Advanced Data Integration, Knowledge Extraction, and Application in Energy-Efficient Telehealth IoT Systems

Abstract

This paper further studies the previously proposed energy-efficient telehealth Internet of Things (IoT) model that focuses on data integration, knowledge extraction, and application in fog-cloud hybrid architecture. Our current study concentrates on how the system uses adaptive machine learning and data mining to optimize the system operation for increased real-time data analysis and reduced energy use, thus providing more effective patient monitoring in telehealth. The simulation designed for the patients in both a fog-enabled model and a cloud-only model applies various workloads sent from patients. In this fog-enabled model, data from IoT devices is preprocessed at fog nodes by investigating anomalies, trends, or other relevant machine learning algorithms, and then this data is transmitted to the cloud. It compares key performance metrics-energy, latency, speed of processing data, and prediction accuracy—in both a fog-enabled and a cloud-only model. Results show that the fog-enabled model reduces energy consumption by 20% and latency by 50%, compared to a cloud-only configuration. This indicates the distinct advantages of localized processing. Compared to the existing system, higher speed in processing data and improved accuracy in detecting statistical anomalies, thereby demonstrating the possibility that the system offers for real-time and scalable telehealth capabilities. Meanwhile, this work presents a comprehensive model for the sustainability and scalability of telehealth infrastructures, supported by simulation data and analysis evidencing the effectiveness of the model.

Received: 2 December 2024 | Revised: 4 September 2025 | Accepted: 16 October 2025

Conflicts of Interest

The authors declare that they have no conflicts of interest to this work.

Data Availability Statement

Data are available on request from the corresponding author upon reasonable request.

Author Contribution Statement

Nathan Guo: Conceptualization, Investigation, Resources, Writing — original draft, Visualization. Yunyong Guo: Methodology, Validation, Writing — review & editing, Supervision, Project administration. Bryan Guo: Software, Formal analysis, Data curation.