Anomaly detection in ECG based on trend symbolic aggregate approximation

Chunkai Zhang; Yingyang Chen; Ao Yin; Xuan Wang; Chunkai Zhang; Yingyang Chen; Ao Yin; Xuan Wang

doi:10.3934/mbe.2019105

Mathematical Biosciences and Engineering

2019, Volume 16, Issue 4: 2154-2167. doi: 10.3934/mbe.2019105

Previous Article Next Article

Research article Special Issues

Anomaly detection in ECG based on trend symbolic aggregate approximation

Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China

Received: 18 December 2018 Accepted: 28 January 2019 Published: 12 March 2019

ECG anomaly detection is a necessary approach to detect disease Electrocardiography(ECG) signals before the detail diagnosis process in medical field to gauge the health of the human heart. Nowadays, there are many anomaly detection methods for ECG detection including supervised learning and unsupervised learning. For supervised learning, it requires the knowledge of expert and different types of Arrhythmia data for training. However, since the anomalies are less and unknown in many cases which are di cult to distinguish and be labeled, unsupervised methods are more suitable to detect the ECG anomalies. Furthermore, the existing unsupervised learning studies do not take ECG shape into account where different diseases have different shapes. In this paper, a novel simple trend aggregate approximation method is proposed, the relative binary trend representation are used to record the shape feature in original time series and to detect the anomaly heart signals by similarity comparison. We use the ECG dataset in UCR Time Series Classification Archive to obtain ECG time series data and the experiment results are assessed by means of sensitivity, specificity, false alarm rate measures which is robust and promising with high accuracy.
- similarity measurement,
- trend distance,
- electrocardiography,
- anomaly detection,
- binary String
Citation: Chunkai Zhang, Yingyang Chen, Ao Yin, Xuan Wang. Anomaly detection in ECG based on trend symbolic aggregate approximation[J]. Mathematical Biosciences and Engineering, 2019, 16(4): 2154-2167. doi: 10.3934/mbe.2019105

Related Papers:

Abstract

ECG anomaly detection is a necessary approach to detect disease Electrocardiography(ECG) signals before the detail diagnosis process in medical field to gauge the health of the human heart. Nowadays, there are many anomaly detection methods for ECG detection including supervised learning and unsupervised learning. For supervised learning, it requires the knowledge of expert and different types of Arrhythmia data for training. However, since the anomalies are less and unknown in many cases which are di cult to distinguish and be labeled, unsupervised methods are more suitable to detect the ECG anomalies. Furthermore, the existing unsupervised learning studies do not take ECG shape into account where different diseases have different shapes. In this paper, a novel simple trend aggregate approximation method is proposed, the relative binary trend representation are used to record the shape feature in original time series and to detect the anomaly heart signals by similarity comparison. We use the ECG dataset in UCR Time Series Classification Archive to obtain ECG time series data and the experiment results are assessed by means of sensitivity, specificity, false alarm rate measures which is robust and promising with high accuracy.

