Selected Publications

. iPlug: Decentralised Dispatch of Distributed Generation. In COMSNETS, 2016.


. Taxonomy grounded aggregation of classifiers with different label sets. 2015.


. A context vector regression based approach for demand forecasting in district heating networks. In IEEE ISGT-ASIA, 2015.


. From multiple views to single view: a neural network approach. In ACM-IKDD CODS, 2015.



Predictive modelling for critical patient events using healthcare data

Predicting clinical outcomes using longitudinal electronic health record (EHRs) data is a clinically important and computationally challenging task. In this project, we are working on predicting adverse events like patient death, bleeding, or heart failure using carefully extracted features from patient records.

Proof completion in the formal verification language - Coq

Formal verification is an important field in Software Engineering and in Computer Science in general. With increasingly complex algorithms and models being implemented in today’s world, verifying their correctness has become that much more important. Formal languages like Coq help us achieve this task by providing us a framework to write proofs. However, the learning curve for these kinds of functional languages is steep since it involves rigorous proofs and the languages have a unique syntax structure. Programmers can use helpful suggestions about what tactics to use while writing their proofs. The aim of this project is to provide these useful suggestions by looking at previous proofs.


Teaching Assistant, Artifical Intelligence COMPSCI-383 with Prof. Phil Thomas, Spring 2018