Freshly Printed - allow 7 days lead
Couldn't load pickup availability
Artificial Intelligence and IoT in Online Education Systems
Monitoring, Assessment, and Evaluation
Ramanujam E. (Edited by), Ramanujam (Author), Chandan Chakraborty (Edited by)
9781394302635, Wiley
Hardback, published 12 December 2025
560 pages
28 x 19 x 2.5 cm, 0.998 kg
Design the future of digital education with this essential book that provides a comprehensive guide to leveraging AI and IoT to create dynamic, inclusive virtual learning environments and effectively implement advanced online proctoring solutions. The rapid development of online learning environments and virtual classrooms, coupled with the need for scalable, personalized education systems, has positioned AI as a key enabler of modern education. The advent of these technologies promises to reshape how we deliver, monitor, assess, and evaluate online learning. This book explores these critical intersections of technology and education, emphasizing the potential of AI and IoT not only to optimize outcomes but also to create more dynamic, responsive, and inclusive virtual learning environments. Focusing on problems that can be solved through computer vision, video and audio streaming, class imbalance data, audio-to-text processes, multi-modal and bi-modal aspects, hand-written strokes, text similarity, biomedical ethics, and advancements in machine and deep learning algorithms, this book comprehensively explores the effectiveness of these technologies in online proctoring. This essential guide will equip educators, technologists, administrators, and policymakers with the knowledge and perspective necessary to leverage these technologies effectively. Readers will find the book: Audience Educational researchers and policymakers, as well as computer scientists working in AI, machine learning, data science, deep learning, computer vision, and statistics.
Preface xix Part 1: Introduction to AI Tools for Online Proctoring 1 1 AI Literacy and Online Proctoring: Educational Perspectives and Strategies 3 1.1 Introduction 4 1.2 AI in Education — Theoretical Framework 6 1.3 AI-Assisted Educational Practices 8 1.3.1 Hyper Sentient Syllabus 8 1.3.2 Role of AI in Redesigning Assessment Strategies 9 1.3.3 Framework for Adopting and Implementing AI-Assisted Online Proctoring Systems 11 1.3.4 Ethical Implications of AI in Online Proctoring 19 1.4 Strengthening Teacher Preparation for AI Literacy in Higher Education Curricula 19 1.4.1 Updating Educator’s Knowledge of AI Concepts 19 1.4.2 Utilizing AI-Enhanced Technologies for Personalized Learning 20 1.4.3 Integrating AI Literacy Education with the TPACK Framework 20 1.5 Conclusion and Implications 21 References 22 2 Next-Generation Online Education Integrating AI and IoT for Superior Management and Evaluation 27 2.1 Introduction 28 2.2 AI and IoT in Online Education Systems 31 2.2.1 Overview 31 2.2.2 Smart Online Education Model 33 2.2.3 Smart Online Classroom 34 2.2.4 Smart Online Labs 36 2.2.5 Smart Online Tutoring 36 2.2.6 Smart Simulation 37 2.2.7 Smart Online Evaluation 38 2.2.8 Smart Online Security and Content Adaptation 38 2.2.9 Application and Infrastructure Levels 41 2.3 Functional Structure of IoT System 41 2.3.1 Online Exam Management 42 2.3.2 Automated Correction of Exam Papers 