The Investigation of Heart Rate Variability for Paroxysmal Atrial Fibrillation Detection DOI

Md. Shahin Kadir Sakib,

Md Mayenul Islam, Mohammod Abdul Motin

et al.

Published: Dec. 13, 2023

Paroxysmal atrial fibrillation ( PAF) i s t he initial phase of AF), often progressing stealthily to the chronic stage due absence noticeable symptoms. Hence, timely identification PAF is pretty necessary. This study proposes an automated machine learning-based detection algorithm utilizing a single-lead electrocardiogram signal. A total 25 features are extracted from 1-minute segments and optimal feature set, selected by deploying minimum redundancy maximum relevance algorithm, used train decision tree (DT) random forest (RF) classifiers. The training testing stages included 43 subjects, subjectwise 10-fold cross-validation was performed. RF outperforms DT classifier chieving 91.94% accuracy, 91.75% sensitivity, 91.47% F1 score. higher accuracy using shorter ECG remarks significance proposed model for AF monitoring.

Language: Английский

ECG Quality Detection and Noise Classification for Wearable Cardiac Health Monitoring Devices DOI
Achinta Mondal, M. Sabarimalai Manikandan, Ram Bilas Pachori

et al.

2022 14th International Conference on Electronics, Computers and Artificial Intelligence (ECAI), Journal Year: 2024, Volume and Issue: unknown, P. 1 - 6

Published: June 27, 2024

Language: Английский

Citations

2
An Improved Approach for Atrial Fibrillation Detection in Long-Term ECG Using Decomposition Transforms and Least-Squares Support Vector Machine DOI Creative Commons
Tomasz Pander

Applied Sciences, Journal Year: 2023, Volume and Issue: 13(22), P. 12187 - 12187

Published: Nov. 9, 2023

Atrial fibrillation is a common heart rhythm disorder that now becoming significant healthcare challenge as it affects more and people in developed countries. This paper proposes novel approach for detecting this disease. For purpose, we examined the ECG signal by QRS complexes then selecting 30 successive R-peaks analyzing atrial activity segment with variety of indices, including entropy change, variance wavelet transform distribution energy bands determined dual-Q tunable Q-factor coefficients Hilbert ensemble empirical mode decomposition. These transformations provided vector 21 features characterized relevant part electrocardiography signal. The MIT-BIH Fibrillation Database was used to evaluate proposed method. Then, using K-fold cross-validation method, sets were fed into LS-SVM SVM classifiers trilayered neural network classifier. Training test subsets set up avoid sampling from single participant maintain balance between classes. In addition, individual classification quality scores analyzed each determine dependencies on subject. results obtained during testing procedure showed sensitivity 98.86%, positive predictive value 99.04%, accuracy 98.95%.

Language: Английский

Citations

5
Enhancing point annotations with superpixel and confident learning guided for improving semi-supervised OCT fluid segmentation DOI
Tengjin Weng, Yang Shen, Kai Jin

et al.

Biomedical Signal Processing and Control, Journal Year: 2024, Volume and Issue: 94, P. 106283 - 106283

Published: April 5, 2024

Language: Английский

Citations

1
AugPaste: A one-shot approach for diabetic retinopathy detection DOI

Jiaming Qiu,

Wei‐Kai Huang,

Yijin Huang

et al.

Biomedical Signal Processing and Control, Journal Year: 2024, Volume and Issue: 96, P. 106489 - 106489

Published: May 30, 2024

Language: Английский

Citations

1
Novel algorithm for beat-to-beat heart rate measurement from the BCG in seated, standing and supine positions: Towards an universal algorithm DOI
José Alberto García-Limón, Laura Ivonne Flores-Nunez, Carlos Alvarado-Serrano

et al.

