A Modified Dynamic Time Warping (MDTW) Approach and Innovative Average Non-Self Match Distance (ANSD) Method for Anomaly Detection in ECG Recordings

ECGs objectively reflects the working conditions of the hearts as these signals contain vast physiological and pathological information. In this work, in order to improve the efficiency and accuracy of "best so far" time series analysisbased ECG anomaly detection methods, a novel method, comprising a modified dynamic time warping (MDTW) and an innovative average non-self match distance (ANSD) measure, is proposed for ECG anomaly detection. To evaluate the performance of the proposed method, the proposed method is applied to real ECG data selected from the MIT-BIH heartbeat database. To provide a reference for comparison, two existing anomaly detection methods, namely, brute force discord discovery (BFDD) and adaptive window discord discovery (AWDD), are also applied to the same data. The experimental results show that our proposed method outperforms BFDD and AWD.

[1]  Eamonn J. Keogh,et al.  HOT SAX: efficiently finding the most unusual time series subsequence , 2005, Fifth IEEE International Conference on Data Mining (ICDM'05).

[2]  Meinard Müller,et al.  Information retrieval for music and motion , 2007 .

[3]  Mooi Choo Chuah,et al.  ECG Anomaly Detection via Time Series Analysis , 2007, ISPA Workshops.

[4]  Francisca Nonyelum Ogwueleka.  DATA MINING APPLICATION IN CREDIT CARD FRAUD DETECTION SYSTEM , 2011 .

[5]  Prasan Kumar Sahoo,et al.  A Cardiac Early Warning System with Multi Channel SCG and ECG Monitoring for Mobile Health , 2017, Sensors.

[6]  Duong Tuan Anh,et al.  Time series discord discovery using WAT algorithm and iSAX representation , 2012, SoICT '12.

[7]  Rüdiger W. Brause,et al.  Neural data mining for credit card fraud detection , 1999, Proceedings 11th International Conference on Tools with Artificial Intelligence.

[8]  Lovekesh Vig,et al.  Anomaly detection in ECG time signals via deep long short-term memory networks , 2015, 2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA).

[9]  K. Krishneswari,et al.  Anomaly Detection for Cyber Security of the Substations: A Survey , 2015 .

[10]  André Paim Lemos,et al.  ECG Anomalies Identification Using a Time Series Novelty Detection Technique , 2007 .

[11]  Alan Bundy,et al.  Dynamic Time Warping , 1984 .

[12]  Donald J. Berndt,et al.  Using Dynamic Time Warping to Find Patterns in Time Series , 1994, KDD Workshop.

[13]  S. Benson Edwin Raj,et al.  Analysis on credit card fraud detection methods , 2011, 2011 International Conference on Computer, Communication and Electrical Technology (ICCCET).

[14]  Ravneet Kaur,et al.  A survey of data mining and social network analysis based anomaly detection techniques , 2016 .

[15]  Eamonn J. Keogh,et al.  Approximations to magic: finding unusual medical time series , 2005, 18th IEEE Symposium on Computer-Based Medical Systems (CBMS'05).

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

[17]  Jian Pei,et al.  WAT: Finding Top-K Discords in Time Series Database , 2007, SDM.

[18]  Eamonn J. Keogh,et al.  Finding the most unusual time series subsequence: algorithms and applications , 2006, Knowledge and Information Systems.

[19]  Jugal K. Kalita,et al.  Network Anomaly Detection: Methods, Systems and Tools , 2014, IEEE Communications Surveys & Tutorials.

[20]  Huilong Duan,et al.  On local anomaly detection and analysis for clinical pathways , 2015, Artif. Intell. Medicine.

[21]  Eamonn J. Keogh,et al.  Finding Unusual Medical Time-Series Subsequences: Algorithms and Applications , 2006, IEEE Transactions on Information Technology in Biomedicine.

[22]  Jun Cheng,et al.  A Wearable Smartphone-Based Platform for Real-Time Cardiovascular Disease Detection Via Electrocardiogram Processing , 2010, IEEE Transactions on Information Technology in Biomedicine.