43 2.3.3 Student’s Performance Calculation 44 2.4 Emerging Technologies in the Online Education System 45 2.4.1 AI Technologies 45 2.4.2 AR, VR 48 2.4.3 Big Data Technology 49 2.4.4 Robotics and IoT Labs 49 2.4.5 Cloud Computing Technology 50 2.4.6 Machine Learning Technology 50 2.4.7 Deep Learning Technology 51 2.4.8 IoT Technology 51 2.4.9 5G Technology 52 2.4.10 Learning Management System (LMS) 52 2.5 Challenges of AI and IoT in Online Education System 54 2.6 The Future Vision of AI and IoT in Online Education Systems 56 2.6.1 Emerging Trends and Future Applications 57 2.7 Conclusion 58 References 59 Part 2: Ethics of Using AI Tools in Education 63 3 Ethical Integrity in Educational Contexts 65 3.1 Introduction 66 3.2 Types and Methods of Fake Credentials 67 3.2.1 Counterfeit Diploma and Degrees 67 3.2.2 Fake Transcripts 68 3.2.3 Misrepresentation of Professional Licenses and Certifications 68 3.2.4 Online Credential Verification Scams 69 3.2.5 Impersonation of Genuine Graduates 70 3.2.6 Use of Photoshop and Graphic Design Software 71 3.3 Consequences of Fake Credentials 72 3.3.1 Legal Consequences 73 3.3.2 Educational and Professional Consequences 75 3.3.3 Financial Consequences 76 3.3.4 Loss of Trust 77 3.3.5 Long-Term Implications 80 3.3.6 Ethical and Psychological Consequences 81 3.3.7 Public Shame 83 3.4 Challenges in Detecting and Verifying Fake Credentials 84 3.5 Role of Technology in Facilitating and Combating Fake Credentials 86 3.6 Impact on Organizational Reputation and Public Trust 90 3.7 Multi-Layered Approach to Tackling the Problem 91 3.8 Innovative Solutions and Technologies 94 3.9 Promoting Awareness and Education 96 3.10 Future Trends and Strategies 99 3.11 Conclusion 99 References 100 4 Psychological and Ethical Aspects of Using Intelligent Systems in Online Proctoring 103 4.1 Introduction 104 4.1.1 Importance of Proctoring in Online Examination 107 4.1.2 Briefing on Intelligent Systems (AI, BD, IoT) 108 4.1.3 Relevance of Intelligent Systems to Online Proctoring 111 4.2 The Advent of AI in Online Proctoring 112 4.2.1 The Need for AI in Online Proctoring 112 4.2.2 Evolution and Current State of AI Applications in Online Proctoring 114 4.3 The Prevailing Situation 116 4.4 Psychological Aspects 119 4.4.1 User Perceptions of AI-Driven Proctoring 119 4.4.2 Impact on Test Taker Stress and Performance 121 4.4.3 Privacy Concerns and their Psychological Implications 122 4.5 Ethical Aspects 124 4.5.1 Ethical Implications of Using AI for Surveillance 125 4.5.2 Potential for Bias and Discrimination in AI Proctoring 126 4.6 Discussion and Recommendations 127 4.6.1 Strategies for Ethically Implementing AI in Online Proctoring 127 4.6.2 Recommendations for Addressing Psychological Concerns 128 4.7 Conclusion 128 Acknowledgments 131 References 131 Part 3: State-of-the-Art AI Tools and Techniques for Online Proctoring 137 5 A Comprehensive Review of Deep Learning Models on Detecting Student Emotions in Online Education 139 5.1 Introduction 140 5.1.1 Research Overview 140 5.1.2 Importance of Detecting Student Emotions in Online Education 141 5.1.3 Purpose of the Literature Review 141 5.2 Understanding Student Emotions 142 5.2.1 Definition of Emotions 142 5.2.2 The Role of Emotions in Learning 142 5.2.3 Significance of Detecting Student Emotions in