Evaluating the Effectiveness of Complexity Features of Eye Movement on Computer Activities Detection
Recently, tools developed for detecting human activities have been quite prominent in contributing to health issue prevention and long-term healthcare. For this occasion, the current study aimed to evaluate the performance of eye-movement complexity features (from multi-scale entropy analysis) compa...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Healthcare |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9032/10/6/1016 |
| _version_ | 1797486994508480512 |
|---|---|
| author | Twin Yoshua R. Destyanto Ray F. Lin |
| author_facet | Twin Yoshua R. Destyanto Ray F. Lin |
| author_sort | Twin Yoshua R. Destyanto |
| collection | DOAJ |
| description | Recently, tools developed for detecting human activities have been quite prominent in contributing to health issue prevention and long-term healthcare. For this occasion, the current study aimed to evaluate the performance of eye-movement complexity features (from multi-scale entropy analysis) compared to eye-movement conventional features (from basic statistical measurements) on detecting daily computer activities, comprising reading an English scientific paper, watching an English movie-trailer video, and typing English sentences. A total of 150 students participated in these computer activities. The participants’ eye movements were captured using a desktop eye-tracker (GP3 HD Gazepoint™ Canada) while performing the experimental tasks. The collected eye-movement data were then processed to obtain 56 conventional and 550 complexity features of eye movement. A statistic test, analysis of variance (ANOVA), was performed to screen these features, which resulted in 45 conventional and 379 complexity features. These eye-movement features with four combinations were used to build 12 AI models using Support Vector Machine, Decision Tree, and Random Forest (RF). The comparisons of the models showed the superiority of complexity features (85.34% of accuracy) compared to conventional features (66.98% of accuracy). Furthermore, screening eye-movement features using ANOVA enhances 2.29% of recognition accuracy. This study proves the superiority of eye-movement complexity features. |
| first_indexed | 2024-03-09T23:41:17Z |
| format | Article |
| id | doaj.art-d541409850f74229a88b2c89b1968ac4 |
| institution | Directory Open Access Journal |
| issn | 2227-9032 |
| language | English |
| last_indexed | 2024-03-09T23:41:17Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Healthcare |
| spelling | doaj.art-d541409850f74229a88b2c89b1968ac42023-11-23T16:51:37ZengMDPI AGHealthcare2227-90322022-05-01106101610.3390/healthcare10061016Evaluating the Effectiveness of Complexity Features of Eye Movement on Computer Activities DetectionTwin Yoshua R. Destyanto0Ray F. Lin1Department of Industrial Engineering and Management, Yuan Ze University, Taoyuan 32003, TaiwanDepartment of Industrial Engineering and Management, Yuan Ze University, Taoyuan 32003, TaiwanRecently, tools developed for detecting human activities have been quite prominent in contributing to health issue prevention and long-term healthcare. For this occasion, the current study aimed to evaluate the performance of eye-movement complexity features (from multi-scale entropy analysis) compared to eye-movement conventional features (from basic statistical measurements) on detecting daily computer activities, comprising reading an English scientific paper, watching an English movie-trailer video, and typing English sentences. A total of 150 students participated in these computer activities. The participants’ eye movements were captured using a desktop eye-tracker (GP3 HD Gazepoint™ Canada) while performing the experimental tasks. The collected eye-movement data were then processed to obtain 56 conventional and 550 complexity features of eye movement. A statistic test, analysis of variance (ANOVA), was performed to screen these features, which resulted in 45 conventional and 379 complexity features. These eye-movement features with four combinations were used to build 12 AI models using Support Vector Machine, Decision Tree, and Random Forest (RF). The comparisons of the models showed the superiority of complexity features (85.34% of accuracy) compared to conventional features (66.98% of accuracy). Furthermore, screening eye-movement features using ANOVA enhances 2.29% of recognition accuracy. This study proves the superiority of eye-movement complexity features.https://www.mdpi.com/2227-9032/10/6/1016human activity recognitioneye-movement featurescomplexitymulti-scale entropy |
| spellingShingle | Twin Yoshua R. Destyanto Ray F. Lin Evaluating the Effectiveness of Complexity Features of Eye Movement on Computer Activities Detection Healthcare human activity recognition eye-movement features complexity multi-scale entropy |
| title | Evaluating the Effectiveness of Complexity Features of Eye Movement on Computer Activities Detection |
| title_full | Evaluating the Effectiveness of Complexity Features of Eye Movement on Computer Activities Detection |
| title_fullStr | Evaluating the Effectiveness of Complexity Features of Eye Movement on Computer Activities Detection |
| title_full_unstemmed | Evaluating the Effectiveness of Complexity Features of Eye Movement on Computer Activities Detection |
| title_short | Evaluating the Effectiveness of Complexity Features of Eye Movement on Computer Activities Detection |
| title_sort | evaluating the effectiveness of complexity features of eye movement on computer activities detection |
| topic | human activity recognition eye-movement features complexity multi-scale entropy |
| url | https://www.mdpi.com/2227-9032/10/6/1016 |
| work_keys_str_mv | AT twinyoshuardestyanto evaluatingtheeffectivenessofcomplexityfeaturesofeyemovementoncomputeractivitiesdetection AT rayflin evaluatingtheeffectivenessofcomplexityfeaturesofeyemovementoncomputeractivitiesdetection |