Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
124 tokens/sec
GPT-4o
8 tokens/sec
Gemini 2.5 Pro Pro
47 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Event Detection in Time Series: Universal Deep Learning Approach (2311.15654v3)

Published 27 Nov 2023 in stat.ML and cs.LG

Abstract: Event detection in time series is a challenging task due to the prevalence of imbalanced datasets, rare events, and time interval-defined events. Traditional supervised deep learning methods primarily employ binary classification, where each time step is assigned a binary label indicating the presence or absence of an event. However, these methods struggle to handle these specific scenarios effectively. To address these limitations, we propose a novel supervised regression-based deep learning approach that offers several advantages over classification-based methods. Our approach, with a limited number of parameters, can effectively handle various types of events within a unified framework, including rare events and imbalanced datasets. We provide theoretical justifications for its universality and precision and demonstrate its superior performance across diverse domains, particularly for rare events and imbalanced datasets.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (44)
  1. Handling imbalanced data for improved classification performance: Methods and challenges. In 2023 3rd International Conference on Emerging Smart Technologies and Applications (eSmarTA), pp.  1–8, 2023. doi: 10.1109/eSmarTA59349.2023.10293442.
  2. Credit card fraud detection using state-of-the-art machine learning and deep learning algorithms. IEEE Access, 10:39700–39715, 2022.
  3. A survey of methods for time series change point detection. Knowl. Inf. Syst., 51(2):339–367, May 2017.
  4. A comprehensive python library for deep learning-based event detection in multivariate time series data and information retrieval in nlp, 2023.
  5. Nearly-tight vc-dimension and pseudodimension bounds for piecewise linear neural networks. Journal of Machine Learning Research, 20(63):1–17, 2019. URL http://jmlr.org/papers/v20/17-612.html.
  6. TAnoGAN: Time series anomaly detection with generative adversarial networks. In 2020 IEEE Symposium Series on Computational Intelligence (SSCI). IEEE, December 2020.
  7. Credit card fraud detection model based on LSTM recurrent neural networks. J. Adv. Inf. Technol., 12(2):113–118, 2021.
  8. SMOTE: synthetic minority over-sampling technique. CoRR, abs/1106.1813, 2011. URL http://arxiv.org/abs/1106.1813.
  9. Deep learning for anomaly detection: A survey. 2019.
  10. 4. Image Denoising, pp.  145–206. doi: 10.1137/1.9780898717877.ch4. URL https://epubs.siam.org/doi/abs/10.1137/1.9780898717877.ch4.
  11. Automated bow shock and magnetopause boundary detection with cassini using threshold and deep learning methods. Front. Astron. Space Sci., 9, October 2022.
  12. Deep learning for anomaly detection in time-series data: Review, analysis, and guidelines. IEEE Access, 9:120043–120065, 2021a. doi: 10.1109/ACCESS.2021.3107975.
  13. Deep learning for anomaly detection in time-series data: Review, analysis, and guidelines. IEEE Access, 9:120043–120065, 2021b.
  14. Lipschitz Functions. Lecture notes in mathematics. Springer Nature, Cham, Switzerland, 1 edition, May 2019.
  15. Deep learning for time series anomaly detection: A survey, 2022.
  16. Modeling extreme events in time series prediction. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD ’19, pp.  1114–1122, New York, NY, USA, 2019. Association for Computing Machinery. ISBN 9781450362016. doi: 10.1145/3292500.3330896. URL https://doi.org/10.1145/3292500.3330896.
  17. Finder: A novel approach of change point detection for multivariate time series. Appl. Intell., 52(3):2496–2509, February 2022.
  18. Automated Multi-Dataset analysis (AMDA): an on-line database and analysis tool for heliospheric and planetary plasma data. Planet. Space Sci., (105214):105214, April 2021.
  19. A comparative study of detecting anomalies in time series data using LSTM and TCN models. 2021.
  20. Granjon, P. The CuSum algorithm - a small review. Technical report, June 2013. URL https://hal.science/hal-00914697.
  21. Real-time Change-Point detection: A deep neural network-based adaptive approach for detecting changes in multivariate time series data. Expert Syst. Appl., 209(118260):118260, December 2022.
