The increasing demand for continuous healthcare monitoring has led to the development of intelligent systems capable of analyzing health-related data efficiently. Traditional healthcare systems rely heavily on periodic checkups and manual evaluation, which often result in delayed diagnosis and limited personalization. This paper presents a personalized health monitoring system based on hybrid learning techniques that integrate Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and Attention mechanisms. The proposed system processes both uploaded datasets and manually entered health parameters such as blood pressure, glucose levels, temperature, weight, and sleep duration. A preprocessing module ensures data quality by handling missing values and eliminating inconsistencies. The hybrid model captures both feature-level and temporal dependencies, providing accurate classification of health status into categories such as healthy, unhealthy, and needs attention. The system is implemented using a web-based architecture that allows users to visualize results and maintain historical records. The proposed approach enhances prediction accuracy, reduces manual effort, and supports proactive healthcare management.

The proposed VitaCore Health Monitoring System presents an effective and user-friendly solution for analyzing and tracking individual health parameters. By integrating data input, preprocessing, analysis, visualization, and storage into a single platform, the system addresses several limitations of existing healthcare monitoring applications. The implementation of a rule-based evaluation model enables quick and interpretable health assessments without the need for complex computational resources, making the system suitable for real-time applications. The developed prototype successfully demonstrates the feasibility of a web-based health monitoring system that allows users to input their physiological data and receive immediate feedback regarding their health status. The inclusion of a structured database for storing health records further enhances the system by enabling long- term monitoring and trend analysis. Additionally, the interactive dashboard and separate saved records module improve user engagement and provide a clear understanding of health conditions. Overall, the system contributes to the advancement of digital healthcare by offering an accessible and scalable solution for continuous health monitoring. It promotes health awareness, supports early detection of potential risks, and reduces dependency on traditional healthcare methods for basic assessments. The proposed platform serves as a foundation for future enhancements, such as integration with IoT devices, implementation of advanced machine learning models, and incorporation of security mechanisms to ensure data privacy. Thus, the system holds significant potential for real-world healthcare applications.

[1]O. Boursalie, R. Samavi, and T. Doyle, “Machine Learning-Based Health Monitoring Systems,” Journal of Medical Systems, 2018. [2]K. G. Sheela and S. N. Deepa, “Machine Learning Based Health Monitoring System,” Materials Today: Proceedings, vol. 33, pp. 467–472, 2020. [3]S. Thangam, M. Gurupriya, A. Adithya Vardhan, and M. A. U. S. Kumar, “Smart Health Monitoring System using IoT and Machine Learning,” 2024. [4]S. Gupta, G. F. Nama, and S. Deivasigamani, “Real-Time Monitoring of Patient Activity Using IoT and Machine Learning in Healthcare,” International Journal of Intelligent Systems, 2023. [5]Y. Rimal et al., “Comparative Analysis of Heart Disease Prediction using Machine Learning Algorithms,” IJCRT Journal, 2025. [6]AI-Based Health Monitoring System, International Journal of Engineering Research & Technology (IJERT), 2025.

© 2025 International Journal of Engineering and Techniques (IJET).

Digital Object Identifier (DOI)

IJET assigns a unique DOI to every accepted article via Zenodo for persistent linking and citation. Your article’s DOI: https://doi.org/{{doi}}

Open DOI About Zenodo DOI

Close