Skip to content

Research Institute

K.P. Unnikrishnan, PhD

Research Institute
Center for Clinical and Research Informatics
Director, Neurological Research Informatics

Education

  • Undergraduate: B.Sc. (Major: Physics; Minors: Mathematics and Chemistry) Calicut University, Calicut, Kerala, India
    M.Sc. (Major: Physics; Specialization: Electronics) Cochin University, Cochin, Kerala, India
  • Graduate:
    • Pre-doctoral training: 1983 - Biophysics of Neural Function Summer School Instructor: Dr. Daniel Alkon Marine Biological Laboratory, Woods Hole, MA
    • 1985 - Computational Neuroscience Summer School Instructors: Professors Ellen Hildreth and Anthony Movshon, Cold Spring Harbor Laboratory, Cold Spring Harbor, NY
  • Postgraduate: Ph.D. (Physics: Biophysics Concentration ) Advisor: Professor Erich Harth Dissertation Title:  “A Hierarchical Model of Visual Perception” Syracuse University, Syracuse, NY
  • Postgraduate: Post-doctoral training: 1987-1989  -  Post-doctoral Member of Technical Staff Biophysics Department Mentors:  Professor John Hopfield and Dr. David Tank, AT&T Bell Laboratories, Murray Hill, NJ
  • Postgraduate: Senior Post-doctoral training: Cognitive Neuroscience Summer School Instructor: Professor Steven Kosslyn, Harvard University, Harvard, MA

Research Interests

  • Integrated Biomedical Informatics: My primary focus here is to help create “personalized medicine” through data mining. Towards this goal, we i) develop data mining algorithms for analysis of medical and biological data, and ii) mine Electronic Health Records (EHRs) and Billing Records, along with Genomic, Proteomic, and Metabolomic data using these algorithms. My research involves close collaborations with Computer Scientists, Statisticians, Mathematicians, Bioinformaticians, and practitioners of Clinical Medicine.
  • Data Mining and its Applications to Neuroinformatics: This follows a three-year long basic research program I led at General Motors Research. We believe that by studying complex biological systems from a computational view point will lead to organizational principles that not only reveal how the natural system functions in its environment, but also suggest ways to engineer better artifacts endowed with similar intelligent behavior. Research along this line will lead to better understanding of basic mechanisms of perception, and memory and also lead to applications in better neuro-prosthetic devices.
  • Surveillance and Disease Prevention: Data mining algorithms, due to their ability to discover combinatorially large patterns, gives extreme sensitivity to monitor network activity. We are analyzing transfer of patients in a large network of Intensive Care Units, and also developing predictive models for Sepsis, MRSA, and C difficile in hospitals.
  • Network Analytics: Biological, other natural, and man-made systems form networks at many levels. Throughout my career, I have been a champion of interdisciplinary sciences. I plan to create, co-ordinate, and participate in large inter-disciplinary studies of networks, thereby helping create the field of Network Analytics.

Honors and Awards

  • (2006)  General Motors Charles L. McCuen Special Achievement Award - Awarded for the development of data mining algorithms and their deployment for root-cause diagnostics in automotive assembly plants
  • (2006-2009) General Motors Discovery Project Award - Awarded to less than 1% of research staff to conduct basic research in non-automotive areas. I was the recipient of the largest Discovery Project ever.

Professional Memberships/Affiliations/Activities

  • (1982-1997) Society for Neuroscience
  • (1982-present)  American Association for the Advancement of Science (AAAS)
  • (1999-present)  Association for Computing Machinery (ACM) Special interest Group in Knowledge Discovery and Data Mining (SIGKDD)
  • (2010-present)  American Medical Informatics Association (AMIA) 

Scholarly Work

Publications in Peer-Review Journals: (Note: Citation counts are from Google scholar, as of 10/22/2011. Based on this search, the h-index of K P Unnikrishnan is 13)

