Sparse modeling has demonstrated its superior performances in many applications. Compared to optimization based approaches, Bayesian sparse modeling generally provides a more sparse result with a knowledge of confidence. Using the Spike and Slab priors, we propose the hierarchical sparse models for the scenario of single task and multitask - Hi-BCS and CHi-BCS. We draw the connections of these two methods to their optimization based counterparts and use expectation propagation for inference. The experiment results using synthetic and real data demonstrate that the performance of Hi-BCS and Chi-BCS are comparable or better than their optimization based counterparts.
Next generation neural recording and brain-machine interface (BMI) devices call for high density or distributed systems with more than 1000 recording sites. As the recording site density grows, the device generates data on the scale of several hundred megabits per second (Mbps). Transmitting such large amounts of data induces significant power consumption and heat dissipation for the implanted electronics. Facing these constraints, efficient on-chip compression techniques become essential to the reduction of implanted systems power consumption. This paper analyzes the communication channel constraints for high density neural recording devices. This paper then quantifies the improvement on communication channel using efficient on-chip compression methods. Finally, This paper describes a Compressed Sensing (CS) based system that can reduce the data rate by > 10× times while using power on the order of a few hundred nW per recording channel.
Promising results have been achieved in image classification problems by exploiting the discriminative power of sparse representations for classification (SRC). Recently, it has been shown that the use of \emph{class-specific} spike-and-slab priors in conjunction with the class-specific dictionaries from SRC is particularly effective in low training scenarios. As a logical extension, we build on this framework for multitask scenarios, wherein multiple representations of the same physical phenomena are available. We experimentally demonstrate the benefits of mining joint information from different camera views for multi-view face recognition.
Insect based Mobile Wireless Sensor Nodes (MWSN) has gained interests from the research community in recent year. These small biological entities have excellent maneuverability and can enter extreme areas not accessible to human. In order not to hinder the flight of the insect, the image sensors carried by these small insects must be light, low power, high speed and is capable of providing high quality images for different scene conditions and flight speed. In this paper, we present an implementation of pixel-wise coded exposure image sensor, developed based on the theory of Compressed Sensing (CS). This architecture can provide up to 18× more frame rate with both high spatial and temporal resolution compared to a traditional image sensor with the same readout speed. Additionally, through adaptive control of the pixel exposure duration, this architecture can be made to provide optimal image quality under all conditions. The test pixel array consumes 46 μW at 100 fps.
Model-based compressive sensing (CS) exploits the structure inherent in sparse signals for the design of better signal recovery algorithms. This information about structure is often captured in the form of a prior on the sparse coefficients, the Laplacian being the most common such choice (leading to l 1 -norm minimization). The recent seminal contribution by Wright et al. exploits the discriminative capability of sparse representations for image classification, specifically face recognition. Their approach employs the analytical framework of CS with class-specific dictionaries. Our contribution is a logical extension of these ideas into structured sparsity for classification. We use class-specific dictionaries in conjunction with discriminative class-specific priors, specifically the spike-and-slab prior widely applied in Bayesian regression. Significantly, the proposed framework takes the burden off the demand for abundant training image samples necessary for the success of sparsity-based classification schemes.
There is an increased use of both dynamic and structural magnetic resonance imaging (MRI) methods on studies in normal and disordered speeches. However, due to the anatomical variation among subjects, it has been a challenge to obtain quantitative results from a series of subjects or patients. To compare inter- and intrasubjects’ MRI data a 3-D digital articulator labeled atlas is presented. Experts, head and neck surgeons and speech language pathologists, manually segmented the tongue, soft and hard palate, lips, pharyngeal walls, and larynx from three sets of MRI of healthy volunteers. Then, 30 naïve raters segmented the same articulators with a multiple-structure semiautomated approach for rapid delineation. Concept, application, and comparison with multiple raters and fully manual delineation are provided. [Work supported by NIH-NIDCD Grant No. R00-DC009279.]
Sparsity driven signal processing has gained tremendous popularity in the last decade. At its core, the assumption is that the signal of interest is sparse with respect to either a fixed transformation or a signal dependent dictionary. To better capture the data characteristics, various dictionary learning methods have been proposed for both reconstruction and classification tasks. For classification particularly, most approaches proposed so far have focused on designing explicit constraints on the sparse code to improve classification accuracy while simply adopting $l_0$-norm or $l_1$-norm for sparsity regularization. Motivated by the success of structured sparsity in the area of Compressed Sensing, we propose a structured dictionary learning framework (StructDL) that incorporates the structure information on both group and task levels in the learning process. Its benefits are two-fold: (i) the label consistency between dictionary atoms and training data are implicitly enforced; and (ii) the classification performance is more robust in the cases of a small dictionary size or limited training data than other techniques. Using the subspace model, we derive the conditions for StructDL to guarantee the performance and show theoretically that StructDL is superior to $l_0$-norm or $l_1$-norm regularized dictionary learning for classification. Extensive experiments have been performed on both synthetic simulations and real world applications, such as face recognition and object classification, to demonstrate the validity of the proposed DL framework.
Purpose Accurate tissue motion tracking within the tongue can help professionals diagnose and treat vocal tract–related disorders, evaluate speech quality before and after surgery, and conduct various scientific studies. The authors compared tissue tracking results from 4 widely used deformable registration (DR) methods applied to cine magnetic resonance imaging (MRI) with harmonic phase (HARP)–based tracking applied to tagged MRI. Method Ten subjects repeated the phrase “a geese” multiple times while sagittal images of the head were collected at 26 Hz, first in a tagged MRI data set and then in a cine MRI data set. HARP tracked the motion of 8 specified tissue points in the tagged data set. Four DR methods including diffeomorphic demons and free-form deformations based on cubic B-spline with 3 different similarity measures were used to track the same 8 points in the cine MRI data set. Individual points were tracked and length changes of several muscles were calculated using the DR- and HARP-based tracking methods. Results The results showed that the DR tracking errors were nonsystematic and varied in direction, amount, and timing across speakers and within speakers. Comparison of HARP and DR tracking with manual tracking showed better tracking results for HARP except at the tongue surface, where mistracking caused greater errors in HARP than DR. Conclusions Tissue point tracking using DR tracking methods contains nonsystematic tracking errors within and across subjects, making it less successful than tagged MRI tracking within the tongue. However, HARP sometimes mistracks points at the tongue surface of tagged MRI because of its limited bandpass filter and tag pattern fading, so that DR has better success measuring surface tissue points on cine MRI than HARP does. Therefore, a hybrid method is being explored.
