E-learning Sessions Research Articles

Computer Vision for E-learning Student Face Reaction Detection for Improving Learning Rate

In the advent of e-learning, understanding student engagement and reaction is crucial for improving the quality of education and enhancing the learning rate. With the advancement of computer vision technologies, there is a significant opportunity to analyze and interpret student reactions in a non-intrusive manner. This study proposes a novel framework employing Faster R-CNN integrated with DenseNet architecture for real-time detection of student facial reactions during e-learning sessions. The proposed method leverages the strengths of Faster R-CNN in generating high-quality region proposals for object detection tasks, coupled with the DenseNet’s efficiency in feature propagation and reduction in the number of parameters, which is well-suited for processing the intricate patterns in facial expressions. Our approach begins with the application of Faster R-CNN to extract potential facial regions with high accuracy and reduced computational cost. The integration of DenseNet as a backbone for feature extraction within Faster R-CNN capitalizes on its densely connected convolutional networks, ensuring maximum information flow between layers in the network. By doing so, the system becomes exceptionally adept at recognizing subtle changes in facial features that indicate various student reactions, such as confusion, engagement, or boredom. We conducted a series of experiments using a diverse dataset of e-learning interactions, collected under various lighting conditions and involving multiple ethnicities to ensure robustness and generalizability. The model was trained and validated on this dataset, and the results demonstrate a significant improvement in detection rates of student reactions compared to existing methods.

Early Bird or Night Owl: Insights into Dutch Students’ Study Patterns using the Medical Faculty’s E-learning Registrations

Phenomenon : Educational activities for students are typically arranged without consideration of their preferences or peak performance hours. Students might prefer to study at different times based on their chronotype, aiming to optimize their performance. While face-to-face activities during the academic schedule do not offer flexibility and cannot reflect students’ natural learning rhythm, asynchronous e-learning facilitates studying at one’s preferred time. Given their ubiquitous accessibility, students can use e-learning resources according to their individual needs and preferences. E-learning usage data hence serves as a valuable proxy for certain study behaviors, presenting research opportunities to explore students’ study patterns. This retrospective study aims to investigate when and for how long undergraduate students used medical e-learning modules. Approach : We performed a cross-sectional analysis of e-learning usage at one medical faculty in the Netherlands. We used data from 562 undergraduate multimedia e-learning modules for pre-clinical students, covering various medical topics over a span of two academic years (2018/19 and 2019/20). We employed educational data mining approaches to process the data and subsequently identified patterns in access times and durations. Findings : We obtained data from 70,805 e-learning sessions with 116,569 module visits and 1,495,342 page views. On average, students used e-learning for 16.8 min daily and stopped using a module after 10.2 min, but access patterns varied widely. E-learning was used seven days a week with an hourly access pattern during business hours on weekdays. Across all other times, there was a smooth increase or decrease in e-learning usage. During the week, more students started e-learning sessions in the morning (34.5% vs. 19.1%) while fewer students started in the afternoon (42.6% vs. 50.8%) and the evening (19.4% vs. 27.0%). We identified ‘early bird’ and ‘night owl’ user groups that show distinct study patterns. Insights : This retrospective educational data mining study reveals new insights into the study patterns of a complete student cohort during and outside lecture hours. These findings underline the value of 24/7 accessible study material. In addition, our findings may serve as a guide for researchers and educationalists seeking to develop more individualized educational programs.

Exploring Learning Analytics In E-Learning: A Comprehensive Analysis of Student Characteristics and Behavior

