors: | Zarita Zainuddin Pauline Ong |
| |
| Affiliation: | 1. Department of Food Science and Biotechnology, Kangwon National University, Chuncheon 24341, Republic of Korea;2. STR Biotech Co., LTD, Chuncheon 24234, Republic of Korea;3. Department of Biomedical Sciences, Seoul National University College of Medicine, Seoul 08826, Republic of Korea;4. Department of Food Science and Biotechnology, CHA University, Kyonggi 13488, Republic of Korea;5. Department of Food Science and Nutrition, Hallym University, Chuncheon 24252, Republic of Korea;1. School of Computer Engineering and Technology, Shanghai University, Shanghai, China;2. Faculty of Human Sciences, Waseda University, Tokorozawa, Japan;1. Laboratório de Toxicologia Experimental, Departamento de Análises Clínicas e Toxicológicas da Faculdade de Farmácia, Universidade Federal de Minas Gerais, Brazil;2. Laboratório de Patologia Comparada, Departamento de Patologia Geral, Instituto de Ciências Biológicas, Universidade Federal de Minas Gerais, Brazil;3. Centro Bioanalítico de Medicamentos da Faculdade de Farmácia, Universidade Federal do Rio Grande do Sul, Brazil;4. Departamento de Química, Instituto de Ciências Exatas, Universidade Federal de Minas Gerais, Brazil;1. Intertek Cantox, Suite 308, 2233 Argentia Rd., Mississauga, Ontario, Canada L5N 2X7;2. Intertek Cantox, Room 1036, Building A8, Cody Technology Park, Ively Road, Farnborough, Hampshire GU14 0LX, UK;3. Eurofins|Product Safety Laboratories, 2394 Highway 130, Dayton, NJ 08810, United States;1. School of Pharmacy, Kaohsiung Medical University, Kaohsiung 80708, Taiwan;2. PhD Program in Toxicology, Kaohsiung Medical University, Kaohsiung 80708, Taiwan;3. National Environmental Health Research Center, National Health Research Institutes, Miaoli County 35053, Taiwan |
| |
| Abstract: | Properly designing a wavelet neural network (WNN) is crucial for achieving the optimal generalization performance. In this paper, two different approaches were proposed for improving the predictive capability of WNNs. First, the types of activation functions used in the hidden layer of the WNN were varied. Second, the proposed enhanced fuzzy c-means clustering algorithm—specifically, the modified point symmetry-based fuzzy c-means (MSFCM) algorithm—was employed in selecting the locations of the translation vectors of the WNN. The modified WNN was then applied to heterogeneous cancer classification using four different microarray benchmark datasets. The comparative experimental results showed that the proposed methodology achieved an almost 100% classification accuracy in multiclass cancer prediction, leading to superior performance with respect to other clustering algorithms. Subsequently, performance comparisons with other classifiers were made. An assessment analysis showed that this proposed approach outperformed most of the other classifiers. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