Online Education 143 5.3 Overview of Deep Learning 143 5.3.1 Definition of Deep Learning 143 5.3.2 Benefits of Deep Learning in Educational Research 143 5.3.3 Applications of Deep Learning in Detecting Emotions 144 5.4 Literature Review 144 5.4.1 Studies on Detecting Student Emotions in Online Education 145 5.4.1.1 Methods Used for Emotion Detection 146 5.4.1.2 Effectiveness of Different Approaches 147 5.4.2 Applications of Deep Learning in Emotion Detection 148 5.4.2.1 Algorithms Used in Deep Learning for Emotion Recognition 149 5.4.2.2 Success Stories and Challenges Faced in Using Deep Learning 150 5.4.2.3 Proposed Model for Student Behavior Analysis in Classroom 151 5.4.2.4 Literature Summary and Analysis 153 5.5 Challenges in Detecting Student Emotions 153 5.5.1 Technical Challenges 156 5.5.1.1 Data Collection and Processing 156 5.5.1.2 Model Accuracy and Reliability 156 5.5.2 Ethical Considerations 157 5.5.2.1 Privacy Concerns 157 5.5.2.2 Bias in Emotion Detection Algorithms 157 5.6 Future Directions and Recommendations 158 5.7 Conclusion 159 References 160 6 Deep Learning Models for Monitoring Student’s Emotion During the Class: A Comprehensive Survey 165 6.1 Introduction 166 6.2 Literature Survey 168 6.2.1 Deep Learning Approach 169 6.2.2 Transfer Learning 171 6.3 Research Background 178 6.3.1 Computer Vision 178 6.3.2 Internet of Things (IoT) 181 6.3.3 Deep Learning Architectures 183 6.3.3.1 ConvNet 184 6.3.3.2 Recurrent Neural Network 186 6.3.4 Pre-Trained Models 189 6.4 Prediction Models for Tracking and Monitoring Students 193 6.4.1 Emotion Recognition Models 194 6.4.2 Learning Engagement Models 196 6.5 Conclusion 197 References 198 7 Comparative Analysis of Head Pose Estimation and Eye Gaze Tracking with Machine Learning Classifiers for Proctored Online Examination 203 7.1 Introduction 204 7.1.1 Head Pose Estimation 204 7.1.2 Eye Gaze Tracking 204 7.1.3 Relevance of Head Pose Estimation and Eye Gaze Tracking in Online Proctored Exams 206 7.2 Benchmark Datasets for Head Pose and Eye Gaze Tracking 207 7.3 Apparatus for Estimating Head Pose and Tracking Eye Gaze 214 7.4 Models for Head Pose Estimation and Eye Gaze Tracking 217 7.4.1 Geometrical Method Based on Interest Points 217 7.4.2 Gradient Boosting Regression 218 7.4.3 Genetic Algorithm 219 7.4.4 Linear Discriminant Analysis (LDA) and Discrete Wavelet Transform (DWT) 220 7.4.5 Aff Net 221 7.4.6 FSA-Net 223 7.4.7 Multi-Modal Convolutional Neural Network 223 7.5 Comparison of Models for Head Pose Estimation and Eye Gaze Tracking 224 7.6 Conclusion 226 References 227 8 Uni- and Multi-Modal Aspects in the Online Proctoring System: Survey 231 8.1 Introduction 232 8.1.1 Online Proctoring Techniques 235 8.1.2 Concerns in Online Proctoring Systems 237 8.2 AI-Based Online Proctoring System 240 8.2.1 Online Proctoring Process 240 8.2.1.1 Proctoring Prior to Examination 241 8.2.1.2 Proctoring During Examination 243 8.2.1.2(a) Examinee Behavior Screening 244 8.2.1.2(b) Examinee System Screening 247 8.2.1.2(c) Examinee Environment Screening 248 8.3 Existing AI-Based Online Proctoring Frameworks 249 8.4 Challenges in AI-Based Online Proctoring Frameworks 253 8.5 Future Scope of AI-Based Proctoring Frameworks 256 8.6 Conclusion 259 References 260 9 Advancing Academic Integrity: AI and IoT in Enhancing