Real-Time HealthCare Recommendation System for Social Media Platforms

Abstract

Biomedical services play a vital role in calibration and validation of services with the influence of social media platform and big-data processing toolkits such as “Spark”, the processing and recommendation system can achieve a higher order of reliability and validation. In this research article, a novel framework is proposed to provide a recommendation of biomedical services from various social media platforms datasets. The framework is supported by a distributed processing technique under spark framework principle to segregate and process datasets based on SQL injection queries. The proposed technique’s distributed datasets are trained and validated under a distributed storage. The Spark-bits are processed with a recommendation system for healthcare services. The technique deploys a fuzzy neural principle in cross-reference identification of recommended framework with supportive decision making. The categorization and adapting distributed programming and storage using Spark extracts relevance in recommended properties. These qualities support decision-making using Controlled Learning based Neural Networking model (CLNN). The proposed technique has provided a higher value of reliability in a real-time recommendation environment.

Keywords

• Healthcare recommendation
• machine learning techniques
• social media recommendation