Literature DB >> 27078889

Unsupervised classification of operator workload from brain signals.

Matthias Schultze-Kraft1, Sven Dähne, Manfred Gugler, Gabriel Curio, Benjamin Blankertz.   

Abstract

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.

Mesh:

Year:  2016        PMID: 27078889     DOI: 10.1088/1741-2560/13/3/036008

Source DB:  PubMed          Journal:  J Neural Eng        ISSN: 1741-2552            Impact factor:   5.379


  7 in total

Review 1.  The Berlin Brain-Computer Interface: Progress Beyond Communication and Control.

Authors:  Benjamin Blankertz; Laura Acqualagna; Sven Dähne; Stefan Haufe; Matthias Schultze-Kraft; Irene Sturm; Marija Ušćumlic; Markus A Wenzel; Gabriel Curio; Klaus-Robert Müller
Journal:  Front Neurosci       Date:  2016-11-21       Impact factor: 4.677

2.  Assessing the Depth of Cognitive Processing as the Basis for Potential User-State Adaptation.

Authors:  Irina-Emilia Nicolae; Laura Acqualagna; Benjamin Blankertz
Journal:  Front Neurosci       Date:  2017-10-04       Impact factor: 4.677

3.  Single-Trial Cognitive Stress Classification Using Portable Wireless Electroencephalography.

Authors:  Justin A Blanco; Ann C Vanleer; Taylor K Calibo; Samara L Firebaugh
Journal:  Sensors (Basel)       Date:  2019-01-25       Impact factor: 3.576

4.  Estimating Cognitive Workload in an Interactive Virtual Reality Environment Using EEG.

Authors:  Christoph Tremmel; Christian Herff; Tetsuya Sato; Krzysztof Rechowicz; Yusuke Yamani; Dean J Krusienski
Journal:  Front Hum Neurosci       Date:  2019-11-14       Impact factor: 3.169

5.  Decoding subjective emotional arousal from EEG during an immersive virtual reality experience.

Authors:  Simon M Hofmann; Felix Klotzsche; Alberto Mariola; Vadim Nikulin; Arno Villringer; Michael Gaebler
Journal:  Elife       Date:  2021-10-28       Impact factor: 8.140

6.  Evaluation of a New Lightweight EEG Technology for Translational Applications of Passive Brain-Computer Interfaces.

Authors:  Nicolina Sciaraffa; Gianluca Di Flumeri; Daniele Germano; Andrea Giorgi; Antonio Di Florio; Gianluca Borghini; Alessia Vozzi; Vincenzo Ronca; Fabio Babiloni; Pietro Aricò
Journal:  Front Hum Neurosci       Date:  2022-07-14       Impact factor: 3.473

7.  EEG Theta Power Activity Reflects Workload among Army Combat Drivers: An Experimental Study.

Authors:  Carolina Diaz-Piedra; María Victoria Sebastián; Leandro L Di Stasi
Journal:  Brain Sci       Date:  2020-03-28
  7 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.