CFP last date
15 April 2024
Reseach Article

Outliers Detection in Sensor Time Series using Robust moving Least Squares

by Crislanio de Souza Macedo, Jose Everardo Bessa Maia
International Journal of Applied Information Systems
Foundation of Computer Science (FCS), NY, USA
Volume 12 - Number 33
Year of Publication: 2020
Authors: Crislanio de Souza Macedo, Jose Everardo Bessa Maia
10.5120/ijais2020451884

Crislanio de Souza Macedo, Jose Everardo Bessa Maia . Outliers Detection in Sensor Time Series using Robust moving Least Squares. International Journal of Applied Information Systems. 12, 33 ( September 2020), 1-5. DOI=10.5120/ijais2020451884

@article{ 10.5120/ijais2020451884,
author = { Crislanio de Souza Macedo, Jose Everardo Bessa Maia },
title = { Outliers Detection in Sensor Time Series using Robust moving Least Squares },
journal = { International Journal of Applied Information Systems },
issue_date = { September 2020 },
volume = { 12 },
number = { 33 },
month = { September },
year = { 2020 },
issn = { 2249-0868 },
pages = { 1-5 },
numpages = {9},
url = { https://www.ijais.org/archives/volume12/number33/1097-2020451884/ },
doi = { 10.5120/ijais2020451884 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2023-07-05T19:10:40.628189+05:30
%A Crislanio de Souza Macedo
%A Jose Everardo Bessa Maia
%T Outliers Detection in Sensor Time Series using Robust moving Least Squares
%J International Journal of Applied Information Systems
%@ 2249-0868
%V 12
%N 33
%P 1-5
%D 2020
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Sensors are ubiquitous elements, whether through smart phones and other personal devices, or via wireless sensor networks, body area networks or IoT in general. However, due to noise, intermittent operation or message loss, sensor time series often arrive with outliers at processing centers. In this work, the problem of detecting isolated outliers in sensor time series is addressed using Robust Moving Least Square prediction (RMLS). The performance of RMLS is compared against that of the Sequentially Discounting Autoregressive (SDAR), which is a well-established state of the art method. The results show that RMLS has performance compatible with SDAR in all tests, with the advantage that RMLS is less sensitive to outliers present in the predictors window.

