Wearable Bioimpedance-Based Deep Learning Techniques for Live Fish Health Assessment under Waterless and Low-Temperature Conditions
(1) Background: At present, physiological stress detection technology is a critical means for precisely evaluating the comprehensive health status of live fish. However, the commonly used biochemical tests are invasive and time-consuming and cannot simultaneously monitor and dynamically evaluate mul...
Published in: | Sensors |
---|---|
Main Authors: | , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2023
|
Subjects: | |
Online Access: | https://doi.org/10.3390/s23198210 https://doaj.org/article/ef87a0271db74f4394f71ae5e781c8aa |
id |
ftdoajarticles:oai:doaj.org/article:ef87a0271db74f4394f71ae5e781c8aa |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:ef87a0271db74f4394f71ae5e781c8aa 2023-11-12T04:27:41+01:00 Wearable Bioimpedance-Based Deep Learning Techniques for Live Fish Health Assessment under Waterless and Low-Temperature Conditions Yongjun Zhang Longxi Chen Huanhuan Feng Xinqing Xiao Marina A. Nikitina Xiaoshuan Zhang 2023-09-01T00:00:00Z https://doi.org/10.3390/s23198210 https://doaj.org/article/ef87a0271db74f4394f71ae5e781c8aa EN eng MDPI AG https://www.mdpi.com/1424-8220/23/19/8210 https://doaj.org/toc/1424-8220 doi:10.3390/s23198210 1424-8220 https://doaj.org/article/ef87a0271db74f4394f71ae5e781c8aa Sensors, Vol 23, Iss 8210, p 8210 (2023) live fish health monitoring waterless and low-temperature conditions deep learning wearable bioimpedance monitoring stress evaluation Chemical technology TP1-1185 article 2023 ftdoajarticles https://doi.org/10.3390/s23198210 2023-10-15T00:35:14Z (1) Background: At present, physiological stress detection technology is a critical means for precisely evaluating the comprehensive health status of live fish. However, the commonly used biochemical tests are invasive and time-consuming and cannot simultaneously monitor and dynamically evaluate multiple stress levels in fish and accurately classify their health levels. The purpose of this study is to deploy wearable bioelectrical impedance analysis (WBIA) sensors on fish skin to construct a deep learning-based stress dynamic evaluation model for precisely estimating their accurate health status. (2) Methods: The correlation of fish (turbot) muscle nutrients and their stress indicators are calculated using grey relation analysis (GRA) for allocating the weight of the stress factors. Next, WBIA features are sieved using the maximum information coefficient (MIC) in stress trend evaluation modeling, which is closely related to the key stress factors. Afterward, a convolutional neural network (CNN) is utilized to obtain the features of the WBIA signals. Then, the long short-term memory (LSTM) method learns the stress trends with residual rectification using bidirectional gated recurrent units (BiGRUs). Furthermore, the Z-shaped fuzzy function can accurately classify the fish health status by the total evaluated stress values. (3) Results: The proposed CNN-LSTM-BiGRU-based stress evaluation model shows superior accuracy compared to the other machine learning models (CNN-LSTM, CNN-GRU, LSTM, GRU, SVR, and BP) based on the MAPE, MAE, and RMSE. Moreover, the fish health classification under waterless and low-temperature conditions is thoroughly verified. High accuracy is proven by the classification validation criterion (accuracy, F1 score, precision, and recall). (4) Conclusions: the proposed health evaluation technology can precisely monitor and track the health status of live fish and provides an effective technical reference for the field of live fish vital sign detection. Article in Journal/Newspaper Turbot Directory of Open Access Journals: DOAJ Articles Sensors 23 19 8210 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
live fish health monitoring waterless and low-temperature conditions deep learning wearable bioimpedance monitoring stress evaluation Chemical technology TP1-1185 |
spellingShingle |
