Smart Health Monitoring System

Project Domain / Category

Web Application

Abstract / Introduction

Health issues such as diabetes, hypertension, obesity, cardiovascular diseases, and stress-related conditions are on the rise due to sedentary lifestyles, poor diets, and irregular medical checkups. Many people neglect their health until symptoms become severe, leading to late diagnosis and expensive treatments. While regular checkups can aid in early detection, they are often costly, time-consuming, and impractical for daily use. Existing health tracking solutions mainly rely on IoT devices like smartwatches or are too complex for ordinary users who require a simple, affordable, and accessible way to monitor their well-being.

The Smart Health Monitoring System (SHMS) addresses this gap by allowing users to manually input their daily health information. Using Artificial Intelligence, it offers early predictions of potential health risks, lifestyle recommendations, and clear visualizations of health trends, empowering individuals to monitor and enhance their health proactively.

Functional Requirements:

Below are some functional requirements in the form of modules. Students will analyze, identify, and provide detailed functional requirements in the Software Requirement Specifications (SRS) document.

        Health Data Entry Module

        A web-based interface for users to manually enter their information (e.g., weight, blood pressure, sugar level, sleep hours, exercise minutes, mood or stress level).

        Validate user input to prevent negative or unrealistic values.

        Store each user entry with a timestamp for future analysis.

        Allow users to update or delete past entries.

        Data Storage, Management, Pre-processing & Cleaning

        Utilize a secure and structured database to store the data entered into the monitoring system.

        Provide an interface to upload users into the system in CSV/Excel format.

        Allow import/export of user data in SQL/CSV/Excel files.

        Pre-process and clean data received through any medium before entering it into the system.

        AI Prediction & Risk Analysis

        Apply machine learning algorithms to predict early risks of diseases (e.g., diabetes, hypertension).

        Perform anomaly detection for sudden unusual readings (e.g., very high blood pressure).

        Assign a risk level (Low, Medium, and High) for each parameter.

Page 135 of 167