Journal cover Journal topic
Natural Hazards and Earth System Sciences An interactive open-access journal of the European Geosciences Union
https://doi.org/10.5194/nhess-2017-325
© Author(s) 2017. This work is distributed under
the Creative Commons Attribution 4.0 License.
Research article
26 Oct 2017
Review status
This discussion paper is a preprint. It is a manuscript under review for the journal Natural Hazards and Earth System Sciences (NHESS).
Bag-of-words-based anomaly-detection principal component analysis and stochastic optimization for debris flow detection and evacuation planning
Chia-Chun Kuo1, Yi-Ren Yeh2, Kuan-wen Chou3, Chien-Lin Huang3, and Ming-Che Hu1 1Department of Bioenvironmental Systems Engineering, National Taiwan University, No. 1, Sec. 4, Roosevelt Road, Taipei 10617, Taiwan
2Department of Mathematics, National Kaohsiung Normal University, No. 62, Shenjhong Road, Yanchao District, Kaohsiung, Taiwan
3hetengtech Company Limited, Rm. 6A, 2F., No. 7, Sec. 3, New Taipei Blvd., Xinzhuang Dist., New Taipei City 242, Taiwan
Abstract. Debris flows are natural disasters, with soil mass, rocks, and water traveling down a mountainside slope. Debris flows are extremely dangerous; their occurrence incurs huge losses to life and property. The purpose of this research is to develop debris flow detection and emergency evacuation systems. A bag-of-words model is established for analyzing the features of debris flow events, and an anomaly-detection principal component analysis (PCA) model is proposed to detect debris flow. Using real-time debris flow prediction and monitoring, a stochastic optimization model for evacuation planning is formulated. Case studies of debris flow detection in Shenmu village and Fengchiu, central Taiwan, are conducted. Shenmu village and Fengchiu are areas of high potential debris flow, and each has a population of around 800 people. The results show that combining bag-of-words and anomaly-detection PCA methods could predict 6 out of 8 occurrences of actual events, providing a prediction rate of 75 %. In addition, the models make 13 predictions, and 6 of them are correct, providing a prediction accuracy of 46 %. Optimal parameters (including window size, bag length, filter ratio of training data, and anomaly threshold) of the models are also examined to increase the accuracy of debris flow prediction.

Citation: Kuo, C.-C., Yeh, Y.-R., Chou, K.-W., Huang, C.-L., and Hu, M.-C.: Bag-of-words-based anomaly-detection principal component analysis and stochastic optimization for debris flow detection and evacuation planning, Nat. Hazards Earth Syst. Sci. Discuss., https://doi.org/10.5194/nhess-2017-325, in review, 2017.
Chia-Chun Kuo et al.
Chia-Chun Kuo et al.
Chia-Chun Kuo et al.

Viewed

Total article views: 138 (including HTML, PDF, and XML)

HTML PDF XML Total BibTeX EndNote
117 19 2 138 0 0

Views and downloads (calculated since 26 Oct 2017)

Cumulative views and downloads (calculated since 26 Oct 2017)

Viewed (geographical distribution)

Total article views: 138 (including HTML, PDF, and XML)

Thereof 135 with geography defined and 3 with unknown origin.

Country # Views %
  • 1

Saved

Discussed

Latest update: 18 Nov 2017
Publications Copernicus
Download
Short summary
Debris flows are natural disasters, with soil mass, rocks, and water traveling down a mountainside slope. Debris flows are extremely dangerous; their occurrence incurs huge losses to life and property. The purpose of this research is to develop debris flow detection and emergency evacuation systems. Case studies of debris flow detection in Shenmu village and Fengchiu, central Taiwan, are conducted.
Debris flows are natural disasters, with soil mass, rocks, and water traveling down a...
Share