Modelling of an intelligent biosurveillance system based on electronic sensors, big data and statistical analysis for the prediction of variations in biological parameters

Abstract

Modern biosurveillance benefits from the convergence of biology, electronics, the Internet of Things, big data, statistical analysis and artificial intelligence. Wearable sensors and biosensors can generate continuous time series describing various physiological or biochemical parameters. However, the scientific value of these measurements depends on the quality of the sensors, signal processing, the ability to manage large data flows and the use of appropriate statistical methods.

This article proposes the modelling of an intelligent biosurveillance system based on an integrated chain ranging from the electronic acquisition of biological parameters to the prediction of their variations. The model combines sensors, signal conditioning, a microcontroller, IoT communication, Big Data infrastructure, pre-processing, multivariate statistical analysis and predictive models.

The proposed methodology is quantitative, longitudinal, analytical and predictive. It involves assessing sensor reliability, conducting descriptive and correlational analyses of signals, analysing time series, and comparing several machine learning and deep learning algorithms. Particular attention is paid to data quality, artefacts, inter-individual variability, confidentiality and the cautious interpretation of algorithmic outputs.

Keywords: Biomonitoring; biosensors; electronics; Big Data; statistical analysis; biological parameters; time series; machine learning; IoT; prediction.

Received Date: June 19, 2026

Accepted Date: July 10, 2026

Published Date: August 01, 2026

Available Online at: https://www.ijsrisjournal.com/index.php/ojsfiles/article/view/900