Recommendation Model-Based 5G Network and Cognitive System of Cloud Data with AI Technique in IOMT Applications

Abstract

Recommender system provides the significant suggestion towards the effective service offers for the vast range of big data. The Internet of Things (IoT) environment exhibits the value added application services to the customer with the provision of the effective collection and processing of information. In the extension of the IoT, Internet of Medical Things (IoMT) is evolved for the patient healthcare monitoring and processing. The data collected from the IoMT are stored and processed with the cognitive system for the data transmission between the users. However, in the conventional system subjected to challenges of processing big data while transmission with the cognitive radio network. In this paper, developed a effective cognitive 5G communication model with the recommender model for the IoMT big data processing. The proposed model is termed as Ranking Strategy Internet of Medical Things (RSIoMT). The proposed RSIoMT model uses the distance vector estimation between the feature variables with the ranking. The proposed RSIoMT model perform the recommender model with the ranking those are matches with the communication devices for improved wireless communication quality. The proposed system recommender model uses the estimation of direct communication link between the IoMT variables in the cognitive radio system. The proposed RSIoMT model evaluates the collected IoMT model data with the consideration of the four different healthcare datasets for the data transmission through cognitive radio network. Through the developed model the performance of the system is evaluated based on the deep learning model with the consideration of the collaborative features. The simulation analysis is comparatively examined based on the consideration of the wireless performance. Simulation analysis expressed that the proposed RSIoMT model exhibits the superior performance than the conventional classifier. The comparative analysis expressed that the proposed mode exhibits ~3 – 4% performance improvement over the conventional classifiers. The accuracy of the  developed model achieves 99% which is ~3 – 9% higher than the conventional classifier. In terms of the channel performance, the proposed RSIoMT model exhibits the reduced recommender relay selection count of 1 while the other technique achieves the relay value of 13 which implies that proposed model performance is ~4-6% higher than the other techniques.