1Assistant Professor, Department of Artificial Intelligence and Data Science, SNS College of Technology, Coimbatore - 641107. Email: gulshanasif97@gmail.com
2*Associate Professor, Department of Computer Science and Engineering, Karthir College of Engineering. Email: sukanmukesh@gmail.com (Corresponding Author)
3Assistant Professor, Department of Artificial Intelligence and Data Science, KGISL Institute of Technology, Coimbatore. Email: durga033@gmail.com
4Department of Artificial Intelligence and Data Science, Kathir College of Engineering, Coimbatore - 641048. Email: usha.samiappan@gmail.com
5Professor & Deputy Director, School of Engineering and Technology, CMR University (Lake Side Campus), Near International Airport, Chagalatti, Bengaluru, Karnataka, India. Mobile: 99413 52094. Email: dr.mani1973@gmail.com
6Assistant Professor, Department of Information Technology, Sri Krishna College of Engineering and Technology. Email: shivaofficial.1987@gmail.com
7Assistant Professor, Department of Computer Science and Engineering, Dhanalakshmi Srinivasan College of Engineering, Coimbatore - 641105. Email: aswathynairb@gmail.com
8Assistant Professor, Department of Artificial Intelligence and Data Science, Easa College of Engineering and Technology. Email: ratheeshkumargopika@gmail.com
Received: 15th Feb, 2026; Revised: 27th Feb 2026; Accepted: 20th Mar, 2026; Available Online: 5th Apr, 2026
For applications targeting older adults, where personal support has been shown to potentially contribute to happiness and autonomy, emotionally aware human-machine interfaces can play a pivotal role in facilitating adaptable and engaging conversational interfaces. The lack of older adults in contemporary datasets and models restrains the ability to apply contemporary methodologies to age-related interfaces despite their improvements in affective computing and multimodal emotion recognition. This work discusses the development of the emotion expression recognition module of the virtual coach by presenting data collection, annotation design, and a preliminary methodological approach tailored to the specifications of the project. In the latter, we investigate the role of multiple modalities-speech from audio, and facial expressions, gaze, and head dynamics from video-in a standalone and combined manner for the detection of discrete emotion expressions in this setting. The collected corpus, consisting of users from Norway, France, and Spain, was annotated independently for the audio and video channels with unique emotional labels, and thus allowed for a cross-cultural performance comparison. The results confirm the informative value of the modalities with respect to the considered emotional categories; multimodal approaches generally outperformed others. The results are expected to guide the development of future systems and contribute to the limited literature on emotion recognition applied to elderly individuals in conversational human-machine interaction.
Keywords: Affective Computing, Multimodal Emotion Recognition, Human–Machine Interaction, Older Adults, Virtual Coaching Systems, Speech and Facial Analysis, Behavioral Cues
How to cite this article: Gulshan Banu A, Sukanya M, Kanaga Durga M, Usha S, Manikandan SP, Shiva Shankar S, Aswathy PB, Gopika P. Adult Learning Management with Emotion Sensing and Progress Tracking in Virtual Environments. Int J Drug Deliv Technol. 2026;16(4): 73. DOI: 10.25258/ijddt.16.4.10
Source of support: Nil.
Conflict of interest: None