Diagnostic grade wireless ECG monitoring.

In remote monitoring of Electrocardiogram (ECG), it is very important to ensure that the diagnostic integrity of signals is not compromised by sensing artifacts and channel errors. It is also important for the sensors to be extremely power efficient to enable wearable form factors and long battery life. We present an application of Compressive Sensing (CS) as an error mitigation scheme at the application layer for wearable, wireless sensors in diagnostic grade remote monitoring of ECG. In our previous work, we described an approach to mitigate errors due to packet losses by projecting ECG data to a random space and recovering a faithful representation using sparse reconstruction methods. Our contributions in this work are twofold. First, we present an efficient hardware implementation of random projection at the sensor. Second, we validate the diagnostic integrity of the reconstructed ECG after packet loss mitigation. We validate our approach on MIT and AHA databases comprising more than 250,000 normal and abnormal beats using EC57 protocols adopted by the Food and Drug Administration (FDA). We show that sensitivity and positive predictivity of a state-of-the-art ECG arrhythmia classifier is essentially invariant under CS based packet loss mitigation for both normal and abnormal beats even at high packet loss rates. In contrast, the performance degrades significantly in the absence of any error mitigation scheme, particularly for abnormal beats such as Ventricular Ectopic Beats (VEB).

Packet loss mitigation for biomedical signals in healthcare telemetry.

In this work, we propose an effective application layer solution for packet loss mitigation in the context of Body Sensor Networks (BSN) and healthcare telemetry. Packet losses occur due to many reasons including excessive path loss, interference from other wireless systems, handoffs, congestion, system loading, etc. A call for action is in order, as packet losses can have extremely adverse impact on many healthcare applications relying on BAN and WAN technologies. Our approach for packet loss mitigation is based on Compressed Sensing (CS), an emerging signal processing concept, wherein significantly fewer sensor measurements than that suggested by Shannon/Nyquist sampling theorem can be used to recover signals with arbitrarily fine resolution. We present simulation results demonstrating graceful degradation of performance with increasing packet loss rate. We also compare the proposed approach with retransmissions. The CS based packet loss mitigation approach was found to maintain up to 99% beat-detection accuracy at packet loss rates of 20%, with a constant latency of less than 2.5 seconds.

Adaptive feature-specific imaging for recognition of non-Gaussian classes.

We present an adaptive feature-specific imaging (AFSI) system for application to an M-class recognition task. The proposed system uses nearest-neighbor-based density estimation to compute the (non-Gaussian) class-conditional densities. We refine the density estimates based on the training data and the knowledge from previous measurements at each step. The projection basis for the AFSI system is also adapted based on the previous measurements at each step. The decision-making process is based on sequential hypothesis testing. We quantify the number of measurements required to achieve a specified probability of error (P(e)) and we compare the AFSI system with an adaptive-conventional (ACONV) system. The AFSI system exhibits significant improvement compared to the ACONV system at low signal-to-noise ratio (SNR), and it is shown that, for an M=4 hypotheses, SNR=-10 dB, and a desired P(e)=10(-2), the AFSI system requires 30 times fewer measurements than the ACONV system. Experimental results validating the AFSI system are presented.

Recognition using information-optimal adaptive feature-specific imaging.

We present an information-theoretic adaptive feature-specific imaging (AFSI) system for a M-class recognition task. The proposed system utilizes the recently developed task-specific information (TSI) framework to incorporate the knowledge from previous measurements and adapt the projection matrix at each step. The decision-making framework is based on sequential hypothesis testing. We quantify the number of measurements required to achieve a specified probability of misclassification (P(e)), and we compare the performances of three approaches: the new TSI-based AFSI system, a previously reported statistical AFSI system, and static FSI (SFSI). The TSI-based AFSI system exhibits significant improvement compared with SFSI and statistical AFSI at low signal-to-noise ratio (SNR). It is shown that for M=4 hypotheses, SNR=-20 dB and desired P(e)=10(-2), TSI-based AFSI requires 3 times fewer measurements than statistical AFSI, and 16 times fewer measurements than SFSI. We also describe an extension of the proposed method that is suitable for recognition in the presence of nuisance parameters such as illumination conditions and target orientations.