live fish health monitoring waterless and low-temperature conditions deep learning wearable bioimpedance monitoring stress evaluation Chemical technology TP1-1185 Yongjun Zhang Longxi Chen Huanhuan Feng Xinqing Xiao Marina A. Nikitina Xiaoshuan Zhang Wearable Bioimpedance-Based Deep Learning Techniques for Live Fish Health Assessment under Waterless and Low-Temperature Conditions |
topic_facet |
live fish health monitoring waterless and low-temperature conditions deep learning wearable bioimpedance monitoring stress evaluation Chemical technology TP1-1185 |
description |
(1) Background: At present, physiological stress detection technology is a critical means for precisely evaluating the comprehensive health status of live fish. However, the commonly used biochemical tests are invasive and time-consuming and cannot simultaneously monitor and dynamically evaluate multiple stress levels in fish and accurately classify their health levels. The purpose of this study is to deploy wearable bioelectrical impedance analysis (WBIA) sensors on fish skin to construct a deep learning-based stress dynamic evaluation model for precisely estimating their accurate health status. (2) Methods: The correlation of fish (turbot) muscle nutrients and their stress indicators are calculated using grey relation analysis (GRA) for allocating the weight of the stress factors. Next, WBIA features are sieved using the maximum information coefficient (MIC) in stress trend evaluation modeling, which is closely related to the key stress factors. Afterward, a convolutional neural network (CNN) is utilized to obtain the features of the WBIA signals. Then, the long short-term memory (LSTM) method learns the stress trends with residual rectification using bidirectional gated recurrent units (BiGRUs). Furthermore, the Z-shaped fuzzy function can accurately classify the fish health status by the total evaluated stress values. (3) Results: The proposed CNN-LSTM-BiGRU-based stress evaluation model shows superior accuracy compared to the other machine learning models (CNN-LSTM, CNN-GRU, LSTM, GRU, SVR, and BP) based on the MAPE, MAE, and RMSE. Moreover, the fish health classification under waterless and low-temperature conditions is thoroughly verified. High accuracy is proven by the classification validation criterion (accuracy, F1 score, precision, and recall). (4) Conclusions: the proposed health evaluation technology can precisely monitor and track the health status of live fish and provides an effective technical reference for the field of live fish vital sign detection. |
format |
Article in Journal/Newspaper |
author |
Yongjun Zhang Longxi Chen Huanhuan Feng Xinqing Xiao Marina A. Nikitina Xiaoshuan Zhang |
author_facet |
Yongjun Zhang Longxi Chen Huanhuan Feng Xinqing Xiao Marina A. Nikitina Xiaoshuan Zhang |
author_sort |
Yongjun Zhang |
title |
Wearable Bioimpedance-Based Deep Learning Techniques for Live Fish Health Assessment under Waterless and Low-Temperature Conditions |
title_short |
Wearable Bioimpedance-Based Deep Learning Techniques for Live Fish Health Assessment under Waterless and Low-Temperature Conditions |
title_full |
Wearable Bioimpedance-Based Deep Learning Techniques for Live Fish Health Assessment under Waterless and Low-Temperature Conditions |
title_fullStr |
Wearable Bioimpedance-Based Deep Learning Techniques for Live Fish Health Assessment under Waterless and Low-Temperature Conditions |
title_full_unstemmed |
Wearable Bioimpedance-Based Deep Learning Techniques for Live Fish Health Assessment under Waterless and Low-Temperature Conditions |
title_sort |
wearable bioimpedance-based deep learning techniques for live fish health assessment under waterless and low-temperature conditions |
publisher |
MDPI AG |
publishDate |
2023 |
url |
https://doi.org/10.3390/s23198210 https://doaj.org/article/ef87a0271db74f4394f71ae5e781c8aa |
genre |
Turbot |
genre_facet |
Turbot |
op_source |
Sensors, Vol 23, Iss 8210, p 8210 (2023) |
op_relation |
https://www.mdpi.com/1424-8220/23/19/8210 https://doaj.org/toc/1424-8220 doi:10.3390/s23198210 1424-8220 https://doaj.org/article/ef87a0271db74f4394f71ae5e781c8aa |
op_doi |
https://doi.org/10.3390/s23198210 |
container_title |
Sensors |
container_volume |
23 |
container_issue |
19 |
container_start_page |
8210 |
_version_ |
1782341193584082944 |