References

[1]	N. Rui and N. Horta, A new sax-ga methodology applied to investment strategies optimization, in Conference on Genetic and Evolutionary Computation, (2012), 1055–1062.
[2]	C. Krgel, T. Toth and E. Kirda, Service specific anomaly detection for network intrusion detection, in Proc. 2002 ACM Symposium on Applied Computing, (2002), 201–208.
[3]	P. Garcia-Teodoro, J. Diaz-Verdejo and G. Maciá-Fernández, et al., Anomaly-based network intrusion detection: Techniques, systems and challenges, Comput. Secur., 28 (2009), 18–28.
[4]	M. Anderka, S. Priesterjahn and S. Priesterjahn, Automatic atm fraud detection as a sequencebased anomaly detection problem, in International Conference on Pattern Recognition Applications and Methods, (2014), 759–764.
[5]	W. Zhang and X. He, An anomaly detection method for medicare fraud detection, in IEEE International Conference on Big Knowledge, (2017), 309–314.
[6]	V. Chandola, A. Banerjee and V. Kumar, Anomaly detection: A survey, ACM. Comput. Surv., 41 (2009), 15.
[7]	J. Sigholm and M. Raciti, Best-effort data leakage prevention in inter-organizational tactical manets, in Military Communications Conference, (2013).
[8]	J. Cucurull, M. Asplund and S. Nadjmtehrani, Anomaly Detection and Mitigation for Disaster Area Networks, Recent Advance. Int. Detect.n, (2010).
[9]	Q. Yu, L. Jibin and L. Jiang, An improved ARIMA-based traffic anomaly detection algorithm for wireless sensor networks, Taylor Francis, (2016).
[10]	A. Pyayt, A. Kozionov and V. Kusherbaeva, et al., Signal analysis and anomaly detection for flood early warning systems, J. Hydroinf., 16 (2014), 1025–1043.
[11]	M. Zhang, A. Raghunathan and N. K. Jha, Medmon: securing medical devices through wireless monitoring and anomaly detection, IEEE J. Sel. Top Signal Process, 7 (2013), 871.
[12]	D. Jiang, Z. Yuan and P. Zhang, et al., A traffic anomaly detection approach in communication networks for applications of multimedia medical devices, Multimed Tools Appl., 75 (2016), 1–25.
[13]	O. Salem, A. Guerassimov and A. Mehaoua, et al., Anomaly detection in medical wireless sensor networks using svm and linear regression models, IJEHMC, 5 (2014), 20–45.
[14]	W. Einthoven, The string galvanometer and the measurement of the action currents of the heart, Nobel Lecture, December, 11.
[15]	S. Chauhan and L. Vig, Anomaly detection in ecg time signals via deep long short-term memory networks, in IEEE International Conference on Data Science and Advanced Analytics, (2015), 1–7.
[16]	M. C. Chuah and F. Fu, Ecg anomaly detection via time series analysis, in International Conference on Frontiers of High PERFORMANCE Computing and NETWORKING, (2007), 123–135.
[17]	J. Ma, L. Sun and H.Wang, et al., Supervised anomaly detection in uncertain pseudoperiodic data streams, ACM T. INTERNET. TECHN., 16 (2016), 4.
[18]	C. Zhang, A. Yin and Y. Deng, et al., A novel anomaly detection algorithm based on trident tree, in Cloud Computing – CLOUD 2018, (2018), 295–306.
[19]	C. Zhang, Y. Ao and H. Liu, Design and application of electrocardiograph diagnosis system based on multifractal theory, Chin. J. Netw. Inf. Scy..
[20]	C. Zhang, A. Yin and Y. Wu, et al., Fast time series discords detection with privacy preserving, in 2018 17th IEEE International Conference On Trust, Security And Privacy In Computing And Communications/12th IEEE International Conference On Big Data Science And Engineering (TrustCom/BigDataSE), IEEE, (2018), 1129–1139.
[21]	H. Sivaraks and C. A. Ratanamahatana, Robust and accurate anomaly detection in ecg artifacts using time series motif discovery, Comput. Math Methods Med., 2015 (2015), 453214.
[22]	J. Shen, S. D. Bao, Y. C. Yang, et al., The plr-dtw method for ecg based biometric identification, in International Conference of the IEEE Engineering in Medicine & Biology Society, (2011), 5248.
[23]	H. Ren, M. Liu and Z. Li, et al., A piecewise aggregate pattern representation approach for anomaly detection in time series, Knowledge-Based Systems.
[24]	E. Keogh, J. Lin and A. Fu, Hot sax: efficiently finding the most unusual time series subsequence, in IEEE International Conference on Data Mining, (2006), 226–233.
[25]	J. L. Rodrguez-Sotelo, D. H. Peluffo-Ordoez and D. Lpez-Londoo, Segment clustering for holter recordings analysis, in International Work-Conference on the Interplay Between Natural and Artificial Computation, (2017), 456–463.
[26]	T. Kamiyama and G. Chakraborty, Real-time anomaly detection of continuously monitored periodic bio-signals like ecg, in Jsai International Symposium on Artificial Intelligence, (2015).
[27]	J. Lin, E. Keogh, L. Wei, et al., Experiencing sax: a novel symbolic representation of time series, Data Min. Knowl. Disc., 15 (2007), 107–144.
[28]	B. Kulahcioglu, S. Ozdemir and B. Kumova, Application of symbolic piecewise aggregate approximation (paa) analysis to ecg signals. in 17th IASTED International Conference on Applied Simulation and Modeling, (2008).
[29]	J. Lin, E. Keogh, S. Lonardi, et al., A symbolic representation of time series, with implications for streaming algorithms, in ACM SIGMOD Workshop on Research Issues in Data Mining and Knowledge Discovery, (2003), 2–11.
[30]	B. Lkhagva, Y. Suzuki and K. Kawagoe, Extended sax: Extension of symbolic aggregate approximation for financial time series data representation, DEWS2006 4A-i8, 7.
[31]	Y. Sun, J. Li and J. Liu, et al., An improvement of symbolic aggregate approximation distance measure for time series, Neurocomputing, 138 (2014), 189–198.
[32]	M. Yoshimural and I. Yoshimura, An application of the sequential dynamic programming matching method to off-line signature verification, in Brazilian Symposium on Advances in Document Image Analysis, (1997), 299–310.
[33]	M. Kachuee, S. Fazeli and M. Sarrafzadeh, Ecg heartbeat classification: A deep transferable representation, in IEEE International Conference on Healthcare Informatics, (2018), 443–444.
[34]	U. K. Tanaka Y, Motif discovery algorithm from motion data, in Proc of the 18th Annual Conf of the Japanese Society for Artificial Intelligence, (2004), 2–3.

Reader Comments

Your name:*

Email:*
© 2019 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)