Towards Emotionally Aware AI Smart Classroom: Current Issues and Directions for Engineering and Education
Open Access
- 10 January 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 6, 5308-5331
- https://doi.org/10.1109/access.2018.2791861
Abstract
Future smart classrooms that we envision will significantly enhance learning experience and seamless communication among students and teachers using real-time sensing and machine intelligence. Existing developments in engineering have brought the state-of-the-art to an inflection point, where they can be utilized as components of a smart classroom. In this paper, we propose a smart classroom system that consists of these components. Our proposed system is capable of making realtime suggestions to an in-class presenter to improve the quality and memorability of their presentation by allowing the presenter to make real-time adjustments/corrections to their non-verbal behavior, such as hand gestures, facial expressions, and body language. We base our suggested system components on existing research in affect sensing, deep learning-based emotion recognition, and real-time mobile-cloud computing. We provide a comprehensive study of these technologies and determine the computational requirements of a system that incorporates these technologies. Based on these requirements, we provide a feasibility study of the system. Although the state-of-the-art research in most of the components we propose in our system are advanced enough to realize the system, the main challenge lies in the (i) integration of these technologies into a holistic system design, (ii) their algorithmic adaptation to allow real-time execution, and (iii) quantification of valid educational variables for use in algorithms. In this paper, we discuss current issues and provide future directions in engineering and education disciplines to deploy the proposed system.Keywords
This publication has 114 references indexed in Scilit:
- Tracking continuous emotional trends of participants during affective dyadic interactions using body language and speech informationImage and Vision Computing, 2013
- LIBSVMACM Transactions on Intelligent Systems and Technology, 2011
- Survey on speech emotion recognition: Features, classification schemes, and databasesPattern Recognition, 2011
- Effects of visual and verbal presentation on cognitive load in vigilance, memory, and arithmetic tasksPsychophysiology, 2010
- Self‐Assessment of Oral Communication Presentations in Food Science and NutritionJournal of Food Science Education, 2009
- Learning Deep Architectures for AIFoundations and Trends® in Machine Learning, 2009
- Effects of Immediate Feedback Delivered by Peer Tutors on the Oral Presentation Skills of Adolescents With Learning DisabilitiesRemedial and Special Education, 2008
- Enhancing Instructional Efficiency of Interactive E-learning Environments: A Cognitive Load PerspectiveEducational Psychology Review, 2007
- Cognitive Load Theory and Complex Learning: Recent Developments and Future DirectionsEducational Psychology Review, 2005
- Managing split-attention and redundancy in multimedia instructionApplied Cognitive Psychology, 1999