This article aims to explore learning analytics in e-learning through a comprehensive analysis of student characteristics and behavior. E-learning has become increasingly significant in education, particularly due to the social situation influenced by the pandemic. The Learning Management System (LMS) has become a crucial tool for educators to track and record student learning in e-learning environments. Learning analytics can aid in understanding the context of students, ensuring that they receive a personalized learning experience aligned with learning objectives. However, educators often face challenges in conducting learning analytics for e-learning students, primarily due to the large number of students to analyze and limited data availability. This study seeks to provide a detailed description of e-learning students within the Open and Distance Education (ODE) system. ODE students exhibit high diversity in demographic profiles, learning behaviors, and competency backgrounds. To support this research, we utilize datasets containing student demographic profiles and learning activity data during e-learning sessions. The datasets are obtained from the academic system and LMS log data of Universitas Terbuka. The article employs Exploratory Data Analysis (EDA) and data science approaches as the foundation for predictive and prescriptive analytics of student learning outcomes. Relevant features are extracted from the dataset to build a robust predictive model. The analysis results present patterns and relationships between student characteristics, learning behaviors, and academic achievements. This research aims to provide valuable insights for the development of more effective and personalized e-learning strategies to enhance student learning outcomes in the context of distance education. Moreover, the analysis findings can serve as a basis for informed academic decision-making to improve the quality of e-learning environments.

Difficulties faced by Medical Students of Southern Punjab in E-Learning during COVID-19. A Cross-Sectional Study

Introduction: Amidst the challenges imposed by the COVID-19 pandemic, this cross-sectional study investigates the specific difficulties encountered by medical students in southern Punjab while navigating the realm of e-learning in their academic pursuits
 Objective: The primary objective of this study was to ascertain the challenges faced by MBBS students in southern Punjab while participating in e-learning throughout the COVID-19 pandemic.
 Methods: In May 2020, a cross-sectional study was undertaken during the first wave of COVID-19 lockdown among third and final-year MBBS students attending E-learning sessions. The sample comprised 32 male and 43 female students, totaling 85 in the third year and 18 in the final year, with a targeted response rate of 75 to achieve a 95% confidence interval.
 Results: The study findings reveal that a significant proportion of participants, comprising 66%, faced challenges in online classes owing to connectivity issues arising from their residency in less developed regions of southern Punjab. Forty percent of students did not face any difficulties during E-learning. These findings indicate that a noteworthy percentage of students, accounting for 60%, possess a negative perspective concerning online classes. 
 Conclusion: Our study participants didnot prefer E-learning, with many reporting internet connectivity issues, particularly those from southern Punjab. We thus recommend that the administration and faculty consider implementing asynchronous e-learning activities to enable students in less-developed areas with poor internet connectivity to benefit from online learning.
 Keywords: Distance Education, Online Learning, COVID-19, Medical Students

GPT-Empowered Personalized eLearning System for Programming Languages

The eLearning approach to programming language instruction has gained widespread acceptance due to advantages such as accessibility, temporal flexibility, and content reusability. However, the current eLearning for programming predominantly employs the delivery of one-size-fits-all content, engendering elevated costs in both the development of language coursework and administration of eLearning sessions, which includes the labor-intensive task of grading student submissions. A compelling research question to consider is how to construct an eLearning system capable of delivering personalized, student-centric content, automating the generation of coursework elements, and eliminating the need for instructor involvement in the management of eLearning sessions. Our approach to delivering a definite solution to the question involves the utilization of a suite of advanced software technologies: GPT to dynamically generate course contents/components, prompt engineering to personalize course content for each individual student, and autonomous computing to manage eLearning sessions without the need for human intervention. The research results encompass the design of an eLearning framework covering all programming languages, a fully functional Python-based implementation, seamless integration with ChatGPT for dynamic content generation, a high degree of content personalization, and the elimination of manual effort required for managing eLearning sessions.

Commentary: Effectiveness of a hybrid digital substance abuse prevention approach combining e-learning and in-person class sessions.

Commentary: Effectiveness of a hybrid digital substance abuse prevention approach combining e-learning and in-person class sessions.

