Deep learning-based construction equipment operators’ mental fatigue classification using wearable EEG sensor data

Mehmood, Imran; Li, Heng; Qarout, Yazan; Umer, Waleed; Anwer, Shahnawaz; Wu, Haitao; Hussain, Mudasir; Antwi‐Afari, Maxwell Fordjour

doi:10.1016/j.aei.2023.101978

Cited by 25 publications

(5 citation statements)

References 146 publications

(148 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhuang et al reported spinal cord stimulation may facilitate the recovery of consciousness, and they used an EEG test to predict the process [150]. Thanks to the boom in deep learning, many deep learning models are developed and combined with EEG to detect mental fatigue [151], Parkinson's disease [152], depression [153], schizophrenia [154,155], epilepsy [156][157][158], and neurocognitive disorders [159,160]. In addition to symptom detection, EEG is reported to localize the epileptogenic zone [161,162] and it has the potential to guide the surgery.…”

Section: Bioelectrical Sensorsmentioning

confidence: 99%

Recent Advances in Wearable Healthcare Devices: From Material to Application

Luo,

Tan,

Wen

2024

Bioengineering

View full text Add to dashboard Cite

In recent years, the proliferation of wearable healthcare devices has marked a revolutionary shift in the personal health monitoring and management paradigm. These devices, ranging from fitness trackers to advanced biosensors, have not only made healthcare more accessible, but have also transformed the way individuals engage with their health data. By continuously monitoring health signs, from physical-based to biochemical-based such as heart rate and blood glucose levels, wearable technology offers insights into human health, enabling a proactive rather than a reactive approach to healthcare. This shift towards personalized health monitoring empowers individuals with the knowledge and tools to make informed decisions about their lifestyle and medical care, potentially leading to the earlier detection of health issues and more tailored treatment plans. This review presents the fabrication methods of flexible wearable healthcare devices and their applications in medical care. The potential challenges and future prospectives are also discussed.

show abstract

Section: Bioelectrical Sensorsmentioning

confidence: 99%

Recent Advances in Wearable Healthcare Devices: From Material to Application

Luo,

Tan,

Wen

2024

Bioengineering

View full text Add to dashboard Cite

show abstract

“…In particular, the relationship between psychosocial or mental stressors and WMSDs has been supported by existing studies [40,41]. Recently, the measurement of mental fatigue based on electroencephalogram (EEG) signals has been explored through experimental studies and opened up new possibilities [42,43], while the current limitation on the practicability of EEG in real construction environment may hinder the consideration of psychosocial factors to some extent. In addition, as construction workers often perform tasks in a dynamic outdoor environment, environmental factors can result in increased WMSD risks or aggravated symptoms, such as extreme temperature and poor weather [33,44].…”

Section: Related Workmentioning

confidence: 99%

Evaluation of Ergonomic Risks for Construction Workers Based on Multicriteria Decision Framework with the Integration of Spherical Fuzzy Set and Alternative Queuing Method

Tao,

Hu,

Xue

et al. 2024

Sustainability

View full text Add to dashboard Cite

Ergonomic risks critically impact workers’ occupational health, safety, and productivity, and thereby the sustainability of a workforce. In the construction industry, the physical demands and dynamic environment exposes workers to various ergonomic hazards. While previous research has mainly focused on postural risks, there is a need to broaden the scope to include more relevant factors and assess them systematically. This study introduces a multi-criteria decision framework integrating the Spherical Fuzzy Sets (SFSs) and Alternative Queuing Method (AQM) to evaluate and prioritize ergonomic hazards. First, SFSs are employed to quantify the linguistic expressions of experts, addressing the inherent vagueness and uncertainty. Then, an entropy-based objective weighting method is adopted to determine the criteria weights. Finally, AQM is utilized to generate the risk priority. The proposed method has been implemented in a real-life construction project, where “overexertion due to unreasonable task organization”, “hypertension and heart diseases”, and “existing WMSD record” are identified as the top three ergonomic hazards. Then, a thorough discussion of intervention strategies regarding different risk categories is presented to facilitate ergonomic interventions. This proposed decision support system can promote effective ergonomic risk management, benefiting workers’ health and well-being and contributing to the sustainable workforce development of the construction industry.

show abstract

“…However, the use of supervised learning technique requires hand-crafting of features which could be labor-intensive and may be insufficient to support real-time monitoring of mental workload (Wang et al, 2023). Deep learning techniques, such as convolutional neural networks (CNN), have been used to extract intrinsic features from time-series data for recognizing occupational stress, fatigue and mental workload (Jebelli et al, 2019;Mehmood et al, 2023;Qin & Bulbul, 2023). Recurrent neural network, a class of CNN, is widely used for forecasting time-series data such as brain activity.…”

Section: Machine Learning For Mental Workload Predictionmentioning

confidence: 99%

Predicting Mental Workload of Using Exoskeletons for Construction Work: A Deep Learning Approach

Akanmu,

Afolabi,

Okunola

2023

CONVR 2023 - Proceedings of the 23rd International Conference on Construction Applications of Virtual Reality

View full text Add to dashboard Cite

Exoskeletons are gaining attention as a potential solution for addressing low back injury in the construction industry. However, use of active back-support exoskeletons in construction can trigger unintended consequences which could increase mental workload of users while working with exoskeletons. Prolonged increase in mental workload could impact workers’ wellbeing and productivity. Prediction of mental workload during exoskeleton-use could inform strategies to mitigate the triggers. This study investigates a machine-learning framework for predicting mental workload of workers while using active back-support exoskeletons for construction work. Laboratory experiments were conducted wherein Electroencephalography (EEG) data were collected from participants wearing active back-support exoskeletons to perform flooring task. The EEG data underwent preprocessing, including band filtering, notch filtering, and independent component analysis, to remove artifacts and ensure data quality. A regression-based Long Short-Term Memory network was trained to forecast future time steps of the processed EEG data. The performance of the network was evaluated using root mean square error (RMSE) and r-squared (R2). A RMSE of 0.1527 and R2 of 0.9665 indicating good fit and strong correlation, respectively, were observed between the predicted and actual EEG data. Results of the comparison between the actual and predicted mental workload also show strong correction with an R2 of 0.8692. The findings motivate research directions into real-time monitoring of mental workload of workers during exoskeleton-use. The study has significant implications for stakeholders, enabling them to gain a deeper understanding of the impact of mental workload while using exoskeletons thereby providing opportunities for mitigation

show abstract

Deep learning-based construction equipment operators’ mental fatigue classification using wearable EEG sensor data

Cited by 25 publications

References 146 publications

Recent Advances in Wearable Healthcare Devices: From Material to Application

Recent Advances in Wearable Healthcare Devices: From Material to Application

Evaluation of Ergonomic Risks for Construction Workers Based on Multicriteria Decision Framework with the Integration of Spherical Fuzzy Set and Alternative Queuing Method

Predicting Mental Workload of Using Exoskeletons for Construction Work: A Deep Learning Approach

Contact Info

Product

Resources

About