Unsupervised classification of operator workload from brain signals
Unsupervised classification of operator workload from brain signals
复制标题
根据大脑信号对操作员工作量进行无监督分类
DOI：
10.1088/1741-2560/13/3/036008
复制
发表时间：
2016
影响因子：
4
通讯作者：
B. Blankertz
中科院分区：
文献类型：
--
作者：
M. Schultze-Kraft;S. Dähne;M. Gugler;G. Curio;B. Blankertz
在这项研究中，我们的目标是对操作员的工作负荷进行分类，因为它是在许多现实生活中的工作环境中预期的。我们探讨了大脑信号为基础的工作量预测不同的训练所需的标签信息的水平，包括完全无监督的approachs.ApproachSubjects执行任务的触摸屏上，需要不断努力的视觉和运动处理交替困难。我们首先采用经典的工作负荷状态分类方法，在EEG的传感器空间上操作，并将这些方法与三种最先进的空间滤波方法的性能进行比较：公共空间模式（CSP）分析，需要二进制标签信息;源功率共调制（SSPs）分析，使用受试者的错误率作为目标函数;和典型的SCRESSION（cSCRESSION）分析，其仅利用由不同的工作负载状态引起的交叉频率功率相关性，因此代表无监督的方法。最后，我们研究了融合脑信号和外周生理指标（PPM）的效果，并研究了提高分类性能的附加值。主要结果CSP，SRESS，cSRESS分别达到了94%，92%和82%的平均分类准确率。这些方法优于不使用空间滤波的方法，并且它们提取了生理上合理的成分。无监督的cScrum的性能显着增加，通过增加PPM features. Significance我们的分析确保了用于分类的信号源是皮质起源，而不是污染的文物。我们的研究结果表明，即使使用越来越少的实验范式信息，也可以成功地将工作负荷状态与大脑信号区分开来，从而为现实世界的应用铺平道路，其中标签信息可能是嘈杂的或完全不可用的。
ObjectiveIn 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.ApproachSubjects 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 resultsMean 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.SignificanceOur 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.
登录
查看更多内容
汽车多任务处理认知工作负载的多模态识别
DOI：
--
发表时间：
2010
期刊：
International Conference on Pattern Recognition
影响因子：
--
作者：
F. Putze;J. Jarvis;Tanja Schultz
通讯作者：
Tanja Schultz
影响因子：
5.7
作者：
Daehne, Sven;Nikulin, Vadim V.;Haufe, Stefan
通讯作者：
Haufe, Stefan
影响因子：
2.4
作者：
Olaf Kohlisch;Florian Schaefer
通讯作者：
Olaf Kohlisch;Florian Schaefer
影响因子：
4
作者：
Zander, Thorsten O.;Kothe, Christian
通讯作者：
Kothe, Christian
影响因子：
3.7
作者：
Jensen, O;Gelfand, J;Lisman, JE
通讯作者：
Lisman, JE