Transforming traditional physiotherapy hands-on skills teaching into video-based learning

BackgroundPandemic-induced restrictions forced curriculum transformation from on-site education to virtual learning options. This report describes this transition, the challenge of creating technology-enhanced learning for hands-on psychomotor skills teaching in physiotherapy, and students’ evaluations of the new technology-enhanced learning approach in Complex Decongestive Physiotherapy.MethodsOn-site theoretical background lectures were replaced with e-learning sessions. Faculty hands-on skills demonstrations for the entire class were replaced with video-recorded demonstrations. Videos included verbal and written instructions and were complemented with checklists guiding the students, training in pairs, through their learning tasks. A cross-sectional observational survey for teaching quality evaluated this new technology-enhanced learning approach and assessed students’ preference for traditional or video-based hands-on skills learning.ResultsSurvey return rate was > 50% (46 participating students). Teaching quality was rated between 1.5 ± 0.5 and 1.8 ± 0.4 (Likert scale from − 2 to + 2). Most students (66.7%) preferred the new approach. They appreciated for example that videos were available all the time, enabling self-paced learning, providing an equally good view on skills demonstrations, and the convenience to be able to rewind, re-view, and use speed adjustment options.ConclusionsStudents preferred the new video-based learning of skills for Complex Decongestive Physiotherapy. Because in-class live skills demonstrations were omitted, faculty had more time to provide individual feedback and answer questions. The shift from teacher- to student-centered learning enabled students to control their own learning pace. The innovative program was maintained after pandemic-induced restrictions were lifted. The success of this approach should be tested in other physiotherapy settings and different educational institutions.

A machine learning-based decision support system for temporal human cognitive state estimation during online education using wearable physiological monitoring devices

Over the last decade, there has been a considerable increase in the popularity of online education. As a result, the online learning or e-learning industry has flourished, providing benefits to students, learners, educators, and education experts. Despite the advantages of e-learning, it also has its drawbacks. While e-learning enables students to access the learning materials at their convenience from any location, one of the significant challenges is the lack of monitoring of their level of attention during e-learning sessions. It is challenging to ascertain whether a student is actively engaged in the learning process. To address this issue, we have proposed a decision support system (DSS) based on wearable physiological sensor signals (i.e., Electroencephalogram (EEG) signals) that can inform the instructor whether a student is attentive. For developing DSS, we recorded an EEG-based dataset using a neurosky device, and 100 individuals participated in the study. The learning state is divided into two categories: attentive and inattentive. In this paper, machine learning techniques are employed to integrate the proposed DSS, which can predict, analyse, and validate the student’s level of attention or inattention throughout the e-learning session. The findings show that the Support Vector Machine (SVM) approach is the most efficient method for attention prediction, achieving an accuracy of 91.68% compared to logistic regression and ridge regression. Additionally, we examined the frequency bands that were most significant in predicting the learning state, with beta and alpha waves being identified as the key contributors in predicting attention. To further evaluate the data, we use K-means and Hierarchical algorithms to cluster beta and alpha data points. K-means effectively identifies an ideal representative of an attentive or inattentive state. Thus, EEG waves can effectively reveal whether a student is attentive during real-time e-learning sessions, providing a promising approach for providing a valuable tool for decision support in the E-Learning Environment.

PENERAPAN ELEMEN NILAI MURNI DAN ETIKA MELALUI PLATFORM E-PEMBELAJARAN PENDIDIKAN ISLAM SEKOLAH RENDAH

Good values and ethics are the cores in developing the personality of each person. They are among the elements that need to be instilled in learning sessions physically or virtually through e-learning platforms. Instilling these elements of good values and ethics will form commendable behaviours to create generations with a great personality. Previous studies have shown that the use of e-learning platforms to replace the face-to-face physical learning sessions in classes has some implications to the development of students’ personality. For example, the students did not give feedback to their teachers during the e-learning sessions, did not start the e-learning sessions with prayer recitation, did not attend the online learning sessions punctually, did not give salutation to the teachers when entering the online classes, and did not complete their assignment properly and ethically. These issues are indirectly related to the effectiveness and roles of Islamic Education teachers in building up the students’ personality through the e-learning platforms. Therefore, this study aimed to observe the experiences of Islamic Education teachers in instilling the elements of good values and ethics in implementing e-learning. This qualitative study employed in-depth interviews involving three Islamic Education teachers. The interview data were analysed thematically using the Nvivo software, version 1.7 to produce the study’s findings. The analysis of interviews found that all the Islamic Education teachers managed to instil some of the elements of good values during the Islamic Education e-learning sessions. Besides, the findings also identified a few challenges in e-learning faced by the Islamic Education teachers that these challenges had led to limitations in instilling the good values in the students. It is hoped that the study would help educators to increase their knowledge in instilling the elements of good values and ethics through the e-learning platforms while also spreading the inputs especially to parents about the challenges faced by the Islamic Education teachers in building up students’ personality.

