Research projects

Researchers: Aliasghar Mohammadsalehi, Waheed U. Bajwa, Dipankar Raychoudhuri One of the aspects of the rings project is to reduce the latency for real-time applications of ml. To achieve this goal, we can reduce the inference time of the models we use in our applications.

Researchers: Yu Wu, Anand D. Sarwate Machine learning models implemented in hardware on physical devices may be deployed for a long time. The computational abilities of the device may be limited and become outdated with respect to newer improvements.

Researchers: Cheng Fang, Waheed U. Bajwa This project is about distributed/decentrazlied machine learning algorithm design and implementation in the presence of adversarial agents. An increasing amount of attention has been drawn to the area of designing reliable and efficient machine learning algorithms.

Researchers: Nitya Sathyavageeswaran, Anand D. Sarwate, Narayan B. Mandayam, Roy D. Yates A source (mobile device) generates time-stamped update packets that are sent to a server and then forwarded to an edge cloud (monitor).

Researchers: Vishakha Ramani, Jiachen Chen, Roy D. Yates This project is about using Ago of Information (AoI) metrics to help design edge-computing applications where information publishers and subscriber work with a shared memory.

Researchers: Vishakha Ramani, Roy D. Yates We consider systems in which source updates require multiple sequential processing stages. We identify, model, and analyze various system designs for processing source updates, considering factors such as the number of processors deployed, communication mechanisms between processors, and energy consumption constraints.

Researchers: Nitya Sathyavageeswaran, Anand D. Sarwate, Narayan B. Mandayam, Roy D. Yates Future real-time applications like smart cities will use complex Machine Learning (ML) models for a variety of tasks. Timely status information is required for these applications to be reliable.

Researchers: Muhammad Zulqarnain, Waheed U. Bajwa The precision of numerous downstream machine learning models is directly linked to the uncorrelated nature of training data. With the increasing trend of data often being streamed, geographically spread out, and having high dimensions, it’s vital to utilize both uncorrelated feature learning and dimension reduction techniques.