Skip to Content

Evaluating the Effect of Visual Stimuli on the Intelligibility of Dysarthric Speech

The main goal of this project is to see if dysarthric speech can be more easily understood if a visual modality is introduced. Dysarthria is a speech disorder that makes individuals difficult to understand due to impaired movement of the muscles used for speech. Demonstrating that pairing visual and audio will increase intelligibility will open

Perception of Emotions Based on Tactile Facial Action Units by Individuals Who are Blind

There are a plethora of emotions that can be perceived through non-verbal communication cues, such as happiness, sadness, and anger. This puts blind and visually impaired individuals at a major disadvantage, as they cannot interpret these visual cues due to their vision loss. With the assistance of haptic technology, this research aims to explore how

Reinforcement Learning with Randomized Rewards

Current reinforcement learning models are brittle and unable to accept change in reward structure. In order to obtain a true general AI our machine learning algorithms must be able to expect changes in a reward structure. That is why the research is taking a look at randomizing the reward that is obtained in simple machine

Chat-Box as Mood Analyzer for Individuals with Social Interaction Disabilities

More than 360 million people worldwide suffer from hearing impairments and autism. They also have a difficult time observing the social world and interpreting it. Similarly, the inherently ambiguous nature of sarcasm sometimes makes it even harder to connect with others from the spoken language. Recognition of sarcasm can benefit sentiment analysis in summarization, dialogue

Development of a Battery Management & Charging System for Autonomous UAVs

The objective of this project is to create a novel battery charging and management solution for a fleet of unmanned aerial vehicles (UAVs) for long term deployments. A contact charging-equipped base station has been designed from scratch, and a custom battery pack for UAV systems has been built to work with this system. This project

Development and Analysis of Reward-Adaptive Reinforcement Learning Agents

This research is attempting to develop an artificially intelligent reinforcement learning agent that can adapt to changes in its reward structure without performing training again. An agent has been developed that successfully plays Atari 2600 games with random reward elements. More powerful reward-adaptive agents (RWA) may inform medical scientists of optimal steps to counteract the

The Use of Augmented Reality (AR) and Physical Activity (PA) to Help Students with ADHD Learn

The research question being investigated is “can augmented reality(AR) and physical activity(PA) be combined using technology to create a beneficial learning experience for students with Attention Deficit Hyperactivity Disorder(ADHD)?” An educational learning app that uses AR and PA is under development. This semester a user study using the app will be carried out to aid