Recognition Method of Drinking-driving Behaviors Based on PCA and RBF Neural Network

  • Yifan Sun Shandong University of Technology http://orcid.org/0000-0002-1409-6520
  • Jinglei Zhang Shandong University of Technology
  • Xiaoyuan Wang Shandong University of Technology
  • Zhangu Wang Shandong University of Technology
  • Jie Yu Shandong University of Technology
Keywords: traffic safety, drinking-driving behaviors, recognition method, principal component analysis, radial basis function neural network

Abstract

Drinking-driving behaviors are important causes of road traffic injuries, which are serious threats to the lives and property of traffic participants. Therefore, reducing the occurrences of drinking-driving behaviors has become an important problem of traffic safety research. Forty-eight male drivers and six female drivers who could drink moderate alcohol were chosen as participants. The drivers’ physiological data, operation behavior data, car running data, and driving environment data were collected by designing various virtual traffic scenes and organizing drivers to conduct driving simulation experiments. The original variables were analyzed by the Principal Component Analysis (PCA), and seven principal components were extracted as the input vector of the Radial Basis Function (RBF) neural network. The principal component data was used to train and verify the RBF neural network. The Levenberg-Marquardt (LM) algorithm was chosen to train the parameters of the neural network and build a drinking-driving recognition model based on PCA and RBF  neural network to realize an accurate recognition of drinking-driving behaviors. The test results showed that the drinking-driving recognition model based on PCA and RBF neural network could identify drinking drivers accurately during driving process with a recognition accuracy of 92.01%, and the operation efficiency of the model was high. The research can provide useful reference for prevention and treatment of drinking and  driving and traffic safety maintenance.

Author Biographies

Yifan Sun, Shandong University of Technology

School of Transportation and Vehicle Engineering

Jinglei Zhang, Shandong University of Technology

School of Transportation and Vehicle Engineering

Xiaoyuan Wang, Shandong University of Technology

School of Transportation and Vehicle Engineering

Zhangu Wang, Shandong University of Technology

School of Transportation and Vehicle Engineering

Jie Yu, Shandong University of Technology

School of Transportation and Vehicle Engineering

References

[1] Olmuş H, Erbaş S. Analysis of Traffic Accidents Caused by Drivers by Using Log-Linear Models. Promet – Traffic & Transportation. 2012;24(6): 495-504.
[2] Sheng-Cai LI, Xiao L. Statistics of industrial accidents in China during the period from January to February in 2016. Journal of Safety & Environment; 2016.
[3] González-Iglesias B, Gómez-Fraguela JA, Sobral J. Potential Determinants of Drink Driving in Young Adults. Traffic Injury Prevention. 2015;16(4).
[4] McCartt AT, Wells JK, Teoh ER. Attitudes toward in-car advanced alcohol detection technology. Traffic Injury Prevention. 2010;11(11): 156-164.
[5] Wu YC, Xia YQ, Xie P, et al. The Design of an Automotive Anti-Drunk Driving System to Guarantee the Uniqueness of Driver. International Conference on Information Engineering and Computer Science IEEE. 2009: 1-4.
[6] Li Z, Han J, Zhao X, et al. Comparison of Drunk Driving Recognizing Methods Based on KNN and SVM. Journal of transportation systems engineering and information technology. 2015;15(5): 246-251.
[7] Li YC, Sze NN, Wong SC, et al. A simulation study of the effects of alcohol on driving performance in a Chinese population. Accident Analysis and Prevention. 2016;95: 334-342.
[8] Zhao X, Zhang X, Rong J. Study of the Effects of Alcohol on Drivers and Driving Performance on Straight Road. Mathematical Problems in Engineering. 2014;2014(1): 1-9.
[9] Xu L, Qian F, Li Y, et al. Resource allocation based on quantum particle swarm optimization and RBF neural network for overlay cognitive OFDM System. Neurocomputing. 2016;173(P3): 1250-1256.
[10] Centeno LLR, Müller C, Ribeiro SM. Cognitive radio signal classification based on subspace decomposition and RBF neural networks. Wireless Networks. 2016;24(3): 1-11.
[11] Csekő LH, Kvasnica M, Lantos B. Explicit MPC-Based RBF Neural Network Controller Design with Discrete-Time Actual Kalman Filter for Semiactive Suspension. IEEE Transactions on Control Systems Technology. 2015;23(5): 1736-1753.
[12] Song E, Kim J, Lee S. Geometric Surface Reconstruction via LM Optimization algorithm. Journal of Clinical Investigation. 2015;63(3): 388-394.
[13] Zhou F, Zhu X. Earthquake Prediction Based on LM-BP Neural Network. Lecture Notes in Electrical Engineering. 2014;270: 13-20.
[14] Nguyen-Truong HT, Le HM. An implementation of the Levenberg-Marquardt algorithm for simultaneous-energy-gradient fitting using two-layer feed-forward neural networks. Chemical Physics Letters. 2015;629(1): 40-45.
[15] Li BN, Yu Q, Wang R, et al. Block PCA With Nongreedy ℓ1-Norm Maximization. IEEE Transactions on Cybernetics; 2015.
[16] Skrobot VL, Castro EVR, Pereira RCC, et al. Use of Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) in Gas Chromatographic (GC) Data in the Investigation of Gasoline Adulteration. Energy & Fuels. 2007;21(6): 5-19.
[17] Rao KD, Laxminarayana P, Reddy KC. RBF Neural Networks for Transient Identification in Nuclear Power Plants. IETE Journal of Research. 1997;43(6): 449-452.
[18] Zhang X, Zhao X, Du H, et al. Effect of different breath alcohol concentrations on driving performance in horizontal curves. Accident Analysis & Prevention. 2014;72: 401-10.
[19] Zhang XJ, Zhao XH, Jian R, et al. Study on the Individual Characteristics and Differences of Driving Behavior in Curves. Journal of Highway & Transportation Research & Development. 2015;9(1): 99-104.
[20] Fusco R, Sansone M, Petrillo A. The Use of the Levenberg–Marquardt and Variable Projection Curve-Fitting Algorithm in Intravoxel Incoherent Motion Method for DW-MRI Data Analysis. Applied Magnetic Resonance. 2015;46(5): 551-558.
Published
2018-08-30
How to Cite
1.
Sun Y, Zhang J, Wang X, Wang Z, Yu J. Recognition Method of Drinking-driving Behaviors Based on PCA and RBF Neural Network. Promet - Traffic & Transportation [Internet]. 30Aug.2018 [cited 15Oct.2018];30(4):407-1. Available from: http://www.fpz.unizg.hr/traffic/index.php/PROMTT/article/view/2657
Section
Articles