| Title |
Recognition of human daytime fatigue using keystroke data / |
| Authors |
Ulinskas, Martynas ; Damaševičius, Robertas ; Maskeliūnas, Rytis ; Woźniak, Marcin |
| DOI |
10.1016/j.procs.2018.04.094 |
| Full Text |
|
| Is Part of |
Procedia computer science: 9th international conference on ambient systems, networks and technologies, ANT-2018 and the 8th international conference on sustainable energy information technology, SEIT 2018, 8-11 May, 2018, Porto, Portugal.. Amsterdam : Elsevier. 2018, vol. 130, p. 947-952.. ISSN 1877-0509 |
| Keywords [eng] |
fatigue recognition ; office ergonomics ; assisted living ; biometrics |
| Abstract [eng] |
Human daytime fatigue has many signs (tiredness, sleepiness, lack of vigilance). The on-set of fatigue during working hours can be dangerous for people of several professions such as lorry drivers or industry workers, however even for office workers it may lead to serious errors. Timely recognition of daytime fatigue using simple computer based tests can reduce fatigue related accidents or errors in workplace. In this paper, we analyze the use of keystroke data derived by typing on computer keyboard to recognize the state of an increased fatigue. Using specific key press and release timing information from text input tasks, we achieve an average daytime fatigue recognition accuracy of 98.11% when only three qualitative classes of daytime fatigue (low, medium and high) are considered. |
| Published |
Amsterdam : Elsevier |
| Type |
Conference paper |
| Language |
English |
| Publication date |
2018 |
| CC license |
|
