Application of Deep Learning on Student Engagement in e-learning environments

Bhardwaj, Prakhar; Gupta, Praveen; Panwar, Harsh; Siddiqui, Mohammad Khubeb; Bhaik, Anubha

doi:10.1016/j.compeleceng.2021.107277

Cited by 55 publications

(27 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, the pink clusters showed searches related to artificial intelligence, machine learning, and deep learning. The researcher can also take these subfields as topics for research in e-learning, especially the last cluster, which formed a recent research trend for many scholars ( Bhardwaj et al, 2021 ; Kashive et al, 2021 ; Rasheed and Wahid, 2021 ).…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

E-Learning Research Trends in Higher Education in Light of COVID-19: A Bibliometric Analysis

et al. 2022

View full text Add to dashboard Cite

This paper provides a broad bibliometric overview of the important conceptual advances that have been published during COVID-19 within “e-learning in higher education.” E-learning as a concept has been widely used in the academic and professional communities and has been approved as an educational approach during COVID-19. This article starts with a literature review of e-learning. Diverse subjects have appeared on the topic of e-learning, which is indicative of the dynamic and multidisciplinary nature of the field. These include analyses of the most influential authors, of models and networks for bibliometric analysis, and progress towards the current research within the most critical areas. A bibliometric review analyzes data of 602 studies published (2020–2021) in the Web of Science (WoS) database to fully understand this field. The data were examined using VOSviewer, CiteSpace, and KnowledgeMatrix Plus to extract networks and bibliometric indicators about keywords, authors, organizations, and countries. The study concluded with several results within higher education. Many converging words or sub-fields of e-learning in higher education included distance learning, distance learning, interactive learning, online learning, virtual learning, computer-based learning, digital learning, and blended learning (hybrid learning). This research is mainly focused on pedagogical techniques, particularly e-learning and collaborative learning, but these are not the only trends developing in this area. The sub-fields of artificial intelligence, machine learning, and deep learning constitute new research directions for e-learning in light of COVID-19 and are suggestive of new approaches for further analysis.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Finally, using artificial intelligence, machine learning, and deep learning to transform the e-learning Industry, this final sub-field formed a recent research trend for many scholars ( Bhardwaj et al, 2021 ; Kashive et al, 2021 ; Rasheed and Wahid, 2021 ).…”

Section: Resultsmentioning

confidence: 99%

E-Learning Research Trends in Higher Education in Light of COVID-19: A Bibliometric Analysis

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In order to be a good receiver of student communication, a lecturer must be aware of many of the subtle nonverbal cues that their students express [ 46 ]. Automated computer vision and deep learning-based approaches are the most popular methods for assessing learners’ engagement based on their facial expression [ 16 – 19 , 47 – 49 ]. There are several studies in the literature on detecting learners’ engagement.…”

Section: Related Workmentioning

confidence: 99%

“…The combination of the two modalities, EEG and facial expression, has the potential to improve performance, but implementing a brain-computer interface (BCI) module in a practical classroom or online learning situation would be difficult because of mental privacy, wearability, portability, and cost constraint [ 26 , 53 , 54 ]. Bhardwaj et al [ 49 ], have introduced a deep learning approach to compute the students’ Mean Engagement Score (MES) in real-time through emotion detection and emotion weights picked up from a survey carried out on students in an hour-long classroom. Tongu et al [ 48 ] used Microsoft’s emotion identification API to identify emotions like sadness, joy, fear, anger, surprise, and contempt throughout the lecture.…”

Section: Related Workmentioning

confidence: 99%

Three-dimensional DenseNet self-attention neural network for automatic detection of student’s engagement

et al. 2022

View full text Add to dashboard Cite

Today, due to the widespread outbreak of the deadly coronavirus, popularly known as COVID-19, the traditional classroom education has been shifted to computer-based learning. Students of various cognitive and psychological abilities participate in the learning process. However, most students are hesitant to provide regular and honest feedback on the comprehensiveness of the course, making it difficult for the instructor to ensure that all students are grasping the information at the same rate. The students’ understanding of the course and their emotional engagement, as indicated via facial expressions, are intertwined. This paper attempts to present a three-dimensional DenseNet self-attention neural network (DenseAttNet) used to identify and evaluate student participation in modern and traditional educational programs. With the Dataset for Affective States in E-Environments (DAiSEE), the proposed DenseAttNet model outperformed all other existing methods, achieving baseline accuracy of 63.59% for engagement classification and 54.27% for boredom classification, respectively. Besides, DenseAttNet trained on all four multi-labels, namely boredom, engagement, confusion, and frustration has registered an accuracy of 81.17%, 94.85%, 90.96%, and 95.85%, respectively. In addition, we performed a regression experiment on DAiSEE and obtained the lowest Mean Square Error (MSE) value of 0.0347. Finally, the proposed approach achieves a competitive MSE of 0.0877 when validated on the Emotion Recognition in the Wild Engagement Prediction (EmotiW-EP) dataset.

show abstract

“…Here, the students are guided for their own learning, can follow the pace they want, and make their own decisions about what to learn. Some state-of-the-art research contributions in the context of DL techniques for the education industry can be found here [89][90][91][92][93][94]. A comparison of some prominent studies is presented in Table 3.…”

Section: Educationmentioning

confidence: 99%

Deep Learning for the Industrial Internet of Things (IIoT): A Comprehensive Survey of Techniques, Implementation Frameworks, Potential Applications, and Future Directions

Latif

Driss

Boulila

et al. 2021

Sensors

View full text Add to dashboard Cite

The Industrial Internet of Things (IIoT) refers to the use of smart sensors, actuators, fast communication protocols, and efficient cybersecurity mechanisms to improve industrial processes and applications. In large industrial networks, smart devices generate large amounts of data, and thus IIoT frameworks require intelligent, robust techniques for big data analysis. Artificial intelligence (AI) and deep learning (DL) techniques produce promising results in IIoT networks due to their intelligent learning and processing capabilities. This survey article assesses the potential of DL in IIoT applications and presents a brief architecture of IIoT with key enabling technologies. Several well-known DL algorithms are then discussed along with their theoretical backgrounds and several software and hardware frameworks for DL implementations. Potential deployments of DL techniques in IIoT applications are briefly discussed. Finally, this survey highlights significant challenges and future directions for future research endeavors.

show abstract

Application of Deep Learning on Student Engagement in e-learning environments

Cited by 55 publications

References 21 publications

E-Learning Research Trends in Higher Education in Light of COVID-19: A Bibliometric Analysis

E-Learning Research Trends in Higher Education in Light of COVID-19: A Bibliometric Analysis

Three-dimensional DenseNet self-attention neural network for automatic detection of student’s engagement

Deep Learning for the Industrial Internet of Things (IIoT): A Comprehensive Survey of Techniques, Implementation Frameworks, Potential Applications, and Future Directions

Contact Info

Product

Resources

About