Shihao Ji

Office:   2475 CIEMAS, Duke University
Phone:   (919) 741-6093
Fax:   (919) 660-5293
Email:   shji@ece.duke.edu

I received my Ph.D. degree from the Department of Electrical and Computer Engineering at Duke University in 2006. My advisor was Dr. Lawrence Carin. I also worked closely with Dr. Ron Parr and Dr. Layne Watson.

Research Interests

  • Machine learning (Bayesian inference, active learning, semi-supervised learning, HMMs)
  • Video analysis (Object detection, tracking, segmentation, recognition)
  • Compressive sensing (Sparse Bayesian learning)
  • Decision-making under uncertainty, POMDP
  • Signal processing, spectrum estimation, image processing, wavelets

Education

  • Ph.D., Electrical and Computer Engineering, Duke University, USA, 2006
         Thesis: Learning and exploitation with hidden Markov models

  • M.S., Electrical Engineering, Xidian University, China, 2001
         Thesis: Adaptive digital beamforming: theory and implementation

  • B.S., Electrical Engineering, Xidian University, China, 1998

Publications

Refereed Publications

  • Shihao Ji, D. Dunson, and L. Carin, "Multi-task compressive sensing," IEEE Trans. Signal Processing, vol. 57, no. 1, pp. 92-106, Jan. 2009. [pdf file | code]

  • Shihao Ji, Y. Xue, and L. Carin, "Bayesian compressive sensing," IEEE Trans. Signal Processing, vol. 56, no. 6, pp. 2346-2356, June 2008. [pdf file | code]

  • T. Wang, T. Furey, J. Connelly, Shihao Ji, S. Nelson, S. Heber, S. Gregory, and E. Hauser, "A general integrative genomic feature transcription factor binding site prediction method applied to analysis of USF1 binding in cardiovascular disease," Human Genomics, vol. 3, no. 3, pp. 221-235, Apr. 2009.

  • Shihao Ji, L. T. Watson, and L. Carin, "Semi-supervised learning of hidden Markov models via a homotopy method," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 31, no. 2, pp. 275-287, Feb. 2009. [pdf file | data | demo]

  • J. Fang, Shihao Ji, Y. Xue, and L.Carin, "Multi-task classification by learning the task relevance," IEEE Signal Processing Letters, vol. 15, pp. 593-596, 2008.

  • Shihao Ji, R. Parr, H. Li, X. Liao, and L. Carin, "Point-based policy iteration," In the 22nd National Conference on Artificial Intelligence (AAAI), Vancouver, Canada, July 22-26, 2007. [pdf file]

  • Shihao Ji and L. Carin, "Bayesian compressive sensing and projection optimization," In the 24th International Conference on Machine Learning (ICML), Corvallis, Oregon, June 20-24, 2007. [pdf file]

  • Shihao Ji and L. Carin, "Cost-sensitive feature acquisition and classification," Pattern Recognition, vol. 40, no. 5, pp. 1474-1485, May 2007. [pdf file]

  • Shihao Ji, R. Parr, and L. Carin, "Non-myopic multi-aspect sensing with partially observable Markov decision processes," IEEE Trans. Signal Processing, vol. 55, no. 6, pp. 2720-2730 June 2007. [pdf file | demo1 ,demo2 ,demo3]

  • L. He, Shihao Ji, W.R. Scott, and L. Carin, "Adaptive multi-modality sensing of landmines," IEEE Trans. Geoscience and Remote Sensing, vol. 45, no. 6, pp.1756-1774, June 2007. [pdf file]

  • Shihao Ji, B. Krishnapuram, and L. Carin, "Variational Bayes for continuous hidden Markov models and its application to active learning," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 28, no. 4, pp. 522-532, Apr. 2006. [pdf file | data]

  • N. Dasgupta, Shihao Ji, and L. Carin, "Homotopy-based semi-supervised hidden Markov tree for texture analysis," in Proc. of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2006. [pdf file]

  • L. He, Shihao Ji, and L. Carin, "Application of partially observable Markov decision processes to robot navigation in a minefield," in ICAPS Workshop on POMDP, Classification and Regression: Relationships and Joint Utilization, June 2006. [pdf file]

  • Shihao Ji, X. Liao, and L. Carin, "Adaptive multi-aspect target classification and detection with hidden Markov models," IEEE Sensors Journal, vol. 5, no. 5, pp. 1035-1042, Oct. 2005. [pdf file]

  • Shihao Ji, X. Liao, and L. Carin, "Adaptive multi-aspect target classification and detection with hidden Markov models," in Proc. of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol. 2, pp. 125-128, May 2004. [pdf file]

Software

  • BCS: a Bayesian framework for solving the inverse problem of compressive sensing

Everything Else

  • Basketball Tournament: Champion 2006.
  • Here's a collection of lectures and tutorials for machine learning and AI: video lectures.
  • BBC Documentary: SuperNatural 1, 2, 3, 4, 5, 6, 7, 8.