Biomedical Signal Processing and Control, Journal Year: 2024, Volume and Issue: 96, P. 106641 - 106641

Published: July 16, 2024

Language: Английский

Citations

1
CNN Based Heart Rate Classification Using ECG Signal Without R-peak Detection for Rhythm-Aware Health and Emotion Monitoring DOI

Jomole Varghese Vadakkan,

M. Sabarimalai Manikandan, Linga Reddy Cenkeramaddi

et al.

2022 14th International Conference on Electronics, Computers and Artificial Intelligence (ECAI), Journal Year: 2024, Volume and Issue: unknown, P. 1 - 5

Published: June 27, 2024

Language: Английский

Citations

1
Fast Straightforward RR Interval Extraction Based Atrial Fibrillation Detection Using Shannon Entropy and Machine Learning Classifiers for Wearables DOI
Nabasmita Phukan, M. Sabarimalai Manikandan, Ram Bilas Pachori

et al.

Published: Oct. 17, 2023

Atrial fibrillation (AF), a complex arrhythmia with substantial morbidity and mortality implications, demands timely detection to preempt chronic cardiac complications. The need for continuous AF monitoring rises the demand an automatic, fast, reliable approach that ensures low computational complexity in terms of model size processing time. This study presents method using fast straightforward RR interval extraction Shannon entropy (ShE). utilizes symbolic dynamics from electrocardiogram (ECG) segments' heart rate sequences calculate ShE. When tested on two datasets (2-lead 12-lead) 10 s 30 durations, achieves accuracy 99.958% 100%, respectively, utilizing five machine learning classifiers. Furthermore, it showcases exceptionally time 0.286 µs multilayer perception neural network. best performance is achieved ECG segments Naive Bayes classifier. classifier obtained 1.5 kB 2.13 µs. In comparison previous studies, evaluation results demonstrate superior sensitivity, specificity, accuracy, speed this newly developed complexity. It clear experimental proposed methodology highly suitable implementation real-time health systems.

Language: Английский

Citations

2
EEG Based Emotion Recognition Using Variational Mode Decomposition and Convolutional Neural Network for Affective Computing Interfaces DOI

Thacchan Dondup,

M. Sabarimalai Manikandan, Linga Reddy Cenkeramaddi

et al.

Published: Nov. 1, 2023

Human emotion recognition plays a vital role in brain-to-brain communication, human-machine interactions and affective computing interfaces. This paper presents electroencephalogram (EEG) based using variational mode decomposition (VMD) convolutional neural network (CNN) by finding optimal hyperparameters for recognizing three emotional classes: positive, neutral negative. The two-stage VMD EEG processing is proposed effectively removing artifacts noises from the signal also decomposing into five brain waves such as delta, theta, alpha,beta gamma. CNN presented on differential entropy feature extracted 1 second instead of directly order to reduce size model. In this study, we created twelve models number layers (2, 5, 7) four activation functions with major objective best model(s). standard SEED database used obtain trained test their performance. Evaluation results show that architecture rectified linear unit (ReLU) yielded higher accuracy 90.33% among functions. For predicting emotions negative neutral, model 2-layer ReLU achieves an 100%, 94.44% 78.2%, respectively whereas 7-layer 94.40% 89.13%, respectively. study demonstrates significance selecting function.

Language: Английский

Citations

1
CA-SegNet: A channel-attention encoder–decoder network for histopathological image segmentation DOI
Feng He,

Weibo Wang,

Lijuan Ren

et al.

Biomedical Signal Processing and Control, Journal Year: 2024, Volume and Issue: 96, P. 106590 - 106590

Published: July 4, 2024

Language: Английский

Citations

0
Noise-Aware Atrial Fibrillation Detection for Resource-Constrained Wearable Devices DOI
Nabasmita Phukan, M. Sabarimalai Manikandan, Ram Bilas Pachori

et al.

2022 14th International Conference on Electronics, Computers and Artificial Intelligence (ECAI), Journal Year: 2024, Volume and Issue: unknown, P. 1 - 6

Published: June 27, 2024

Language: Английский

Citations

0