  1. Stiles, M., E. Tzanakou, R. Michalak, K.P. Unnikrishnan, P. Goyal, and E. Harth (1985) Periodic and nonperiodic burst responses in frog (Rana Pipiens) retinal ganglion cells. Experimental Neurology 88: 176-197.
  2. Harth, E., and K.P. Unnikrishnan (1985) Brainstem control of sensory information: a mechanism for perception. International journal of psychophysiology 3:101-119.
  3. Harth, E., K.P. Unnikrishnan, and A.S. Pandya (1987) The inversion of sensory processing by feedback pathways: A model of visual cognitive functions. Science 237: 184-187. (81 citations).
  4. Harth, E., A.S. Pandya, and K.P. Unnikrishnan (1990) Optimization of cortical responses by feedback modification and synthesis of sensory afferents: A model of perception and REM sleep. Concepts in Neuroscience 1: 53-68.
  5. Unnikrishnan, K.P., J.J. Hopfield, and D.W. Tank (1991) Connected-digit speech recognition by a neural network using learned time-delayed connections. IEEE Transactions on Signal Processing 39: 698-713. (66 citations).
  6. Unnikrishnan, K.P., J.J. Hopfield, and D.W. Tank (1992) Speaker-independent digit recognition using a neural network with time-delayed connections. Neural Computation 4: 108-119.
  7. Sastry. P.S., G. Santaram, and K.P. Unnikrishnan (1994) Memory neuron networks for identification and control of dynamical systems. IEEE Transactions on Neural Networks 5: 306-319. (202 citations).
  8. Unnikrishnan, K.P., and K.P. Venugopal (1994) Alopex: A correlation-based learning algorithm for feed-forward and recurrent neural networks. Neural Computation 6: 469-490. (92 citations).
  9. Sastry, P.S., S. Shah, S. Singh, and K.P. Unnikrishnan (1999) Role of feedback in mammalian vision: A new hypothesis and a computational model. Vision Research 39: 131­148.
  10. Sastry, P.S., M. Magesh, and K.P. Unnikrishnan (2002) Two timescale analysis of the Alopex algorithm for optimization. Neural Computation 14: 2729-2750. (21 citations).
  11. Unnikrishnan, K.P., R. Uthurusamy, and J. Han (2004) The Third SIGKDD Workshop on Mining Temporal and Sequential Data (KDD/TDM 2004). ACM SIGKDD Explorations Newsletter 6: 152.
  12. Laxman, S., P.S. Sastry, and K.P. Unnikrishnan. (2005) Discovering frequent episodes and learning hidden Markov models: a formal connection. IEEE Transactions on Knowledge and Data Engineering 17: 1505-1517. (58 citations).
  13. Unnikrishnan, K.P., N. Ramakrishnan, P. S. Sastry, and R. Uthurusamy (2006) Network reconstruction from dynamic data. ACM SIGKDD Explorations Newsletter 8: 90-91.
  14. Laxman, S., P.S. Sastry, and K.P. Unnikrishnan (2007) Discovering frequent generalized episodes when events persist for different durations. IEEE Transactions on Knowledge and Data Engineering 19: 1188-1201.
  15. Patnaik, D., P. S. Sastry, and K.P. Unnikrishnan (2008) Inferring Neuronal Network Connectivity from Spike Data: A Temporal Data mining Approach. Scientific Programming 16: 49-77. (34 citations).
  16. Diekman, C. O., P.S. Sastry, and K.P. Unnikrishnan (2009) On the statistical significance of sequential firing patterns in multi-neuronal spike trains. Journal of Neuroscience Methods 182: 279-284.
  17. Sastry, P. S., and K. P. Unnikrishnan (2010). Conditional probability based significance tests for sequential patterns in multi-neuronal spike trains. Neural Computation 22: 1025­1059.

Completed manuscripts, to be submitted:

  1. Laxman, S., B. Shadid, P.S. Sastry, and K. P. Unnikrishnan. Temporal data mining for root-cause analysis of machine faults in automotive assembly lines.
  2. Diekman C., Dasgupta K., Nair V., and K.P. Unnikrishnan. Statistical Inference of Functional Connectivity in Neuronal Networks using Frequent Episodes.
  3. Viswanathan, R., P.S. Sastry, and K. P. Unnikrishnan. Efficient Discovery of Large Synchronous Events in Neural Spike Streams.

Book Chapters:

  1. Harth, E., K.P. Unnikrishnan, and A.S. Pandya (1988). Reafferent stimulation: A model for early and late vision. Computer Simulation in Brain Science (Cotterill, ed). Cambridge Univ. Press.
  2. Harth, E., K.P. Unnikrishnan, and A.S. Pandya (1989). The inversion of sensory processing by feedback pathways: A model of visual cognitive functions. In Molecules to Models; Advances in Neuroscience (Kelner and Koshland, eds.) American Association for Advancement of Science (AAAS) Press.

Edited Volumes:

  1. Unnikrishnan K.P., R. Uthurusamy, and J. Han, eds (2004) Proceedings of Third International Workshop on Mining Temporal and Sequential Data, Association for Computing Machinery (ACM).
  2. Unnikrishnan K.P., and R. Uthurusamy, eds. (2002) Proceedings of the Second International Workshop on Temporal Data Mining, Association for Computing Machinery (ACM).
  3. Unnikrishnan K.P., and R. Uthurusamy, eds. (2000) Proceedings of the First Temporal Data Mining Workshop, Association for Computing Machinery (ACM).

