ECG Sensor Design Assessment with Variational Autoencoder-Based Digital Watermarking

Designing an ECG sensor circuit requires a comprehensive approach to detect, amplify, filter, and condition the weak electrical signals produced by the heart. To evaluate sensor performance under realistic conditions, diverse ECG signals with embedded watermarks are generated, enabling an assessment...

Full description

Saved in:
Bibliographic Details
Main Authors: Chih-Yu Hsu, Chih-Yin Chang, Yin-Chi Chen, Jasper Wu, Shuo-Tsung Chen
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/7/2321
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849730213650366464
author Chih-Yu Hsu
Chih-Yin Chang
Yin-Chi Chen
Jasper Wu
Shuo-Tsung Chen
author_facet Chih-Yu Hsu
Chih-Yin Chang
Yin-Chi Chen
Jasper Wu
Shuo-Tsung Chen
author_sort Chih-Yu Hsu
collection DOAJ
description Designing an ECG sensor circuit requires a comprehensive approach to detect, amplify, filter, and condition the weak electrical signals produced by the heart. To evaluate sensor performance under realistic conditions, diverse ECG signals with embedded watermarks are generated, enabling an assessment of how effectively the sensor and its signal-conditioning circuitry handle these modified signals. A Variational Autoencoder (VAE) framework is employed to generate the watermarked ECG signals, addressing critical concerns in the digital era, such as data security, authenticity, and copyright protection. Three watermarking strategies are examined in this study: embedding watermarks in the mean (μ) of the VAE’s latent space, embedding them through the latent variable (z), and using post-reconstruction watermarking in the frequency domain. Experimental results demonstrate that watermarking applied through the mean (μ) and in the frequency domain achieves a low Mean Squared Error (MSE) while maintaining stable signal fidelity across varying watermark strengths (α), latent space dimensions, and noise levels. These findings indicate that the mean (μ) and frequency domain methods offer robust performance and are minimally affected by changes in these parameters, making them particularly suitable for preserving ECG signal quality. By contrasting these methods, this study provides insights into selecting the most appropriate watermarking technique for ECG sensor applications. Incorporating watermarking into sensor design not only strengthens data security and authenticity but also supports reliable signal acquisition in modern healthcare environments. Overall, the results underscore the effectiveness of combining VAEs with watermarking strategies to produce high-fidelity, resilient ECG signals for both sensor performance evaluation and the protection of digital content.
format Article
id doaj-art-eab4cedc8ac54ffabea482a7051b2b52
institution DOAJ
issn 1424-8220
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-eab4cedc8ac54ffabea482a7051b2b522025-08-20T03:08:56ZengMDPI AGSensors1424-82202025-04-01257232110.3390/s25072321ECG Sensor Design Assessment with Variational Autoencoder-Based Digital WatermarkingChih-Yu Hsu0Chih-Yin Chang1Yin-Chi Chen2Jasper Wu3Shuo-Tsung Chen4School of Transportation, Fujian University of Technology, Fuzhou 350118, ChinaDepartment of Medical Informatics, Chung Shan Medical University, Taichung 40201, TaiwanDepartment of Medical Informatics, Chung Shan Medical University, Taichung 40201, TaiwanKang Chiao International School, Linkou Campus, New Taipei City 244, TaiwanDepartment of Electronic Engineering, National Kaohsiung University of Science and Technology, Kaohsiung City 807618, TaiwanDesigning an ECG sensor circuit requires a comprehensive approach to detect, amplify, filter, and condition the weak electrical signals produced by the heart. To evaluate sensor performance under realistic conditions, diverse ECG signals with embedded watermarks are generated, enabling an assessment of how effectively the sensor and its signal-conditioning circuitry handle these modified signals. A Variational Autoencoder (VAE) framework is employed to generate the watermarked ECG signals, addressing critical concerns in the digital era, such as data security, authenticity, and copyright protection. Three watermarking strategies are examined in this study: embedding watermarks in the mean (μ) of the VAE’s latent space, embedding them through the latent variable (z), and using post-reconstruction watermarking in the frequency domain. Experimental results demonstrate that watermarking applied through the mean (μ) and in the frequency domain achieves a low Mean Squared Error (MSE) while maintaining stable signal fidelity across varying watermark strengths (α), latent space dimensions, and noise levels. These findings indicate that the mean (μ) and frequency domain methods offer robust performance and are minimally affected by changes in these parameters, making them particularly suitable for preserving ECG signal quality. By contrasting these methods, this study provides insights into selecting the most appropriate watermarking technique for ECG sensor applications. Incorporating watermarking into sensor design not only strengthens data security and authenticity but also supports reliable signal acquisition in modern healthcare environments. Overall, the results underscore the effectiveness of combining VAEs with watermarking strategies to produce high-fidelity, resilient ECG signals for both sensor performance evaluation and the protection of digital content.https://www.mdpi.com/1424-8220/25/7/2321variational AutoEncoderFourier-simulated ECG datasetlatent variable spacewatermarking technology
spellingShingle Chih-Yu Hsu
Chih-Yin Chang
Yin-Chi Chen
Jasper Wu
Shuo-Tsung Chen
ECG Sensor Design Assessment with Variational Autoencoder-Based Digital Watermarking
Sensors
variational AutoEncoder
Fourier-simulated ECG dataset
latent variable space
watermarking technology
title ECG Sensor Design Assessment with Variational Autoencoder-Based Digital Watermarking
title_full ECG Sensor Design Assessment with Variational Autoencoder-Based Digital Watermarking
title_fullStr ECG Sensor Design Assessment with Variational Autoencoder-Based Digital Watermarking
title_full_unstemmed ECG Sensor Design Assessment with Variational Autoencoder-Based Digital Watermarking
title_short ECG Sensor Design Assessment with Variational Autoencoder-Based Digital Watermarking
title_sort ecg sensor design assessment with variational autoencoder based digital watermarking
topic variational AutoEncoder
Fourier-simulated ECG dataset
latent variable space
watermarking technology
url https://www.mdpi.com/1424-8220/25/7/2321
work_keys_str_mv AT chihyuhsu ecgsensordesignassessmentwithvariationalautoencoderbaseddigitalwatermarking
AT chihyinchang ecgsensordesignassessmentwithvariationalautoencoderbaseddigitalwatermarking
AT yinchichen ecgsensordesignassessmentwithvariationalautoencoderbaseddigitalwatermarking
AT jasperwu ecgsensordesignassessmentwithvariationalautoencoderbaseddigitalwatermarking
AT shuotsungchen ecgsensordesignassessmentwithvariationalautoencoderbaseddigitalwatermarking