Compressive imaging system design using task-specific information.

We present a task-specific information (TSI) based framework for designing compressive imaging (CI) systems. The task of target detection is chosen to demonstrate the performance of the optimized CI system designs relative to a conventional imager. In our optimization framework, we first select a projection basis and then find the associated optimal photon-allocation vector in the presence of a total photon-count constraint. Several projection bases, including principal components (PC), independent components, generalized matched-filter, and generalized Fisher discriminant (GFD) are considered for candidate CI systems, and their respective performance is analyzed for the target-detection task. We find that the TSI-optimized CI system design based on a GFD projection basis outperforms all other candidate CI system designs as well as the conventional imager. The GFD-based compressive imager yields a TSI of 0.9841 bits (out of a maximum possible 1 bit for the detection task), which is nearly ten times the 0.0979 bits achieved by the conventional imager at a signal-to-noise ratio of 5.0. We also discuss the relation between the information-theoretic TSI metric and a conventional statistical metric like probability of error in the context of the target-detection problem. It is shown that the TSI can be used to derive an upper bound on the probability of error that can be attained by any detection algorithm.

Random projections based feature-specific structured imaging.

We present a feature-specific imaging system based on the use of structured illumination. The measurements are defined as inner products between the illumination patterns and the object reflectance function, measured on a single photodetector. The illumination patterns are defined using random binary patterns and thus do not employ prior knowledge about the object. Object estimates are generated using L(1)-norm minimization and gradient-projection sparse reconstruction algorithms. The experimental reconstructions show the feasibility of the proposed approach by using 42% fewer measurements than the object dimensionality.

Adaptive feature-specific imaging: a face recognition example.

We present an adaptive feature-specific imaging (AFSI) system and consider its application to a face recognition task. The proposed system makes use of previous measurements to adapt the projection basis at each step. Using sequential hypothesis testing, we compare AFSI with static-FSI (SFSI) and static or adaptive conventional imaging in terms of the number of measurements required to achieve a specified probability of misclassification (Pe). The AFSI system exhibits significant improvement compared to SFSI and conventional imaging at low signal-to-noise ratio (SNR). It is shown that for M=4 hypotheses and desired Pe=10(-2), AFSI requires 100 times fewer measurements than the adaptive conventional imager at SNR= -20 dB. We also show a trade-off, in terms of average detection time, between measurement SNR and adaptation advantage, resulting in an optimal value of integration time (equivalent to SNR) per measurement.

Task-specific information for imaging system analysis.

Imagery is often used to accomplish some computational task. In such cases there are some aspects of the imagery that are relevant to the task and other aspects that are not. In order to quantify the task-specific quality of such imagery, we introduce the concept of task-specific information (TSI). A formal framework for the computation of TSI is described and is applied to three common tasks: target detection, classification, and localization. We demonstrate the utility of TSI as a metric for evaluating the performance of three imaging systems: ideal geometric, diffraction-limited, and projective. The TSI results obtained from the simulation study quantify the degradation in the task-specific performance with optical blur. We also demonstrate that projective imagers can provide higher TSI than conventional imagers at small signal-to-noise ratios.

Feature-specific structured imaging.

We present a feature-specific imaging system based on the use of structured light. Feature measurements are obtained by projecting spatially structured illumination onto an object and collecting all the reflected light onto a single photodetector. Principal component features are used to define the illumination patterns. The optimal linear minimum mean-square error (LMMSE) operator is used to generate object estimates from the measured features. We study the optimal allocation of illumination energy into each feature measurement in the presence of additive white Gaussian detector noise and optical blur. We demonstrate that this new imaging approach reduces imager complexity and provides improved image quality in high noise environments. Compared to the optimal LMMSE postprocessing of a conventional image, feature-specific structured imaging provides a 38% rms error reduction and requires 400 times fewer measurements for a noise standard deviation of sigma = 2 x 10(-3). Experimental results validate these theoretical predictions.