A Hybrid Deep Learning Models for Hetrogeneous Medical Big Data Integration

Data sharing and integration is the main role for establishing the data warehouse. But, the existing data integration techniques need brighter light of the research
in various areas such as duplication prevention, long-term preservation, accurate diagnosis. Integration mechanism is now changing its face of minimizing the abovementioned drawbacks but still requires the improvisation. This paper proposes the new deep learning algorithms for the integration of heterogeneous data and knowledge sources in medical health care systems. The deep learning integration profile
we proposed is mainly focused on users with the several body disorders. This hybrid models are used not only for integration but also to provide the intelligent analytics of the various disorders by connecting the event information. The various performance metrics such as time complexity, accuracy of detection were calculated and compared with existing integration schemes. Final outcome indicates that this model is well suited for integrating the heterogeneous medical data sources and also outperforms the existing models.