基于和声搜索算法的超参数优化方法，提高一维卷积神经网络人体呼吸模式识别系统的性能。

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

机构信息

Department of Computer Engineering, Gachon University, Seongnam 13120, Korea.

Department of Energy IT, Gachon University, Seoongnam 13120, Korea.

出版信息

Sensors (Basel). 2020 Jul 1;20(13):3697. doi: 10.3390/s20133697.

DOI:10.3390/s20133697

PMID:32630344

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC7374394/

Abstract

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.

摘要

在这项研究中，我们提出了一种方法，通过使用调和搜索算法，找到最优的超参数组合，以提高一维卷积神经网络（CNN）中呼吸模式识别的准确性。该方法旨在与一维 CNN 集成。在实验中，我们将一维 CNN 的卷积层的深度、每层的核数和大小以及密集层的神经元数作为优化的超参数。实验结果表明，所提出的方法平均提供了约 96.7%的五种呼吸模式识别率，比现有方法提高了约 2.8%。此外，在之前的研究中，获得最优超参数组合所需的迭代次数为 200 万次。相比之下，所提出的方法仅需 3652 次迭代。