Hybrid System for Engagement Recognition During Cognitive Tasks Using a CFS + KNN Algorithm
Engagement is described as a state in which an individual involved in an activity can ignore other influences. The engagement level is important to obtaining good performance especially under study conditions. Numerous methods using electroencephalograph (EEG), electrocardiograph (ECG), and near-inf...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/18/11/3691 |
| _version_ | 1811302308893425664 |
|---|---|
| author | Fadilla Zennifa Sho Ageno Shota Hatano Keiji Iramina |
| author_facet | Fadilla Zennifa Sho Ageno Shota Hatano Keiji Iramina |
| author_sort | Fadilla Zennifa |
| collection | DOAJ |
| description | Engagement is described as a state in which an individual involved in an activity can ignore other influences. The engagement level is important to obtaining good performance especially under study conditions. Numerous methods using electroencephalograph (EEG), electrocardiograph (ECG), and near-infrared spectroscopy (NIRS) for the recognition of engagement have been proposed. However, the results were either unsatisfactory or required many channels. In this study, we introduce the implementation of a low-density hybrid system for engagement recognition. We used a two-electrode wireless EEG, a wireless ECG, and two wireless channels NIRS to measure engagement recognition during cognitive tasks. We used electrooculograms (EOG) and eye tracking to record eye movements for data labeling. We calculated the recognition accuracy using the combination of correlation-based feature selection and k-nearest neighbor algorithm. Following that, we did a comparative study against a stand-alone system. The results show that the hybrid system had an acceptable accuracy for practical use (71.65 ± 0.16%). In comparison, the accuracy of a pure EEG system was (65.73 ± 0.17%), pure ECG (67.44 ± 0.19%), and pure NIRS (66.83 ± 0.17%). Overall, our results demonstrate that the proposed method can be used to improve performance in engagement recognition. |
| first_indexed | 2024-04-13T07:25:47Z |
| format | Article |
| id | doaj.art-7d8f6eed6ddd42bb85d1a66449f606be |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-13T07:25:47Z |
| publishDate | 2018-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-7d8f6eed6ddd42bb85d1a66449f606be2022-12-22T02:56:29ZengMDPI AGSensors1424-82202018-10-011811369110.3390/s18113691s18113691Hybrid System for Engagement Recognition During Cognitive Tasks Using a CFS + KNN AlgorithmFadilla Zennifa0Sho Ageno1Shota Hatano2Keiji Iramina3Graduate School of Systems Life Sciences, Kyushu University, 3-1-1 Maidashi, Higashi-Ku, Fukuoka-Shi, Fukuoka 812-8582, JapanGraduate School of Systems Life Sciences, Kyushu University, 3-1-1 Maidashi, Higashi-Ku, Fukuoka-Shi, Fukuoka 812-8582, JapanGraduate School of Systems Life Sciences, Kyushu University, 3-1-1 Maidashi, Higashi-Ku, Fukuoka-Shi, Fukuoka 812-8582, JapanGraduate School of Systems Life Sciences, Kyushu University, 3-1-1 Maidashi, Higashi-Ku, Fukuoka-Shi, Fukuoka 812-8582, JapanEngagement is described as a state in which an individual involved in an activity can ignore other influences. The engagement level is important to obtaining good performance especially under study conditions. Numerous methods using electroencephalograph (EEG), electrocardiograph (ECG), and near-infrared spectroscopy (NIRS) for the recognition of engagement have been proposed. However, the results were either unsatisfactory or required many channels. In this study, we introduce the implementation of a low-density hybrid system for engagement recognition. We used a two-electrode wireless EEG, a wireless ECG, and two wireless channels NIRS to measure engagement recognition during cognitive tasks. We used electrooculograms (EOG) and eye tracking to record eye movements for data labeling. We calculated the recognition accuracy using the combination of correlation-based feature selection and k-nearest neighbor algorithm. Following that, we did a comparative study against a stand-alone system. The results show that the hybrid system had an acceptable accuracy for practical use (71.65 ± 0.16%). In comparison, the accuracy of a pure EEG system was (65.73 ± 0.17%), pure ECG (67.44 ± 0.19%), and pure NIRS (66.83 ± 0.17%). Overall, our results demonstrate that the proposed method can be used to improve performance in engagement recognition.https://www.mdpi.com/1424-8220/18/11/3691electroencephalographyelectrocardiographyelectrooculographyeye trackingnear-infrared spectroscopyengagement recognitionKNNCFShybrid systemsensor |
| spellingShingle | Fadilla Zennifa Sho Ageno Shota Hatano Keiji Iramina Hybrid System for Engagement Recognition During Cognitive Tasks Using a CFS + KNN Algorithm Sensors electroencephalography electrocardiography electrooculography eye tracking near-infrared spectroscopy engagement recognition KNN CFS hybrid system sensor |
| title | Hybrid System for Engagement Recognition During Cognitive Tasks Using a CFS + KNN Algorithm |
| title_full | Hybrid System for Engagement Recognition During Cognitive Tasks Using a CFS + KNN Algorithm |
| title_fullStr | Hybrid System for Engagement Recognition During Cognitive Tasks Using a CFS + KNN Algorithm |
| title_full_unstemmed | Hybrid System for Engagement Recognition During Cognitive Tasks Using a CFS + KNN Algorithm |
| title_short | Hybrid System for Engagement Recognition During Cognitive Tasks Using a CFS + KNN Algorithm |
| title_sort | hybrid system for engagement recognition during cognitive tasks using a cfs knn algorithm |
| topic | electroencephalography electrocardiography electrooculography eye tracking near-infrared spectroscopy engagement recognition KNN CFS hybrid system sensor |
| url | https://www.mdpi.com/1424-8220/18/11/3691 |
| work_keys_str_mv | AT fadillazennifa hybridsystemforengagementrecognitionduringcognitivetasksusingacfsknnalgorithm AT shoageno hybridsystemforengagementrecognitionduringcognitivetasksusingacfsknnalgorithm AT shotahatano hybridsystemforengagementrecognitionduringcognitivetasksusingacfsknnalgorithm AT keijiiramina hybridsystemforengagementrecognitionduringcognitivetasksusingacfsknnalgorithm |