Echo State Network Optimization using Hybrid-Structure Based Gravitational Search Algorithm with Square Quadratic Programming for Time Series Prediction
Zohaib Ahmad School of Electronics and Information Engineering, Beijing University of Technology, China This email address is being protected from spambots. You need JavaScript enabled to view it. |
Muhammad Qasim Memon Department of Information and Computing, University of Sufism and Modern Sciences, Pakistan This email address is being protected from spambots. You need JavaScript enabled to view it. |
Aasma Memon School of Management and Economics, Beijing University of Technology, China This email address is being protected from spambots. You need JavaScript enabled to view it. |
Parveen Munshi Faculty of Education, University of Sufism and Modern Sciences, Pakistan This email address is being protected from spambots. You need JavaScript enabled to view it. |
Muhammad jaffar Memon Civil Engineering Department, SZAB Campus, Mehran University of Engineering and Technology, Pakistan This email address is being protected from spambots. You need JavaScript enabled to view it. |
Abstract: The Echo-State Network (ESN) is a robust recurrent neural network and a generalized form of classical neural networks in time-series model designs. ESN inherits a simple approach for training and demonstrates the high computational capability to solve non-linear problems. However, input weights and the reservoir's internal weights are pre-defined when optimizing with only the output weight matrix. This paper proposes a Hybrid Gravitational Search Algorithm (HGSA) to compute ESN output weights. In Gravitational Search Algorithm (GSA), Square Quadratic Programming (SQP) is united as a local search strategy to raise the standard GSA algorithm's efficiency. Later, an HGSA-SQP and the validation data set to establish the relation configuration of the ESN output weights. Experimental results indicate that the proposed configuration of HGSA-SQP-ESN is more efficient than the other conventional models of ESN with the minimum generalization error.
Keywords: Echo state network, hybrid gravitational search algorithm, network configuration optimization, time series prediction.
Received April 10, 2022; accepted April 28, 2022