A Scalable and Fault Tolerant Health Risk Predictor using Bigdata Process Systems
Timmana Hari Krishna1, C Rajabhushanam2, D. Jayapriya3, S. Deivasigamani4
1Timmana Hari Krishna, Department of Computer Science and Engineering, Bharath Institute of Higher Education and Research, Chennai India.
2C Rajabhushanam, Department of Computer Science and Engineering, Bharath Institute of Higher Education and Research, Chennai India.
3D, Jayapriya, Department of Computer Science and Engineering, Bharath Institute of Higher Education and Research, Chennai India.
4S. Deivasigamani, Department of Computer Science and Engineering, Bharath Institute of Higher Education and Research, Chennai India.
Manuscript received on 04 July 2019 | Revised Manuscript received on 17 July 2019 | Manuscript Published on 23 August 2019 | PP: 609-614 | Volume-8 Issue-9S3 August 2019 | Retrieval Number: I31220789S319/2019©BEIESP | DOI: 10.35940/ijitee.I3122.0789S319
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Fault tolerant system to do real-time analytics for different health care applications. Users can get their health condition analysis report from the system by sending their health records in real-time. The health conditions occurrence can be considered as complex events and it may extended to different heterogeneous scenarios. Based on scalability and availability requirements, the system is developed using Kafka, Spark Streaming and Cassandra and implemented by using Scala. This system is capable for event stream processing and event batch processing. Users send the health data to Kafka through their producer clients in real-time. Spark streaming process the data from Kafka of different window sizes by analyzing the health conditions. In another scenario, user request stored into Cassandra database and is processed asynchronously by spark streaming. This system is tested with the use case of Heart attack hazard and stress prediction with different health datasets Keywords—Healthcare, Bigdata, Spark Streaming, Kafka, cassandra, Heart failure Prediction, Stress Index analysis
Keywords: Implementation, Casagranda Database, Sparkstreaming
Scope of the Article: Big Data Analytics