Welcome to the machine learning research group at Binghamton! Our group works broadly on designing machine learning models for complex, relational, unstructured, and heterogeneous data. Our group focuses both on designing novel algorithms for such complex interconnected data and applications of these algorithms on real-world data.
Specifically, our group works on statistical relational learning, deep learning, probabilistic graphical, and latent variable models. We demonstrate the utility of these models on applications including smart energy, computational social science, education, social media, and urban computing data. For a complete list of ongoing research projects, see our research page.
We are looking for passionate PhD, Masters and Undergraduate students to join the team!
Our paper on characterizing mobility patterns during COVID-19 using cellular network data is now on Arxiv!!October 2020
Our paper on analyzing societal impact during the early days of the COVID-19 pandemic got accepted to SocialCom 2020!!October 2020
Our paper on wireless channel quality prediction using sparse Gaussian conditional random fields got accepted to Consumer Communications and Networking Conference (CCNC)!September 2020
Gissella Bejarano passes her PhD prospectus!! Congratulations, Gissella!!September 2020
Our paper on predicting emergency resolution time using deep learning has been accepted for publication at IEEE CPSCom!September 2020
Our paper on a structured and linguistic approach to understanding recovery and relapse in AA has been accepted for publication in ACM Transactions on the Web (TWEB)!July 2020
Our research on designing ensemble regression models for predicting confirmed COVID-19 cases has been accepted to AI for Social Good Workshop. Check out the NEWS coverage here.April 2020
Prof. Arti Ramesh and Prof. Anand Seetharam have been awarded a SUNY seed grant to understand the societal impact of COVID-19 from social media data!