Affiliations: [a]
Department of Computer Science and Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Chennai, India
| [b] Department of Computer Science, College of Computer Engineering and Sciences, Prince Sattam Bin Abdulaziz University, Alkharj, Saudi Arabia
Correspondence:
[*]
Corresponding author. Surendran Rajendran, Department of Computer Science and Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Chennai, India. E-mail: surendran.phd.it@gmail.com.
Abstract: Multi-agent reinforcement learning (MARL) is a generally researched approach for decentralized controlling in difficult large-scale autonomous methods. Typical features create RL system as an appropriate candidate to develop powerful solutions in variation of healthcare fields, whereas analyzing decision or treatment systems can be commonly considered by a prolonged and sequential process. This study develops a new Penguin Search Optimization Algorithm with Multi-agent Reinforcement Learning for Disease Prediction and Recommendation (PSOAMRL-DPR) model. This research aimed to use a unique PSOAMRL-DPR algorithm to forecast diseases based on data collected from networks and the cloud by a mobile agent. The major intention of the proposed PSOAMRL-DPR algorithm is to identify the presence of disease and recommend treatment to the patient. The model manages the agent container with different mobile agents and fetched data from dissimilar locations of the network as well as cloud. For disease detection and prediction, the PSOAMRL-DPR technique exploits deep Q-network (DQN) technique. In order to tune the hyperparameters related to the DQN technique, the PSOA technique is used. The experimental result analysis of the PSOAMRL-DPR technique is validated on heart disease dataset. The simulation values demonstrate that the PSOAMRL-DPR technique outperforms the other existing methods.
