A Survey on Fatigue Detection of Workers Using Machine Learning

A Survey on Fatigue Detection of Workers Using Machine Learning

Nisha Yadav (JSS Academy of Technical Education, Noida, India), Kakoli Banerjee (JSS Academy of Technical Education, Noida, India) and Vikram Bali (JSS Academy of Technical Education, Noida, India)
Copyright: © 2020 |Pages: 8
DOI: 10.4018/IJEHMC.2020070101


In the software industry, where the quality of the output is based on human performance, fatigue can be a reason for performance degradation. Fatigue not only degrades quality, but is also a health risk factor. Sleep disorders, depression, and stress are all results of fatigue which can contribute to fatal problems. This article presents a comparative study of different techniques which can be used for detecting fatigue of programmers and data miners who spent lots of time in front of a computer screen. Machine learning can used for worker fatigue detection also, but there are some factors which are specific for software workers. One of such factors is screen illumination. Screen illumination is the light of the computer screen or laptop screen that is casted on the workers face and makes it difficult for the machine learning algorithm to extract the facial features. This article presents a comparative study of the techniques which can be used for general fatigue detection and identifies the best techniques.
Article Preview


Different research shows the effect of vehicle driver fatigue. But fatigue has an effect on workers at different kinds of industry. Work fatigue can affect people working on a shift basis, people affected by high noise, pollution, chemicals, and pressure. The current study focuses on the tiredness of software developers and data miners who spend more time in front of the computer or laptop screen.

As the software industry moves towards a more human-centred environment, software developer health care becomes a very important factor where software developers suffer from depression, anxiety, sleep disorders, etc., it becomes important for employees to ensure that software developers do not suffer from signs or effects of fatigue.

Fatigue also has many long-term effects that affect output productivity and quality. Some of the long-term effects of fatigue affecting the software industry are: inability to stay awake, forgetfulness, error of judgment, inability of complex planning, etc. This results in work errors and can also affect the health of workers. Workers who work for longer hours or additional time may also be in danger, as shown by an article in the NSC's Safety + Health magazine. A progress report by the National Institute for Occupational Safety and Health (NIOSH) found that workers in progress occupations have to rest about 7 hours a day compared to all other groups. (source: https://ehsdailyadvisor.blr.com/2017/06/fatigued-workers-hazard-company/).It should be detected and resolved before fatigue becomes a problem and lowers productivity and becomes fatal.

In this paper, as we focus on software developers ' fatigue detection, there are some factors that need to be addressed. As we focus on facial features and especially eye expressions for fatigue detection, the need to capture facial images is required. Once the algorithm captures the images of the face, different features can be extracted and fatigue can be detected. But the most important factor, facing by the algorithm while extracting data from the image captured on the computer screen via a webcam or an inbuilt camera is illumination. In this review paper, a comparison of different techniques is used to detect facial fatigue. The best technique that can take care of the onscreen illumination problem is also identified along with the comparison.

Following are the figures given below that shows the fatigue cycle during the tasks Figure 1 Shows the fatigue related risk and protection against the fatigue with reviews. This figure also explains the scope of risks according to the work type with some implementations.

Figure 1.

Figure 2 shows the fatigue of workers occurred during the work. There are some tips for workers to decreasing the fatigue level as shown in the figure. Also, the impacts of fatigue have been explained in the figure.

Figure 2.

This figure shows impacts of fatigue on workers (source:https://www.ccohs.ca/images/products/infographics/download/fatigue.jpg)


Qi, Li, Wang, Zhang, Xing, Gao, and Zhang in 2018 proposed a new methodology to recognize expressions based on cognitive and mapped binary patterns. First approach depends on the LBP operator to remove facial highlights, second was the foundation of the pseudo 3-D model to segment the facial region into six featured parts. Finally, they played out a similar investigation on the extension of Cohn-kanade (CK+) outward appearance dataset.

Complete Article List

Search this Journal:
Open Access Articles
Volume 12: 6 Issues (2021): Forthcoming, Available for Pre-Order
Volume 11: 4 Issues (2020)
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing