Continuous blood pressure (BP) monitoring plays a crucial role in preventative health care because it provides invaluable assessment of an individual’s cardiovascular health. However, achieving accurate and non-invasive BP estimation remains a significant challenge. Motivated by the need for improved accuracy in BP estimation, this research proposes a novel deep-learning technique to estimate blood pressure from photoplethysmography (PPG) signals based on the temporal attention mechanism by selecting optimal features to improve the estimation accuracy. The proposed deep learning model consists of an embedded temporal attention employed to learn the temporal sequence and selects the optimal competitive features using bidirectional encoder and decoder. PPG features are extracted from traditional feature extraction techniques such as statistical, frequency, time domain-based analysis and chaotic features using two publicly available datasets MIMIC II and PPG-BP. The comparison of proposed model experimental results with the state-of-the-art models demonstrates the advancement of optimal feature selection technique for blood pressure measurement. The mean absolute error (MAE) and standard deviation SD for optimal feature extraction with the temporal attention mechanism model are 2.31 ± 3.16 mmHg and 1.13 ± 2.32 mmHg utilising MIMIC II data and 3.43 ± 3.08 mmHg and 3.29 ± 2.19 mmHg for PPG-BP dataset for SBP and DBP respectively. The proposed model results satisfied the standard requirements published by the British Hypertension Society (BHS) and US Association for the Advancement of Medical Instrumentation (AAMI) standards. The proposed solution can offer continuous BP estimation and can significantly enhance healthcare by helping individuals manage their cardiovascular health more effectively.

The digital transformation of higher education continues to reshape how students learn, how educators teach, and how institutions support academic success