Peer Review Service:

  1. (1994) Reviewer/Panel Member, Panel on Neural Networks, National Science Foundation
  2. (1995-1998) Reviewer, Grants on Neural Networks, National Science Foundation
  3. (2002-2004) Reviewer/Panel Member, SBIR Panel on Data Mining, National Science Foundation
  4. (1995-present) Science Neural Computation
  5. (1995-present) IEEE Computer
  6. (1995-present) IEEE Transactions on Neural Networks
  7. (1995-present) IEEE Transactions on Systems, Man, and Cybernetics
  8. (1995-present) Journal of Neuroscience
  9. (1995-present) Neural Networks
  10. (1995-present) IIE Transaction on Manufacturing
  11. (1995-present) ACM International Conference on Knowledge Discovery and Data Mining
  12. (1995-present) IEEE Conference on Automation Science and Engineering Computers in Biology and Medicine
  13. (1996) Co-chair, Workshop: Role of Feedback in Nervous Systems, San Francisco, CA
  14. (2001) Co-chair, KDD Workshop on Temporal Data Mining, San Francisco, CA
  15. (2002) Co-chair, 2nd KDD Workshop on Temporal Data Mining, Edmonton, Canada
  16. (2002) Program Committee Member, ACM Conference on KDD, Edmonton, Canada
  17. (2004) Co-chair, 3rd KDD Workshop Mining Temporal & Sequential Data, Seattle, WA
  18. (2006) Co-chair, 4th KDD Workshop on Temporal Data Mining, Washington, DC
  19. (2009) Program Committee Member, ACM Conference on KDD, Paris, France
  20. (2009) Program Committee Member, IEEE Conference on Automation Science and Engineering, Bangalore, India
  21. (2010) Program Committee Member, IEEE Conference on Automation Science and Engineering, Toronto, Canada
  22. (2010) Program Committee Member, IEEE International Conference on Data Mining, Sydney, Australia
  23. (2011) Program Committee Member, IEEE International Conference on Data Mining, Vancouver, Canada

Peer-Review Conference Proceedings (Partial list):

  1. Laxman, S., P.S. Sastry, and K.P. Unnikrishnan (2002). Generalized frequent episodes in event sequences. Temporal Data Mining Workshop notes 46-52.
  2. Laxman, S., P.S. Sastry, and K.P. Unnikrishnan (2004). Fast algorithms for frequent episode discovery in event sequences. Proc. Third International Workshop on Mining Temporal and Sequential Data 33-40.
  3. Patnaik, D., P. S. Sastry, and K.P. Unnikrishnan (2006). Discovering Network Patterns in Microelectrode Array Data. Proc. 4th Knowledge Discovery and Data Mining Workshop on Temporal Data Mining 33-40.
  4. S. Laxman, P. S. Sastry, and K.P. Unnikrishnan (2007). A fast algorithm for finding frequent episodes in event streams. Proceedings of Knowledge Discovery and Data Mining 2007: 410-419. (41 citations) 
  5. K.P. Unnikrishnan, D. Patnaik, and T.J. Iwashyna (2010). Discovering specific cascades in critical care transfer networks. IHI’10 Proceedings of the ACM First International Health Informatics Conference 541-544. 
  6. K.P. Unnikrishnan, D. Patnaik, and T.J. Iwashyna (2011). Spatio-temporal structure of US critical care transfer network. Proceedings of the AMIA 2011 Clinical Research Informatics Summit 74-78.

Patents:

  1. K.P. Unnikrishnan, Basel Shadid, P.S. Sastry, and Srivatsan Laxman. Root-cause diagnostics of machine and system faults using temporal data mining. (Patent no: 7509234, issued March 24, 2009).
  2. P.S. Sastry, Srivatsan Laxman, and K.P. Unnikrishnan. System and method for mining of temporal data. (Patent no: 7644078, issued January 5, 2010).
  3. P.S. Sastry, Srivatsan Laxman, and K.P. Unnikrishnan. System and methods for temporal data mining. (Patent no: 7644079, issued January 5, 2010).
  4. Debprakash Patnaik, Pulak Bandyopadhyay, Steven Holland, K.P. Unnikrishnan, and G. PaulMontgomery. Fault prediction framework using temporal data mining. (Patent applicationno: 0172874A1, published July 14, 2011).