MFFNN and GRNN Models for Prediction of Energy Equivalent Speed Values of Involvements in Traffic Accidents

Abstract

Accident reconstruction is a scientific study field that depends on analysis, research and drawing. Scientific reconstruction of related traffic accident on computer eliminates making decisions depending on initiative or experience of the expert and yields impartial decisions and evidences especially on events like matter for the courts or forensic investigations. In this study, data collected from accident scene (police reports, skid marks, deformation situation of involvements, crush depth etc.) were inserted properly into the software called “vCrash” which is able to simulate the accident scene in 2D and 3D. Then, 784 parameters, related to calculating Energy Equivalent Speed (EES) with a prediction error, were prepared according to several accidents. These parameters were also used as teaching data for the Multi-layer Feed Forward Neural Network (MFFNN) and Generalized Regression Neural Network (GRNN) models in order to predict EES values of involvements, which give idea about severity and dissipation of deformation energy corresponding to the observed vehicle residual crush, without requirement of performing simulation for probable accidents in future. Using 10-fold cross validation on the dataset, standard error of estimates (SEE) and multiple correlation coefficients (R) of both models are calculated. The GRNN-based model yields lower SEE whereas the MFFNN-based model yields higher R.

Authors and Affiliations

Ali Can Yilmaz| Department of Automotive Engineering, Cukurova University, Adana, Turkey, Cigdem Inan Aci| Department of Computer Engineering, Cukurova University, Adana, Turkey, Kadir Aydin| Department of Automotive Engineering, Cukurova University, Adana, Turkey

Keywords

Related Articles

Comparative evaluation of pongamia biodiesel with open and re-entrant combustion chambers in a DI diesel engine

The influence of 20% blend of Pongamia Oil Methyl Ester (POME20) as alternative diesel fuel has been studied using a kirloskar made single cylinder, four stroke, direct injection diesel engine. Without altering the compr...

The Simulation of a Full Electric Vehicle Using the City Cycle

In this present study, the design and simulation of an electric vehicle again commonly being started to be used in twenty-first century have been carried out by Matlab program. A full-electric vehicle has been used as a...

Investigation of Echinops Kebericho Mesfin Seed Oil as a Biodiesel Production Feedstock: Opportunities From the Wilderness

The major energy sources of the world depend on coal, natural gasses and petroleum which are exhaustible and environmentally unfriendly. Biodiesel is a mono alkyl organic compound of long chain of fatty acids made of oil...

Evolutıon of Traffıc Noise Impacts in Amman, Jordan

Amman, the capital of Jordan has been subjected to persistent increase in road traffic due to overall increase in prosperity, fast development and expansion of economy, travel and tourism leading to the traffic noise bei...

Investigation of biodiesel fuel from canola oil using various reaction parameters

The production of biodiesel fuel from canola oil was evaluated in this study. The process of alkali-catalyzed transesterification with methanol was carried out to examine the effects of reaction variables on the formatio...

Download PDF file
  • EP ID EP3957
  • DOI -
  • Views 487
  • Downloads 22

How To Cite

Ali Can Yilmaz, Cigdem Inan Aci, Kadir Aydin (2015). MFFNN and GRNN Models for Prediction of Energy Equivalent Speed Values of Involvements in Traffic Accidents. International Journal of Automotive Engineering and Technologies, 4(2), 102-109. https://europub.co.uk/articles/-A-3957