Bangaru, S S; Wang, C; Zhou, X; Jeon, H W and Li, Y (2020) Gesture recognition-based smart training assistant system for construction worker earplug-wearing training. Journal of Construction Engineering and Management, 146(12): 04020144, ISSN 0733-9364
Abstract
Thousands of construction workers suffer noise-induced hearing loss (NIHL) every year from excessive noise exposure on the job, which impairs the quality of their lives and increases the risk of injury. Properly wearing earplugs is very important onsite for worker hearing protection. However, the training provided in the current practice is minimal. Therefore, there is a need to develop an efficient and effective self-Training method that can provide both accurate step-by-step earplug-wearing instructions and timely feedback through monitoring. With the development of artificial intelligence and wearable sensor technologies, the possibility of developing an advanced intelligent training method becomes plausible. Therefore, the objective of this paper is to develop a gesture recognition-based smart training assistant system that can automatically evaluate workers' performance during their earplug-wearing self-Training and provide timely feedback to rectify any mistakes. Through the system feasibility test and performance evaluation, the results show that the proposed system can achieve around 90% training accuracy and around 80% testing accuracy recognizing the classified forearm gestures of wearing earplugs for noise protection training using the developed artificial neural network (ANN) models for both hands. The proposed gesture recognition-based smart training assistant system will eventually help industries to improve the performance and safety of employees with low implementation costs.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | artificial neural network; electromyography; gesture recognition; safety training; wearable sensors |
| Index terms: | construction worker, monitoring, artificial intelligence, testing, accuracy, artificial neural network, injury, onsite, safety training, wearable sensor, performance evaluation, noise-induced hearing loss, exposure, implementation |
| Subjects: | control systems, occupational health and safety management, public and environmental health, contractual arrangements, professional practice, computer vision, performance measurement, modelling and simulation, practitioner, artificial intelligence, professional development, building construction, health conditions and diseases |
| Topics: | Engineering Principles, Construction Technology, Procurement, Information Management, Quality Management, Roles and Professions, Research Practice, Site Management, Digital Applications, Health and Safety |
| Descriptive scope: | 2 PC |
N.B. Descriptive scope is a count of how many of the five facets of empirical research are indicated by the words used in title, abstract and keywords. It is not intended as a judgement on the research; merely a count of the kind of word we would expect to indicate Phenomenon, Concepts, Theoretical framing, Empirical techniques, Analytical techniques. If all five are present, then a code of “5 PCTEA” will indicate this. If you feel the coding for this record is questionable, we welcome discussion around the terms we matched or the way we categorized them. The facet you would expect may not be coded, or a facet may be coded inappropriately. This can also bear on a larger question, of which facets should be treated as defining in construction management research. Please get in touch, and we will look at it. More details here