Education, Science, Technology, Innovation and Life
Open Access
Sign In

Study on Abnormal Data Preprocessing and Preliminary Analysis Method in Landslide Monitoring System

Download as PDF

DOI: 10.23977/acss.2022.060112 | Downloads: 20 | Views: 789

Author(s)

Mingyang Guo 1

Affiliation(s)

1 Hunan University of Science & Technology, Xiangtan, Hunan, 411201, China

Corresponding Author

Mingyang Guo

ABSTRACT

In the process of landslide monitoring, abnormal sensors will lead to abnormal alarm at the monitoring points, and the occurrence of this behavior will reduce the accuracy and adaptability of the early warning system. Since the data collected by the automatic monitoring equipment is an electronic signal, it needs to be transformed into the actual physical measurement value, and there is usually a certain noise in the measurement data in this process. At the same time, the monitoring equipment may have abnormal values or noise due to certain interference due to the influence of other external factors, or the monitoring data may be missing due to equipment failure. In most cases, when the original data is directly used to predict the real evolution trend of the slope, the deviation between the prediction results and the actual situation is too large or the model can not be used to predict at all. Therefore, the original measurement data needs to be processed before using the prediction model to analyze and estimate the landslide state. Furthermore, the existence of outliers will have a great impact on the estimation of sample autocorrelation, partial correlation and prediction model parameters, resulting in prediction failure. Since the occurrence of outliers is often unknown, it is very important to detect outliers and estimate their possible impact.

KEYWORDS

Landslide monitoring, Abnormal data, Noise filtering, Outlier elimination

CITE THIS PAPER

Mingyang Guo, Study on Abnormal Data Preprocessing and Preliminary Analysis Method in Landslide Monitoring System. Advances in Computer, Signals and Systems (2022) Vol. 6: 90-96. DOI: http://dx.doi.org/10.23977/acss.2022.060112.

REFERENCES

[1] Chaoyang He. Research on key technology and application of landslide real-time monitoring and early warning system.2020.Chengdu University of Technology,PhD dissertation.
[2] Junqing Fan. Research on multi-source heterogeneous sensor information fusion method for landslide monitoring.2015.China University of Geosciences, PhD dissertation.
[3] Zhiwei Wang. Research on multi-source heterogeneous monitoring data fusion algorithm of loess landslide.2020.Chang'an University,MA thesis.
[4] Chuowen Feng, et al. "Comparative study on detection methods of abnormal wind power data." New technology of electrical energy 40.07(2021):55-61. doi:CNKI:SUN:DGDN.0.2021-07-007.
[5] Bo Yu, et al. "Sensitive data identification and abnormal behavior analysis of unstructured documents." Journal of Intelligent Systems: doi:10.11992/tis.202104028.
[6] Deping Gao. "Anomaly detection of mobile terminal network data based on isolated forest." information technology .06(2021):125-129. doi:10.13274/j.cnki.hdzj.2021.06.023.
[7] Ge Yang, et al. "Research on abnormal value identification technology of dam safety monitoring data based on singular spectrum analysis." Hydropower generation .
[8] Jiaxu Huang, Xianhui Zeng,and Chenjun Shi. "Research on equipment energy consumption anomaly recognition algorithm based on real-time data stream feature extraction."Information technology and network security 40.05(2021):45-50. doi:10.19358/j.issn.2096-5133.2021.05.008.
[9] Li Hui, et al. "Toward data anomaly detection for automated structural health monitoring: Exploiting generative adversarial nets and autoencoders." Structural Health Monitoring 20.4(2021): doi:10.1177/1475921720924601.
[10] Zhang Ting, et al. "A new method of data missing estimation with FNN-based tensor heterogeneous ensemble learning for internet of vehicle." Neurocomputing 420.(2021): doi:10.1016/J.NEUCOM.2020.09.042.
[11] "Alibaba Group Holding Limited; Patent Application Titled "Method And Device For Determining Data Anomaly" Published Online (USPTO 20200329063)." Internet Business Newsweekly .(2020).
[12] Boukela Lynda, et al. "An outlier ensemble for unsupervised anomaly detection in honeypots data." Intelligent Data Analysis 24.4(2020): doi:10.3233/IDA-194656.
[13] Yufei Guo.Study on prediction and early warning system of single landslide.2013.China University of Geosciences (Beijing),PhD dissertation.

Downloads: 11330
Visits: 240216

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.