Cardiac Arrhythmia Diagnosis based on Features Extraction and Convolutional Neural Network from ECG Signals

Mohonta, Shadhon Chandra; Ali, Mohamad Wijayanuddin

doi:10.1109/iceeict53905.2021.9667807

Cited by 2 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is apparent from Figure 7 and Figure 8 that the accuracy, and loss are 99.39%, and 0.015 respectively. Besides, the accuracy of the proposed CNN model is better than using a pretrained AlexNet model (Mohonta & Ali, 2021). Besides, the statistical indices such as sensitivity (Se), specificity (Sp), and accuracy (Acc) of this classification are portrayed in Table 2.…”

Section: Resultsmentioning

confidence: 99%

Full Issue (Vol. 10, December 2022)

Team¹

2022

MIJST

View full text Add to dashboard Cite

The use of ultra-wideband (UWB) in target detection, radar and wireless connectivity, specifically in the medical world, has attracted a lot of attention. The concept that the IR-UWB system does not necessarily require carrier signals is one of its most appealing features. IR-UWB can transmit information using short Gaussian monocycle pulses. In light of these advantages, this paper proposes a novel UWB transmitter system which consists of UWB signal generating circuits and UWB antenna, which work together to create entire UWB transmitter. It is based on impulses and has a simple architecture with low power consumption. The proposed transmitter is realized in Cadence tools with 90nm CMOS technology and proposed UWB antenna is simulated using Advanced Design System (ADS) simulator software. In addition, the transmitter circuit and the antenna are co-simulated using ADS software. The illustrated UWB transmitter uses a low-power supply and generates pulse amplitude with pulse duration of for the Gaussian monocycle pulse. Due to its increased output voltage swing and reduced power consumption when comparing to other circuits, the proposed architecture is functional and suitable for use in short-range wireless networks and medical applications.

show abstract

Section: Resultsmentioning

confidence: 99%

Full Issue (Vol. 10, December 2022)

Team¹

2022

MIJST

View full text Add to dashboard Cite

show abstract

Section: Resultsmentioning

confidence: 99%

A Novel Approach to Detect Cardiac Arrhythmia Based on Continuous Wavelet Transform and Convolutional Neural Network

Mohonta¹,

Ali²

2022

MIJST

View full text Add to dashboard Cite

Electrocardiogram (ECG) signal is informative as well as non-invasive clinical tool to diagnose cardiac diseases of human heart. However, the diagnosis requires professionals’ clarification and is also time-consuming. To make the diagnosis proficient, a novel convolutional neural network (CNN) has been proposed for automatic arrhythmia detection. In this work, the ECG data collected from the MIT-BIH database have been preprocessed, and segmented in short ECG segments of 60 s. Then, all these segments have been transformed into scalogram images obtained from time-frequency analysis using continuous wavelet transform (CWT). Finally, these scalogram images have been exploited as an input for our designed CNN classifier to classify cardiac arrhythmia. In this approach, the overall accuracy, sensitivity, and specificity are 99.39%, 98.79%, and 100% respectively. Proposed CNN model has significant advantages, and it can be used to differentiate the healthy and arrhythmic patients effectively.

show abstract

Cardiac Arrhythmia Diagnosis based on Features Extraction and Convolutional Neural Network from ECG Signals

Cited by 2 publications

References 15 publications

Full Issue (Vol. 10, December 2022)

Full Issue (Vol. 10, December 2022)

A Novel Approach to Detect Cardiac Arrhythmia Based on Continuous Wavelet Transform and Convolutional Neural Network

Contact Info

Product

Resources

About