Affiliations: [a] Department of Networking and Communications, SRM Institute of Science and Technology, SRM Nagar, Kattankulathur | [b] Computer Science Department, Vardhaman College of Engineering Hyderabad
| [c] Department of Computer Science, Kebri Dehar University, Kebri Dehar, Ethiopia
| [d] Department of CSE, Koneru Lakshmaiah Education Foundation, Vaddeswaram, AP, India
| [e] Department of IT, Lakireddy Bali Reddy College of Engineering, Mylavaram
| [f] Department of Computer Science and Engineering, SNS College of Technology, Coimbatore, India | [g] AP / AI and DS, Karpagam Institute of Technology, Coimbatore
Correspondence:
[*]
Corresponding author. K. Nimala, Department of Networking and Communications, SRM Institute of Science and Technology, SRM Nagar, Kattankulathur - 603 203, E-mail: [email protected].
Abstract: The creation of sensor-based software for health monitoring using Internet of Things (IoT) technology is the main goal of this project. The program’s objective is to continuously monitor human physiological data, including ECG, SPO2, heart rate, and respiration, by employing biomedical sensor networks. These sensors collect data, which is then processed by a processor and transmitted to an edge server through a transceiver. A node of corner facilitates for real transmission has processed each data will be patient’s phone and the clinicians’ LED display. To address the optimization challenge, the program utilizes a Double Deep-Q-Network approach, with parameters optimized using a hybrid genetic algorithm-based simulated annealing technique. However, healthcare records obtained from the sensors are susceptible to change due to environmental factors, leading to potential performance issues. In order to overcome this challenge, an optimization approach is employed to refine the proposed technique, ensuring accurate prediction of readings. The study conducted experiments to evaluate the program’s performance, utilizing various metrics and different parameters. The results to provide light on how well the program that was created for leveraging IoT technologies for health monitoring is working. This study presents an innovative sensor-based program for IoT technology-based health monitoring, which continuously monitors human physiological data. The program incorporates a hybrid optimization approach to ensure accurate prediction of readings, accounting for environmental factors. The proposed Double Deep-Q-Network and the evaluation metrics employed demonstrate the originality and contributions of this research in advancing health monitoring systems.
