Detection of student engagement in e-learning environments using EfficientnetV2-L together with RNN-based models
Automatic detection of student engagement levels from videos, which is a spatio-temporal classification problem is crucial for enhancing the quality of online education. This paper addresses this challenge by proposing four novel hybrid end-to-end deep learning models designed for the automatic dete...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tech Science Press
2024
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/116897/ http://psasir.upm.edu.my/id/eprint/116897/1/116897.pdf |
| _version_ | 1848867113301704704 |
|---|---|
| author | Rezaee, Mohammadreza Perumal, Thinagaran Shiri, Farhad Mortezapour Ahmadi, Ehsan |
| author_facet | Rezaee, Mohammadreza Perumal, Thinagaran Shiri, Farhad Mortezapour Ahmadi, Ehsan |
| author_sort | Rezaee, Mohammadreza |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | Automatic detection of student engagement levels from videos, which is a spatio-temporal classification problem is crucial for enhancing the quality of online education. This paper addresses this challenge by proposing four novel hybrid end-to-end deep learning models designed for the automatic detection of student engagement levels in e-learning videos. The evaluation of these models utilizes the DAiSEE dataset, a public repository capturing student affective states in e-learning scenarios. The initial model integrates EfficientNetV2-L with Gated Recurrent Unit (GRU) and attains an accuracy of 61.45%. Subsequently, the second model combines EfficientNetV2-L with bidirectional GRU (Bi-GRU), yielding an accuracy of 61.56%. The third and fourth models leverage a fusion of EfficientNetV2-L with Long Short-Term Memory(LSTM)and bidirectionalLSTM(Bi-LSTM),achieving accuracies of 62.11% and 61.67%, respectively. Our findings demonstrate the viability of these models in effectively discerning student engagement levels, with the EfficientNetV2-L+LSTM model emerging as the most proficient, reaching an accuracy of 62.11%. This study underscores the potential of hybrid spatio-temporal networks in automating the detection of student engagement, thereby contributing to advancements in online education quality. |
| first_indexed | 2025-11-15T14:31:20Z |
| format | Article |
| id | upm-116897 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T14:31:20Z |
| publishDate | 2024 |
| publisher | Tech Science Press |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-1168972025-04-17T04:46:44Z http://psasir.upm.edu.my/id/eprint/116897/ Detection of student engagement in e-learning environments using EfficientnetV2-L together with RNN-based models Rezaee, Mohammadreza Perumal, Thinagaran Shiri, Farhad Mortezapour Ahmadi, Ehsan Automatic detection of student engagement levels from videos, which is a spatio-temporal classification problem is crucial for enhancing the quality of online education. This paper addresses this challenge by proposing four novel hybrid end-to-end deep learning models designed for the automatic detection of student engagement levels in e-learning videos. The evaluation of these models utilizes the DAiSEE dataset, a public repository capturing student affective states in e-learning scenarios. The initial model integrates EfficientNetV2-L with Gated Recurrent Unit (GRU) and attains an accuracy of 61.45%. Subsequently, the second model combines EfficientNetV2-L with bidirectional GRU (Bi-GRU), yielding an accuracy of 61.56%. The third and fourth models leverage a fusion of EfficientNetV2-L with Long Short-Term Memory(LSTM)and bidirectionalLSTM(Bi-LSTM),achieving accuracies of 62.11% and 61.67%, respectively. Our findings demonstrate the viability of these models in effectively discerning student engagement levels, with the EfficientNetV2-L+LSTM model emerging as the most proficient, reaching an accuracy of 62.11%. This study underscores the potential of hybrid spatio-temporal networks in automating the detection of student engagement, thereby contributing to advancements in online education quality. Tech Science Press 2024-04-24 Article PeerReviewed text en cc_by_4 http://psasir.upm.edu.my/id/eprint/116897/1/116897.pdf Rezaee, Mohammadreza and Perumal, Thinagaran and Shiri, Farhad Mortezapour and Ahmadi, Ehsan (2024) Detection of student engagement in e-learning environments using EfficientnetV2-L together with RNN-based models. Journal on Artificial Intelligence, 6 (1). pp. 85-103. ISSN 2579-003X https://www.techscience.com/jai/v6n1/56239 10.32604/jai.2024.048911 |
| spellingShingle | Rezaee, Mohammadreza Perumal, Thinagaran Shiri, Farhad Mortezapour Ahmadi, Ehsan Detection of student engagement in e-learning environments using EfficientnetV2-L together with RNN-based models |
| title | Detection of student engagement in e-learning environments using EfficientnetV2-L together with RNN-based models |
| title_full | Detection of student engagement in e-learning environments using EfficientnetV2-L together with RNN-based models |
| title_fullStr | Detection of student engagement in e-learning environments using EfficientnetV2-L together with RNN-based models |
| title_full_unstemmed | Detection of student engagement in e-learning environments using EfficientnetV2-L together with RNN-based models |
| title_short | Detection of student engagement in e-learning environments using EfficientnetV2-L together with RNN-based models |
| title_sort | detection of student engagement in e-learning environments using efficientnetv2-l together with rnn-based models |
| url | http://psasir.upm.edu.my/id/eprint/116897/ http://psasir.upm.edu.my/id/eprint/116897/ http://psasir.upm.edu.my/id/eprint/116897/ http://psasir.upm.edu.my/id/eprint/116897/1/116897.pdf |