Abstract
Detecting anomalies in electrocardiogram (ECG) signals is crucial for identifying abnormal heart rhythms and diagnosing cardiac conditions. This paper investigates the effectiveness of variable thresholding for an autoencoder-based anomaly detection approach to detect abnormal signals in two widely-used databases. This unsupervised approach uses a deep autoencoder to learn the underlying patterns of the ECG signals and then applies a thresholding method to detect anomalies in the reconstructed signals. We evaluate the performance using Receiver Operating Characteristics (ROC) curve, which demonstrates the trade-off between True Positive Rate (TPR) and False Positive Rate (FPR) over different thresholds. Our empirical study aims to analyze the effectiveness of using different thresholding methods in combination with the Autoencoder-based anomaly detection architecture. For this purpose, we considered two thresholding methods: Random Thresholding and Distribution based Thresholding.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Aboah A (2021) A vision-based system for traffic anomaly detection using deep learning and decision trees. In: Proceedings of IEEE/CVF conference on computer vision & pattern recognition, pp 4207–4212
Bergmann Paul, Batzner Kilian, Fauser Michael, Sattlegger David, Steger Carsten (2021) The mvtec anomaly detection dataset: a comprehensive real-world dataset for unsupervised anomaly detection. Int J Comput Vis 129(4):1038–1059
Fawcett Tom (2006) An introduction to ROC analysis. Pattern Recogn Lett 27(8):861–874
Chong Sun Hong (2009) Optimal threshold from ROC and CAP curves. Commun Stat Simul Comput 38(10):2060–2072
Hou B, Yang J, Wang P, Yan R (2019) LSTM-based auto-encoder model for ECG arrhythmias classification. IEEE Trans Instrum Meas 69(4):1232–1240
Karpinski M, Khoma V, Dudvkevych V, Khoma Y, Sabodashko D (2018) Autoencoder neural networks for outlier correction in ECG-based biometric identification. In: Proceedings of IEEE 4th international symposium on wireless systems, international conferences on intelligent data acquisition and advanced computing systems (IDAACS-SWS), pp 210–215
Kieu T, Yang B, Guo C, Jensen CS (2019) Outlier detection for time series with recurrent autoencoder ensembles. In: Proceedings of 28th international joint conference on artificial intelligence (IJCAI), pp 2725–2732
Lai KH, Zha D, Xu J, Zhao Y, Wang G, Hu X (2021) Revisiting time series outlier detection: Definitions and benchmarks. In: Proceedings of 35th conference neural information processing systems datasets and benchmarks track (Round 1)
Liu Pengfei, Sun Xiaoming, Han Yang, He Zhishuai, Zhang Weifeng, Chenxu Wu (2022) Arrhythmia classification of LSTM autoencoder based on time series anomaly detection. Biomed Sign Process Control 71:103228
Malhotra P, Ramakrishnan A, Anand G, Vig L, Agarwal P, Shroff G (2016) LSTM-based encoder-decoder for multi-sensor anomaly detection
Metz Charles E (1978) Basic principles of ROC analysis. Semin Nuclear Med 8(4):283–298
Pereira João, Silveira Margarida (2019) Unsupervised representation learning and anomaly detection in ECG sequences. Int J Data Min Bioinf 22(4):389–407
Sun Le, Zhong Zhaoyi, Zhiguo Qu, Xiong Neal (2022) Perae: an effective personalized autoencoder for ecg-based biometric in augmented reality system. IEEE J Biomed Health Inf 26(6):2435–2446
Thill Markus, Konen Wolfgang, Wang Hao, Bäck Thomas (2021) Temporal convolutional autoencoder for unsupervised anomaly detection in time series. Appl Soft Comput 112:107751
Weszka JS, Rosenfeld A (1978) Threshold evaluation techniques. IEEE Trans Syst Man Cybern 8(8):622–629
Wu X, Lu X, Leung H (2017) An adaptive threshold deep learning method for fire and smoke detection. In: Proceedings of IEEE international conference on systems, man, & cybernetics (SMC), pp 1954–1959
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Mishra, B., Kumar, R. (2023). Empirical Analysis of Variable Thresholding for Autoencoder Anomaly Detector in ECG. In: Choudrie, J., Mahalle, P.N., Perumal, T., Joshi, A. (eds) IOT with Smart Systems. ICTIS 2023. Lecture Notes in Networks and Systems, vol 720. Springer, Singapore. https://doi.org/10.1007/978-981-99-3761-5_45
Download citation
DOI: https://doi.org/10.1007/978-981-99-3761-5_45
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-3760-8
Online ISBN: 978-981-99-3761-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)