Automated Personalized Health Analytics using IoT and Machine Learning Algorithms

This research work develops and implements an integrated system using IoT technologies and machine learning algorithm to measure Body Mass Index (BMI) and perform health analytics in hospitals. Obesity, overweight, and chronic diseases are major public health issues. Healthcare workers need accurate and quick BMI readings to monitor weight status and health issues. To overcome these limitations, the proposed system uses IoT sensors to automate BMI evaluations and collect real-time health data. Wireless IoT devices interface with hospital information systems. The Support Vector Machine (SVM) algorithm analyzes BMI, physical activity, and vital sign data. It can identify and predict BMI values from data. SVM can predict BMI for customized weight loss recommendations. The proposed setup helps hospitals to automate BMI measuring, thus reducing medical staff burden and manual intervention. Real-time monitoring and analysis enable early identification and individualized treatment of obesity-related health concerns. IoT devices with the SVM algorithm enable data-driven decision-making, improving patient outcomes and healthcare efficiency.

I. Introduction

A machine automatically assessing BMI is the standard statistic for analyzing body composition and health. The design, hardware, and software elements of the BMI measuring machine's development are covered in the article. The automated BMI measuring equipment works similarly to manual measures, giving a practical and time-saving option for BMI testing [1]. It includes information on the technical features and operation of the automated BMI calculation equipment [2]. This study aims to develop interpretable machine-learning methods for mapping functions that relate anthropometric measures to BMI. It can precisely estimate BMI using various body measures. To provide insights into the association between anthropometric measurements and BMI, it highlights the interpretability of the machine learning models deployed [3].