References
  1. Hermine N Akouemo and Richard J Povinelli. Probabilistic anomaly detection in natural gas time series data. International Journal of Forecasting, 32(3):948–956, 2016.
  2. Peter Bodik, Wei Hong, Carlos Guestrin, Sam Madden, Mark Paskin, and Romain Thibaux. Intel lab data. Online dataset, 2004.
  3. Andrew Cook, G¨oksel Misirli, and Zhong Fan. Anomaly detection for iot time-series data: A survey. IEEE Internet of Things Journal, 2019.
  4. Pedro Galeano and Daniel Pe˜na. Finding outliers in linear and nonlinear time series. In Robustness and Complex Data Structures, pages 243–260. Springer, 2013.
  5. Federico Giannoni, Marco Mancini, and Federico Marinelli. Anomaly detection models for iot time series data. arXiv preprint arXiv:1812.00890, 2018.
  6. Mustafa Gul and F Necati Catbas. Statistical pattern recognition for structural health monitoring using time series modeling: Theory and experimental verifications. Mechanical Systems and Signal Processing, 23(7):2192–2204, 2009.
  7. Manish Gupta, Jing Gao, Charu C Aggarwal, and Jiawei Han. Outlier detection for temporal data: A survey. IEEE Transactions on Knowledge and data Engineering, 26(9):2250–2267, 2013.
  8. Milos Hauskrecht, Iyad Batal, Michal Valko, Shyam Visweswaran, Gregory F Cooper, and Gilles Clermont. Outlier detection for patient monitoring and alerting. Journal of biomedical informatics, 46(1):47–55, 2013.
  9. Yann-A¨el Le Borgne, Jean-Michel Dricot, and Gianluca Bontempi. Principal component aggregation for energy efficient information extraction in wireless sensor networks. Knowledge Discovery from Sensor Data, 2007.
  10. Xiaolei Li, Zhenhui Li, Jiawei Han, and Jae-Gil Lee. Temporal outlier detection in vehicle traffic data. In 2009 IEEE 25th International Conference on Data Engineering, pages 1319–1322. IEEE, 2009.
  11. Alberto Luce˜no. Detecting possibly non-consecutive outliers in industrial time series. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 60(2):295– 310, 1998.
  12. Jose E Bessa Maia, Angelo Brayner, and Fernando Rodrigues. A framework for processing complex queries in wireless sensor networks. ACM SIGAPP Applied Computing Review, 13(2):30–41, 2013.
  13. Allan D McQuarrie and Chih-Ling Tsai. Outlier detections in autoregressive models. Journal of Computational and Graphical Statistics, 12(2):450–471, 2003.
  14. Saeed Mehrang, Elina Helander, Misha Pavel, Angela Chieh, and Ilkka Korhonen. Outlier detection in weight time series of connected scales. In 2015 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pages 1489–1496. IEEE, 2015.
  15. Fl´avio Nunes and Jos´e Maia. Continuous monitoring in wireless sensor networks: A fuzzy-probabilistic approach. In Anais do XVI Encontro Nacional de Inteligˆencia Artificial e Computacional, pages 96–107. SBC, 2019.
  16. Giuseppe Nunnari and Valeria Nunnari. Forecasting monthly sales retail time series: A case study. In 2017 IEEE 19th Conference on Business Informatics (CBI), volume 1, pages 1–6. IEEE, 2017.
  17. Bernard Rosner et al. Fundamentals of biostatistics, 2011.
  18. Peter J Rousseeuw and Annick M Leroy. Robust regression and outlier detection, volume 589. John wiley & sons, 2005.
  19. Maximilian Schmidt and Marko Simic. Normalizing flows for novelty detection in industrial time series data. arXiv preprint arXiv:1906.06904, 2019.
  20. Jethro Shell, Simon Coupland, and Eric Goodyer. Fuzzy data fusion for fault detection in wireless sensor networks. In 2010 UK Workshop on Computational Intelligence (UKCI), pages 1–6. IEEE, 2010.
  21. Jun-ichi Takeuchi and Kenji Yamanishi. A unifying framework for detecting outliers and change points from time series. IEEE transactions on Knowledge and Data Engineering, 18(4):482–492, 2006.
  22. Yee Lin Tan, Vivek Sehgal, and Hamid Haidarian Shahri. Sensoclean: Handling noisy and incomplete data in sensor networks using modeling. Main, pages 1–18, 2005.
  23. Jussi Tolvi et al. Outliers in eleven finnish macroeconomic time series. Finnish Economic Papers, 14(1):14–32, 2001.
  24. Bin Wang, Xiao-Chun Yang, Guo-Ren Wang, and Ge Yu. Outlier detection over sliding windows for probabilistic data streams. Journal of Computer Science and Technology, 25(3):389–400, 2010.
  25. Christine Wright and David Booth.Water treatment control using the joint estimation outlier detection method. Environmental Modeling & Assessment, 6(1):77–82, 2001.
  26. Kenji Yamanishi and Jun-ichi Takeuchi. A unifying framework for detecting outliers and change points from nonstationary time series data. In Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining, pages 676–681, 2002.
  27. Chunyong Yin, Sun Zhang, Jin Wang, and Neal N Xiong. Anomaly detection based on convolutional recurrent autoencoder for iot time series. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2020.
  28. Yufeng Yu, Yuelong Zhu, Shijin Li, and Dingsheng Wan. Time series outlier detection based on sliding window prediction. Mathematical problems in Engineering, 2014, 2014.
  29. Yusheng Zhou, Rufu Qin, Huiping Xu, Shazia Sadiq, and Yang Yu. A data quality control method for seafloor observatories: the application of observed time series data in the east china sea. Sensors, 18(8):2628, 2018.
Index Terms

Computer Science
Information Sciences

Keywords

Outlier Detection Sensor Time Series Robust Moving Least Square Sequentially Discounting Autoregressive Linear Prediction