Accident of Traffic Classification of Using Neural Networks Based on Algorithm PSO

People in traffic routes represents the ninth cause of death worldwide and it has been estimated that it will scale to the fifth position by 2030. In Chile, the situation is not very different. The authors study how to classify accidents, in order to better understand the consequences of certain traffic conditions to raise awareness and reduce the social and private costs, so in this paper it is proposed to classify the transit accident using networks algorithms based de Particle Swarm Optimization (PSO). The structure of the proposed model is calibrated with 12 input nodes representing the causes of accidents and the result that people are uninjured or injured, 9 hidden node with activation functions sigmoidal , in the case of an output neuron, which represents the conditions of the person after the accident, whether uninjured or injured. The results of propose model are 82%, 94% and 71% for accuracy, sensitivity and specificity respectively.

• Record URL:
  • https://aetransport.org/past-etc-papers/conference-papers-2013
• Supplemental Notes:
  • Abstract used by permission of Association for European Transport. Alternate title: Traffic Accident Classification with Neural Networks with PSO Algorithm.
• Corporate Authors:

  Association for European Transport (AET)

  1 Vernon Mews, Vernon Street, West Kensington
  London W14 0RL,    
• Authors:
  • Moya, Jose Fierro
  • Veas, Cecilia Montt
  • Agurto, Nibaldo Rodriguez
• Conference:
  • European Transport Conference 2013
  • Location: Frankfurt , Germany
  • Date: 2013-9-30 to 2013-10-2
• Publication Date: 2013

Language

• English

Media Info

• Media Type: Digital/other
• Features: Figures; References; Tables;
• Pagination: 10p
• Monograph Title: European Transport Conference 2013: Strands

Subject/Index Terms

• TRT Terms: Algorithms; Crash causes; Crash injuries; Data mining; Fatalities; Neural networks; Traffic crashes
• Geographic Terms: Chile
• Subject Areas: Highways; Safety and Human Factors; I81: Accident Statistics;

Filing Info

• Accession Number: 01545814
• Record Type: Publication
• Files: TRIS
• Created Date: Nov 26 2014 4:01PM