Robust QRS detection for HRV estimation from compressively sensed ECG measurements for remote health-monitoring systems

OBJECTIVE

To present a new compressive sensing (CS)-based method for the acquisition of ECG signals and for robust estimation of heart-rate variability (HRV) parameters from compressively sensed measurements with high compression ratio.

APPROACH

CS is used in the biosensor to compress the ECG signal. Estimation of the locations of QRS segments is carried out by applying two algorithms on the compressed measurements. The first algorithm reconstructs the ECG signal by enforcing a block-sparse structure on the first-order difference of the signal, so the transient QRS segments are significantly emphasized on the first-order difference of the signal. Multiple block-divisions of the signals are carried out with various block lengths, and multiple reconstructed signals are combined to enhance the robustness of the localization of the QRS segments. The second algorithm removes errors in the locations of QRS segments by applying low-pass filtering and morphological operations.

MAIN RESULTS

The proposed CS-based method is found to be effective for the reconstruction of ECG signals by enforcing transient QRS structures on the first-order difference of the signal. It is demonstrated to be robust not only to high compression ratio but also to various artefacts present in ECG signals acquired by using on-body wireless sensors. HRV parameters computed by using the QRS locations estimated from the signals reconstructed with a compression ratio as high as 90% are comparable with that computed by using QRS locations estimated by using the Pan-Tompkins algorithm.

SIGNIFICANCE

The proposed method is useful for the realization of long-term HRV monitoring systems by using CS-based low-power wireless on-body biosensors.

An Advanced Hybrid Technique of DCS and JSRC for Telemonitoring of Multi-Sensor Gait Pattern

The jointly quantitative analysis of multi-sensor gait data for the best gait-classification performance has been a challenging endeavor in wireless body area networks (WBANs)-based gait telemonitoring applications. In this study, based on the joint sparsity of data, we proposed an advanced hybrid technique of distributed compressed sensing (DCS) and joint sparse representation classification (JSRC) for multi-sensor gait classification. Firstly, the DCS technique is utilized to simultaneously compress multi-sensor gait data for capturing spatio-temporal correlation information about gait while the energy efficiency of the sensors is available. Then, the jointly compressed gait data are directly used to develop a novel neighboring sample-based JSRC model by defining the sparse representation coefficients-inducing criterion (SRCC), in order to yield the best classification performance as well as a lower computational time cost. The multi-sensor gait data were selected from an open wearable action recognition database (WARD) to validate the feasibility of our proposed method. The results showed that when the comparison ratio and the number of neighboring samples are selected as 70% and 40%, respectively, the best accuracy (95%) can be reached while the lowest computational time spends only 60 ms. Moreover, the best accuracy and the computational time can increase by 5% and decrease by 40 ms, respectively, when compared with the traditional JSRC techniques. Our proposed hybrid technique can take advantage of the joint sparsity of data for jointly processing multi-sensor gait data, which greatly contributes to the best gait-classification performance. This has great potential for energy-efficient telemonitoring of multi-sensor gait.

Performance of compressive sensing for the reconstruction of different QRS pulses in ECG signals

Compressive sensing (CS) is studied for the acquisition of different QRS complexes in ECG signals. By applying sparse binary measurement matrix and by applying regularization for promoting temporal correlation, performance of CS techniques for the reconstruction of ECG segments containing different QRS complexes, such as, normal QRS, paced QRS, right bundle branch block beat, left bundle branch block beat, and ventricular flutter beat, has been studied. Simulation results demonstrate that performance of CS differs with the types of beats, and ECG segments with well-known beats can be reconstructed with signal-to-noise ratio (SNR) approximately equal to 25dB for the realization of CS systems with compression ratio as high as 95%; for lower compression ratio much higher SNR can be attained.

An advanced scheme of compressed sensing of acceleration data for telemonintoring of human gait

Background

The compressed sensing (CS) of acceleration data has been drawing increasing attention in gait telemonitoring application. In such application, there still exist some challenging issues including high energy consumption of body-worn device for acceleration data acquisition and the poor reconstruction performance due to nonsparsity of acceleration data. Thus, the novel scheme of compressive sensing of acceleration data is needed urgently for solutions that are found to these issues.

Methods

In our scheme, the sparse binary matrix is firstly designed as an optimal measurement matrix only containing a smallest number of nonzero entries. And then the block sparse Bayesian learning (BSBL) algorithm is introduced to reconstruct acceleration data with high fidelity by exploiting block sparsity. Finally, some commonly used gait classification models such as multilayer perceptron (MLP), support vector machine (SVM) and KStar are applied to further validate the feasibility of our scheme for gait telemonitoring application.

Results

The acceleration data were selected from open Human Activity Dataset of Southern California University (USC-HAD). The optimal sparse binary matrix (a smallest number of nonzero entries is 8) is as strong as the full optimal measurement matrix such as Gaussian random matrix. Moreover, BSBL algorithm significantly outperforms existing conventional CS reconstruction algorithms, and reaches the maximal signal-to-noise ratio value (70 dB). In comparison, MLP is best for gait classification, and it can classify upstairs and downstairs patterns with best accuracy of 95 % and seven gait patterns with maximal accuracy of 92 %, respectively.

Conclusions

These results show that sparse binary matrix and BSBL algorithm are feasibly applied in compressive sensing of acceleration data to achieve the perfect compression and reconstruction performance, which has a great potential for gait telemonitoring application.