DNN based Medication Recommender System in an IoT based Environment

Abstract

The internet of things (IoT), is the internetworking of physical devices, vehicles (also referred to as "connected devices" and "smart devices"), buildings and other items embedded with electronics, software, sensors, actuators, and network connectivity that enable these objects to collect and exchange data. We present the results of the evaluations that demonstrate its suitability towards real world deployments. Our proposed middleware is built on Android platform. The whole system is incorporated in such a way that it is easy to use and user friendly interface is designed. The designed system is mainly based on Deep Neutral Network (DNN) as backend for the processing and the application is designed on ANDROID platform, which work in cooperation with MATLAB as frontend. The system designed is known as “DNN based Medication Recommender System in an IoT based Environment”. The person who is suffering from any illness uses the system as a medicine recommender. The person fills up the details in symptom form after connecting to the system. After filling all details of the symptom form is forwarded to the system, the system processes the data using deep neural network (DNN) and makes a decision. On the basis of this decision the system gives output which results the name of disease from which the person is infected and the name of medicine for cure of disease. The comparison is also performed in which the disease and medicine predicted by system is compared with the disease and medicine which are recommended by the doctors with the given symptoms of a person. The results of the architecture shows that system is working very efficiently and the prediction of diseases and medicine same as done by the doctors and system is giving 100% efficiency.