Current Projects

ExpressionBot (Socio-SDS)
This project, developing SocioBot-SDS (SocioBot-Spoken Dialog System), an instrument in the form of a robotic character with an emotional response, is expected to advance research involving next generation human-machine interactions. [… more]

Robot-Based Autism Therapy
This project aims at to develop and utilize humanoid robots for analyzing behavior principles of children with ASDs and go beyond simple goals of using robots as a neat toy to make kids smile or maybe even engage in joint attention.[… more]

Facial Expressions Recognition (Affective Computing)
The objective of this project is to develop and implement state-of-the-art computer vision algorithms for recognition of facial expressions. Our focus is on using deep neural networks on in-the-wild dataset of facial expressions. [… more]

Deep Learning for Visual Object Recognition
This project aims at developing state-of-the-art computer vision algorithms for visual object recognition using deep neural networks. Our approach is unique and instead of adding more layers to neural networks, we have been focusing on either reformulating the cost function used for supervised learning in Neural Networks or modeling more complex and nonlinear pre-activation functions for artificial neurons. [… more]

Behavior Recognition from Brain Signals (Deep-Brain Stimulation / Parkinson’s Disease)
This project focuses on developing a robust pattern recognition system to recognize and classify human’s behavior (e.g. language and motor tasks) from different brain electrical signals. [… more]

Outdoor positioning systems based on the Global Navigation Satellite System have several shortcomings that have deemed their use for positioning inside buildings and in urban canyons impractical. Location fingerprinting, which utilizes machine learning, has emerged as a viable solution for such scenarios due to its simple concept and good results. Shallow learning algorithms are traditionally used in location fingerprinting.[… more]