You are currently viewing a new version of our website. To view the old version click .
Bioengineering
  • This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
  • Article
  • Open Access

30 December 2025

Pragmatic Models for Detection of Hypertension Using Ballistocardiograph Signals and Machine Learning

and
Department of Artificial Intelligence Convergence, Hallym University, Chuncheon 24252, Republic of Korea
*
Author to whom correspondence should be addressed.
Bioengineering2026, 13(1), 43;https://doi.org/10.3390/bioengineering13010043 
(registering DOI)
This article belongs to the Section Biosignal Processing

Abstract

To identify hypertension, Ballistocardiograph (BCG) signals can be primarily utilized. The BCG signal must be thoroughly understood and interpreted so that its application in the classification process could become clearer and more distinct. Various unhealthy habits such as excess consumption of alcohol and tobacco, accompanied by a lack of good diet and a sedentary lifestyle, lead to hypertension. Common symptoms of hypertension include chest pain, shortness of breath, blurred vision, mood swings, frequent urination, etc. In this work, two pragmatic models are proposed for the detection of hypertension using BCG signals and machine learning models. The first model uses K-means clustering, the maximum overlap discrete wavelet transform (MODWT) and the Empirical Wavelet Transform (EWT) techniques for feature extraction, followed by the Binary Tunicate Swarm Algorithm (BTSA) and Information Gain (IG) for feature selection, as well as two efficient hybrid classifiers such as the Hybrid AdaBoost–-Maximum Uncertainty Linear Discriminant Analysis (MULDA) classifier and the Hybrid AdaBoost–Random Forest (RF) classifier for the classification of BCG signals. The second model uses Principal Component Analysis (PCA), Kernel Principal Component Analysis (KPCA) and the Random Feature Mapping (RFM) technique for feature extraction, followed by IG and the Aquila Optimization Algorithm (AOA) for feature selection, as well as two versatile hybrid classifiers such as the Hybrid AutoRegressive Integrated Moving Average (ARIMA)–AdaBoost classifier and the Time-weighted Hybrid AdaBoost–Support Vector Machine (TW-HASVM) classifier for the classification of BCG signals. The proposed methodology was tested on a publicly available BCG dataset, and the best results were obtained when the KPCA feature extraction technique was used with the AOA feature selection technique and classified using the Hybrid ARIMA–AdaBoost classifier, reporting a good classification accuracy of 96.89%.

Article Metrics

Citations

Article Access Statistics

Article metric data becomes available approximately 24 hours after publication online.