Fatigue Monitoring Through Wearables: A State-of-the-Art Review

Abstract

The objective measurement of fatigue is of critical relevance in areas such as occupational health and safety as fatigue impairs cognitive and motor performance, thus reducing productivity and increasing the risk of injury. Wearable systems represent highly promising solutions for fatigue monitoring as they enable continuous, long-term monitoring of biomedical signals in unattended settings, with the required comfort and non-intrusiveness. This is a p rerequisite for the development of accurate models for fatigue monitoring in real-time. However, monitoring fatigue through wearable devices imposes unique challenges. To provide an overview of the current state-of-the-art in monitoring variables associated with fatigue via wearables and to detect potential gaps and pitfalls in current knowledge, a systematic review was performed. The Scopus and PubMed databases were searched for articles published in English since 2015, having the terms “fatigue,” “drowsiness,” “vigilance,” or “alertness” in the title, and proposing wearable device-based systems for non-invasive fatigue quantification. Of the 612 retrieved articles, 60 satisfied the inclusion criteria. Included studies were mainly of short duration and conducted in laboratory settings. In general, researchers developed fatigue models based on motion (MOT), electroencephalogram (EEG), photoplethysmogram (PPG), electrocardiogram (ECG), galvanic skin response (GSR), electromyogram (EMG), skin temperature (Tsk), eye movement (EYE), and respiratory (RES) data acquired by wearable devices available in the market. Supervised machine learning models, and more specifically, binary classification models, are predominant among the proposed fatigue quantification approaches. These models were considered to perform very well in detecting fatigue, however, little effort was made to ensure the use of high-quality data during model development. Together, the findings of this review reveal that methodological limitations have hindered the generalizability and real-world applicability of most of the proposed fatigue models. Considerably more work is needed to fully explore the potential of wearables for fatigue quantification as well as to better understand the relationship between fatigue and changes in physiological variables.

Fatigue Driving Detection Method Based on Combination of BP Neural Network and Time Cumulative Effect

“…Hence, they are not suitable for fatigue recognition over the long term. Martins et al [15] provided an overview of the current state-of-the-art monitoring variables associated with fatigue via wearables and detected potential gaps and pitfalls in current knowledge.…”

Machine Learning Approach to Model Physical Fatigue during Incremental Exercise among Firefighters

“…Since physical exertion is considered the primary source of fatigue, different methods have been proposed for its estimation, such as monitoring physiological responses and the use of subjective scales [ 12 ]. To avoid subjectivity and allow continuous monitoring, wearable technology has also made major advances, facilitating the noninvasive collection of multiple physiological variables in real-time [ 13 , 14 ]. Accordingly, literature has evidenced that combining different physiological variables can help in more accurate physical fatigue assessments, and recent studies have addressed this multivariable approach among occupational groups [ 15 , 16 , 17 ].…”

A rapid, non-invasive method for fatigue detection based on voice information

“…Many algorithms have been reported in the field of voiceprint recognition to extract and recognize voiceprint features ( Sun et al, 2018 ), and there are also many new achievements in the research and development of wearable devices. Wearable active sensors have extensive applications in mobile biosensing and human-machine interaction ( Li et al, 2017 ; Adao Martins et al, 2021 ).…”

“…Objective detection methods primarily use physiological signals, such as electroencephalogram (EEG) and electromyography (EMG), but the conventional EEG and EMG methods are inconvenient to operate in the detection process and need to interrupt the normal operation process of the participant ( Furutera et al, 2021 ). The physiological signals are susceptible to several other factors, such as environmental conditions, emotions, and pathophysiological issues ( Adao Martins et al, 2021 ). Other detection methods use physiological signals or changes in behavioral characteristics, such as eye movements ( Sampei et al, 2016 ; Ko et al, 2020 ), but these signals are not easily detected either.…”