Ramesh Kumar Sunkaria

The detection and analysis of the elusive U-wave in an electrocardiogram (ECG) presents a captivating yet intricate research problem. Despite its correlation with early prognosis of cardiac disorders, the origin of the U-wave peak remains enigma. Advances in the detection and characterization of the U-wave hold tremendous potential for improving our understanding of heart disease and advancing its diagnosis and treatment. This challenge represents a significant opportunity for further research in the field of detecting cardiac dysfunctioning. In this study, a new approach for automatically identifying the U-wave peak in the TP-segment, TU-segment, and RR-interval using ensemble machine-learning technique has been developed. The method consists of three stages: pre-processing and segmentation, feature extraction, and classification. The ensemble machine learning algorithm and novel feature extraction techniques are utilized to achieve accurate results. The results are evaluated using a publicly available QT database with annotation of the waveform to produce highly accurate classifiers. The achieved average precision, recall, F1 score, and accuracy using an ensemble machine learning algorithm for detection of U-wave classes are 98.23%, 98.30%, 98.50%, and 98.40% respectively. The experimental result demonstrates that an ensemble machinelearning algorithm outperforms as compared to the other state-of-the-art techniques.

Objective. The T-wave in electrocardiogram (ECG) signal has the potential to enumerate various cardiac dysfunctions in the cardiovascular system. The primary objective of this research is to develop an efficient method for detecting T-waves in ECG signals, with potential applications in clinical diagnosis and continuous patient monitoring. Approach. In this work, we propose a novel algorithm for T-wave peak detection, which relies on a non-decimated stationary wavelet transform method (NSWT) and involves the cancellation of the QRS complex by utilizing its local extrema. The proposed scheme contains three stages: firstly, the technique is pre-processed using a two-stage median filter and Savitzky–Golay (SG) filter to remove the various artifacts from the ECG signal. Secondly, the NSWT technique is implemented using the bior 4.4 mother wavelet without downsampling, employing 2⁴ scale analysis, and involves the cancellation of QRS-complex using its local positions. After that, Sauvola technique is used to estimate the baseline and remove the P-wave peaks to enhance T-peaks for accurate detection in the ECG signal. Additionally, the moving average window and adaptive thresholding are employed to enhance and identify the location of the T-wave peaks. Thirdly, false positive T-peaks are corrected using the kurtosis coefficients method. Main results. The robustness and efficiency of the proposed technique have been corroborated by the QT database (QTDB). The results are also validated on a self-recorded database. In QTDB database, the sensitivity of 98.20%, positive predictivity of 99.82%, accuracy of 98.04%, and detection error rate of 1.95% have been achieved. The self-recorded dataset attains a sensitivity, positive predictivity, accuracy, and detection error rate of 99.94%, 99.96%, 99.90%, and 0.09% respectively. Significance. A T-wave peak detection based on NSWT and QRS complex cancellation, along with kurtosis analysis technique, demonstrates superior performance and enhanced detection accuracy compared to state-of-the-art techniques.

Automated classification of cardiac rhythms from electrocardiogram (ECG) signals is significant for diagnosis of cardiovascular dysfunctioning. A biggest challenge in automated ECG classification is to address the task's specific characteristics, such as time dependencies between observations and a strong class imbalance. To address these issues, this work proposes machine learning ensemble techniques (Random Forest, Support Vector Machine, Xgboost, Adaboost and Stacked Ensemble Classifier) and an ensemble of convolutional neural network (CNN) and bi-directional long short-term memory (Bi-LSTM) architecture for classification of cardiac arrhythmias in ECG signals. The proposed model has been trained and tested on the MIT-BIH arrhythmias database which contains total 109443 ECG beats with 90589 normal beats (NB), 8039 supraventricular beats (SB), 7236 ventricular beats (VB), 2776 fusion beats (FB) and 803 unknown beats (QB) respectively. Here, in this study, we incorporate synthetic minority oversampling technique (SMOTE) for balancing dataset along with time-series feature extraction library (TSFEL) for extracting feature and an ensemble of CNN-LSTM to predict fast features of upcoming ECG signals to enhance the performance of heartbeat classification as compare to the state-of-the-art techniques. The achieved average accuracy (Acc), sensitivity (SE), precision (PE) and F1 score using stacked ensemble machine learning algorithm for detection arrhythmias heartbeat classes are 98.67%, 96%, 97.80% and 96.80% respectively. With ensemble CNN-BiLSTM method, the average accuracy of 99.88% has been achieved. The SE and PE values for SB and VB beats are 84.40%, 99.79%, 96.40% and 98.54% respectively. Experimental results demonstrate that an ensemble CNN-BiLSTM technique outperforms as compare to existing classification techniques in terms sensitivity, accuracy and precision.

Background. In telecardiology, the bio-signal acquisition processing and communication for clinical purposes occupies larger storage and significant bandwidth over a communication channel. Electrocardiograph (ECG) compression with effective reproductivity is highly desired. In the present work, a compression technique for ECG signals with less distortion by using a non-decimated stationary wavelet with a run-length encoding scheme has been proposed. Method. In the present work non-decimated stationary wavelet transform (NSWT) method has been developed to compress the ECG signals. The signal is subdivided into N levels with different thresholding values. The wavelet coefficients having values larger than the threshold are evaluated and the remaining are suppressed. In the presented technique, the biorthogonal (bior) wavelet is employed as it improves the compression ratio as well percentage root means square ratio (PRD) when compared to the existing method and exhibits improved results. After pre-processing, the coefficients are subjected to the Savitzky-Golay filter to remove corrupted signals. The wavelet coefficients are then quantized using dead-zone quantization, which eliminates values that are close to zero. To encode these values, a run-length encoding (RLE) scheme is applied, resulting in compressed ECG signals. Results. The presented methodology has been evaluated on the MITDB arrhythmias database which contains 4800 ECG fragments from forty-eight clinical records. The proposed technique has achieved an average compression ratio of 33.12, PRD of 1.99, NPRD of 2.53, and QS of 16.57, making it a promising approach for various applications. Conclusion. The proposed technique exhibits a high compression ratio and reduces distortion compared to the existing method.