Feature Extraction of Electrocardiogram Signals by Applying Adaptive Threshold and Principal Component Analysis

Rodriguez, Ricardo; Mexicano, Adriana; Bíla, Jiří; Cervantes, Salvador; Ponce, Rafael

doi:10.1016/j.jart.2015.06.008

Cited by 107 publications

(47 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rodríguez et al [15] implemented a QRS detector which includes the processing of bandpass filter, differentiation, Hilbert transform and adaptive thresholding, whereas Li et al [52] employed wavelet transforms for R-peak detection. Although both wavelet and Hilbert transforms are effective techniques for time-frequency analysis and are capable of characterizing the local regularity of signals, both techniques are computationally costly and inefficient for real-time ECG analysis compared with the proposed method.…”

Section: Discussionmentioning

confidence: 99%

“…Wavelet transform (WT) methods have been used in ECG feature extraction along with other enhancements [7][8][9][10]. Other techniques include Geometric Analysis [11], Difference Operation Method [12], Spectral Analysis [13], Cumulative Sums of Squares [14], and Principal Component Analysis [15]. However, the majority of these highly accurate QRS detection algorithms employ complex methods, which require complex time-frequency domain conversion, e.g.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A lightweight QRS detector for single lead ECG signals using a max-min difference algorithm

Pandit

Zhang

Liu

et al. 2017

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

Northumbria University has developed Northumbria Research Link (NRL) to enable users to access the University's research output. Copyright © and moral rights for items on NRL are retained by the individual author(s) and/or other copyright owners. Single copies of full items can be reproduced, displayed or performed, and given to third parties in any format or medium for personal research or study, educational, or not-for-profit purposes without prior permission or charge, provided the authors, title and full bibliographic details are given, as well as a hyperlink and/or URL to the original metadata page. The content must not be changed in any way. Full items must not be sold commercially in any format or medium without formal permission of the copyright holder. The full policy is available online: http://nrl.northumbria.ac.uk/policies.html This document may differ from the final, published version of the research and has been made available online in accordance with publisher policies. To read and/or cite from the published version of the research, please visit the publisher's website (a subscription may be required.) A Lightweight QRS AbstractBackground and Objectives: Detection of the R-peak pertaining to the QRS complex of an ECG signal plays an important role for the diagnosis of a patient's heart condition. To accurately identify the QRS locations from the acquired raw ECG signals, we need to handle a number of challenges, which include noise, baseline wander, varying peak amplitudes, and signal abnormality. This research aims to address these challenges by developing an efficient lightweight algorithm for QRS (i.e., R-peak) detection from raw ECG signals. Methods:A lightweight real-time sliding window-based Max-Min Difference (MMD) algorithm for QRS detection from Lead II ECG signals is proposed. Targeting to achieve the best trade-off between computational efficiency and detection accuracy, the proposed algorithm consists of five key steps for QRS detection, namely, baseline correction, MMD curve generation, dynamic threshold computation, R-peak detection, and error correction. Five annotated databases from Physionet are used for evaluating the proposed algorithm in R-peak detection. Integrated with a feature extraction technique and a neural network classifier, the proposed ORS detection algorithm has also been extended to undertake normal and abnormal heartbeat detection from ECG signals. Results:The proposed algorithm exhibits a high degree of robustness in QRS detection and achieves an average sensitivity of 99.62% and an average positive predictivity of 99.67%. Its performance compares favorably with those from the existing state-of-the-art models reported in the literature. In regards to normal and abnormal heartbeat detection, the proposed QRS detection algorithm in combination with the feature extraction technique and neural network classifier achieves an overall accuracy rate of 93.44% based on an empirical evaluation using the MIT-BIH Arrhythmia data set with 10-fold cross validation. Conclusio...

