Papers
Updated in Dec. 2012
For
updates, please check the new page:
https://sites.google.com/site/researchbyzhang/
Search all my papers and citations via Google
Scholar
Books
[1]
Zhilin Zhang, Sparse
Bayesian Learning: Theories, Algorithms, and Applications, (preprint
chapters will be posted soon on https://sites.google.com/site/researchbyzhang/)
Patents
[1]
Zhilin Zhang, Bhaskar D. Rao, Low Energy
Wireless Body-Area Networks for Remote Telemonitoring
of Physiological Signals Such as Fetal ECG and EEG, (pending)
Ph.D.
Dissertation
Sparse Signal Recovery Exploiting Spatiotemporal
Correlation, University of California, San Diego, 2012
Selected
Journal Papers
[15] Biomarker Identification and Cognitive Score Prediction from MRI Images Using Sparse Bayesian Learning: Part II
Zhilin Zhang, Jing Wan, Shiaofen Fang, Andrew Saykin, Li Shen
In preparation for submitting to NeuroImage
[14] Biomarker Identification and Cognitive Score Prediction from MRI Images Using Sparse Bayesian Learning: Part I
Jing Wan, Zhilin Zhang, Shiaofen Fang, Andrew Saykin, Li Shen
In preparation for submitting to NeuroImage
[13] Fast Marginalized Block SBL Algorithm
Benyuan Liu, Zhilin Zhang, Hongqi Fan, Zaiqi Lu, Qiang Fu
submitted to IEEE Signal Processing Letters,
2012
[A fast BSBL algorithm developed by marginalized maximum likelihood.]
[12] Face Recognition via Block Sparse Bayesian Learning
Taiyong Li, Zhilin Zhang
submitted to Neurocomputing, 2012
[Application of BSBL to face recognition.]
[11] Spatiotemporal Sparse Bayesian Learning with Applications to Compressed Sensing of Multichannel ECG for Wireless Telemonitoring
Zhilin Zhang, Tzyy-Ping Jung, Scott Makeig, Bhaskar D. Rao
submitted to IEEE Trans. on Biomedical Engineering, 2012
[SBL exploiting spatio-temporal correlation, with applications to recover non-sparse multichannel signals.]
[10] Compressed Sensing of EEG for
Wireless Telemonitoring with Low Energy Consumption
and Inexpensive Hardware
Zhilin Zhang, Tzyy-Ping Jung, Scott Makeig, Bhaskar D. Rao
IEEE Trans. on Biomedical Engineering, accepted
[Application of BSBL to wireless telemonitoring of raw EEG, showing its ability to recover less-sparse
signals.]
[9] Compressed Sensing for Energy-Efficient Wireless Telemonitoring of Non-Invasive Fetal ECG via Block Sparse Bayesian Learning
Zhilin Zhang, Tzyy-Ping Jung, Scott Makeig, Bhaskar D. Rao
IEEE Trans. on Biomedical Engineering, accepted
[Application of BSBL to wireless telemonitoring of raw fetal ECG, showing its ability to
directly recover non-sparse signals.]
[8] Extension of SBL Algorithms for the Recovery of Block Sparse Signals with Intra-Block Correlation
Zhilin Zhang, Bhaskar D. Rao
IEEE Trans. on Signal Processing, accepted
[Proposed the
Block
Sparse Bayesian Learning (BSBL) framework and its extension for
recovering block sparse signals with or without knowledge of block partition; Intro-block
correlation was exploited for better performance; Provided a
strategy to improve group Lasso type algorithms.]
[7] Evolving Signal Processing for Brain-Computer Interface (invited review)
Scott Makeig, Christian Kothe, Tim Mullen, Nima Bigdely-Shamlo, Zhilin Zhang, Kenneth Kreutz-Delgado
Proceedings of the IEEE, vol.100, Special Centennial Issue, pp.1567-1584, 2012
[PDF]
[Discuss the challenges associated
with building robust and useful BCI models from accumulated biological
knowledge and data, and the technical problems associated with incorporating
multimodal physiological, behavioral, and contextual data that may become
ubiquitous in the future.]
[6] Sparse Signal Recovery with
Temporally Correlated Source Vectors Using Sparse Bayesian Learning
Zhilin Zhang, Bhaskar D. Rao
IEEE Journal of Selected Topics in Signal Processing, vol.5, no. 5, pp. 912-926, 2011
[Proposed the T-MSBL algorithm exploiting
temporal correlation for the MMV model.]