International recruitment of radiographers and the development of a workplace integration support package: Project evaluation

IntroductionIn October 2020, a regional workforce action group was established jointly by Health Education England (HEE) and NHS England and Improvement (NHSEI) in the South West to work collaboratively to address the workforce challenges within diagnostic imaging. Fifty-eight internationally recruited radiographers were offered employment in departments across the region, the majority of them taking up their posts in the UK in early 2021. The aim of the study presented here was to evaluate the efficacy of a training resource developed by Plymouth Marjon University, with input from HEE and NHSEI, to support workplace and cultural integration for the new recruits. MethodsThe training package to help newly recruited radiographers from outside the UK integrate into their host departments was developed using flexible learning opportunities centred on reusable digital learning assets. Self-paced e-learning sessions were augmented by group ‘connected’ sessions online. Two surveys were undertaken, exploring the impact of this workforce integration programme for International radiographers joining the NHS. ResultsSurvey results indicate that the integration programme's three-phase strategy has seen an impact on 6 out of 12 self-efficacy measures, raised awareness of challenges, and increased personal awareness of implications for practice. By the end of the programme, delegates were in the top two quintiles for their average well-being score. ConclusionPrincipal recommendations include ensuring digital accessibility for new recruits as part of the on-boarding process, considering the timing of delivery of any online connected support sessions, the provision of long-term pastoral support; and mandating the training requirement for managers and team leaders. Implications for practiceSuccess of international recruitment campaigns can be enhanced through the implementation of an online integration package

Deep Analysis of Student Body Activities to Detect Engagement State in E-Learning Sessions

In this paper, we propose new 3D CNN prediction models for detecting student engagement levels in an e-learning environment. The first generated model classifies students’ engagement to high positive engagement or low positive engagement. The second generated model classifies engagement to low negative engagement or disengagement. To predict the engagement level, the proposed prediction models learn the deep spatiotemporal features of the body activities of the students. In addition, we collected a new video dataset for this study. The new dataset was collected in realistic, uncontrolled settings from real students attending real online classes. Our findings are threefold: (1) Spatiotemporal features are more suitable for analyzing body activities from video data; (2) our proposed prediction models outperform state-of-the-art methods and have proven their effectiveness; and (3) our newly collected video dataset, which reflects realistic scenarios, contributed to delivering comparable results to current methods. The findings of this work will strengthen the knowledge base for the development of intelligent and interactive e-learning systems that can give feedback based on user engagement.

Professional shariah audit training via the e-learning approach during COVID-19: challenges and prospects

PurposeThis study aims to explore and identify potential challenges and prospects for conducting the professional shariah audit training programme via an e-learning approach during coronavirus disease 2019 (COVID-19).Design/methodology/approachQuestionnaires were administered to 296 participants who were enrolled in the professional shariah audit training programme via e-learning during the COVID-19 pandemic outbreak in 2020. These participants were final-year students from selected Malaysian public universities.FindingsFindings show that several main challenges are faced in adopting an e-learning approach for conducting the professional shariah audit training programme such as the inability to do more hands-on, group and physical activities, different understandings based on academic backgrounds, difficulty in learning practical and technical topics, technical issues and problems during e-learning sessions. These lead to the unsuitability of conducting professional training via the e-learning approach. In terms of prospects of knowledge learnt via the e-learning approach, participants showed that they are able to master all six modules covered in the professional shariah audit training programme via the e-learning approach. These include (1) shariah principles; (2) shariah governance; (3) Islamic financial transactions; (4) shariah risk management; (5) shariah audit planning and programme; and (6) shariah audit fieldwork and communication.Practical implicationsBased on the findings, it is suggested to have more time spent and earlier preparation on the learning contents and sessions, more discussion on actual contents and practical exercises and competency of the trainers in delivering e-learning sessions.Originality/valueThis study is believed to be one among the pioneering studies on the potential challenges and prospects in adopting e-learning for conducting the professional shariah audit training programme due to COVID-19.

