Toward Mental Effort Measurement Using Electrodermal Activity Features
The ability to monitor mental effort during a task using a wearable sensor may improve productivity for both work and study. The use of the electrodermal activity (EDA) signal for tracking mental effort is an emerging area of research. Through analysis of over 92 h of data collected with the Empatic...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/19/7363 |
| _version_ | 1827653040381886464 |
|---|---|
| author | William Romine Noah Schroeder Tanvi Banerjee Josephine Graft |
| author_facet | William Romine Noah Schroeder Tanvi Banerjee Josephine Graft |
| author_sort | William Romine |
| collection | DOAJ |
| description | The ability to monitor mental effort during a task using a wearable sensor may improve productivity for both work and study. The use of the electrodermal activity (EDA) signal for tracking mental effort is an emerging area of research. Through analysis of over 92 h of data collected with the Empatica E4 on a single participant across 91 different activities, we report on the efficacy of using EDA features getting at signal intensity, signal dispersion, and peak intensity for prediction of the participant’s self-reported mental effort. We implemented the logistic regression algorithm as an interpretable machine learning approach and found that features related to signal intensity and peak intensity were most useful for the prediction of whether the participant was in a self-reported high mental effort state; increased signal and peak intensity were indicative of high mental effort. When cross-validated by activity moderate predictive efficacy was achieved (AUC = 0.63, F1 = 0.63, precision = 0.64, recall = 0.63) which was significantly stronger than using the model bias alone. Predicting mental effort using physiological data is a complex problem, and our findings add to research from other contexts showing that EDA may be a promising physiological indicator to use for sensor-based self-monitoring of mental effort throughout the day. Integration of other physiological features related to heart rate, respiration, and circulation may be necessary to obtain more accurate predictions. |
| first_indexed | 2024-03-09T21:11:30Z |
| format | Article |
| id | doaj.art-d557809d96984932b8ba5a55b9779d11 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T21:11:30Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-d557809d96984932b8ba5a55b9779d112023-11-23T21:47:58ZengMDPI AGSensors1424-82202022-09-012219736310.3390/s22197363Toward Mental Effort Measurement Using Electrodermal Activity FeaturesWilliam Romine0Noah Schroeder1Tanvi Banerjee2Josephine Graft3Department of Biological Sciences, Wright State University, Dayton, OH 45435, USADepartment of Leadership Studies in Education and Organizations, Wright State University, Dayton, OH 45435, USADepartment of Computer Science, Wright State University, Dayton, OH 45435, USADepartment of Biological Sciences, Wright State University, Dayton, OH 45435, USAThe ability to monitor mental effort during a task using a wearable sensor may improve productivity for both work and study. The use of the electrodermal activity (EDA) signal for tracking mental effort is an emerging area of research. Through analysis of over 92 h of data collected with the Empatica E4 on a single participant across 91 different activities, we report on the efficacy of using EDA features getting at signal intensity, signal dispersion, and peak intensity for prediction of the participant’s self-reported mental effort. We implemented the logistic regression algorithm as an interpretable machine learning approach and found that features related to signal intensity and peak intensity were most useful for the prediction of whether the participant was in a self-reported high mental effort state; increased signal and peak intensity were indicative of high mental effort. When cross-validated by activity moderate predictive efficacy was achieved (AUC = 0.63, F1 = 0.63, precision = 0.64, recall = 0.63) which was significantly stronger than using the model bias alone. Predicting mental effort using physiological data is a complex problem, and our findings add to research from other contexts showing that EDA may be a promising physiological indicator to use for sensor-based self-monitoring of mental effort throughout the day. Integration of other physiological features related to heart rate, respiration, and circulation may be necessary to obtain more accurate predictions.https://www.mdpi.com/1424-8220/22/19/7363electrodermal activitygalvanic skin responsecognitive loadmental effortwearable sensor |
| spellingShingle | William Romine Noah Schroeder Tanvi Banerjee Josephine Graft Toward Mental Effort Measurement Using Electrodermal Activity Features Sensors electrodermal activity galvanic skin response cognitive load mental effort wearable sensor |
| title | Toward Mental Effort Measurement Using Electrodermal Activity Features |
| title_full | Toward Mental Effort Measurement Using Electrodermal Activity Features |
| title_fullStr | Toward Mental Effort Measurement Using Electrodermal Activity Features |
| title_full_unstemmed | Toward Mental Effort Measurement Using Electrodermal Activity Features |
| title_short | Toward Mental Effort Measurement Using Electrodermal Activity Features |
| title_sort | toward mental effort measurement using electrodermal activity features |
| topic | electrodermal activity galvanic skin response cognitive load mental effort wearable sensor |
| url | https://www.mdpi.com/1424-8220/22/19/7363 |
| work_keys_str_mv | AT williamromine towardmentaleffortmeasurementusingelectrodermalactivityfeatures AT noahschroeder towardmentaleffortmeasurementusingelectrodermalactivityfeatures AT tanvibanerjee towardmentaleffortmeasurementusingelectrodermalactivityfeatures AT josephinegraft towardmentaleffortmeasurementusingelectrodermalactivityfeatures |