Granular estimation of user cognitive workload using multi-modal physiological sensors

被引:0
|
作者
Wang, Jingkun [1 ]
Stevens, Christopher [2 ]
Bennett, Winston [2 ]
Yu, Denny [1 ]
机构
[1] Purdue Univ, Sch Ind Engn, W Lafayette, IN 47906 USA
[2] USAF, Res Lab, Dayton, OH USA
来源
关键词
mental workload; mental workload modeling; physiological sensors; teleoperation task; multiple mental workload level; MENTAL WORKLOAD; WORKING-MEMORY; TASK; EEG; INDEXES; LOAD;
D O I
10.3389/fnrgo.2024.1292627
中图分类号
TB18 [人体工程学];
学科分类号
1201 ;
摘要
Mental workload (MWL) is a crucial area of study due to its significant influence on task performance and potential for significant operator error. However, measuring MWL presents challenges, as it is a multi-dimensional construct. Previous research on MWL models has focused on differentiating between two to three levels. Nonetheless, tasks can vary widely in their complexity, and little is known about how subtle variations in task difficulty influence workload indicators. To address this, we conducted an experiment inducing MWL in up to 5 levels, hypothesizing that our multi-modal metrics would be able to distinguish between each MWL stage. We measured the induced workload using task performance, subjective assessment, and physiological metrics. Our simulated task was designed to induce diverse MWL degrees, including five different math and three different verbal tiers. Our findings indicate that all investigated metrics successfully differentiated between various MWL levels induced by different tiers of math problems. Notably, performance metrics emerged as the most effective assessment, being the only metric capable of distinguishing all the levels. Some limitations were observed in the granularity of subjective and physiological metrics. Specifically, the subjective overall mental workload couldn't distinguish lower levels of workload, while all physiological metrics could detect a shift from lower to higher levels, but did not distinguish between workload tiers at the higher or lower ends of the scale (e.g., between the easy and the easy-medium tiers). Despite these limitations, each pair of levels was effectively differentiated by one or more metrics. This suggests a promising avenue for future research, exploring the integration or combination of multiple metrics. The findings suggest that subtle differences in workload levels may be distinguishable using combinations of subjective and physiological metrics.
引用
收藏
页数:13
相关论文
共 50 条
  • [1] Continuous identity authentication using multi-modal physiological sensors
    Crosby, ME
    Ikehara, CS
    [J]. BIOMETRIC TECHNOLOGY FOR HUMAN IDENTIFICATION, 2004, 5404 : 393 - 400
  • [2] Study of Different Classifiers and Multi-modal Sensors in Assessment of Workload
    MacNeil, Emma
    Bishop, Ashley
    Izzetoglu, Kurtulus
    [J]. AUGMENTED COGNITION, AC 2022, 2022, 13310 : 151 - 161
  • [3] Multi-Modal Physiological Data Fusion for Affect Estimation Using Deep Learning
    Hssayeni, Murtadha D.
    Ghoraani, Behnaz
    [J]. IEEE ACCESS, 2021, 9 : 21642 - 21652
  • [4] User Identification from Gait Analysis Using Multi-Modal Sensors in Smart Insole
    Choi, Sang-Il
    Moon, Jucheol
    Park, Hee-Chan
    Choi, Sang Tae
    [J]. SENSORS, 2019, 19 (17)
  • [5] Workload categorization for hazardous industries: The semantic modelling of multi-modal physiological data
    Konig, Jemma L.
    Hinze, Annika
    Bowen, Judy
    [J]. FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2023, 141 : 369 - 381
  • [6] Multi-modal and multi-granular learning
    Zhang, Bo
    Zhang, Ling
    [J]. ADVANCES IN KNOWLEDGE DISCOVERY AND DATA MINING, PROCEEDINGS, 2007, 4426 : 9 - +
  • [7] Automatic pain intensity estimation using multi-modal data from wearable sensors
    Martinez, D. Lopez
    Rudovic, O.
    Doughty, D.
    Subramony, J. Anand
    Picard, R.
    [J]. JOURNAL OF PAIN, 2017, 18 (04): : S60 - S60
  • [8] Continuous user authentication using multi-modal biometrics
    Saevanee, Hataichanok
    Clarke, Nathan
    Furnell, Steven
    Biscione, Valerio
    [J]. COMPUTERS & SECURITY, 2015, 53 : 234 - 246
  • [9] Cognitive workload estimation using physiological measures: a review
    Das Chakladar, Debashis
    Roy, Partha Pratim
    [J]. COGNITIVE NEURODYNAMICS, 2024, 18 (04) : 1445 - 1465
  • [10] A Cognitive User Interface for a Multi-modal Human-Machine Interaction
    Tschoepe, Constanze
    Duckhorn, Frank
    Huber, Markus
    Meyer, Werner
    Wolff, Matthias
    [J]. SPEECH AND COMPUTER (SPECOM 2018), 2018, 11096 : 707 - 717