Extracting cardiac dynamics within ECG signal for human identification and cardiovascular diseases classification

Deng, Muqing; Wang, Cong; Tang, Min; Zheng, Tongjia

doi:10.1016/j.neunet.2018.01.009

Cited by 63 publications

(23 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Typical examples of features are the RR interval, namely the distance between two consecutive R-peaks, the amplitude and the width of QRS complex, as well as shape descriptors for the local waveforms like P-wave, T-wave, and ST-segment (see Figure 1). Other features can be extracted from the vectorcardiogram [25], computed through a linear transformation of the 12 leads ECG, or in wavelet domain [1] it is more appropriate to specifically refer to domain-adaptation or transductive transfer learning methods [16].…”

Section: Related Workmentioning

confidence: 99%

Online anomaly detection for long-term ECG monitoring using wearable devices

Carrera

Rossi

Fragneto

et al. 2019

Pattern Recognition

View full text Add to dashboard Cite

Many successful algorithms for analyzing ECG signals leverage data-driven models that are learned for each specific user. Unfortunately, a few algorithmic challenges are still to be addressed before employing these models in wearable devices, thus enabling online and long-term monitoring. In particular, since the heartbeats morphology changes with the heart rate, models learned in resting conditions need to be adapted to analyze ECG signals recorded during everyday activities. We propose an online ECG monitoring solution where normal heartbeats of each specific user are modeled by dictionaries yielding sparse representations, and heartbeats that do not conform to this model are detected as anomalous. We track heart rate variations by adapting the user-specific dictionary with a set of user-independent, linear, transformations. Our experiments demonstrate that these transformations can be successfully learned from a public dataset of ECG signals and that, thanks to an optimized anomaly-detection algorithm, our solution enables online and long-term ECG monitoring.

show abstract

Section: Related Workmentioning

confidence: 99%

Online anomaly detection for long-term ECG monitoring using wearable devices

Carrera

Rossi

Fragneto

et al. 2019

Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…Usually, the existing healthcare systems use electronic health records to store this data. Advances in computer and information technologies can deal with this routine data to make critical medical decisions [4].…”

Section: Introductionmentioning

confidence: 99%

“…According to Shafenoor et al [3], a proper evaluation and comparison for testing different data mining techniques can improve the accuracy of predicting cardiovascular disease. Also, Deng et al [4] have explored a dynamical ECG recognition framework for human identification and cardiovascular diseases classification based on radial basis function (RBF). Besides, Bouali and Akaichi [6] have used many machine learning techniques, such as: Baysian Network, Decision tree, Artificial Neural Network, Fuzzy pattern tree and Support Vector Machine (SVM), to classify the Cleavland heart disease dataset using 10-fold-cross validation.…”

Section: Introductionmentioning

confidence: 99%

Neighborhood Component Analysis and Support Vector Machines for Heart Disease Prediction

Djerioui¹,

Brik²,

Ladjal³

et al. 2019

ISI

View full text Add to dashboard Cite

Nowadays, one of the main reasons for disability and mortality premature in the world is the heart disease, which make its prediction is a critical challenge in the area of healthcare systems. In this paper, we propose a heart disease prediction system based on Neighborhood Component Analysis (NCA) and Support Vector Machine (SVM). In fact, NCA is used for selecting the most relevant parameters to make a good decision. This can seriously reduce the time, materials, and labor to get the final decision while increasing the prediction performance. Besides, the binary SVM is used for predicting the selected parameters in order to identify the presence/absence of heart disease. The conducted experiments on real heart disease dataset show that the proposed system achieved 85.43% of prediction accuracy. This performance is 1.99% higher than the accuracy obtained with the whole parameters. Also, the proposed system outperforms the state-of-the-art heart disease prediction.

show abstract

“…For example, the ECG signal is especially useful for diagnosing cardiac, pulmonary, and cardiovascular diseases [18][19][20], while the EMG signal is for neurological and neuromuscular problems [21,22]. Additionally, all the mentioned signals are used in human-machine interfaces for the control of different types of devices [23][24][25][26].…”

Section: Introductionmentioning

confidence: 99%

Implementation of a Cost-Effective Didactic Prototype for the Acquisition of Biomedical Signals

2018

View full text Add to dashboard Cite

This paper presents the implementation of a cost-effective didactic prototype, which was designed as a tool for theoretical and practical learning in the biomedical instrumentation area for engineering students. The prototype provides integrated hardware and software components that allow online acquisition, processing, and visualization of electrocardiographic (ECG), electroencephalographic (EEG), electromyographic (EMG), and electrooculographic (EOG) signals, as well as measurements of bio-impedance from the skin. A control system using an Arduino Uno board and the PIC16F877A and PIC18F2550 microcontrollers was implemented. This control system allows selecting the type of module; the lead to be used in the ECG module; the input channel for the EEG, EMG, and EOG modules; and controlling the signal generator for the bioimpedance module. In addition, a graphical interface was developed in LabVIEW, in which all the acquired biomedical signals can be visualized in real time. It is highlighted as a novelty the modular implementation of the prototype, the incorporation of five modules in a single device and the graphical user-friendly interface. The final result is a low-cost device capable of processing and visualizing bioelectric signals through an interface in LabVIEW, which also allows the user to interact with each of the stages.

show abstract

Extracting cardiac dynamics within ECG signal for human identification and cardiovascular diseases classification

Cited by 63 publications

References 48 publications

Online anomaly detection for long-term ECG monitoring using wearable devices

Online anomaly detection for long-term ECG monitoring using wearable devices

Neighborhood Component Analysis and Support Vector Machines for Heart Disease Prediction

Implementation of a Cost-Effective Didactic Prototype for the Acquisition of Biomedical Signals

Contact Info

Product

Resources

About