Effectiveness of blended versus fully digital training in primary care psychiatry: A retrospective comparison from India.

We compared effectiveness of blended mode (consisting of traditional classroom teaching and e-learning sessions) and fully digital mode (e-learning sessions alone) of primary care psychiatry training for primary care doctors in Chhattisgarh. We retrospectively compared the engagement in training, knowledge (K), attitude (A), and practice (P) in primary care psychiatry, and patient identification by primary care doctors (n = 941) from Chhattisgarh region who underwent training through either blended training mode (n = 546) or fully digital training mode (n = 395) for 16 h each, using Clinical Schedules for Primary Care Psychiatry based modules between June 2019 and November 2020 with a tertiary care center (NIMHANS, Bengaluru) as hub. The Statistical Package for the Social Sciences version 27 was used to analyze the data. Continuous variables were analyzed using the independent samples t-test, and discrete variables were analyzed using the Chi-square test. A repeated measures analysis of variance (ANOVA) (two-way mixed design) was used to see the interaction of training type and time of pre- and post-KAP measurement while controlling for years of experience. The number of patients identified by both training groups over 8 months was also compared using the repeated measures ANOVA (two-way mixed design). Engagement inferred by the number of participants completing pre-KAP forms (75%), post-KAP forms (43%), post-session assessments (37- 47%), case presentation (33.9%), and certification (32.1%) was better in the blended group (P < 0.05). The mean gain in KAP scores was significantly higher in the blended group controlling for the years of experience as primary care doctor (PCD) (F = 30.36, P < 0.001). PCDs in the blended training group consistently identified a higher number of patients with mental illness over 8 months of follow-up (F = 6.21, P < 0.001). The blended mode yielded better results in primary care psychiatry training compared to fully digital mode. In-person interactions while provided for a very brief proportion of the training seem to have an unmistakable imprint on the outcomes and seem critical for better consolidation and assimilation of information, which translates into better practice.

Monitoring and Evaluating Quality of e-Learning in Basic Sciences Section and Introduction to Clinical Medicine Section in the School of Medicine During COVID-19 Pandemic

Many universities have turned to e-learning during the Corona Virus Disease 2019 (COVID-19) pandemic around the world. Ensuring the quality of higher education, especially in medicine, is considered one of the tasks of the education system, which is essential for both traditional methods and e-learning. This study aimed to monitor and evaluate the quality of e-learning conducted using the university LMS system for courses offered in the BS section and ICM section of medicine during the COVID-19 pandemic. The present study was an evaluation study using a goal-based approach that was conducted using the descriptive cross-sectional method. This study included 76 specialized courses offered in the first semester of the academic year of Bandar Abbas University of Medical Sciences, and participants were evaluated in terms of compliance with the course plan and the quality of the uploaded content. About 60% of e-learning courses presented in the course plan were in compliance with the curriculum. The uploaded educational content of 46.1% of the courses was good, 38.2% of the courses were relatively good, and 15.8% of the courses were not good. In the general review, e-learning courses offered were at a relatively desired level. Due to the new e-learning in medical schools, there is a need to monitor e-learning sessions during the course.

Effectiveness of a hybrid digital substance abuse prevention approach combining e-Learning and in-person class sessions.