  22. Event detection from time series data. In Proceedings of the Fifth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’99, pp.  33–42, New York, NY, USA, 1999. Association for Computing Machinery. ISBN 1581131437. doi: 10.1145/312129.312190. URL https://doi.org/10.1145/312129.312190.
  23. Annual variations in the martian bow shock location as observed by the mars express mission. J. Geophys. Res. Space Phys., 121(11):11,474–11,494, November 2016.
  24. Learning sparse latent graph representations for anomaly detection in multivariate time series. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, New York, NY, USA, August 2022. ACM.
  25. Hoffman, M. J. Continuity of inverse functions. Math. Mag., 48(2):66, March 1975.
  26. Multilayer feedforward networks are universal approximators. Neural Netw., 2(5):359–366, January 1989.
  27. A machine learning based credit card fraud detection using the GA algorithm for feature selection. J. Big Data, 9(1), December 2022.
  28. Jaccard, P. Étude comparative de la distribution florale dans une portion des alpes et du jura. 1901.
  29. Testing for a change in mean after changepoint detection. J. R. Stat. Soc. Series B Stat. Methodol., 84(4):1082–1104, September 2022.
  30. A novel deep learning approach for anomaly detection of time series data. Scientific Programming, 2021:1–11, 2021. doi: 10.1155/2021/6636270. URL https://doi.org/10.1155/2021/6636270.
  31. Krawczyk, B. Learning from imbalanced data: open challenges and future directions. Prog. Artif. Intell., 5(4):221–232, November 2016.
  32. Anomaly detection with generative adversarial networks for multivariate time series. 2018.
  33. Automatic change-point detection in time series via deep learning, 2023.
  34. An LSTM-autoencoder architecture for anomaly detection applied on compressors audio data. Computational and Mathematical Methods, 2022:1–22, September 2022.
  35. Event detection in marine time series data. In Hölldobler, S., Peñaloza, R., and Rudolph, S. (eds.), KI 2015: Advances in Artificial Intelligence, pp.  279–286, Cham, 2015. Springer International Publishing. ISBN 978-3-319-24489-1.
  36. A survey of statistical, machine learning, and deep learning-based anomaly detection techniques for time series. In Garg, D., Narayana, V. A., Suganthan, P. N., Anguera, J., Koppula, V. K., and Gupta, S. K. (eds.), Advanced Computing, pp.  221–234, Cham, 2023. Springer Nature Switzerland. ISBN 978-3-031-35644-5.
  37. MTEDS: Multivariant time series-based encoder-decoder system for anomaly detection. Comput. Intell. Neurosci., 2022:4728063, September 2022.
  38. Mathématiques pour l’ingénieur. ATAN, Association Tunisienne d’Automatique et de Numérisation, 2009. URL https://hal.science/hal-00519555.
  39. Anomaly detection in QAR data using VAE-LSTM with multihead self-attention mechanism. Mob. Inf. Syst., 2022:1–14, September 2022.
  40. Rudin, W. Principles of Mathematical Analysis. Zhong yang tu shu chu ban she, Taibei Shi, Taiwan, 1967.
  41. Robust anomaly detection for multivariate time series through stochastic recurrent neural network. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, New York, NY, USA, July 2019. ACM.
  42. A test of the mean square error criterion for restrictions in linear regression. Journal of the American Statistical Association, 63(322):558–572, 1968. ISSN 01621459. URL http://www.jstor.org/stable/2284027.
  43. Credit card fraud detection - machine learning methods. In 2019 18th International Symposium INFOTEH-JAHORINA (INFOTEH). IEEE, March 2019.
  44. LSTM-GAN-XGBOOST based anomaly detection algorithm for time series data. In 2020 11th International Conference on Prognostics and System Health Management (PHM-2020 Jinan). IEEE, October 2020.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets