Sang Peter Chin

An Efficient and Compact Compressed Sensing Microsystem for Implantable Neural Recordings

Multi-Electrode Arrays (MEA) have been widely used in neuroscience experiments. However, the reduction of their wireless transmission power consumption remains a major challenge. To resolve this challenge, an efficient on-chip signal compression method is essential. In this paper, we first introduce a signal-dependent Compressed Sensing (CS) approach that outperforms previous works in terms of compression rate and reconstruction quality. Using a publicly available database, our simulation results show that the proposed system is able to achieve a signal compression rate of 8 to 16 while guaranteeing almost perfect spike classification rate. Finally, we demonstrate power consumption measurements and area estimation of a test structure implemented using TSMC 0.18 μm process. We estimate the proposed system would occupy an area of around 200 μm ×300 μm per recording channel, and consumes 0.27 μW operating at 20 KHz .

Real Time Compressive Sensing Video Reconstruction in Hardware

Compressive sensing has allowed for reconstruction of missing pixels in incomplete images with higher accuracy than was previously possible. Moreover, video data or sequences of images contain even more correlation, leading to a much sparser representation as demonstrated repeatedly in numerous digital video formats and international standards. Compressive sensing has inspired the design of a number of imagers which take advantage of the need to only subsample a scene, which reduces power consumption by requiring acquisition and transmission of fewer samples. In this paper, we show how missing pixels in a video sequence can be estimated using compressive sensing techniques. We present a real time implementation of our algorithm and show its application to an asynchronous time-based image sensor (ATIS) from the Austrian Institute of Technology. The ATIS only provides pixel intensity data when and where a change in pixel intensity is detected, however, noise randomly causes intensity changes to be falsely detected, thereby providing random samples of static regions of the scene. Unlike other compressive sensing imagers, which typically have pseudo-random sampling designed in at extra effort, the ATIS used here provides random samples as a side effect of circuit noise. Here, we describe and analyze a field-programmable gate array implementation of a matching pursuit (MP) algorithm for compressive sensing reconstruction capable of reconstructing over 1.9 million 8 × 8 pixel regions per second with a sparsity of 11 using a basis dictionary containing 64 elements. In our application to ATIS we achieve throughput of 28 frames per second at a resolution of 304 × 240 pixels with reconstruction accuracy comparable to that of state of the art algorithms evaluated offline.

An unsupervised dictionary learning algorithm for neural recordings

To meet the growing demand of wireless and power efficient neural recordings systems, we demonstrate an unsupervised dictionary learning algorithm in Compressed Sensing (CS) framework which can be implemented in VLSI systems. Without prior label information of neural spikes, we extend our previous work to unsupervised learning and construct a dictionary with discriminative structures for spike sorting. To further improve the reconstruction and classification performance, we proposed a joint prediction to determine the class of neural spikes in dictionary learning. When the neural spikes is compressed 50 times, our approach can achieve an average gain of 2 dB and 15 percentage units over state-of-the-art of CS approaches in terms of the reconstruction quality and classification accuracy respectively.

Structured sparse representation with low-rank interference

This paper proposes a novel framework that is capable of extracting the low-rank interference while simultaneously promoting sparsity-based representation of multiple correlated signals. The proposed model provides an efficient approach for the representation of multiple measurements where the underlying signals exhibit a structured sparsity representation over some proper dictionaries but the set of testing samples are corrupted by the interference from external sources. Under the assumption that the interference component forms a low-rank structure, the proposed algorithms minimize the nuclear norm of the interference to exclude it from the representation of multivariate sparse representation. An efficient algorithm based on alternating direction method of multipliers is proposed for the general framework. Extensive experimental results are conducted on two practical applications: chemical plume detection and classification in hyperspectral sequences and robust speech recognition in noisy environments to verify the effectiveness of the proposed methods.

Reconstruction of neural action potentials using signal dependent sparse representations

We demonstrate a method to build signal dependent sparse representation dictionary for neural action potentials using K-SVD algorithm and Discrete Wavelets Transform. We also show a method to utilize this dictionary to recover the neural signal in the Compressive Sensing (CS) framework. Comparing against the non-signal dependent CS recovery algorithms, this new recovery algorithm can achieve same reconstruction quality with 2.5 times less compressed sensing measurements. For the same compression ratio, the purposed approach can increase recovery signals signal to noise and distortion ratio (SNDR) by around 6 dB compare to non-signal dependent recovery method. We also evaluated the recovered signal using spike sorting techniques. The results have shown that the spikes clusters still maintain clear separation even when the compression ratio is at 15-20% of the Nyquist rate. This work also implies that any hardware implementation of compressed sensing could be scaled down in term of power and chip area by the same order if this signal dependent framework is used to recover the signal.

