Applicability of Spiral Drawing Test for Mental Fatigue Modelling
| Autor: | Sven Nõmm, Aaro Toomela, Olesja Senkiv |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
0209 industrial biotechnology
Computer science business.industry 020208 electrical & electronic engineering Cognition 02 engineering and technology Machine learning computer.software_genre Test (assessment) 020901 industrial engineering & automation Control and Systems Engineering 0202 electrical engineering electronic engineering information engineering Artificial intelligence Focus (optics) business computer Spiral |
| Zdroj: | IFAC-PapersOnLine. 51:190-195 |
| ISSN: | 2405-8963 |
| DOI: | 10.1016/j.ifacol.2019.01.064 |
| Popis: | Applicability of the spiral drawing test to fatigue modelling is in focus of the present research. During the recent time fatigue detection and modelling gain a lot of attention. Nevertheless, relatively few results are devoted to the applicability of fine motor tests to tackle the problem. Initially developed to diagnose and model cognitive impairments, like those caused by neurodegenerative disease, fine motor tests provide the unique insight in the state of human motor functions both, on the levels of planning and execution of limb motions. The spiral drawing test was chosen due to its popularity among practitioners and due to the fact that it was among the first to be digitised. The latest, provide different opportunities to use commonly used features to describe and interpret achieved results. Performance of the four most popular machine learning techniques: decision trees, logistic regression, k-nearest neighbours and support vector machines was evaluated with respect to their ability to distinguish between the individuals experiencing fatigue and control group individuals. It is demonstrated that features describing the smoothness of the fine motor motions possess the same discriminating power as commonly used temporal features. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|