Real-Time Anomaly Detection over ECG Data Stream Based on Component Spectrum

Anomaly detection is a popular research in the age of Big Data. As a typical application scenario, anomaly detection over ECG data stream is confronted with particular difficulties including high real-time requirement and poor data quality. In this article, a novel method based on component spectrum is presented to provide a practicable solution for the problem. Experiments on real data show that the proposed method achieves high sensitivity, high specificity and low false alarm rate.

[1]  H. E. Stephenson,et al.  Some common denominators in 1200 cases of cardiac arrest. , 1953, Annals of surgery.

[2]  Bharadwaj Veeravalli,et al.  Design of a real-time morphology-based anomaly detection method from ECG streams , 2015, 2015 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[3]  VARUN CHANDOLA,et al.  Anomaly detection: A survey , 2009, CSUR.

[4]  Hans-Peter Kriegel,et al.  LOF: identifying density-based local outliers , 2000, SIGMOD 2000.

[5]  Charu C. Aggarwal,et al.  Outlier Analysis , 2013, Springer New York.

[6]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[7]  Lei Cao,et al.  Scalable distance-based outlier detection over high-volume data streams , 2014, 2014 IEEE 30th International Conference on Data Engineering.

[8]  Yu-Liang Hsu,et al.  ECG arrhythmia classification using a probabilistic neural network with a feature reduction method , 2013, Neurocomputing.

[9]  Christine L. Tsien,et al.  Reducing False Alarms in the Intensive Care Unit: A Systematic Comparison of Four Algorithms , 1997, AMIA.

[10]  Michael Elad,et al.  Improving Dictionary Learning: Multiple Dictionary Updates and Coefficient Reuse , 2013, IEEE Signal Processing Letters.

[11]  Yanchun Zhang,et al.  Supervised Anomaly Detection in Uncertain Pseudoperiodic Data Streams , 2016, ACM Trans. Internet Techn..

[12]  Saeid Nahavandi,et al.  Unsupervised mining of long time series based on latent topic model , 2013, Neurocomputing.

[13]  Siyuan Liu,et al.  SMC: A Practical Schema for Privacy-Preserved Data Sharing over Distributed Data Streams , 2015, IEEE Transactions on Big Data.

[14]  Mehmet Korürek,et al.  A new ECG beat clustering method based on kernelized fuzzy c-means and hybrid ant colony optimization for continuous domains , 2012, Appl. Soft Comput..

[15]  Sergei Vassilvitskii,et al.  k-means++: the advantages of careful seeding , 2007, SODA '07.

[16]  Qiang Qu,et al.  Graph-Based Knowledge Representation Model and Pattern Retrieval , 2008, 2008 Fifth International Conference on Fuzzy Systems and Knowledge Discovery.

[17]  Zou Yan-biao.  Home health telemonitoring system and data analyzing of physical parameters , 2011 .

[18]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[19]  Dan Wu,et al.  Indexable online time series segmentation with error bound guarantee , 2013, World Wide Web.

[20]  Dinkar Sitaram,et al.  Parallelization of searching and mining time series data using Dynamic Time Warping , 2015, 2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI).