Academic Profile

Professor Rajapakse is with the School of Computer Engineering and the Director of BioInformatics Research Center. He is presently a Visiting Professor to the Department of Biological Engineering, Massachusettes Institute of Technology (MIT). He received his First Class (Hons) Bachelor degree in Electronic and Telecommunication Engineering from the University of Moratuwa (Sri Lanka). He began his post-graduate studies under the Fulbright Scholarship at University of Buffalo (USA) where he received Master and Ph.D. degrees in Electrical and Computer Engineering. Before joining NTU in 1998, he was a Visiting Fellow at the National Institute of Mental Health (USA) and a Visiting Scientist at the Max-Planck-Institute of Brain and Cognitive Sciences (Germany).

His research interests are in the areas of neuroinformatics and bioinformatics. He has made fundamental contributions in his area of research and published over 210 top quality international conference and journal papers, which are widely cited by the research community. He serves as Associate Editor for IEEE Transactions on Medical Imaging, IEEE Transactions on Computational Biology and Bioinformatics, and IEEE Engineering in Medicine and Biology Magazine, and in editorial boards of several other journals. He is presently the Chair of IAPR Technical Committee on Pattern Recognition for Bioinformatics.
asjagath_1_2.JPG picture
Prof Jagath Chandana Rajapakse
Professor, School of Computer Science and Engineering

Professor Rajapakse's areas of expertise are machine learning, brain imaging, and computational and systems biology.

Professor Rajapakse has pioneered several techniques for analysis of anatomical and functional MR images. His team was the first to develop techniques to model brain connectivity in an exploratory manner, using functional MR images. Presently, his team is investigating brain connectivity patterns underlying higher-order brain functions such as language and memory, and brain disease such as Parkinson's disease. He is also working on potential applications of brain connectivity and constrained independent component analysis (cICA) in Brain Computater Interface applications, especially in identifying different mental states and extracting features robust to inter- and intra-subject variations.

Professor Rajapakse is presently working on identifying key targets in biological pathways. His research is centered on identifying co-regulated genes, building gene regulary networks, fusion of protein-interactions, and identifying key molecules and core networks in pathways. His team also develops techniques to segment cells and nuclei, identify protein subcellular localizations, and model spatiotemporal changes of cell morphologies from cellular images obtained from electron microscopy and high content screening.
  • Developing Unsupervised Machine Learning Techniques for Discovering Novel Ocular and Brain Imaging Biomarkers of Alzheimer’s Disease

  • Machine learning for Demand Forecasting

  • Multilayer networks for identification of biomarkers and prediction of clinical variables from multi-omics data
  • J. C. Rajapakse, S. Gupta, X. Sui. (2017). Fitting network models for functional brain connectivity. IEEE International Symposium on Biomedical Imaging (ISBI 2017).

  • Kumar A, Lin F, and Rajapakse JC. (2016). Mixed spectrum analysis on fMRI time series. IEEE Transactions on Medical Imaging, 35(6), 1555-1564.

  • Kumar A, Lin F, Rajapakse JC. (2016). Proceedings of the International Symposium on Biomedical Imaging (ISBI 2016): Mixed spectral analysis in spatial context: application to fMRI. International Symposium on Biomedical Imaging (ISBI 2016) (pp. 1555-1564)IEEE.

  • Sui X, Li S, Rajapakse JC. (2016). Proceedings of the International Symposium on Biomedical Imaging (ISBI 2016): Locally regularized sparse subspace clustering with application to cortex parcellation on resting fMRI. International Symposium on Biomedical Imaging (ISBI 2016) (pp. 1286-1290).

  • Piyushkumar A. Mundra, Roy E. Welsch, and Jagath C. Rajapakse. (2012). Bootstrapping of short time-series multivariate gene-expression data. 20th International Conference on Computational Statistics.