Earticle

초록

영어

Dangerous signal mining method of dangerous goods transport vehicles and how to improve the accuracy of the mining are studied in the paper. There are many dangerous conditions such as high temperature, high pressure and other dangerous condition caused by the influence of the external factors such as friction in the transportation process of dangerous goods. If people can discover these dangerous condition signals as soon as possible, they can deal with them as soon as possible, which can effectively reduce the transport accidents and loss. The dangerous condition signals change as the interference of different nonlinear random mutation is present. The traditional signal mining methods have not a good solution to properly capture abnormal signal nonlinear changes, which causing flammable signal detection in the transport of dangerous goods inaccurate. The paper proposes a dangerous signal mining model based on the characteristics association mining algorithm for dangerous goods transport vehicles. First, the paper studies Cluster analysis theory and present the model for dangerous signal mining for dangerous goods transport vehicles. Second, the paper present wavelet transform model for the data extraction from transport vehicle status signal feature, and present a new mining model based the characteristics association data mining algorithm for dangerous signal mining, which can improve the accuracy of the mining. Finally, the experiment was done and shown that the new mining model for dangerous goods transport vehicles dangerous signal mining, can greatly improve the accuracy of the excavation.

목차

Abstract
 1. Introduction
 2. The Dangerous Signal Mining Model for Dangerous Goods Transport Vehicles
  2.1. Cluster Analysis
  2.2. Centroid-based Clustering
  2.3. The Model of High-risk Signal Detection
 3. Optimization of the Dangerous Signal Mining Model
  3.1 The Data Extraction from Transport Vehicle Status Signal Feature
  3.2 Characteristics Association Data Mining to enable better High-risk Signal Mining
 4. Experiment Results Analysis
 5. Conclusion
 References

키워드

저자

• Shengpu Li [ Collage of Computer Science and Technology, Pingdingshan University, Pingdingshan, Henan, China ]
• Xiaohui Wang [ Collage of Computer Science and Technology, Pingdingshan University, Pingdingshan, Henan, China ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Control and Automation

• 간기

  월간

• pISSN

  2005-4297

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605