Signal-Specific and Signal-Independent Features for Real-Time Beat-by-Beat ECG Classification with AI for Cardiac Abnormality Detection

Tsai, I Hua; Morshed, Bashir I.

doi:10.3390/electronics14132509

Open AccessArticle

Signal-Specific and Signal-Independent Features for Real-Time Beat-by-Beat ECG Classification with AI for Cardiac Abnormality Detection

by

I Hua Tsai

^1,*

and

Bashir I. Morshed

²

¹

Department of Computer Science and Cybersecurity, University of Central Missouri, Warrensburg, MO 64093, USA

²

Department of Computer Science, Texas Tech University, Lubbock, TX 79409, USA

^*

Author to whom correspondence should be addressed.

Electronics 2025, 14(13), 2509; https://doi.org/10.3390/electronics14132509

Submission received: 12 May 2025 / Revised: 18 June 2025 / Accepted: 19 June 2025 / Published: 20 June 2025

(This article belongs to the Special Issue Edge AI for Biomedical Applications: Innovations in Sensing, Computing and Security)

Download

Browse Figures

Review Reports Versions Notes

Abstract

ECG monitoring is central to the early detection of cardiac abnormalities. We compared 28 manually selected signal-specific features with 159 automatically extracted signal-independent descriptors from the MIT BIH Arrhythmia Database. ANOVA reduced features to the 10 most informative attributes, which were evaluated alone and in combination with the signal-specific features using Random Forest, SVM, and deep neural networks (CNN, RNN, ANN, LSTM) under an interpatient 80/20 split. Merging the two feature groups delivered the best results: a 128-layer CNN achieved 100% accuracy. Power profiling revealed that deeper models improve accuracy at the cost of runtime, memory, and CPU load, underscoring the trade-off faced in edge deployments. The proposed hybrid feature strategy provides beat-by-beat classification with a reduction in the number of features, enabling real-time ECG screening on wearable and IoT devices.

Keywords: ECG classification; cardiac episode; machine learning; deep learning; feature selection; feature ranking; signal-specific features; signal-independent features

Share and Cite

MDPI and ACS Style

Tsai, I.H.; Morshed, B.I. Signal-Specific and Signal-Independent Features for Real-Time Beat-by-Beat ECG Classification with AI for Cardiac Abnormality Detection. Electronics 2025, 14, 2509. https://doi.org/10.3390/electronics14132509

AMA Style

Tsai IH, Morshed BI. Signal-Specific and Signal-Independent Features for Real-Time Beat-by-Beat ECG Classification with AI for Cardiac Abnormality Detection. Electronics. 2025; 14(13):2509. https://doi.org/10.3390/electronics14132509

Chicago/Turabian Style

Tsai, I Hua, and Bashir I. Morshed. 2025. "Signal-Specific and Signal-Independent Features for Real-Time Beat-by-Beat ECG Classification with AI for Cardiac Abnormality Detection" Electronics 14, no. 13: 2509. https://doi.org/10.3390/electronics14132509

APA Style

Tsai, I. H., & Morshed, B. I. (2025). Signal-Specific and Signal-Independent Features for Real-Time Beat-by-Beat ECG Classification with AI for Cardiac Abnormality Detection. Electronics, 14(13), 2509. https://doi.org/10.3390/electronics14132509

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Signal-Specific and Signal-Independent Features for Real-Time Beat-by-Beat ECG Classification with AI for Cardiac Abnormality Detection

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI