An EEG-based mental workload estimator trained on working memory task can work well under simulated multi-attribute task
Mental workload (MW)-based adaptive system has been found to be an effective approach to enhance the performance of human-machine interaction and to avoid human error caused by overload. However, MW recognized from the spontaneously generated electroencephalogram (EEG) was found to be task-specific....
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2014-09-01
|
| Series: | Frontiers in Human Neuroscience |
| Subjects: | |
| Online Access: | http://journal.frontiersin.org/Journal/10.3389/fnhum.2014.00703/full |
| _version_ | 1828397603612524544 |
|---|---|
| author | Yufeng eKe Hongzhi eQi Feng eHe Shuang eLiu Xin eZhao Peng eZhou Lixin eZhang Dong eMing |
| author_facet | Yufeng eKe Hongzhi eQi Feng eHe Shuang eLiu Xin eZhao Peng eZhou Lixin eZhang Dong eMing |
| author_sort | Yufeng eKe |
| collection | DOAJ |
| description | Mental workload (MW)-based adaptive system has been found to be an effective approach to enhance the performance of human-machine interaction and to avoid human error caused by overload. However, MW recognized from the spontaneously generated electroencephalogram (EEG) was found to be task-specific. In existing studies, EEG-based MW classifier can work well under the task used to train the classifier (within-task) but crash completely when used to classify MW of a task that is similar to but not included in the training data (cross-task). The possible causes have been considered to be the task-specific EEG patterns, the mismatched workload across tasks and the temporal effects. In this study, cross-task performance-based feature selection and regression model were tried to cope with these challenges, in order to make EEG-based MW estimator trained on working memory tasks work well under a complex simulated multi-attribute task (MAT). The results show that the performance of regression model trained on working memory task and tested on multi-attribute task with the feature subset picked-out were significantly improved (COR: 0.740±0.147 and 0.598±0.161 for feature selection data and validation data respectively) when compared to the performance in the same condition with all features (chance level). It can be inferred that there do exist some MW-related EEG features can be picked out and there are something in common between MW of a relatively simple task and a complex task. This study provides a promising approach to measure MW across tasks. |
| first_indexed | 2024-12-10T08:50:41Z |
| format | Article |
| id | doaj.art-823e9f6c7ab1428e9007afff6de8ba2f |
| institution | Directory Open Access Journal |
| issn | 1662-5161 |
| language | English |
| last_indexed | 2024-12-10T08:50:41Z |
| publishDate | 2014-09-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Human Neuroscience |
| spelling | doaj.art-823e9f6c7ab1428e9007afff6de8ba2f2022-12-22T01:55:36ZengFrontiers Media S.A.Frontiers in Human Neuroscience1662-51612014-09-01810.3389/fnhum.2014.00703107808An EEG-based mental workload estimator trained on working memory task can work well under simulated multi-attribute taskYufeng eKe0Hongzhi eQi1Feng eHe2Shuang eLiu3Xin eZhao4Peng eZhou5Lixin eZhang6Dong eMing7Tianjin UniversityTianjin UniversityTianjin UniversityTianjin UniversityTianjin UniversityTianjin UniversityTianjin UniversityTianjin UniversityMental workload (MW)-based adaptive system has been found to be an effective approach to enhance the performance of human-machine interaction and to avoid human error caused by overload. However, MW recognized from the spontaneously generated electroencephalogram (EEG) was found to be task-specific. In existing studies, EEG-based MW classifier can work well under the task used to train the classifier (within-task) but crash completely when used to classify MW of a task that is similar to but not included in the training data (cross-task). The possible causes have been considered to be the task-specific EEG patterns, the mismatched workload across tasks and the temporal effects. In this study, cross-task performance-based feature selection and regression model