BackgroundEffective school-based programs for preventing substance abuse offer considerable public health potential. Yet limited class time and uneven implementation fidelity can be barriers to widespread adoption and high-quality implementation. A hybrid digital approach may be effective and help address these barriers.ObjectiveTo evaluate the effectiveness of a hybrid substance abuse prevention program for middle school students consisting of e-learning modules and in-person class sessions.DesignTwenty-three United States (U.S.) middle schools were randomly assigned either to an intervention condition (13 schools) or a treatment-as-usual control condition (10 schools) where standard health education material was delivered. There were 1,447 participants who completed the pre-test and post-test assessments, of which 48.3% were male and 51.7% female.InterventionThe hybrid digital intervention consisted of 14 brief e-learning modules and six classroom sessions adapted from an evidence-based program designed for classroom implementation to increase knowledge of adverse consequences of substance use and improve social skills, personal coping skills, and skills for resisting social influences to smoke, drink, or use drugs.MeasuresParticipating students completed online pre-test and post-test surveys to assess substance use, knowledge, and life skills.ResultsThere were significant reductions in substance use for the hybrid digital condition compared to the control condition as well as significant increases in health knowledge, skills knowledge, and life skills.ConclusionsA hybrid digital approach to substance abuse prevention is effective and offers potential for overcoming common barriers to widespread adoption and high-quality implementation.

Blended Oncology Nursing Training: A Quality Initiative in East Africa

Lack of education and awareness about cancer treatment may result in suboptimal care of patients with cancer. Unlike high-income countries, resource-limited countries lack the standardized training and scope of practice in oncology nursing. This quality improvement project was conducted to assess nurses' knowledge gain, retention of knowledge and clinical skill set, and feasibility of a blended learning approach in the care of adult oncology patients across four hospitals in Kenya and Tanzania. We used a combination of computer-led eLearning sessions and face-to-face interactions over 12 months for cancer education to oncology nurses. Pre- and posttests with each training session were combined with face-to-face clinical skills training at beginning and completion of the course. A comprehensive postassessment was conducted immediately after the training, and at 6, 9, and 12 months to evaluate knowledge gain and retention. Of 21 participants across four sites, there was a statistically significant improvement in knowledge scores for 12 participants (P value < .05). The mean pre- and posttest results found significant differences across 10 sessions individually and cumulatively (P value < .01). Results from a one-way repeated measures analysis of variance (ANOVA) test on comprehensive test results suggested that there was no significant difference in knowledge retention across 9 months (F(2, 30) = 1.648412, P > .05). Blended learning is an effective tool in improving knowledge, skills, and self-efficacy for clinicians practicing in resource-limited countries. Developing a structured oncology training program has implications for bridging knowledge gaps among clinicians in resource-limited countries and promoting international knowledge exchange.

Perception of medical students regarding E-learning during lockdown in COVID–19 pandemic: A cross-sectional study in a medical college, North Kerala

Background: The digital learning in this pandemic era of COVID-19 evolved out in a perplexed environment as a viable alternative to offline or traditional classes. The e-learning carries its own merits as well as demerits, but however, this happened to be the only possible solution in this dreaded situation. With respect to medicos, as they are prone to be exposed to environments connected with Covid infected patients, additional care including online classes turned to be the better option. Aim and Objective: To determine the perception of medical students regarding e-learning during lockdown in COVID-19 pandemic. Settings and Design: A cross-sectional study was conducted among medical students of all the batches in a private medical College, Kozhikode. Methods and Material: Primary data were collected using structured Google questionnaire. Stratified sampling method has been adopted and the sample size was 400. Statistical analysis used: Data analysed using SPSS 18 software. Results: Majority of the participants used Zoom as modality of learning and half of the total participants got adapted to the system over time. During e-learning sessions, most of the medicos expressed their concerns regarding lack of clinical exposure, in addition to their losses in social communication skills. Factors such as the legitimate requirements of clinical phase students, issues of poor internet connectivity and health problems were inclined to demand traditional learning, which were statistically significant. Conclusion: Even though they were subjected to both online and offline methods of education, majority of respondents preferred traditional learning.

