Real-time work intensity estimation algorithm based on deep learning using heart rate and skin temperature
3
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In harsh environments where high-intensity work is performed, predicting the work intensity based on the vital signs of a worker can be useful in preventing accidents. Considering existing worker management systems are analyzed using set thresholds, they cannot resolve variables caused by individual differences. Therefore, we propose an algorithm to estimate the work intensity of workers based on their heart rate and body temperature using a deep learning-based 1D CNN-LSTM model. The proposed algorithm uses time-series signals of 60 s to accurately estimate the work intensity by considering the time-series characteristics. In addition, the proposed algorithm considers the individual differences in bio-signals by extracting and using data from the exercise and rest states of workers. To verify the performance of the proposed algorithm, we compared estimation performance factors such as model accuracy, precision, recall, and F1 score with those of various models; the results showed a high estimation accuracy of 99.96%. We believe the proposed algorithm can help minimize damage by preemptively responding to unexpected accidents that may occur at work sites by accurately estimating the work intensity based on the individual differences among workers.
Abstract
In harsh environments where high-intensity work is performed, predicting the work intensity based on the vital signs of a worker can be useful in preventing accidents. Considering existing worker management systems are analyzed using set thresholds, they cannot resolve variables caused by individual differences. Therefore, we propose an algorithm to estimate the work intensity of workers based on their heart rate and body temperature using a deep learning-based 1D CNN-LSTM model. The proposed algorithm uses time-series signals of 60 s to accurately estimate the work intensity by considering the time-series characteristics. In addition, the proposed algorithm considers the individual differences in bio-signals by extracting and using data from the exercise and rest states of workers. To verify the performance of the proposed algorithm, we compared estimation performance factors such as model accuracy, precision, recall, and F1 score with those of various models; the results showed a high estimation accuracy of 99.96%. We believe the proposed algorithm can help minimize damage by preemptively responding to unexpected accidents that may occur at work sites by accurately estimating the work intensity based on the individual differences among workers.
참고문헌 (27)
- 이민혜, "영상 인식 및 생체 신호를 이용한 운전자 졸음 감지 시스템", 한국정보통신학회논문지, 26(6), pp.859~864 (2022), 한국정보통신학회[DOI]
- A. Trnčić, "Biomedical signal analysis for automatic detection of diseases and disorders in prenatal age", 2022 11th Mediterranean Conference on Embedded Computing (MECO), pp.1~4 (2022)
- H. Hamil, "Design of a secured tele-health system based on multiple biosignals diagnosis and classification for iot application", Expert Systems, 39(4) (2022)
- 최경호, "생체신호를 통한 헬스케어 디바이스 기술 동향 연구", 한국엔터테인먼트산업학회논문지, 14(2), pp.165~176 (2020), 한국엔터테인먼트산업학회[DOI]
- 김채원, "화재경보 네트워크 활용 신변이상자 위치 파악 시스템", 한국마린엔지니어링학회지, 43(4), pp.321~327 (2019), 한국마린엔지니어링학회[DOI]
- 손남례, "유비쿼터스 헬스케어 기반 실시간 선박승무원 관리 시스템 설계 및 구현", 한국통신학회논문지, 35(3), pp.279~286 (2010), 한국통신학회
- 백승안, "심박수를 이용한 임목수확작업의 작업강도 분석", 한국산업융합학회논문집, 23(4), pp.593~601 (2020), 한국산업융합학회[DOI]
- 성지훈, "손목형 웨어러블 디바이스에서 사람의 심박변화와 활동강도를 이용한 운동 검출 방법", 정보처리학회논문지. 컴퓨터 및 통신시스템, 8(4), pp.93~102 (2019), 한국정보처리학회[DOI]
- G. Borg, "Psychophysical bases of perceived exertion", Medicine & Science in Sports & Exercise, 14(5), pp.377~381 (1982)
- 이온, "Borg 10단계 비율척도의 운동 강도 설명력에 관한 연구", 운동과학, 25(2), pp.92~99 (2016), 한국운동생리학회[DOI]
- 김도윤, "운동강도 척도(RPE)의 운동강도 기준으로서의 타당도 검사", 한국체육학회지, 45(2), pp.557~568 (2006), 한국체육학회
- 김병훈, "작업 현장에서 육체적 작업 강도를 평가하는 도구로서 Borg’s Scale과 심박 수의 비교", 한국산업보건학회지, 29(3), pp.368~374 (2019), 한국산업보건학회[DOI]
- 김정만, "심박수에 근거한 주관적 작업강도의 평가", 대한설비관리학회지, 14(3), pp.61~66 (2009), 대한설비관리학회
- Z. Yang, "As-sessment of construction workers’ labor intensity based on wearable smartphone system", Journal of Construction En-gineering and Management, 145(7) (2019)
- W. Fang, "Au-tomated detection of workers and heavy equipment on con-struction sites : a convolutional neural network approach", Advanced Engineering Informatics, 37, pp.139~149 (2018)
- S. M. Spook, "Implementing sensor technology applications for workplace health promotion : A needs assessment among workers with physically demanding work", BMC Public Health, 19(1), pp.1~9 (2019)
- S. Anwer, "Evaluation of physiological metrics as real-time measurement of physical fatigue in construction workers: State-of-the-art review", Journal of Construction Engineer-ing and Management, 147(5) (2021)
- 박상욱, "EEG를 이용한 LSTM 기반의 행동 식별 딥러닝 알고리즘", 전기학회논문지, 70(12), pp.1924~1933 (2021), 대한전기학회
- 배진경, "비정상심박 검출을 위해 영상화된 심전도 신호를 이용한 비교학습 기반 딥러닝 알고리즘", 한국정보통신학회논문지, 26(1), pp.30~40 (2022), 한국정보통신학회[DOI]
- P. Davidson, "Smartwatch-derived data and machine learning al-gorithms estimate classes of ratings of perceived exertion in runners : A pilot study", Sensors, 20(9), pp.2637~ (2020)
- M. T. Darbandy, "A new approach to detect the physical fatigue utilizing heart rate signals", Research in Cardiovascular Medicine, 9(1), pp.23~27 (2020)
- S. Hochreiter, "Long short-term memory", Neural Computation, 9(8), pp.1735~1780 (1997)
- A. Shoeibi, "Automatic diagnosis of schizophre-nia in EEG signals using CNN-LSTM models", Frontiers in Neuroinformatics, 15 (2021)
- J. Zhu, "Classification of human ac-tivities based on radar signals using 1D-CNN and LSTM", 2020 IEEE International Symposium on Circuits and Sys-tems (ISCAS), pp.1~5 (2020)
- D. P. Kingma, "Adam: A Method for Stochastic Optimization", arXiv preprint arXiv:1412.6980, ~ (2014)
- M. Kalanadhabhatta, "FatigueSet: A multi-modal dataset for modeling mental fa-tigue and fatigability", International Conference on Perva-sive Computing Technologies for Healthcare, pp.204~217 (2022)
- M. D. Buhmann, "Radial Basis Functions", Acta numerica, 9, pp.1~38 (2000)