Mason Archival Repository Service

Measurements to Detect Mental Fatigue

Show simple item record

dc.contributor.author Asif, Zara
dc.date.accessioned 2020-05-13T22:47:41Z
dc.date.available 2020-05-13T22:47:41Z
dc.date.issued 2020-05
dc.identifier.uri http://hdl.handle.net/1920/11768
dc.description.abstract Mental fatigue is defined as a “state of reduced mental alertness that impairs performance” It affects nearly everyone in society at some point and has become one of the leading causes of workplace accidents [2]. Common symptoms of the condition include discomfort, tiredness, and reduced motivation [1]. Recently, there has been a significant push for the development of technology to detect mental fatigue and prevent related accidents. Through this project, I will review current detection methods and their results. I will then explore whether such a detection system is possible to create with current technology and whether it could feasibly be implemented in real world scenarios. Several signals have been analyzed in their reliability of detecting the onset of mental fatigue. These are blink rate, heart rate variability, respiration, and brain activity. Since blink rate increases with fatigue, it can be analyzed using continuous recording and facial recognition techniques. Similarly, heart rate variability increases and respiration rate becomes more erratic. Both can be measured with physical sensors or physical sensors. Out of these, brain activity is the most accurate indicator of mental fatigue and has to be monitored with an EEG sensor. Yamada and Kobayashi collected eye tracking data from subjects who watched video clips before to induce mental fatigue. They found that participants showed significant increases in blink rate and duration as they became more fatigued and a fatigue detection model was developed which was able to achieve 91% accuracy [6]. To investigate the effects of mental fatigue on heart rate variability and respiration, Huang and his team gave 35 participants a wearable ECG device known as “LaPatch,” which was capable of recording ECG and respiration states. Four classifiers were created and out of these KNN was the most accurate with a 75% chance of correctly identifying mental fatigue [5]. Tanaka and others conducted a study to understand how mental fatigue affects cognitive performance. Magnetoencephalography data was recorded and analyzed. They found that these tasks caused the alpha frequency band power, 8-13 Hz, to decrease, which suggests that mental fatigue causes over activation of the visual cortex [1]. Another approach by Shen and others used Electroencephalography data, which was then classified by a support vector machine algorithm. The results indicated a 90% accuracy in detecting lapses in cognitive performance [2]. The main deterrent to developing a mental fatigue detection system with all four of these signals is that it would not necessarily be contactless. Including an EEG reading would significantly increase the accuracy of the system overall, but it is the only signal that requires a physical sensor. The most beneficial detection system would have to be entirely contactless in order to be applicable in multiple situations and this is not possible with the current technology. As such, currently there is no detection system for mental fatigue on the market. en_US
dc.language.iso en_US en_US
dc.rights Attribution-ShareAlike 3.0 United States *
dc.rights.uri http://creativecommons.org/licenses/by-sa/3.0/us/ *
dc.subject cognitive performance en_US
dc.subject mental fatigue en_US
dc.title Measurements to Detect Mental Fatigue en_US
dc.type Other en_US


Files in this item

The following license files are associated with this item:

This item appears in the following Collection(s)

Show simple item record

Attribution-ShareAlike 3.0 United States Except where otherwise noted, this item's license is described as Attribution-ShareAlike 3.0 United States

Search MARS


Browse

My Account

Statistics