A Transfer-Learning Based Ensemble Architecture for ECG Signal Classification

Ovi, Tareque Bashar; Naba, Sauda Suara; Chanda, Dibaloke; Onim, Md. Saif Hassan

doi:10.1109/tensymp54529.2022.9864449

Cited by 1 publication

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed ensemble for human identification was tested on publicly available datasets such as PTB and CYBHI, demonstrating its effectiveness with an identification accuracy of 99.66% achieved on both healthy and unhealthy subjects. In [ 9 ], two modified VGG-16 approaches and one InceptionResNetV2 design with an additional feature extraction layer and ImageNet weights were proposed. After 5-fold cross-validation with the MIT-BIH normal sinus rhythm database and BIDMC datasets, the model achieved 99.98% accuracy.…”

Section: Related Workmentioning

confidence: 99%

“…An ensemble method of pretrained models was then trained for ECG signal classification using the ECG signal. The backbone consisted of two different VGG-16 [ 8 ] models and an Inception-ResNetV2 model with feature extracting layers and ImageNet weights [ 9 ]. The preprocessing of input ECG signals was accomplished using image processing techniques.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid Deep Learning and Discrete Wavelet Transform-Based ECG Biometric Recognition for Arrhythmic Patients and Healthy Controls

Asif

Faisal

Dar

et al. 2023

Sensors

View full text Add to dashboard Cite

The intrinsic and liveness detection behavior of electrocardiogram (ECG) signals has made it an emerging biometric modality for the researcher with several applications including forensic, surveillance and security. The main challenge is the low recognition performance with datasets of large populations, including healthy and heart-disease patients, with a short interval of an ECG signal. This research proposes a novel method with the feature-level fusion of the discrete wavelet transform and a one-dimensional convolutional recurrent neural network (1D-CRNN). ECG signals were preprocessed by removing high-frequency powerline interference, followed by a low-pass filter with a cutoff frequency of 1.5 Hz for physiological noises and by baseline drift removal. The preprocessed signal is segmented with PQRST peaks, while the segmented signals are passed through Coiflets’ 5 Discrete Wavelet Transform for conventional feature extraction. The 1D-CRNN with two long short-term memory (LSTM) layers followed by three 1D convolutional layers was applied for deep learning-based feature extraction. These combinations of features result in biometric recognition accuracies of 80.64%, 98.81% and 99.62% for the ECG-ID, MIT-BIH and NSR-DB datasets, respectively. At the same time, 98.24% is achieved when combining all of these datasets. This research also compares conventional feature extraction, deep learning-based feature extraction and a combination of these for performance enhancement, compared to transfer learning approaches such as VGG-19, ResNet-152 and Inception-v3 with a small segment of ECG data.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%