Artificial NN is an intelligent model for information processing by simulating the organization and mechanism of the nervous system of the brain. Thanks to its strong self-learning ability, artificial NN can liberate people's labor force to a large extent, so it has been widely studied and alied. The theoretical study of artificial NN can effectively explain the alication principle and potential problems of NN, so that it can be effectively improved and developed. Therefore, the main purpose of this paper is to study the optimization method of person recognition (PR) based on RBF network. In this paper, the damping coefficients of RBF networks with uniform center distribution are studied. This stochastic learning method is an important sulement to how to determine the center and limiting factor of the RBF of the NN, and can also improve the training efficiency of the network. The main research results of this paper are developed by analyzing the convergence of stochastic RBFNN and constructing corresponding models and algorithms. Compared with other algorithms, the results show that the ARBFNN algorithm can make the RBFNN obtain a smaller training error, improve the generalization ability of the network, and have the ability to deal with large data sets and fast convergence. Recognition is more convenient and quicker.

Pan Xiao. Person Recognition Optimization Method Relying on Radial Basis Function Network. International Journal of Neural Network (2021), Vol. 2, Issue 3: 9-18. https://doi.org/10.38007/NN.2021.020302.

[1] Safavi A, Esteki M H, Mirvakili S M, et al. Comparison of Back Propagation Network and RBF Network in Departure from Nucleate Boiling Ratio (DNBR) Calculation. Kerntechnik. (2020) 85(1):15-25. https://doi.org/10.1515/kern-2020-850105

[2] Swpu P. Implementation of Multilayer Perceptron (MLP) and RBF (RBF) Nns to Predict Solution Gas-Oil Ratio of Crude Oil Systems. Petroleum. (2020) 6(1):80-91. https://doi.org/10.1016/j.petlm.2018.12.002

[3] Caglar B. Hybrid RBFNNs for Urban Traffic Signal Control. Journal of Engineering Research. (2020) 8(4):153-168.

[4] Sarker G, Ghosh S. Biometric-Based Unimodal and Multimodal Person Identification with CNN Using Optimal Filter Set. Innovations in Systems and Software Engineering. (2021) 17(2):157-166. https://doi.org/10.1007/s11334-020-00381-4

[5] Subbotin S. Radial-Basis Function NN Synthesis on the Basis of Decision Tree. Optical Memory and NNs. (2020) 29(1):7-18. https://doi.org/10.3103/S1060992X20010051

[6] Algermissen S, Hrnlein M. Person Identification by Footstep Sound Using Convolutional NNs. Alied Mechanics. (2021) 2(2):257-273. https://doi.org/10.3390/applmech2020016

[7] Mokhtari M H, Deilami K, Moosavi V. Spectral Enhancement of Landsat OLI Images By Using Hyperion Data: A Comparison between Multilayer Perceptron and RBF Networks. Earth Science Informatics. (2020) 13(2):1-15. https://doi.org/10.1007/s12145-020-00451-y

[8] Samson M, Deutsch C V. A Hybrid Estimation Technique Using Elliptical Radial Basis NNs and Cokriging. Mathematical Geosciences. (2021) 54(3):573-591. https://doi.org/10.1007/s11004-021-09969-3

[9] Yasin Q, M Majdański, Sohail G M, et al. Fault and Fracture Network Characterization Using Seismic Data: a Study Based On NN Models Assessment. Geomechanics and Geophysics for Geo-Energy and Geo-Resources. (2021) 8(2):1-26. https://doi.org/10.1007/s40948-022-00352-y

[10] Thor M, Kulvicius T, Manoonpong P. Generic Neural Locomotion Control Framework for Legged Robots. IEEE Transactions on NNs and Learning Systems. (2020) (99):1-13.

[11] Ghazvini A, Abdullah S, Hasan M K, et al. Crime Spatiotemporal Prediction with Fused Objective Function in Time Delay NN. IEEE Access. (2020) (99):1-1. https://doi.org/10.1109/ACCESS.2020.3002766

[12] Amirian M, Schwenker F. RBF Networks for Convolutional NNs to Learn Similarity Distance Metric and Improve Interpretability. IEEE Access. (2020) (99):1-1. https://doi.org/10.1109/ACCESS.2020.3007337

[13] Amma N B, Valarmathi P. ORaBaN: an Optimized Radial Basis Neuro Framework for Anomaly Detection in Large Networks. International Journal of Information Technology. (2021) 14(5):2497-2503. https://doi.org/10.1007/s41870-022-00991-0

[14] Hamza S, Ayed Y B. toward improving person identification using the ElectroCardioGram (ECG) signal based on non-fiducial features. Multimedia Tools and Alications. (2021) 81(13):18543-18561. https://doi.org/10.1007/s11042-022-12244-0

[15] Hameed D H, Mahmood M K. Person Identification Based on Different Colour Models Iris Biometric and Contourlet Transform. Journal of Engineering and Sustainable Development. (2020) 24(1):15-33. https://doi.org/10.31272/jeasd.24.1.2

[16] Kenshi, Saho, Keisuke, et al. Person Identification Based on Micro-Doler Signatures of Sit-to-Stand and Stand-to-Sit Movements Using a Convolutional NN. IEEE Sensors Letters. (2020) 4(3):1-4. https://doi.org/10.1109/LSENS.2020.2975219

[17] Castiglione A, Nai M, Ricciardi S. Trustworthy Method for Person Identification in IIoT Environments by Means of Facial Dynamics. IEEE Transactions on Industrial Informatics. (2020) (99):1-1.

[18] Curca G C, Diac I. Forensic Anthropology from Individual Identification to Person Identification. A Review. Romanian Journal of Legal Medicine. (2020) 28(1):28-39. https://doi.org/10.4323/rjlm.2020.28