Monitoring for Online Examination Systems 265 9.1 Introduction 266 9.2 Predictive Analysis of Student Performance 267 9.2.1 Data Collection 269 9.2.2 Data Preprocessing 269 9.2.3 Feature Engineering 270 9.2.4 Model Selection and Training 270 9.2.5 Model Evaluation 270 9.2.6 Model Deployment 271 9.3 Authentication of Students 271 9.4 Supervision of Examination 272 9.4.1 Plagiarism Detection 273 9.4.2 Fraud Detection and Malpractice Prevention 275 9.4.3 Multiple Account Detection 275 9.4.4 E-Cheating Intelligence Agents 276 9.4.5 Detection of Liveliness Spoofs 277 9.4.6 Anomaly Detection 277 9.5 Challenges in Monitoring 279 9.5.1 Privacy Concerns 281 9.5.2 Security Challenges 281 9.5.3 Fairness Consideration 282 9.6 Conclusion 283 References 284 10 Optimizing Academic Excellence: Leveraging Advanced AI Tools for Assessment and Evaluation in Modern Online Examination Systems 287 10.1 Introduction 288 10.2 Role of AI in Online Examination Systems 289 10.2.1 Benefits of AI in Assessments 290 10.2.2 Personalization of Assessments 290 10.2.3 Efficiency and Time-Saving 291 10.2.4 Fairness and Objectivity 291 10.2.5 Scalability and Accessibility 291 10.2.6 Enhanced Security and Integrity 291 10.2.7 Data-Driven Insights 292 10.2.8 Continuous Learning and Improvement 292 10.3 Advanced AI Tools for Assessment 293 10.3.1 Knewton 293 10.3.2 DreamBox 295 10.3.3 Edpuzzle 297 10.3.4 Squirrel AI 300 10.3.5 ProctorU 301 10.3.6 Smart Sparrow 303 10.3.7 MoodleNet 304 10.3.8 Canvas by Instructure 306 10.4 Implementing AI Tools in Online Examination Systems 308 10.4.1 Needs for AI in Online Examination Systems 308 10.4.2 Steps for Implementing AI Tools 309 10.4.3 Advantages of AI in Online Examinations 309 10.4.4 Challenges of Implementing AI 310 10.5 Future Trends 310 10.6 Conclusion 311 References 311 Part 4: Case Studies: AI and IoT in Education, Online Proctoring 315 11 Evaluation of Web Design Deficiency and Anxiety Constructs, with Computer‐Based Test: Use Case in India 317 11.1 Introduction 318 11.2 Review of Literature 319 11.3 Methodology 325 11.4 Results 328 11.4.1 Structural Model 331 11.5 Discussions 335 11.6 Conclusion 338 Acknowledgment 339 References 339 12 AI for Learners’ Emotions — A Perspective Approach of Analysis During Online Assessments 343 12.1 Introduction 344 12.2 Literature Survey 346 12.3 Role of Emotions in Learning 349 12.4 Challenges in Online Assessments 350 12.5 The Rise of AI in Education 351 12.6 AI Tools for Monitoring Learner Emotions 351 12.6.1 Facial Expression Analysis Tools 351 12.6.2 Voice Analysis Tools 352 12.6.3 Sentiment Analysis and NLP Tools 352 12.6.4 Physiological Monitoring Tools 352 12.7 Methodology 353 12.7.1 Selection of Appropriate Tools 354 12.7.2 Data Collection and Consent 354 12.7.3 Integration with Assessment Platforms 354 12.7.4 Training for Educators and Administrators 355 12.7.5 Pilot Testing and Evaluation 355 12.7.6 Full Implementation and Ongoing Monitoring 355 12.7.7 Addressing Ethical and Privacy Concerns 355 12.7.8 Feedback and Continuous Improvement 356 12.8 Advantages of Using AI Tools 356 12.9 Possible Implementational Risks 357 12.10 Demerits and Future Scope 358 12.11 Conclusion 359 References 359 13 Implementing Personalized Adaptive Online Assessments through Deep Learning 365 13.1 Introduction 366 13.1.1 