Chemical plume detection in hyperspectral imagery via joint sparse representation

In this paper, we propose a new spatial-temporal joint sparsity method for the identification and detection of chemical plume in hyperspectral imagery. The proposed algorithm relies on two key observations: 1. each hyperspectral pixel can be approximately represented by a sparse linear combination of the training samples; and 2. neighborhood pixels from the same hyperspectral image as well as consecutive hyperspectral frames usually have similar spectral characteristics. By grouping these pixels into a joint group structure and forcing them to have the same sparsity support of the training samples, we effectively exclude the correlation of not only spatial but also time domain of the HSI data. Before the presence of this paper, almost no methods have made use of the temporal information for the detection of chemical plume in hyperspectral video data. Furthermore, the proposed method shows very competitive results with the Adaptive Matched Subspace Detector (AMSD) algorithm where the chemical types are predefined.

Automatic Vertebra Labeling in Large-Scale 3D CT Using Deep Image-to-Image Network with Message Passing and Sparsity Regularization

Automatic localization and labeling of vertebra in 3D medical images plays an important role in many clinical tasks, including pathological diagnosis, surgical planning and postoperative assessment. However, the unusual conditions of pathological cases, such as the abnormal spine curvature, bright visual imaging artifacts caused by metal implants, and the limited field of view, increase the difficulties of accurate localization. In this paper, we propose an automatic and fast algorithm to localize and label the vertebra centroids in 3D CT volumes. First, we deploy a deep image-to-image network (DI2IN) to initialize vertebra locations, employing the convolutional encoder-decoder architecture together with multi-level feature concatenation and deep supervision. Next, the centroid probability maps from DI2IN are iteratively evolved with the message passing schemes based on the mutual relation of vertebra centroids. Finally, the localization results are refined with sparsity regularization. The proposed method is evaluated on a public dataset of 302 spine CT volumes with various pathologies. Our method outperforms other state-of-the-art methods in terms of localization accuracy. The run time is around 3 seconds on average per case. To further boost the performance, we retrain the DI2IN on additional 1000+ 3D CT volumes from different patients. To the best of our knowledge, this is the first time more than 1000 3D CT volumes with expert annotation are adopted in experiments for the anatomic landmark detection tasks. Our experimental results show that training with such a large dataset significantly improves the performance and the overall identification rate, for the first time by our knowledge, reaches 90%.

Partial face recognition: A sparse representation-based approach

Partial face recognition is a problem that often arises in practical settings and applications. We propose a sparse representation-based algorithm for this problem. Our method firstly trains a dictionary and the classifier parameters in a supervised dictionary learning framework and then aligns the partially observed test image and seeks for the sparse representation with respect to the training data alternatively to obtain its label. We also analyze the performance limit of sparse representation-based classification algorithms on partial observations. Finally, face recognition experiments on the popular AR data-set are conducted to validate the effectiveness of the proposed method.

Video frame interpolation via weighted robust principal component analysis

In this paper, we propose a new video frame interpolation technique by a locally-adaptive robust principal component analysis (RPCA) with weight priors. The proposed algorithm relies on two main steps: 1. the pre-processing step initializes the new frame by a simplified motion-compensated frame interpolation and assigns each pixel a confident weight based on both the difference of motion estimation and local consistency; and 2. the refinement step updates the frame by a proposed weighted robust principal component analysis (WRPCA) algorithm. Experiments demonstrate that the proposed method outperforms the state-of-the-art algorithms, both in visual quality and PSNR performance.

Neural signal processing and closed-loop control algorithm design for an implanted neural recording and stimulation system.

A fully autonomous intracranial device is built to continually record neural activities in different parts of the brain, process these sampled signals, decode features that correlate to behaviors and neuropsychiatric states, and use these features to deliver brain stimulation in a closed-loop fashion. In this paper, we describe the sampling and stimulation aspects of such a device. We first describe the signal processing algorithms of two unsupervised spike sorting methods. Next, we describe the LFP time-frequency analysis and feature derivation from the two spike sorting methods. Spike sorting includes a novel approach to constructing a dictionary learning algorithm in a Compressed Sensing (CS) framework. We present a joint prediction scheme to determine the class of neural spikes in the dictionary learning framework; and, the second approach is a modified OSort algorithm which is implemented in a distributed system optimized for power efficiency. Furthermore, sorted spikes and time-frequency analysis of LFP signals can be used to generate derived features (including cross-frequency coupling, spike-field coupling). We then show how these derived features can be used in the design and development of novel decode and closed-loop control algorithms that are optimized to apply deep brain stimulation based on a patients neuropsychiatric state. For the control algorithm, we define the state vector as representative of a patients impulsivity, avoidance, inhibition, etc. Controller parameters are optimized to apply stimulation based on the state vectors current state as well as its historical values. The overall algorithm and software design for our implantable neural recording and stimulation system uses an innovative, adaptable, and reprogrammable architecture that enables advancement of the state-of-the-art in closed-loop neural control while also meeting the challenges of system power constraints and concurrent development with ongoing scientific research designed to define brain network connectivity and neural network dynamics that vary at the individual patient level and vary over time.