Hyperparameter Optimization Method Based on Harmony Search Algorithm to Improve Performance of 1D CNN Human Respiration Pattern Recognition System

Sensors

Seong-Hoon Kim¹  Gi-Tae Han¹  ZongWoo Geem² 

[1] Department of Computer Engineering, Gachon University, Seongnam 13120, Korea;Department of Energy IT, Gachon University, Seoongnam 13120, Korea;

关键词: 1D convolutional neural network;    ultra-wideband radar;    respiration patterns;    harmony search algorithm;    hyperparameter optimization;   

DOI  :  10.3390/s20133697

来源: DOAJ

【 摘 要 】

In this study, we propose a method to find an optimal combination of hyperparameters to improve the accuracy of respiration pattern recognition in a 1D (Dimensional) convolutional neural network (CNN). The proposed method is designed to integrate with a 1D CNN using the harmony search algorithm. In an experiment, we used the depth of the convolutional layer of the 1D CNN, the number and size of kernels in each layer, and the number of neurons in the dense layer as hyperparameters for optimization. The experimental results demonstrate that the proposed method provided a recognition rate for five respiration patterns of approximately 96.7% on average, which is an approximately 2.8% improvement over an existing method. In addition, the number of iterations required to derive the optimal combination of hyperparameters was 2,000,000 in the previous study. In contrast, the proposed method required only 3652 iterations.

【 授权许可】

Unknown