ECG Heartbeat Classification Using CNN

Chourasia, Mayank; Thakur, Anurag; Gupta, Shresth; Singh, Anurag

doi:10.1109/upcon50219.2020.9376451

Cited by 10 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, we have outperformed [19], by a value of 5% where authors have used ANN architecture. This gain is explained by the whole role that plays our proposed CNN architecture, which is deep, and robust for real time signal classification.…”

Section: Comparison With the State Of The Artmentioning

confidence: 86%

“…Pynq proves to be the best devices in terms of accuracy, time processing and power. Chourasia et al [19] in 2020 have proposed a 1D CNN architecture for ECG classification into five classes; the achieved accuracy has reached 97.36% that is a promising result, thus the importance of using a CNN architecture. Yıldırım et al [20] in 2018 have proposed a deep CNN architecture, for fast ECG signals classification, with less complexity achieving 92% of accuracy.…”

Section: State Of the Artmentioning

confidence: 98%

See 1 more Smart Citation

FPGA Implementation of a CNN Application for ECG Class Detection

Fradi,

Lazhar,

Zahzah

et al. 2024

View full text Add to dashboard Cite

Convolutional Neural Networks (CNN) show huge necessity in medical area diagnosis, CNN can be used for ECG features extraction, heartbeats classification and abnormal beats detection, helping clinicians to get the true diagnosis of cardiovascular diseases at early stage. In this context, an optimized CNN is proposed to be implemented on Pynq-Z2 board for Electrocardiography (ECG) signal class detection. As first step, a CNN has been implemented on the processor ARM Cortex A9 of Pynq Z2. Implementation results show the efficiency of our purpose, achieving accuracies results of 98.86%, 98.61% and 98.39% for the training, validation and test process respectively. Then to improve the inference results a Hardware/Software Codesign has been proposed due to the parallel architecture of FPGA, time process acceleration has reached 10 times compared to the implementation on the Processor. Moreover, a gain of the surface has been achieved by using low number of resources. Thus, a real time application has been reached with a very excellent class accuracy detection going to 99.45% for the training, 99.12% for the validation and 99.03% for the testing processes, when tested on MIT-BIH ECG signals in a short time process with 0.0018s/signal through the test process and 0.005s/ signal during the training.

show abstract

Section: Comparison With the State Of The Artmentioning

confidence: 86%

Section: State Of the Artmentioning

confidence: 98%

FPGA Implementation of a CNN Application for ECG Class Detection

Fradi,

Lazhar,

Zahzah

et al. 2024

View full text Add to dashboard Cite

show abstract

“…ECG Classification with a Convolutional Recurrent Neural Network by V. Sankari [20] In order to extract ECG characteristics, M. Chourasia, A. Thakur, S. Gupta and A. Singh [21] suggested using a 21-layer 1D convolutional recurrent neural network. He also suggested expanding the convolution filter to enhance local awareness and using residual connection, normalisation, and other techniques to increase the efficiency of the algorithm.…”

Section: Related Workmentioning

confidence: 99%

Robust and Efficient ECG Classification with Privacy Preservation using LSTM+CNN and Adaptive Least Signal Bit

Sakr,

Ahmed,

Rezk

2023

IJCI. International Journal of Computers and Information

View full text Add to dashboard Cite

Maintaining patient data privacy is a critical concern in the medical domain. However, safeguarding crucial information during data transmission presents significant challenges for healthcare professionals and organizations. Additionally, the accurate classification of electrocardiogram (ECG) signals is hindered by the need for supplementary information to ensure precise examinations and accurate diagnoses. This paper introduces a novel hybrid framework that addresses both ECG classification challenges and privacy preservation. The proposed framework consists of two main phases. In the first phase, a combination of Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) with an attention gate is employed for ECG classification. This phase enhances the accuracy of ECG signal classification by incorporating deep learning techniques. The second phase of the framework utilizes adaptive least signal bit with neutrosophic logic to conceal critical medical data during transmission. Neutrosophic sets, which represent data as degrees of truth, falsehood, and indeterminacy, are leveraged and passed through an embedding layer. In the sender part, important data is converted into three degrees and embedded within the ECG signal using true and false degrees. An intermediate set acts as a shared dynamic key between the sender and receiver. The receiver can reconstruct the important data using either the shared dynamic key or the intermediate set. The experiments done prove the efficiency of different parts of the framework; the augmentation model archives 14.67 and 37.89 for the inception score and freshet inception distance, respectively. The hybrid approach also achieves 99.01 and 99.12 for dice score and accuracy, respectively.

show abstract

“…The respiratory effort classifier (lower half of Fig. 4) is a CNN based on architectures that have proven successful for the analysis of 1-dimensional physiological signals such as ECG [18][19][20]. Similar to its acoustic counterpart, it takes as input the raw effort signal for a 30-s segment, and outputs the probability of the segment containing apneahypopnea events.…”

Section: Late Decision Fusionmentioning

confidence: 99%

Obstructive sleep apnea screening with breathing sounds and respiratory effort: a multimodal deep learning approach

Romero¹,

Brown²,

Johnson³

2023

Interspeech 2023

View full text Add to dashboard Cite

Obstructive sleep apnea (OSA) is a chronic and prevalent condition with well-established comorbidities. Due to limited diagnostic resources and high cost, a significant OSA population lives undiagnosed, and accurate and low-cost methods to screen for OSA are needed. We propose a novel screening method based on breathing sounds recorded with a smartphone and respiratory effort. Whole night recordings are divided into 30-s segments, each of which is classified for the presence or absence of OSA events by a multimodal deep neural network. Data fusion techniques were investigated and evaluated based on the apnea-hypopnea index estimated from whole night recordings. Real-world recordings made during home sleep apnea testing from 103 participants were used to develop and evaluate the proposed system. The late fusion system achieved the best sensitivity and specificity when screening for severe OSA, at 0.93 and 0.92, respectively. This offers the prospect of inexpensive OSA screening at home.

show abstract

ECG Heartbeat Classification Using CNN

Cited by 10 publications

References 13 publications

FPGA Implementation of a CNN Application for ECG Class Detection

FPGA Implementation of a CNN Application for ECG Class Detection

Robust and Efficient ECG Classification with Privacy Preservation using LSTM+CNN and Adaptive Least Signal Bit

Obstructive sleep apnea screening with breathing sounds and respiratory effort: a multimodal deep learning approach

Contact Info

Product

Resources

About