"The question is not whether the intelligent machines can have any emotions, but whether machines can be intelligent without any emotions."
- Marvin Minsky
I am an Assistant Professor at the Indraprastha Institute of Information Technology, Delhi (IIIT-Delhi), where I hold joint affiliations with the Departments of Computer Science and Engineering, as well as Human-Centered Design. My research is centered around empowering machines with adaptive and emotional interaction abilities, with a primary goal of improving the quality of life in health and social care domains.
At the core of my work is the exploration of interpretation algorithms and techniques that enable machines to infer knowledge about users' emotional and interaction states. This involves analyzing audio-visual, behavioral, and physiological signals to gain insights into user experiences. By developing computational models of human social intelligence, I aim to equip social robots with the ability to assist in the cognitive rehabilitation and diagnosis of developmental disorders, such as intellectual disability and autism spectrum disorder.
In addition to my research endeavors, I am actively engaged in teaching various courses at IIIT-Delhi. These include Affective Computing, Machine Learning, and Social Robotics. As an educator, I find immense inspiration and learning opportunities in interacting with the bright minds of the younger generation, allowing me to further enrich my knowledge and stay attuned to emerging trends and perspectives in the field.
Affective Computing (CSE661/DES507)
- Affective Computing enables machines to recognize emotions and interact adaptively.
- It combines Computer Science, design, and human psychology.
- The course covers emotion theory, computational modeling of emotions, and analysis using various modalities.
- Modalities include voice, facial expressions, and physiological signals.
- Machine learning and signal processing techniques are used in emotion analysis.
- Ethical, legal, and social implications of affective computing in Human-Machine Interaction are discussed.
Machine Learning (CSE343)
- This is an introductory course on Machine Learning (ML) for undergraduate and graduate students.
- The course covers both theoretical and practical aspects of well-established ML techniques.
- Assignments include theory and programming questions to strengthen theoretical foundations and develop ML solutions.
- Students will work with simulated and publicly available real datasets.
- The project(s) require students to develop a complete ML solution, including preprocessing, classifier/regressor design, training and validation, and testing and evaluation.
- Quantitative performance comparisons will be conducted.
Social Robotics (CSE5SR)
- The aim of this course is to introduce social robotics and human-robot interaction.
- The course explores the distinctiveness, application domains, and interaction methods of social robots.
- Challenges and opportunities specific to this growing field are discussed.
1. HaptiDrag: A Device with the Ability to Generate Varying Levels of Drag (Friction) Effects on Real Surfaces
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT) [UbiComp/ISWC]'2022.
2. ExpressEar: Sensing Fine-Grained Facial Expressions with Earables
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT) [UbiComp/ISWC]'2021.
3. Exploring Semi-Supervised Learning for Predicting Listener Backchannels
Conference on Human Factors in Computing Systems (CHI)'2021.
4. Feature Extraction and Feature Selection for Emotion Recognition from Electrodermal Activity
IEEE Transactions on Affective Computing (IEEE TAC)' 2019.
5. Robot Assisted Interventions for Individuals with Intellectual Disabilities: Impact on Users and Caregivers
International Journal of Social Robotics (IJSR)' 2019.