Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2409.16126 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908495864922112 |
|---|---|
| author | Singh, Alakhsimar Goyal, Kanav Verma, Nischay Kumar, Puneet Li, Xiaobai Singh, Amritpal |
| author_facet | Singh, Alakhsimar Goyal, Kanav Verma, Nischay Kumar, Puneet Li, Xiaobai Singh, Amritpal |
| contents | This paper presents VisioPhysioENet, a novel multimodal system that leverages visual and physiological signals to detect learner engagement. It employs a two-level approach for extracting both visual and physiological features. For visual feature extraction, Dlib is used to detect facial landmarks, while OpenCV provides additional estimations. The face recognition library, built on Dlib, is used to identify the facial region of interest specifically for physiological signal extraction. Physiological signals are then extracted using the plane-orthogonal-toskin method to assess cardiovascular activity. These features are integrated using advanced machine learning classifiers, enhancing the detection of various levels of engagement. We thoroughly tested VisioPhysioENet on the DAiSEE dataset. It achieved an accuracy of 63.09%. This shows it can better identify different levels of engagement compared to many existing methods. It performed 8.6% better than the only other model that uses both physiological and visual features. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_16126 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | VisioPhysioENet: Visual Physiological Engagement Detection Network Singh, Alakhsimar Goyal, Kanav Verma, Nischay Kumar, Puneet Li, Xiaobai Singh, Amritpal Computer Vision and Pattern Recognition This paper presents VisioPhysioENet, a novel multimodal system that leverages visual and physiological signals to detect learner engagement. It employs a two-level approach for extracting both visual and physiological features. For visual feature extraction, Dlib is used to detect facial landmarks, while OpenCV provides additional estimations. The face recognition library, built on Dlib, is used to identify the facial region of interest specifically for physiological signal extraction. Physiological signals are then extracted using the plane-orthogonal-toskin method to assess cardiovascular activity. These features are integrated using advanced machine learning classifiers, enhancing the detection of various levels of engagement. We thoroughly tested VisioPhysioENet on the DAiSEE dataset. It achieved an accuracy of 63.09%. This shows it can better identify different levels of engagement compared to many existing methods. It performed 8.6% better than the only other model that uses both physiological and visual features. |
| title | VisioPhysioENet: Visual Physiological Engagement Detection Network |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.16126 |