Primary Research in the field of Big Data transfer through multibeam antennae, this involves research into matrix decompositions, data preservation, multibeam communication and a tinge of graph theory.
Other research interests are in image retrieval, matchine learning algorithms and methods of statistical analysis like PCA, ICA, and related factor analysis techniques.
A problem with its roots in early 1900's and wide spread use in both psychology and statistics. Here I look into the perturbation properties of factor analysis and help determine better algorithms and approaches. Also, S&P has no factors that can give a one day ahead prediction
While this is a cool decomposition, it's power and elegance is often overlooked in current research. People prefer Singular Value Decomposition (SVD) because of its simplicity, but how close does QR decomposition come to capture SVD details? QR is multiple times faster and has orders of complexity less than SVD.
Features are extracted from images (Eg: Scale Invariant Feature Transform (SIFT)) to form basis of image recognition. Which features are best?, which are redundat? What does Non-negative Matrix Factorization (NMF) and Independant Component Analysis (ICA) have to say about extracted features?
Advances in Wireless Networks have now enabled massive data transfer speeds, with its advance, the queues at routers and at network nodes are huge. Here we develop good queuing models which help in optimal solutions to data transfer over multiple hops