Unsupervised classification of operator workload from brain signals

• Published in: Journal of neural engineering Vol. 13; no. 3; p. 036008
• Main Authors: Schultze-Kraft, Matthias, Dähne, Sven, Gugler, Manfred, Curio, Gabriel, Blankertz, Benjamin
• Format: Journal Article
• Language: English
• Published: England IOP Publishing 01.06.2016
• Subjects: Adult; Algorithms; Brain; Brain - physiology; brain-computer interface; Brain-Computer Interfaces; Cerebral Cortex - physiology; Classification; EEG; Electroencephalography; Error detection; Galvanic Skin Response; Heart Rate; Humans; Labels; Male; Models, Statistical; Operators; Psychomotor Performance; Reproducibility of Results; Respiratory Rate; Signal Processing, Computer-Assisted; Spatial filtering; unsupervised; Workload
• ISSN: 1741-2560; 1741-2552
• DOI: 10.1088/1741-2560/13/3/036008

Objective. In this study we aimed for the classification of operator workload as it is expected in many real-life workplace environments. We explored brain-signal based workload predictors that differ with respect to the level of label information required for training, including entirely unsupervised approaches. Approach. Subjects executed a task on a touch screen that required continuous effort of visual and motor processing with alternating difficulty. We first employed classical approaches for workload state classification that operate on the sensor space of EEG and compared those to the performance of three state-of-the-art spatial filtering methods: common spatial patterns (CSPs) analysis, which requires binary label information; source power co-modulation (SPoC) analysis, which uses the subjects' error rate as a target function; and canonical SPoC (cSPoC) analysis, which solely makes use of cross-frequency power correlations induced by different states of workload and thus represents an unsupervised approach. Finally, we investigated the effects of fusing brain signals and peripheral physiological measures (PPMs) and examined the added value for improving classification performance. Main results. Mean classification accuracies of 94%, 92% and 82% were achieved with CSP, SPoC, cSPoC, respectively. These methods outperformed the approaches that did not use spatial filtering and they extracted physiologically plausible components. The performance of the unsupervised cSPoC is significantly increased by augmenting it with PPM features. Significance. Our analyses ensured that the signal sources used for classification were of cortical origin and not contaminated with artifacts. Our findings show that workload states can be successfully differentiated from brain signals, even when less and less information from the experimental paradigm is used, thus paving the way for real-world applications in which label information may be noisy or entirely unavailable.