A Novel Cardiac Arrhythmias Detection Approach for Real-Time Ambulatory ECG Diagnosis

Zhou, Haiying; Zhu, Xiancheng; Wang, Sishan; Zhou, Kui; Ma, Zheng; Li, Jian; Hou, Kun Mean; Vaulx, Christophe de

doi:10.1142/s0218001417580046

Cited by 4 publications

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The characteristic extraction technique used during the realization of the present contribution consisted in both the morphological characterization of the different cardiac pathologies that are to be classified, as well as in the use of mathematical transformations (wavelet transform [10][11][12]).…”

Section: Characterization and Feature Extractionmentioning

confidence: 99%

Wearable Intelligent System for the Diagnosis of Cardiac Diseases Working in Real Time and with Low Energy Cost

et al. 2018

View full text Add to dashboard Cite

Heart disease is currently one of the leading causes of death in developed countries. The electrocardiogram is an important source of information for identifying these conditions, therefore, becomes necessary to seek an advanced system of diagnosis based on these signals. In this paper we used samples of electrocardiograms of MIT-related database with ten types of pathologies and a rate corresponding to normal (healthy patient), which are processed and used for extraction from its two branches of a wide range of features. Next, various techniques have been applied to feature selection based on genetic algorithms, principal component analysis and mutual information. To carry out the task of intelligent classification, 3 different scenarios have been considered. These techniques allow us to achieve greater efficiency in the classification methods used, namely support vector machines (SVM) and decision trees (DT) to perform a comparative analysis between them. Finally, during the development of this contribution, the use of very non-invasive devices (2 channel ECG) was analyzed, we could practically classify them as wearable, which would not need interaction by the user, and whose energy consumption is very small to extend the average life of the user been on it.

show abstract

Section: Characterization and Feature Extractionmentioning

confidence: 99%

Wearable Intelligent System for the Diagnosis of Cardiac Diseases Working in Real Time and with Low Energy Cost

et al. 2018

View full text Add to dashboard Cite

show abstract

“…The other feature extraction technique widely used for the task is wavelet [12]- [16] since it is believed to be the best feature extraction method for arrhythmia detection [9]. For the classifier, the conventional techniques employed for the task is Linear Discriminant (LD) [17], Fuzzy Logic [18]- [20], Decision Tree-based methods [21]- [23], Support Vector Machine (SVM) [16], [24], [25], and Artificial Neural Network (ANN) [10], [11], [15]. The feature extraction is often not needed by a more modern algorithm such as reservoir computing [26] and deep learning-based technique [27]- [30].…”

Section: Introductionmentioning

confidence: 99%

Re-implementation of Convolutional Neural Network for Arrhythmia Detection

Rizqyawan¹,

Siradj²,

Amri³

et al. 2022

International Journal on Advanced Science, Engineering and Information Technology

View full text Add to dashboard Cite

Arrhythmia is an irregular heartbeat that may cause serious problems such as cardiac arrest and heart failure if left untreated. A dozen of studies have been conducted to make an automated arrhythmia detector. The classification approach uses a simple rule-based model, traditional machine learning, to a modern deep-learning technique. However, comparing an arrhythmia classifier performance is not an easy task. There are several different datasets, classification standards, data splitting schemes, and metrics. To assess the real performance of the developed models, it is important to train and evaluate the model in a standardized method such as the result score can become standard too. In this study, a set of CNN models from Acharya were re-implemented by retraining and re-evaluating it in a more standardized method. The model uses a raw ECG waveform with 260 samples around the QRS peaks and classifies it into five arrhythmia classes. The experiment was conducted using three configurations, using both intra-patient and inter-patient schemes. The experimental results show good performance for the intra-patient scheme but not for the inter-patient. There is a reduction of sensitivity and precision in the intra-patient scheme using a standardized method in this study compared to the original paper. This result indicates biased results caused by the oversampled test data in the original paper. In addition to the intrapatient result, the inter-patient result is also provided for a standardized comparison to other works in the future.

show abstract

An energy-efficient and accuracy-aware edge computing framework for heart arrhythmia detection: A joint model selection and task offloading approach

2022

View full text Add to dashboard Cite

A Novel Cardiac Arrhythmias Detection Approach for Real-Time Ambulatory ECG Diagnosis

Abstract: Int. J. Patt. Recogn. Artif. Intell. Downloaded from www.worldscientific.com by MONASH UNIVERSITY on 04/22/17. For personal use only.algorithm has 92.8% sensitivity and 97.5% speci¯city in average, so that it is suitable for realtime cardiac arrhythmias monitoring.

Cited by 4 publications

References 26 publications

Wearable Intelligent System for the Diagnosis of Cardiac Diseases Working in Real Time and with Low Energy Cost

Wearable Intelligent System for the Diagnosis of Cardiac Diseases Working in Real Time and with Low Energy Cost

Re-implementation of Convolutional Neural Network for Arrhythmia Detection

An energy-efficient and accuracy-aware edge computing framework for heart arrhythmia detection: A joint model selection and task offloading approach

Contact Info

Product

Resources

About