Who Am I?
I am a PhD student and a computer science researcher at the Human Experience Research Lab located in the University of Florida where we are currently working on breakthrough technologies for fostering how people build and use machine learning systems. My research lies at the crossroads of human-computer interaction and machine learning. In particular, I am passionate in creating tools to support both practitioner and end-user interaction with machine learning systems. My passion is in developing a foundation for future human-centered AI in domains such as healthcare and justice system.
LinkedIn Resume GithubAs time progress, autonomous vehicles may be a common mode of transportation, and companies like Lyft and Uber will adopt them in place of human drivers. Therefore, we want to explore whether current data from rideshare companies, such as Uber and Lyft, will cause them to be bias to only certain areas when deciding where autonomous vehicles should be located for pickup. We aim to propose solutions which gaurantee the equity for accessing these services in both rural and urban areas.
Application Quest, known as AQ, could be used in domains such as HR and admissions to reduce the implicit bias and human error. Using unsupervised learning methods, AQ will select the most holistic and representative sample to increase diversity. We are working on a publication for AAAI2020. So Stay tuned!
Most machine learning models used in the society are considered black box models, which means the user could not understand steps it took to reach a specific decision. Currently, many advocates and researchers are working to make machine learning models more transparent and explainable to end-users. In this project, I am working on mental health data to propose an interpretable machine learning method which could identify significant problems and illness. This tool could not replace doctors but could be a virtual assistant for them!
Brain waves and signals are unique to each person. This made us to think if machine learning methods could classify users by only looking at signals coming from brain through BCI devices. This research could make difference in biometric authentication.
We developed an application to help users in practicing their physical therapy exercises in a more interesting and effective way. This work will be presented this Fall at HFES 2019 so you will hear more about it.
Conversational Voice User Interfaces (VUIs) help us in performing tasks in a wide range of domains these days. While there have been several efforts around designing dialogue systems and conversation flows, little information is available about technical concepts to extract critical information for addressing the users’ needs. AI could help us in extracting dialogue information and address user needs. We developed an AI-based mobile-decision-aid (MODA) that predictively models and addresses users’ decision strategies to facilitate users’ in-store shopping decision process. Here we share our design and subsystems to make our research reproducible. To make our research producible, the code of backend server and dialogflow agent used will be published on my github!