Pilot Study Using An Online Platform “EPrescribe” in the Training and Assessment of 4th Year Medical Students’ Competency in Prescribing

PURPOSEThe Association of American Medical Colleges has delineated 13 Entrustable Professional Activities (EPAs) that entering residents should be expected to perform on day 1 of residency without direct supervision. EPA4, Enter and discuss orders and prescriptions, describes an activity that all recent medical graduates (Interns) spend a great deal of time daily on.Additionally, with the ever‐increasing numbers of pharmaceuticals and biologics, there is a need for clinical pharmacology education in the curriculum to help students achieve EPA4. The Department of Medical Education at GCSOM partnered with the BPS to use their online platform in a two‐week clinical pharmacology elective for 4th year medical students. The hypothesis of this study was that completion of the program modules will enhance student learning and satisfaction with respect to prescribing.METHODSWe used the BPS Assessment platform which provides prescribing skills modules for learners, which they access through a cloud‐based, content‐rich online assessment environment, with real‐time feedback. The assessments were reconciled to the US context insuring they were relevant to our students. Mean scores before and after completing the modules were compared using a paired t‐test. Students also completed a satisfaction questionnaire.RESULTSTo date, 6 students have completed the program. The average scores (±SD) after completing the modules increased significantly (Before: 42%±14%; After: 74%±10%; p=0.001). This represented a normalized gain of 54%. Students tended to Agree/Strongly Agree to the 6 items related to the eLearning sessions, interface and assessment in the satisfaction questionnaire.CONCLUSIONSThe results indicate that students’ knowledge and skills in prescribing increased as a result of their study of the modules. Their high ratings of the program suggest that students found it useful. In conclusion, the BPS program facilitates students’ abilities in prescribing therapies or interventions beneficial to patients and will be helpful in meeting the expectations of EPA4 as students enter residency.

SCHOOL CHILDREN IN E-CAMPUS - NEW INSIGHT

Introduction: The current pandemic has affected the education of children in an unprecedented way. Children are not able to go to school and in a short span of time schools have tried to come up with online teaching methods which have not been validated. This study was undertaken to assess children's viewpoint on this new mode of teaching. Aims: The primary objective of the present study was to assess the clarity, logical flow and effectiveness of online teaching learning in middle school and high school students. The secondary objective was to assess the student satisfaction after 6 months of online teaching. We also wanted to identify the mental health of students after e-learning. Methodology: After obtaining consent from parents and school principal, a questionnaire on new learning method and the ease of understanding was shared with students in google form.Their responses were assessed in various dimensions. Results: Students felt lonely and tired at the end of e-learning sessions. They felt that they are missing on co-curricular and extracurricular activities. There was difficulty in falling asleep and missing of peer groups. Conclusions: E –learning is the need of the hour. Despite user ease and accessibility, e–learning cannot completely replace in-campus learning. Multiple aspects of student mental health are being compromised in a pure e-learning school. Blended learning is a useful modality and its implications remain to be analyzed.

Students Engagement Level Detection in Online e-Learning Using Hybrid EfficientNetB7 Together With TCN, LSTM, and Bi-LSTM

Students engagement level detection in online e-learning has become a crucial problem due to the rapid advance of digitalization in education. In this paper, a novel Videos Recorded for Egyptian Students Engagement in E-learning (VRESEE) dataset is introduced for students engagement level detection in online e-learning. This dataset is based on an experiment conducted on a group of Egyptian college students by video recording them during online e-learning sessions. Each recorded video is labeled with a value from 0 to 3 representing the level of engagement of each student during the online session. Moreover, three new hybrid end-to-end deep learning models have been proposed for detecting student’s engagement level in an online e-learning video. These models are evaluated using the VRESEE dataset and also using a public Dataset for the Affective States in E-Environment (DAiSEE). The first proposed hybrid model uses EfficientNet B7 together with Temporal Convolution Network (TCN) and achieved an accuracy of 64.67% on DAiSEE and 81.14% on VRESEE. The second model uses a hybrid EfficientNet B7 along with Long Short Term Memory (LSTM) and reached an accuracy of 67.48% on DAiSEE and 93.99% on VRESEE. Finally, the third hybrid model uses EfficientNet B7 along with a Bidirectional LSTM and achieved an accuracy of 66.39% on DAiSEE and 94.47% on VRESEE. The results of the first, second and third proposed models outperform the results of currently existing models by 1.08%, 3.89%, and 2.8% respectively in students engagement level detection.