The Need for Adaptive Assessment Systems 366 13.1.2 The Role of DL in Education 367 13.1.3 Research Context and Case Studies 367 13.2 Literature Review 368 13.3 Methodology 370 13.3.1 Description of the DL Algorithms and Models 370 13.3.1.1 Convolutional Neural Networks (CNNs) 371 13.3.1.2 Recurrent Neural Networks (RNNs) 371 13.3.1.3 Long Short-Term Memory (LSTM) Networks 372 13.3.2 Data Collection and Pre-Processing Methods 373 13.3.2.1 Data Collection 373 13.3.2.2 Data Pre-Processing 374 13.3.3 Steps Involved in Developing and Implementing the Adaptive Assessment System 375 13.3.3.1 Model Design and Training 375 13.3.3.2 Adaptive Assessment Generation 376 13.3.3.3 Real-Time Feedback System 376 13.3.3.4 Implementation and Testing 377 13.4 Case Studies 378 13.4.1 Case Study 1: Beaconhouse International College (bic) 378 13.4.1.1 Background and Context 378 13.4.1.2 Implementation Process 378 13.4.1.3 Key Findings 380 13.4.1.4 Challenges and Solutions 381 13.4.2 Case Study 2: Government College University Faisalabad (GCUF) 381 13.4.2.1 Background and Context 381 13.4.2.2 Implementation Process 382 13.4.2.3 Key Findings 382 13.4.2.4 Challenges and Solutions 383 13.5 Results and Discussion 384 13.5.1 Improvement in Learning Outcomes 384 13.5.2 Increase in Engagement Rates 386 13.5.3 Reduction in Exam-Related Anxiety 388 13.5.4 Enhanced Overall Performance 390 13.5.5 Comparative Analysis of the Case Studies 392 13.5.5.1 Similarities 392 13.5.5.2 Differences 392 13.5.6 Future Research Directions 394 13.5.7 Limitations of the Study 395 13.6 Conclusion 395 References 396 14 Generative Artificial Intelligence for Online Education Systems 399 14.1 Introduction 400 14.2 The Types of GAI Models 401 14.3 Working of GAI 401 14.3.1 Generative Modeling 402 14.3.2 GANs 403 14.3.3 Transformer-Based Models 404 14.4 Use Cases of GAI 406 14.5 The Limitations of GAI 407 14.6 Adaptive Learning Platforms 408 14.7 GAI and Adaptive Learning Intersection 409 14.7.1 Potential Benefits of Integrating GAI and Adaptive Learning 409 14.7.2 Some Examples of Successful Integration 409 14.7.3 Future Trends of GAI and Adaptive Learning 410 14.7.4 Prospective Developments in GAI for the Education Sector 411 14.8 Implications for Educators and Learners 412 14.9 GAI Effect on Workforce 412 14.10 GAI Has Already Transformed Education 413 14.11 Effect on the Participation and Performance of Learners 414 14.11.1 Develop Their Expressiveness and Creativity 414 14.11.2 Develop Their Information Literacy and Research Abilities 414 14.11.3 Improve Their Capacity for Self-Control and Metacognition 415 14.12 The Education Sector’s Challenges with GAI 415 14.12.1 Challenge Cause Due to Plagiarism 415 14.12.2 Equity 415 14.12.3 Privacy 416 14.12.4 Efficacy 416 14.12.5 Detection 417 14.12.6 Appropriate Use 417 14.12.7 Authorship 417 14.13 Policymakers and Educators Need to Reconsider the Current Educational Paradigm 418 14.14 Access and Equity Comes First 418 14.15 United Nations Educational, Scientific and Cultural Organization’s (UNESCO’s) Policy for Reshaping Education by Using GAI 419 14.16 Conclusion 420 References 420 15 Level of Academic Misconduct During Online Unproctored Examination with Perception of Engineering Students in India 423 15.1 Introduction 424 15.2 Literature Review 425 15.3 