[5] Morphologically Constrained ICA for Extracting Weak Temporally Correlated Signals
Zhi-Lin Zhang
Neurocomputing 71(7-9) (2008) 1669-1679
[Gives detailed analysis on
constrained ICA framework, and provides a hybrid algorithm for extracting weak
sources with temporal structures]
[4] A Fast and Adaptive ICA Algorithm with Its
Application to Fetal Electrocardiogram Extraction
Yalan Ye, Zhi-Lin Zhang
Applied Mathematics and Computation, 205
(2) (2008) 799-806
[New algorithm for extracting fetal ECG]
[3] Robust Extraction of Specific
Signals with Temporal Structure
Zhi-Lin Zhang, Zhang Yi
Neurocomputing
69 (7-9) (2006) 888-893
[New class of BSE algorithms for
extracting sources with temporal structures via maximizing multiple delayed
autocorrelation]
[2] Extraction of Temporally Correlated
Sources with Its Application to Non-invasive Fetal Electrocardiogram Extraction,
Zhi-Lin Zhang, Zhang Yi
Neurocomputing 69 (7-9)
(2006) 900-904
[PDF]
[New BSE algorithm based on the
combination of temporal structures and higher-order statistics of desired
sources]
[1] Extraction of a Source Signal Whose
Kurtosis Value Lies in a Specific Range
Zhi-Lin Zhang, Zhang Yi
Neurocomputing 69 (7-9) (2006) 894-899
[PDF]
[New BSE algorithm exploiting a prior
on the kurtosis range of desired sources]
Selected
Conference Papers
[8] Sparse Bayesian Multi-Task Learning for Predicting Cognitive Outcomes from Neuroimaging Measures in Alzheimer's Disease
Jing Wan*, Zhilin Zhang*, Jingwen Yan, Taiyong Li, Bhaskar D. Rao, Shiaofen Fang, Sungeun Kim, Shannon Risacher, Andrew Saykin, Li Shen (*equal contribution)
IEEE Int. Conf. on Computer Vision and Pattern Recognition (CVPR 2012), Rhode Island, USA, June, 2012 (acceptance rate: 24%)
[PDF] [Code]
[Proposed a much fast variant of
T-MSBL for multi-task
learning, with a connection to group Lasso and mixed L2-L1 based
algorithms, etc; Achieved the highest prediction accuracy]
[7] Sparse Signal Recovery in the
Presence of Intra-Vector and Inter-Vector Correlation (invited)
Bhaskar D. Rao, Zhilin Zhang, Yuzhe Jin
International Conference on Signal Processing and Communications (SPCOM 2012), Bangalore, India, July, 2012
[PDF]
[A short review paper on the problem
of sparse signal recovery when there is correlation among the values of
non-zero entries of solution vectors/matrices]
[6] Recovery of Block Sparse Signals Using the Framework of Block Sparse Bayesian Learning
Zhilin Zhang, Bhaskar D. Rao
Proc. of the 37th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2012), Japan, March, 2012
[PDF] [Supplementary] [Code] [Web Page] [Slides]
[Proposed the
Block Sparse Bayesian Learning (BSBL) framework and its extension for
recovering block sparse signals with intra-block correlation. The journal
version can be found here]
[5] Iterative Reweighted Algorithms for Sparse Signal Recovery with Temporally Correlated Source Vectors
Zhilin Zhang, Bhaskar D. Rao
Proc. of the 36th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2011), Prague, the Czech Republic, May, 2011
[By
connecting the T-MSBL to iterative reweighted L2 algorithms, the paper proposed
an effective strategy
to improve iterative reweighted L2 algorithms for the MMV model. As an
example, a temporal extension of M-FOCUSS is derived.]
[4] Sparse Signal Recovery in the Presence of Correlated Multiple Measurement
Vectors
Zhilin
Zhang, Bhaskar D. Rao
Proc. of the 35th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2010), Texas, USA, 2010
[Exploited the temporal correlation in the
MMV model; The AR-SBL algorithm is proposed.]
[3] Linear Prediction Based Blind Source Extraction Algorithms in Practical Applications
Zhi-Lin Zhang, Liqing Zhang
Proc. of the 7th International Conference on Independent Component Analysis and Blind Signal Separation (ICA 2007), UK, 2007
[PDF] [Color Version]
[Points out that most
linear-prediction based BSE algorithms have two crucial problems, i.e, the MCA nature and the switch phenomenon]
[2] A Two-stage Based Approach for Extracting
Periodic Signals
Zhi-Lin Zhang, Liqing Zhang
Proc. of the 6th International Conference on Independent Component Analysis and Blind Signal Separation (ICA 2006), USA, 2006
[New BSE algorithm to extract
periodic or quasi-periodic signals by exploiting autocorrelation and adaptive
nonlinearities.]
[1] Two-Stage Temporally Correlated
Source Extraction Algorithm with Its Application in Extraction and
Classification of Event-Related Potentials
Zhi-Lin Zhang, Liqing
Zhang, Xiu-Ling Wu, Jie Li,
Qibin Zhao
Proc. of the 13th International Conference on Neural
Information Processing (ICONIP 2006), Lecture Notes in Computer Science, Vol.
4233, Hong Kong, Oct. 2006, pp. 523-532
[PDF]
[Apply BSE algorithm to ERP extraction and classification]
Research
Notes, Technical Reports, Abstracts
[3] Clarify Some
Issues on the Sparse Bayesian Learning for Sparse Signal Recovery
Zhilin Zhang, Bhaskar D. Rao
Technical Report, University of California, San Diego, September, 2011
[PDF]
[Clarifies some misunderstandings on
SBL and serves as guidance for correctly using SBL.]
[2] Exploiting
Correlation in Sparse Signal Recovery Problems: Multiple Measurement Vectors,
Block Sparsity, and Time-Varying Sparsity
Zhilin Zhang, Bhaskar D. Rao
ICML
2011 Workshop on Structured Sparsity: Learning and
Inference, July, 2011
[Comment: advises the use of MMV models to approximate time-varying sparsity model]
[1] Comparison
of Sparse Signal Recovery Algorithms with Highly Coherent Dictionary Matrices:
The Advantage of T-MSBL
Zhilin Zhang
Research Note
[Shows the superiority of T-MSBL to
other eleven typical compressed sensing algorithms when sensing/dictionary
matrices are highly coherent]