An efficient approach for outlier detection in big sensor data of health care. (2nd July 2017)

• Record Type: Journal Article
• Authors: Saneja, Bharti; Rani, Rinkle
• Is Part Of: International journal of communication systems. Volume 30:Number 17(2017)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2017-07-02
• Subjects: big data -- correlation -- outlier detection -- prediction -- wireless sensor networks; Telecommunication systems -- Periodicals; 621.382
• DOI: 10.1002/dac.3352
• Languages: English
• ISSNs: 1074-5351

Abstract

Summary: In recent years, wireless sensor networks are pervasive and are generating tons of data every second. Performing outlier detection to detect faulty sensors from such a large amount of data becomes a challenging task. Most of the existing techniques for outlier detection in wireless sensor networks concentrate only on contents of the data source without considering correlation among different data attributes. Moreover, these methods are not scalable to big data. To address these 2 limitations, this paper proposes an outlier detection approach based on correlation and dynamic SMO (sequential minimal optimization) regression that is scalable to big data. Initially, correlation is used to find out strongly correlated attributes and then the point anomalous nodes are detected using dynamic SMO regression. For fast processing of big data, Hadoop MapReduce framework is used. The experimental analysis demonstrates that the proposed approach efficiently detects the point and contextual anomalies and reduces the number of false alarms. For experiments, real data of sensors used in body sensor networks are taken from Physionet database. Abstract : The paper proposed an integrated approach based on correlation and regression for detection of outliers. MapReduce framework has been used to efficiently deal with big sensor data. The analysis done in the paper is based on the real sensor data obtained from the Physionet database. The study reveals that the proposed approach efficiently detects point as well as contextual anomalies with high outlier detection rate and low false positives.