A SEPARATE MODALITY PROCESSING WITH CASCADING ARCHITECTURE BY EMBEDDING INVERSION OF LATENCY(IOL) ML TO IMPROVE PERCEIVED LATENCY FOR BETTER PERFORMANCE AND STREAMING OF THE DATA

In recent times the research on healthcare doctor recommendation systems are increasingly designed with relatively low-latency where the patient’s interaction with the doctor’s recommendation system have been very slow due to network issues and low capabilities as far as the design models are concerned. In this regard there is a great need where certain machine learning models need to be leveraged to handle patient-doctor matching efficiently. A collaborative machine learning models with collaborative filtering is needed to match patients with specialists’ doctors is needed by minimizing the service delay. This can really be achieved by increasing the latency in terms of the design of the system by incorporating Inversion of Latency (IOL) by cascading Machine learning model (Reinforcement ML) with existing queuing models for better transmission of streaming data. This will really improvise a means for interacting with the patients with various specialist doctors based on the type of the disease and the diagnosed reports. This cascading model will improve the continuous interaction of various activities of the patient with respect to specialist doctor’s recommendation system without any delay in the interaction due to IOL machine learning model. This will really improve the performance of the system with very much minimal delay in network data transmissions.