An Electro-Oculogram (EOG) Sensor’s Ability to Detect Driver Hypovigilance Using Machine Learning
Driving safely is crucial to avoid death, injuries, or financial losses that can be sustained in an accident. Thus, a driver’s physical state should be monitored to prevent accidents, rather than vehicle-based or behavioral measurements, and provide reliable information in this regard. Electrocardio...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/6/2944 |
| _version_ | 1797609123909468160 |
|---|---|
| author | Suganiya Murugan Pradeep Kumar Sivakumar C. Kavitha Anandhi Harichandran Wen-Cheng Lai |
| author_facet | Suganiya Murugan Pradeep Kumar Sivakumar C. Kavitha Anandhi Harichandran Wen-Cheng Lai |
| author_sort | Suganiya Murugan |
| collection | DOAJ |
| description | Driving safely is crucial to avoid death, injuries, or financial losses that can be sustained in an accident. Thus, a driver’s physical state should be monitored to prevent accidents, rather than vehicle-based or behavioral measurements, and provide reliable information in this regard. Electrocardiography (ECG), electroencephalography (EEG), electrooculography (EOG), and surface electromyography (sEMG) signals are used to monitor a driver’s physical state during a drive. The purpose of this study was to detect driver hypovigilance (drowsiness, fatigue, as well as visual and cognitive inattention) using signals collected from 10 drivers while they were driving. EOG signals from the driver were preprocessed to remove noise, and 17 features were extracted. ANOVA (analysis of variance) was used to select statistically significant features that were then loaded into a machine learning algorithm. We then reduced the features by using principal component analysis (PCA) and trained three classifiers: support vector machine (SVM), k-nearest neighbor (KNN), and ensemble. A maximum accuracy of 98.7% was obtained for the classification of normal and cognitive classes under the category of two-class detection. Upon considering hypovigilance states as five-class, a maximum accuracy of 90.9% was achieved. In this case, the number of detection classes increased, resulting in a reduction in the accuracy of detecting more driver states. However, with the possibility of incorrect identification and the presence of issues, the ensemble classifier’s performance produced an enhanced accuracy when compared to others. |
| first_indexed | 2024-03-11T05:56:05Z |
| format | Article |
| id | doaj.art-39366b2d662847eea7dc99fbc17642fa |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T05:56:05Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-39366b2d662847eea7dc99fbc17642fa2023-11-17T13:43:43ZengMDPI AGSensors1424-82202023-03-01236294410.3390/s23062944An Electro-Oculogram (EOG) Sensor’s Ability to Detect Driver Hypovigilance Using Machine LearningSuganiya Murugan0Pradeep Kumar Sivakumar1C. Kavitha2Anandhi Harichandran3Wen-Cheng Lai4Department of Computing Technologies, SRM Institute of Science and Technology—KTR, Chennai 603203, IndiaDepartment of Electrical and Electronics Engineering, Vels Institute of Science Technology and Advanced Studies, Chennai 600117, IndiaDepartment of Computer Science and Engineering, Sathyabama Institute of Science and Technology, Chennai 600119, IndiaDepartment of Biomedical Engineering, Agni College of Technology, Chennai 600130, IndiaBachelor Program in Industrial Projects, National Yunlin University of Science and Technology, Douliu 640301, TaiwanDriving safely is crucial to avoid death, injuries, or financial losses that can be sustained in an accident. Thus, a driver’s physical state should be monitored to prevent accidents, rather than vehicle-based or behavioral measurements, and provide reliable information in this regard. Electrocardiography (ECG), electroencephalography (EEG), electrooculography (EOG), and surface electromyography (sEMG) signals are used to monitor a driver’s physical state during a drive. The purpose of this study was to detect driver hypovigilance (drowsiness, fatigue, as well as visual and cognitive inattention) using signals collected from 10 drivers while they were driving. EOG signals from the driver were preprocessed to remove noise, and 17 features were extracted. ANOVA (analysis of variance) was used to select statistically significant features that were then loaded into a machine learning algorithm. We then reduced the features by using principal component analysis (PCA) and trained three classifiers: support vector machine (SVM), k-nearest neighbor (KNN), and ensemble. A maximum accuracy of 98.7% was obtained for the classification of normal and cognitive classes under the category of two-class detection. Upon considering hypovigilance states as five-class, a maximum accuracy of 90.9% was achieved. In this case, the number of detection classes increased, resulting in a reduction in the accuracy of detecting more driver states. However, with the possibility of incorrect identification and the presence of issues, the ensemble classifier’s performance produced an enhanced accuracy when compared to others.https://www.mdpi.com/1424-8220/23/6/2944drowsinessvisual inattentionmachine learningdrowsiness detectionsignals |
| spellingShingle | Suganiya Murugan Pradeep Kumar Sivakumar C. Kavitha Anandhi Harichandran Wen-Cheng Lai An Electro-Oculogram (EOG) Sensor’s Ability to Detect Driver Hypovigilance Using Machine Learning Sensors drowsiness visual inattention machine learning drowsiness detection signals |
| title | An Electro-Oculogram (EOG) Sensor’s Ability to Detect Driver Hypovigilance Using Machine Learning |
| title_full | An Electro-Oculogram (EOG) Sensor’s Ability to Detect Driver Hypovigilance Using Machine Learning |
| title_fullStr | An Electro-Oculogram (EOG) Sensor’s Ability to Detect Driver Hypovigilance Using Machine Learning |
| title_full_unstemmed | An Electro-Oculogram (EOG) Sensor’s Ability to Detect Driver Hypovigilance Using Machine Learning |
| title_short | An Electro-Oculogram (EOG) Sensor’s Ability to Detect Driver Hypovigilance Using Machine Learning |
| title_sort | electro oculogram eog sensor s ability to detect driver hypovigilance using machine learning |
| topic | drowsiness visual inattention machine learning drowsiness detection signals |
| url | https://www.mdpi.com/1424-8220/23/6/2944 |
| work_keys_str_mv | AT suganiyamurugan anelectrooculogrameogsensorsabilitytodetectdriverhypovigilanceusingmachinelearning AT pradeepkumarsivakumar anelectrooculogrameogsensorsabilitytodetectdriverhypovigilanceusingmachinelearning AT ckavitha anelectrooculogrameogsensorsabilitytodetectdriverhypovigilanceusingmachinelearning AT anandhiharichandran anelectrooculogrameogsensorsabilitytodetectdriverhypovigilanceusingmachinelearning AT wenchenglai anelectrooculogrameogsensorsabilitytodetectdriverhypovigilanceusingmachinelearning AT suganiyamurugan electrooculogrameogsensorsabilitytodetectdriverhypovigilanceusingmachinelearning AT pradeepkumarsivakumar electrooculogrameogsensorsabilitytodetectdriverhypovigilanceusingmachinelearning AT ckavitha electrooculogrameogsensorsabilitytodetectdriverhypovigilanceusingmachinelearning AT anandhiharichandran electrooculogrameogsensorsabilitytodetectdriverhypovigilanceusingmachinelearning AT wenchenglai electrooculogrameogsensorsabilitytodetectdriverhypovigilanceusingmachinelearning |