Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025;44(3):325-347.
doi: 10.1080/15368378.2025.2503334. Epub 2025 May 10.

An ECG signal processing and cardiac disease prediction approach for IoT-based health monitoring system using optimized epistemic neural network

B Sushma  1 , P Chinniah  2 , P S Ramesh  3 , Balasubbareddy Mallala  4
Affiliations

An ECG signal processing and cardiac disease prediction approach for IoT-based health monitoring system using optimized epistemic neural network

B Sushma et al. Electromagn Biol Med. 2025.

Abstract

The rising prevalence of cardiac diseases necessitates advanced IoT-driven health monitoring systems for early detection and diagnosis. This study presents an efficient ECG-based cardiac disease prediction framework leveraging a multi-phase approach to enhance computational efficiency and classification accuracy. The Convolutional Lightweight Deep Auto-encoder Wiener Filter (CLDAWF) is employed for signal preprocessing, while the Quantized Discrete Haar Wavelet Transform (QD-HWT) extracts critical cardiac features, including P-wave fluctuations, QRS complex, and T-wave intervals. These refined features are classified using an optimized Epistemic Neural Network (ENN), whose parameters are fine-tuned via the Boosted Sooty Tern Optimization algorithm, improving accuracy and reducing system loss. The proposed model achieves 99.65% accuracy, demonstrating its effectiveness in real-time cardiac disease monitoring and offering a scalable, high-performance solution for IoT-based healthcare systems.

Keywords: ECG signal processing; IoT-based health monitoring; boosted sooty tern optimization; convolutional lightweight deep auto-encoder Wiener filter (CLDAWF); quantized discrete Haar; wavelet transform (QD-HWT).

Plain language summary

Cardiac diseases are increasingly common, highlighting the need for efficient health monitoring systems to enable early detection and diagnosis. This study introduces an Internet of Things (IoT)-based health sickness prediction system that analyzes ECG signals from both healthy individuals and those with cardiac conditions to detect and classify irregularities. The proposed system employs a multi-phase approach to enhance prediction accuracy and reduce computational complexity through advanced signal pre-processing and feature extraction. The Convolutional Lightweight Deep Auto-encoder Wiener Filter (CLDAWF) is utilized for pre-processing ECG signals, ensuring noise reduction and clarity. Key cardiac features, such as P-wave fluctuations, QRS complex variations, and T-wave intervals, are extracted using the Quantized Discrete Haar Wavelet Transform (QD-HWT), enabling precise characterization of cardiac activity. These features are input into an optimized Epistemic Neural Network (ENN) for classification and prediction. To maximize the system’s accuracy, the ENN’s parameters are fine-tuned using the Boosted Sooty Tern Optimization algorithm, which enhances classification precision and minimizes losses. The model achieves a remarkable classification accuracy of 99.65%, demonstrating its efficacy in identifying and categorizing cardiac irregularities. This system provides a robust, scalable, and reliable solution for cardiac health monitoring, leveraging IoT integration to facilitate real-time analysis and prediction. Its advanced methods in feature extraction, optimization, and classification ensure a significant step forward in cardiac disease management and prevention, offering a promising tool for healthcare professionals and patients alike.

PubMed Disclaimer

Similar articles

See all similar articles

LinkOut - more resources