Arrhythmia Diagnosis by Using Level-Crossing ECG Sampling and Sub-Bands Features Extraction for Mobile Healthcare

Abstract

Mobile healthcare is an emerging technique for clinical applications. It is usually based on cloud-connected biomedical implants. In this context, a novel solution is presented for the detection of arrhythmia by using electrocardiogram (ECG) signals. The aim is to achieve an effective solution by using real-time compression, efficient signal processing, and data transmission. The system utilizes level-crossing-based ECG signal sampling, adaptive-rate denoising, and wavelet-based sub-band decomposition. Statistical features are extracted from the sub-bands and used for automated arrhythmia classification. The performance of the system was studied by using five classes of arrhythmia, obtained from the MIT-BIH dataset. Experimental results showed a three-fold decrease in the number of collected samples compared to conventional counterparts. This resulted in a significant reduction of the computational cost of the post denoising, features extraction, and classification. Moreover, a seven-fold reduction was achieved in the amount of data that needed to be transmitted to the cloud. This resulted in a notable reduction in the transmitter power consumption, bandwidth usage, and cloud application processing load. Finally, the performance of the system was also assessed in terms of the arrhythmia classification, achieving an accuracy of 97%.

Baseline wander and power‐line interference elimination of ECG signals using efficient signal‐piloted filtering

“…It promises a similar factor of gain in terms of transmission and post-analysis module activities [ 10 , 12 ]. The idea of embedding the signal-piloted acquisition and processing in the automatic cardiovascular diagnostic is quite novel [ 9 , 12 , 17 ]. The above results assure that a wise integration of this approach can also introduce a significant processing efficiency in other ECG denoising tactics such as the EVD [ 4 ], and the EKF-EMD-WT [ 6 , 16 ].…”

Multirate Processing with Selective Subbands and Machine Learning for Efficient Arrhythmia Classification

“…The ECG signal may be changed by interference and physiological artifacts, which reduces the efficacy of the automatic diagnostic. Several signal processing techniques have been used to address these limitations, such as wavelet transform [ 7 ], adaptive-rate filtering [ 8 ], eigenvalue decomposition [ 9 ], extended Kalman filtering [ 10 ] and Fourier decomposition [ 11 ]. To identify attributes that can help in automated diagnosis, the denoised ECG signals are analysed.…”

“…Therefore, automated ECG signal processing and analysis approaches have been proposed [ 6 , 7 , 12 , 14 , 15 , 16 , 17 , 22 , 23 , 24 , 25 ]. In the event of a poorly tolerated rhythm disorder, the type of arrhythmia should be diagnosed quickly in order to start treatment as quickly as possible [ 6 , 7 , 12 , 14 ]. Depending on the type of arrhythmia, several medications may be prescribed.…”

“…Onward, rotation forest (RoF) is used to recognise arrhythmia based on these extracted features. In [ 7 ] Qaisar et al used wavelet decomposition-based subbands statistical features extraction approach with random forest (RF) for arrhythmia classification. In [ 12 ] Jha et al Used TQWT for features extraction and support vector machine (SVM) for the arrhythmia classification.…”

“…The realization of cloud-connected wireless ECG wearables is constrained due to strict limits on the volume, weight and power consumption. Hence methods with signal compression [ 20 , 21 , 26 ] irregular sampling [ 6 , 27 ] and adaptive rate processing [ 6 , 7 , 8 ] have been conducted in this area. The low computational complexity approaches are required for efficient wearable ECG gadgets and cloud-based mobile healthcare solutions.…”