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

A lightweight QRS detector for single lead ECG signals using a max-min difference algorithm

Pandit

Zhang

Liu

et al. 2017

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

show abstract

“…The detection stage is a pre-processing stage to determine whether to intervene or not. We include three techniques: simple thresholding [15], line length [16] and bandpass with integral function. These specifically address on entities of signal amplitudes, signal change rates and frequency domains.…”

Section: Bmi Processing Toolboxmentioning

confidence: 99%

The Neural Engine: A Reprogrammable Low Power Platform for Closed-Loop Optogenetics

Luo

Firflionis

Turnbull

et al. 2020

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

Brain-machine Interfaces (BMI) hold great potential for treating neurological disorders such as epilepsy. Technological progress is allowing for a shift from open-loop, pacemaker-class, intervention towards fully closed-loop neural control systems. Low power programmable processing systems are therefore required which can operate within the thermal window of 2O C for medical implants and maintain long battery life. In this work, we have developed a low power neural engine with an optimized set of algorithms which can operate under a power cycling domain. We have integrated our system with a custom-designed brain implant chip and demonstrated the operational applicability to the closedloop modulating neural activities in in-vitro and in-vivo brain tissues: the local field potentials can be modulated at required central frequency ranges. Also, both a freely-moving non-human primate (24-hour) and a rodent (1-hour) in-vivo experiments were performed to show system reliable recording performance. The overall system consumes only 2.93mA during operation with a biological recording frequency 50Hz sampling rate (the lifespan is approximately 56 hours). A library of algorithms has been implemented in terms of detection, suppression and optical intervention to allow for exploratory applications in different neurological disorders. Thermal experiments demonstrated that operation creates minimal heating as well as battery performance exceeding 24 hours on a freely moving rodent. Therefore, this technology shows great capabilities for both neuroscience invitro/in-vivo applications and medical implantable processing units.

show abstract

“…Signal filtering is performed using proposed approach and corresponding filtered signals are depicted in figure 5(g)-5 (k). Based on these filtered signals, the performance of proposed approach is measured as presented in The performance of proposed approach is compared with existing techniques such as WT-Sub-band [47], S-Transform [48], BPNN [22], and Butterworth guided filter [49]. First of all, the performance is measured for muscle artifact noise in terms of SNR for varied noise dB as 1.25dB and 5 dB in table 3 and table 4 respectively.…”

Section: Comparative Performancementioning

confidence: 99%

“…For feature extraction also, Wavelet based schemes plays important role [19]. Banerjee and Mitra [20] presented a cross wavelet based scheme for ECG classification, dual tree complex wavelet based feature extraction [21], adaptive threshold & Principal Component Analysis (PCA) [22], Morphological and statistical features [23], non-linear feature extraction such as principal component analysis (PCA) and kernel independent component analysis (KICA) [24]. These features are used for generating the trained model for different types of classifiers.…”

mentioning

confidence: 99%

Linearized Kalman Filter aided Wavelet Transform with Adaptive Thresholding Methodfor ECG signal

2019

IJITEE

View full text Add to dashboard Cite

Cardiovascular diseases (CVD) are the most chronic and dangerous diseases in worldwide. The early prediction of CVD can help to prevent deaths due to these diseases, using bio-medical signal analysis. In this field, the ECG signal plays an important role due to its significant nature of providing the health-related information. However, the signal acquisition process is a crucial step where signals get corrupted due to electrode movement, muscle movement and other types of interference which can degrade the performance of the signal analysis. Several approaches have been introduced but achieving the desired performance robustly is still considered as a challenging task. This paper presents a novel approach for ECG signal filtering by combining a combination of the extended Kalman filter, wavelet transform and an adaptive thresholding approach called as Linearized Kalman Filter aided Wavelet transform with Adaptive Thresholding (LKFWAT). In this process, the initial states of the signal are observed using a Kalman filter, later; a linearization scheme is presented to represent the signal in the linear form. Finally, an adaptive threshold method is applied to reduce the noise during signal construction. It will show the significant improvement in next level process of disease classification. A comparative experimental analysis is carried out which shows that the proposed approach achieves improved performance when compared with the state-of-art ECG denoising techniques.

show abstract

Feature Extraction of Electrocardiogram Signals by Applying Adaptive Threshold and Principal Component Analysis

Cited by 107 publications

References 41 publications

A lightweight QRS detector for single lead ECG signals using a max-min difference algorithm

A lightweight QRS detector for single lead ECG signals using a max-min difference algorithm

The Neural Engine: A Reprogrammable Low Power Platform for Closed-Loop Optogenetics

Linearized Kalman Filter aided Wavelet Transform with Adaptive Thresholding Methodfor ECG signal

Contact Info

Product

Resources

About