were tried to cope with these challenges, in order to make EEG-based MW estimator trained on working memory tasks work well under a complex simulated multi-attribute task (MAT). The results show that the performance of regression model trained on working memory task and tested on multi-attribute task with the feature subset picked-out were significantly improved (COR: 0.740±0.147 and 0.598±0.161 for feature selection data and validation data respectively) when compared to the performance in the same condition with all features (chance level). It can be inferred that there do exist some MW-related EEG features can be picked out and there are something in common between MW of a relatively simple task and a complex task. This study provides a promising approach to measure MW across tasks.http://journal.frontiersin.org/Journal/10.3389/fnhum.2014.00703/fullEEGFeature SelectionWorking memory taskMental WorkloadCross-taskmulti-attribute task |
| spellingShingle | Yufeng eKe Hongzhi eQi Feng eHe Shuang eLiu Xin eZhao Peng eZhou Lixin eZhang Dong eMing An EEG-based mental workload estimator trained on working memory task can work well under simulated multi-attribute task Frontiers in Human Neuroscience EEG Feature Selection Working memory task Mental Workload Cross-task multi-attribute task |
| title | An EEG-based mental workload estimator trained on working memory task can work well under simulated multi-attribute task |
| title_full | An EEG-based mental workload estimator trained on working memory task can work well under simulated multi-attribute task |
| title_fullStr | An EEG-based mental workload estimator trained on working memory task can work well under simulated multi-attribute task |
| title_full_unstemmed | An EEG-based mental workload estimator trained on working memory task can work well under simulated multi-attribute task |
| title_short | An EEG-based mental workload estimator trained on working memory task can work well under simulated multi-attribute task |
| title_sort | eeg based mental workload estimator trained on working memory task can work well under simulated multi attribute task |
| topic | EEG Feature Selection Working memory task Mental Workload Cross-task multi-attribute task |
| url | http://journal.frontiersin.org/Journal/10.3389/fnhum.2014.00703/full |
| work_keys_str_mv | AT yufengeke aneegbasedmentalworkloadestimatortrainedonworkingmemorytaskcanworkwellundersimulatedmultiattributetask AT hongzhieqi aneegbasedmentalworkloadestimatortrainedonworkingmemorytaskcanworkwellundersimulatedmultiattributetask AT fengehe aneegbasedmentalworkloadestimatortrainedonworkingmemorytaskcanworkwellundersimulatedmultiattributetask AT shuangeliu aneegbasedmentalworkloadestimatortrainedonworkingmemorytaskcanworkwellundersimulatedmultiattributetask AT xinezhao aneegbasedmentalworkloadestimatortrainedonworkingmemorytaskcanworkwellundersimulatedmultiattributetask AT pengezhou aneegbasedmentalworkloadestimatortrainedonworkingmemorytaskcanworkwellundersimulatedmultiattributetask AT lixinezhang aneegbasedmentalworkloadestimatortrainedonworkingmemorytaskcanworkwellundersimulatedmultiattributetask AT dongeming aneegbasedmentalworkloadestimatortrainedonworkingmemorytaskcanworkwellundersimulatedmultiattributetask AT yufengeke eegbasedmentalworkloadestimatortrainedonworkingmemorytaskcanworkwellundersimulatedmultiattributetask AT hongzhieqi eegbasedmentalworkloadestimatortrainedonworkingmemorytaskcanworkwellundersimulatedmultiattributetask AT fengehe eegbasedmentalworkloadestimatortrainedonworkingmemorytaskcanworkwellundersimulatedmultiattributetask AT shuangeliu eegbasedmentalworkloadestimatortrainedonworkingmemorytaskcanworkwellundersimulatedmultiattributetask AT xinezhao eegbasedmentalworkloadestimatortrainedonworkingmemorytaskcanworkwellundersimulatedmultiattributetask AT pengezhou eegbasedmentalworkloadestimatortrainedonworkingmemorytaskcanworkwellundersimulatedmultiattributetask AT lixinezhang eegbasedmentalworkloadestimatortrainedonworkingmemorytaskcanworkwellundersimulatedmultiattributetask AT dongeming eegbasedmentalworkloadestimatortrainedonworkingmemorytaskcanworkwellundersimulatedmultiattributetask |