Fatigue Monitoring Using Wearables and AI: Trends, Challenges, and Future Opportunities, 2024, Kakhia

https://arxiv.org/pdf/2412.16847

Fatigue Monitoring Using Wearables and AI: Trends, Challenges, and Future Opportunities

Kourosh Kakhia, Senthil Kumar Jagatheesaperumalb, Abbas Khosravia, Roohallah Alizadehsani*,a, U Rajendra Acharyac

aInstitute for Intelligent Systems Research and Innovation (IISRI), Geelong, 3217, VIC, Australia

bDepartment of Electronics and Communication Engineering, Mepco Schlenk Engineering College, Sivakasi, Tamil Nadu, India

cSchool of Mathematics, Physics and Computing, University of Southern Queensland, Springfield, Australia

Abstract

Background:

Monitoring fatigue is essential for improving safety, particularly for people who work long shifts or in high-demand workplaces. The development of wearable technologies, such as fitness trackers and smartwatches, has made it possible to continuously analyze physiological signals in real-time to determine a person’s level of exhaustion. This has allowed for timely insights into preventing hazards associated with fatigue.

Methods:

This review focuses on wearable technology and artificial intelligence (AI) integration for tiredness detection, adhering to the PRISMA principles. Studies that used signal processing methods to extract pertinent aspects from physiological data, such as ECG, EMG, and EEG, among others, were analyzed as part of the systematic review process. Then, to find patterns of weariness and indicators of impending fatigue, these features were examined using machine learning and deep learning models.

Results:

It was demonstrated that wearable technology and cutting-edge AI methods could accurately identify weariness through multi-modal data analysis. By merging data from several sources, information fusion techniques enhanced the precision and dependability of fatigue evaluation. Significant developments in AI-driven signal analysis were noted in the assessment, which should improve real-time fatigue monitoring while requiring less interference.

Conclusion:

Wearable solutions powered by AI and multi-source data fusion present a strong option for real-time tiredness monitoring in the workplace and other crucial environments. These developments open the door for more improvements in this field and offer useful tools for enhancing safety and reducing fatigue-related hazards .

Keywords: Fatigue, Physiological fatigue, Artificial intelligence, Machine learning, Deep learning.

 

A worrying development if it becomes used as an excuse to invade privacy on a new level of monitoring staff

I say this as having been a sick person who felt they had to hide how ill and I suspect most of us who gif ill enough would hear the advice of telling how bad it was to put x on paper and had to wonder whether that’s going to lead to being managed out for all the official cover disability stuff might provide. And who knows because each of us can only ever choose on side of the fork each time so you never really know.

on the other hand with huge caveats this stuff it’s important if used right

and air traffic control always had to do stuff like this along with truck drivers so you do wonder with other organisations whether if it was done as oversight to show giving people work that meant xhr weeks was causing x,y, z. Not that that would go down well as interference of course!

and imagine having a great culture and top team who did care and brought people in to do this, and then the culture changing at the top and the position the person running that programme would be in re recommendations (if they weren’t going to be happy being told to actually improve conditions) - so would those end up going untested ie get data, suggest offering CBT to all dont tests agsin say all is right in the world.

I think these might be great in theory but the tech is only part of the stumbling block?