Project: Nonnegative Matrix Factorization: Computational Algorithms and Applications
Advisor(s): Akwum Onwunta
Student(s): Hannah Li
Student Prerequisites: 3rd or 4th year; coursework in ISE, Math, Finance/ Economics, or CSE preferred; interested students are required to have basic programming experience in either MATLAB, python, or R.
In the era of data science, the extraction of meaningful features in datasets is a crucial challenge. To do so, a fundamental class of unsupervised linear dimensionality reduction methods is low-rank matrix factorizations (LRMF). Nonnegative matrix factorization (NMF) is an LRMF for analyzing high-dimensional data as it automatically extracts sparse and meaningful features from a set of nonnegative data. It has gained application in hyperspectral imaging and audio source separation. Other applications of NMF include extracting parts of faces from sets of facial images, identifying topics in a collection of documents, learning hidden Markov models, etc. This project aims at developing efficient NMF algorithms for analyzing medical images and detecting communities in large networks.