Explain what AIBDI2023 is.

The book focuses on algorithms and models related to Artificial Intelligence, Big Data, and IoT used to proctor the students' to preserve the ethical context during online examination. This book majorly focuses on problems that can be solved through computer vision, video and audio streaming, class imbalance data, audio-to-text process, multi-modal and bi-modal aspects, and advancements in machine and deep learning algorithms for the effectiveness of online proctoring. Simplified and unique IoT-based systems designed for online proctoring systems have also been explored to analyze the student's trustworthiness in the exam. The chapters in this book will discuss the key issues of remote monitoring such as examinee authentication, registration, enrolment, malpractice, academic misconduct activities, dual mode answering, etc. and its related solutions to online examinations.  The book is intended to support researchers, academicians, and policymakers to understand and explore the AI assisted tools and techniques for development, analysis and implementation aspects of online proctoring examination systems.

Submission Guidelines

All papers must be original and not simultaneously submitted to another book or edited volumes. The following paper categories are welcome (but not limited to):

1. Online Proctoring Tools and Techniques 

2. AI-assisted Students’ online proctoring system: Review 

3. Uni and Multi-modal Aspects in the online proctoring system: Survey 

4. Image information based students' online monitoring system using CNN model 

5. Multi-modal student online monitoring system

6. Academic misconduct detection using deep neural networks through a Transfer learning mechanism 

7. Comparative analysis of head pose estimation, eye gaze tracking with ML classifiers 

8. A novel IoT-based audio-to-text processing multi-modal system for online proctoring 

9. Simplified and Unbiased IoT architecture for Students' online proctoring system 

10. Handling of class imbalance academic misconduct detection using pre-trained convolution models 

11. Handling streaming video data using Edge devices for students' activity monitoring during online examination 

12. Challenges and Future Scope for Enhancements  

Contact

All questions about submissions should be emailed to ramanujamge@ieee.org