High-order neural network based on a hybrid firefly flower pollination algorithm
Rongguo Qu
College of Science, Xi’an Polytechnic University
Yunlong Liu
College of Science, Xi’an Polytechnic University
Qingmei Dong
College of Science, Xi’an Polytechnic University
Jing Zhao
College of Science, Xi’an Polytechnic University
Manyuan Li
College of Science, Xi’an Polytechnic University
Qinwei Fan
College of Science, Xi’an Polytechnic University
DOI: https://doi.org/10.59429/esta.v11i3.7341
Keywords: High order neural network, Firefly algorithm, Flower pollination algorithm
Abstract
Pi Sigma neural network is a kind of high-order feedforward neural network, which is characterized by fast convergence speed and strong nonlinear mapping ability. However, for the growing large dataset, the traditional Pi Sigma neural network suffers from the problems of complex network structure, difficulty in determining weights, and low learning efficiency. Therefore, this paper proposes a hybrid heuristic algorithm that combines the flower pollination algorithm with the firefly algorithm to optimize the weights and biases of the Pi Sigma neural network. The experimental results show that the optimized neural network has good performance in many aspects.
References
[1] Sharma R., Pachori R.B., Sircar, P. Seizures classification based on higher-order statistics and deep neural network[J]. Biomedical Signal Processing and Control 59 (2020): 101921.
[2] Nayak S.C., Misra B.B., Dehuri S., Hybridization of the higher order neural networks with the evolutionary optimization algorithms - An application to financial time series forecasting. Advances in Machine Learning for Big Data Analysis[J]. Singapore: Springer Nature Singapore, 2022. 119-144.
[3] Kang Q., Fan Q. W. Zurada J. M. Huang. T.W. A Pruning Algorithm with Relaxed Conditions for HighOrder Neural Networks based on Smoothing Group L1/2Regularization and Adaptive Momentum[J]. Knowledge Based Systems 257 (2022) 109858.
[4] Ivakhnenko A.G. Polynomial theory of complex systems[J]. IEEE transactions on Systems, Man, and Cybernetics 4 (1971): 364-378.
[5] Giles C.L., Maxwell T. Learning, invariance, and generalization in highorder neural networks[J]. Applied optics 26.23 (1987): 4972-4978.
[6] Shin Y., Ghosh J. The Pi Sigma network: An efficient higher-order neural network for pattern classification and function approximation[J]. IJCNN-91-Seattle international joint conference on neural networks. Vol.1. IEEE, 1991.
[7] Egrioglu E., Bas E. Modified pi sigma artificial neural networks for forecasting[J]. Granular Computing 8.1 (2023): 131-135.
[8] Bas E., Egrioglu E., Tunc T. Multivariate Picture Fuzzy Time Series: New Definitions and a New Forecasting Method Based on Pi Sigma Artificial Neural Network[J]. Computational Economics 61.1(2023): 139- 164.
[9] Dash R., Rautray R., Dash R. Utility of a Shuffled Differential Evolution algorithm in designing of a Pi Sigma Neural Network based predictor model[J]. Applied Computing and Informatics 19.1/2 (2023): 22-40.
[10] Balasubramanian K., Ananthamoorthy N.P., Ramya K. An approach to classify white blood cells using convolutional neural network optimized by particle swarm optimization algorithm[J]. Neural Computing and Applications 34.18 (2022): 16089-16101.
[11] Gupta V., Gupta M. Improved PSO Algorithm-Based Convolutional Neural Network Approach for Ship Detection and Classifications[J]. SN Computer Science 3.4 (2022): 318.
[12] Yang X.S.. Flower pollination algorithm for global optimization[J]. International conference on unconventional computing and natural computation. Berlin, Heidelberg: Springer Berlin Heidelberg, 2012.
[13] Fister I., Fister Jr I., Yang X.S., Brest J. A comprehensive review of firefly algorithms[J]. Swarm and evolutionary computation 13 (2013): 34- 46.
[14] Abdalkareem Z.A., Al-Betar M.A., Amir A., Ehkan P., Hammouri A.I., Salman O.H. Discrete flower pollination algorithm for patient admission scheduling problem[J]. Computers in biology and medicine 141 (2022): 105007.
[15] Gupta S.K., Dalal A. Optimisation of hourly plants water discharges in hydrothermal scheduling using the flower pollination algorithm[J]. International Journal of Ambient Energy 44.1 (2023): 686-692.9
[16] Kaya C.B., Ebubekir K.A. Y.A. A novel approach based to neural network and flower pollination algorithm to predict number of COVID-19 cases[J]. Balkan Journal of Electrical and Computer Engineering 9.4 (2021): 327-336.
[17] Guo Z., Suo R., Zhang X. An improved flower pollination algorithm based on logistic chaotic mapping and natural mutation[J]. Proceedings of the 7th International Conference on Big Data and Computing. 2022.
[18] Cai C., Nie Y., Wu H., Fu M., Meng X. Pattern Synthesis of Antenna Array Based on Improved Flower Pollination Algorithm[J]. Proceedings of the 5th International Conference on Computer Science and Software Engineering. 2022.
[19] Peng X., Yan R., Zhao B.,et al. Fast Low-rank Representation based Spatial Pyramid Matching for Image Classification[J]. Knowledge-Based Systems, 2015, 90(C):14-22.