Year: 2025
Type: article
Abstract: Effective data management and analysis are indispensable for the explosive growth of IoT-enabled exercise healthcare devices. The plethora of data services offered by cloud-computing systems efficiently meet requirements such as scalability, real-time processing, and smooth integration of multiple sources of data. In this framework, an integrated healthcare monitoring network with the best possible decision-making facilitation and patient monitoring in real-time is achieved over the cloud data services linking with IoT sensor data. LSTM networks will develop precise predictions of health metrics such as blood pressure and heart rate after implementation of dimensionality reduction and feature extraction using autoencoders. The system shows adaptability to the changing context based on activity and environment through real-time optimization of system parameters from adaptive feedback loops. The advancements in the forecast accuracy of the systems have enabled their reliable, continuous monitoring. Limits are environmental conditions and sensor reliability issues. Future works are going to be about improving versatility in diverse health care settings, adopting transformer models for advanced forecasting, and improving scalability.
Authors: Archana Chaluvadi, Pramod Begur Nagaraj, Winner Pulakhandam, Visrutatma Rao Vallu, R. Pushpakumar
Language: English
Topic: Internet of Things and AI
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4411798697