Primary motivation of my research is to discover novel approaches to automatically recognize patterns in large datasets and develop tools to answer questions that affect people. Upon noting that, even with the availability of powerful tools, most of the collected data is still unanalyzed and under utilized, I am primarily motivated by how useful inferences can be made with little extra effort on the data that is already available. In this context, I have worked on problems in medicine and sports. Currently, I am working on risk minimization in finance by learning the connections between financial time series.

My masters’ thesis focused on methods to improve the quality of multi-parameter physiological signal data in realtime. Automated systems in an intensive care unit critically depend on uninterrupted real-time monitoring of the physiological signals, but unfortunately, these signals are often corrupted by artifacts, and missing data. Inter-patient variations and the temporal evolution of the signals further exacerbate the problem. I investigated how to reconstruct the corrupted segments using the information available in correlated signals and signal history.

  • Learning Connections in Financial Time Series
  • Gartheeban, G., Guttag, J., Lo A., 2013
    Presented at ICML 2013
    [attachments docid=”669,687,694″ force_saveas=”0″ logged_users=”0″ attachments fields=”title,size”]
  • Real Time Reconstruction of Quasiperiodic Multi Parameter Physiological Signals
    Gartheeban, G., Guttag, J., 2012
    EURASIP Journal on Advances in Signal Processing 2012
    [attachments docid=661 force_saveas=”0″ logged_users=”0″ attachments fields=”title,size”]
  • Predicting the Next Pitch
    Gartheeban, G., Guttag, J., 2012
    Presented at Sports Analytics Conference 2012 (Presentation – Video)
    [attachments docid=605,600,599 force_saveas=”0″ logged_users=”0″ attachments fields=”title,size”]
  • Methods to Improve the Signal Quality of Corrupted Multi-Parameter Physiological Signals
    SM Thesis  – Master of Science in Computer Science and Engineering at the MIT
    [attachments docid=533,536,589,588 force_saveas=”0″ logged_users=”0″ attachments fields=”title,size”]
  • Reconstruction of ECG Signals in  Presence of Corruption
    Gartheeban, G., Jessica F. Liu, and Guttag, J. 2011
    Presented at 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society
    [attachments docid=581,580 force_saveas=”0″ logged_users=”0″ attachments fields=”title,size”]
  • Weighted Time Warping for Temporal Segmentation of Multi- Parameter Physiological Signals
    Gartheeban, G. and Guttag, J. 2011
    Presented at International Conference on Bio-Inspired Systems and Signal Processing 2011
    [attachments docid=465,463 force_saveas=”0″ logged_users=”0″ attachments fields=”title,size”]
  • Content based classification of multi-dimensional objects with PCA
    Gartheeban. G 2008. Sep 2008
    Presented at IET Annual Technical Conference – 2008, Sri Lanka
    [attachments docid=466 force_saveas=”0″ logged_users=”0″ attachments fields=”title,size”]