Cargando…
Hyperparameter Optimization Method Based on Harmony Search Algorithm to Improve Performance of 1D CNN Human Respiration Pattern Recognition System
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...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7374394/ https://www.ncbi.nlm.nih.gov/pubmed/32630344 http://dx.doi.org/10.3390/s20133697 |
_version_ | 1783561688879988736 |
---|---|
author | Kim, Seong-Hoon Geem, Zong Woo Han, Gi-Tae |
author_facet | Kim, Seong-Hoon Geem, Zong Woo Han, Gi-Tae |
author_sort | Kim, Seong-Hoon |
collection | PubMed |
description | 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. |
format | Online Article Text |
id | pubmed-7374394 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2020 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-73743942020-08-06 Hyperparameter Optimization Method Based on Harmony Search Algorithm to Improve Performance of 1D CNN Human Respiration Pattern Recognition System Kim, Seong-Hoon Geem, Zong Woo Han, Gi-Tae Sensors (Basel) Article 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. MDPI 2020-07-01 /pmc/articles/PMC7374394/ /pubmed/32630344 http://dx.doi.org/10.3390/s20133697 Text en © 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Kim, Seong-Hoon Geem, Zong Woo Han, Gi-Tae Hyperparameter Optimization Method Based on Harmony Search Algorithm to Improve Performance of 1D CNN Human Respiration Pattern Recognition System |
title | Hyperparameter Optimization Method Based on Harmony Search Algorithm to Improve Performance of 1D CNN Human Respiration Pattern Recognition System |
title_full | Hyperparameter Optimization Method Based on Harmony Search Algorithm to Improve Performance of 1D CNN Human Respiration Pattern Recognition System |
title_fullStr | Hyperparameter Optimization Method Based on Harmony Search Algorithm to Improve Performance of 1D CNN Human Respiration Pattern Recognition System |
title_full_unstemmed | Hyperparameter Optimization Method Based on Harmony Search Algorithm to Improve Performance of 1D CNN Human Respiration Pattern Recognition System |
title_short | Hyperparameter Optimization Method Based on Harmony Search Algorithm to Improve Performance of 1D CNN Human Respiration Pattern Recognition System |
title_sort | hyperparameter optimization method based on harmony search algorithm to improve performance of 1d cnn human respiration pattern recognition system |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7374394/ https://www.ncbi.nlm.nih.gov/pubmed/32630344 http://dx.doi.org/10.3390/s20133697 |
work_keys_str_mv | AT kimseonghoon hyperparameteroptimizationmethodbasedonharmonysearchalgorithmtoimproveperformanceof1dcnnhumanrespirationpatternrecognitionsystem AT geemzongwoo hyperparameteroptimizationmethodbasedonharmonysearchalgorithmtoimproveperformanceof1dcnnhumanrespirationpatternrecognitionsystem AT hangitae hyperparameteroptimizationmethodbasedonharmonysearchalgorithmtoimproveperformanceof1dcnnhumanrespirationpatternrecognitionsystem |