Research Methodology 428 15.3.1 Sampling 430 15.3.2 Data Analysis and Findings 432 15.3.3 Relative Importance 436 15.4 Conclusion 439 References 439 16 Student Activity Monitoring Using Hybrid Deep Learning Technique During Online Examinations 443 16.1 Introduction 444 16.1.1 Motivations 445 16.1.2 Objective and Design 446 16.1.3 Contributions 447 16.2 Related Works 447 16.2.1 Image Information Systems (IIS) 447 16.2.2 Multi-Modal System (MMS) 449 16.2.3 Behavior-Based Analysis 450 16.3 Methodology — The Theoretical Foundation of the Proposed Model 451 16.3.1 Dataset Collection 451 16.4 Experimental Results and Discussion 456 16.5 Conclusion and Future Work 460 References 461 17 Multicue Facial Emotion Expression Using Lightweight Deep Learning Models 465 17.1 Introduction 466 17.1.1 Types of Facial Expression and Its Features 467 17.2 Related Works 469 17.3 Materials and Method 472 17.3.1 Face and Facial Landmark Detection 474 17.3.2 Convolution Neural Network (ConvNEt) Architecture 475 17.3.3 VGG-16 Architecture 476 17.3.4 InceptionV3 Architecture 477 17.3.5 ResNet 50 477 17.4 Experimental Result Analysis 478 17.5 Conclusion 482 References 482 Part 5: Challenges and Future Scope of AI in Online Proctoring 485 18 Machine-Learning-Based Online Assessment of Students’ Academic Performance in Moodle Learning Management System 487 18.1 Introduction 488 18.2 Literature Review 491 18.3 Research Methodology 493 18.3.1 Dataset Acquisition 494 18.3.2 Dataset Pre-Processing 495 18.3.3 Data Analysis 495 18.3.4 Linear Regression 496 18.3.5 Correlation 496 18.3.6 Multiple Regression 496 18.3.7 Lasso Regression 496 18.4 Results and Discussion 496 18.4.1 Correlation 497 18.4.2 Scatter Plot 498 18.4.3 Linear Regression 500 18.4.4 Multiple Linear Regression 504 18.4.5 Lasso Regression 508 18.5 Conclusion 509 18.6 Future Research 510 References 511 19 Issues and Challenges of Using Artificial Intelligence Proctoring Tools 515 19.1 Introduction 515 19.2 Literature Review 517 19.2.1 Features of AI-Based Online Proctoring Tools 520 19.3 Issues and Challenges of Using AI Proctoring Tools 522 19.4 Case Study 524 19.5 Conclusion 527 References 529 Index 533
Prihana Vasishta, Gitanjaly Chhabra and Noosha Mehdian
Aniket Kumar, Rajesh Kumar, Akshay Kumar, Prashant D. Yelpale and Aman Thakur
C. Santhiya, Ravi Prasath S., Suriya Navaneetha Krishnan K. and Kannappan R.
Mukesh Chaware and Sreejith Alathur
Thangavel Murugan, A.M. Abirami and P. Karthikeyan
Vamshi Krishna B., N. Padmavathy and Ajeet Kumar
Rajarajeswari P., Shivagangatharani B. and Karthikeyan Jothikumar
Diana Moses and Dainty M.
J. Shanthalakshmi Revathy and J. Mangaiyarkkarasi
Manikandakumar M., Karthikeyan P., Senthamarai Kannan K., Arul V. and Vigneshwaran T.
Juby Thomas, Ashique Ali K.A., Vishnu Achutha Menon, Sateesh Kumar T.K. and Lijo P. Thomas
S.J. Sheeba Sharon, R. Mary Sophia Chitra and C. Santhiya
Fawad Naseer, Noreen Sattar, Akhtar Rasool, Kamel Jebreen and Usman Khalid
Munmi Dutta and Vinay Kumar Goyal
S. Sasikala, G. Vidyasree, C. Selvan and R. Ragunath
Devi Naveen, Akshitha Katkeri, Manikantha K., A.K. Sreeja and Satish Kumar V.
S. Hemaswathi, P. Rajkumar, N. Mohan Prabhu and R. Dhivya
Reshma V.K., Nisha A.K., Radhika K. Manjusha, Divya P. and Sundaraselvan S.
V. Senthil
Subject Areas: Computer science [UY]
