Residual MLP Network for Mental Fatigue Classification in Mining Workers from Brain Data
| Autor: | Renan Arthur Tourinho, Mylena N F Reis, Schubert R. Carvalho, Ana Carolina Siravenha, Bruno Gomes, Iraquitan Cordeiro |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
business.industry
Computer science Mental fatigue media_common.quotation_subject Cognition 02 engineering and technology Virtual reality Machine learning computer.software_genre Residual 03 medical and health sciences Mining industry Excavator 0302 clinical medicine Multilayer perceptron 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence business computer 030217 neurology & neurosurgery Vigilance (psychology) media_common |
| Zdroj: | BRACIS |
| DOI: | 10.1109/bracis.2019.00078 |
| Popis: | At the mining industry, human safety and productivity are both desirable in the logistics pipeline. Since the operation of heavy machines requires continued vigilance and mental activity, fatigue caused by long hours of work and constant effort generally occurs in this environment. In general, mental fatigue is related to a loss of efficiency, leading to a decrease in productivity and inducing critical errors, which can provoke equipment breakups or accidents with human victims. At this high cognitive workload environment, there is a need for the development of robust monitoring techniques aiming to predict mental fatigue before workers' movement responses become slower, more variable, and more error-prone. In this work, we introduce a residual multilayer perceptron (MLP) network (ResMLPNet) and assess its performance in the challenging problem of mental fatigue classification from cognitive electrophysiology data, acquired during Virtual Reality (VR) training sessions mimicking a real operation faced by excavator workers at the mining industry. In a three-step training strategy, the ResMLPNet achieved slightly better classification accuracies compared to its plain MLP architecture. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|