Extreme Learning Machine (ELM) and Regularized Extreme Learning Machine (RELM) have advantages of fast training speed and good generalization. However, ELM/RELM often needs numerous number of hidden layer nodes to get better performance. The superabundant nodes in hidden layer maybe lead to low running speed. Thus it is not feasible to use ELM in some fields that require high speed algorithms. Therefore, in this paper, we propose an Improved ELM/RELM Optimized based on Chaos Particle Swarm Optimization (CPSO-ELM/RELM) to reduce the number of hidden layer nodes, but still maintain a desirable accuracy. At the same time, it lowers the running speed compared with other algorithms. To verify the application of this method, we design numerous experiments for ELM and RRELM. Their simulation shows that the approach improves the speed of the algorithms, and the accuracy is still high. This makes it possible to use improved CPSO-ELM/RELM in some system with high real-time requirements.
References
Huang, G. B., Zhu, Q. Y., & Siew, C. K. (2006). Extreme learning machine: theory and applications. Neurocomputing, 70(1), 489-501.
Hu, F. , Wang, L. , Wang, S. , Liu, X. , & He, G. . (2016). A human body posture recognition algorithm based on bp neural network for wireless body area networks. China Communications, 13(8), 198-208.
Argyriou, A., Baldassarre, L., Micchelli, C. A., & Pontil, M. (2013). On sparsity inducing regularization methods for machine learning. Researchgate Net, 205-216.
Deng, W. , Zheng, Q. , & Chen, L. . (2009). Regularized extreme learning machine. 2009 IEEE SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE AND DATA MINING, 389-395.
Zhang, Y. B., & Xing, L. Z. (2016). Algorithm of speech endpoint detection based on wavelet analysis and pso-elm. Journal of North University of China.
Chen, S., Yue, S., & Wu, M. (2016). Application of PSO-ELM in electronic system fault diagnosis. IEEE International Conference on Prognostics & Health Management.
Liu, Y., Zhong, P., Zhang, M., Jin, G. U., & Kong, Y. (2013). Empirical formulae comparison for number selection of hidden layer's nodes in ann model applied for reservoir optimal operation. Water Power.
Huang, G. B., Zhou, H., Ding, X., & Rui, Z. (2012). Extreme learning machine for regression and multiclass classification. IEEE Transactions on Systems Man & Cybernetics Part B, 42(2), 513-529.
Wang, S., Wang, Y. X., Shan, H. L., & Shi, C. X. (2018). Multimodal computer image recognition based on depth neural network. Cluster Computing(45), 1-7.
Ye, Q. , Yuan, S. , & Kim, T. K. . (2016). Spatial attention deep net with partial pso for hierarchical hybrid hand pose estimation.
Shi, Yuhui, Eberhart, & Russell, C. (1998). Parameter Selection in Particle Swarm Optimization. Evolutionary Programming VII.
Tang, X., Ling, Z., Cai, J., & Li, C. (2010). Short communication: multi-fault classification based on support vector machine trained by chaos particle swarm optimization. Knowledge-Based Systems, 23(5), 486-490.
Wang, S., Wang, Y. X., Shan, H. L., & Shi, C. X. (2018). Multimodal computer image recognition based on depth neural network. Cluster Computing(45), 1-7.
