Driving Style Classification Model Based on a Multi-label Semi-supervised Learning Algorithm

LI Mingjun, ZHANG Zhenghao, SONG Xiaolin, CAO Haotian, YI Binlin

Abstract

 This paper designs an experimental scheme based on the driving simulation platform and collects driver's operation information and vehicle status information synchronously. Six characteristic parameters are selected to recognize the driving style. The principal component analysis (PCA) algorithm is used to extract the multi-feature parameters and the first three principal components are used as the input features of the driving style recognition model. The K-means method is used for data labeling. Based on the principles of supervised support vector machine (SVM) method and inductive multi-label classification with unlabeled data (iMLCU) approach, the driving style recognition models of SVM and iMLCU are established, respectively. By adjusting the trained dataset ratios between the labeled and the unlabeled data, the accuracy of driving style recognition between the two models is compared. The results show that iMLCU has better driving style recognition than SVM. The semi-supervised iMLCU model can improve the recognition ability of driving style by using unlabeled samples.

 

Keywords:  driving style,  principal component analysis,  K-means clustering,  support vector machines,  multi-label semi-supervised classification with unlabeled data



Full Text:

PDF


References


LAN F C,LI S C,CHEN J Q,et al. Comprehensive approach for trajectory optimization of autopilot vehicles considering handling stability [J]. Journal of Hunan University (Natural Sciences), 2019,46(10):36—45. (In Chinese)

CAO H T,ZHAO S,SONG X L,et al. An optimal hierarchical framework of the trajectory following by convex optimization for highly automated driving vehicles [J]. Vehicle System Dynamics, 2019,57(9):1287—1317.

SONG X L,ZHOU N,HUANG Z Y,et al. An improved RRT algorithm of local path planning for vehicle collision avoidance[J].Journal of Hunan University (Natural Sciences),2017,44(4):30—37. (In Chinese)

CARSTEN O,KIRCHER K,JAMSON S. Vehicle-based studies of driving in the real world:the hard truth [J]. Accident Analysis & Prevention,2013,58:162—174.

ZENG C,CAI F T,LIU L,et al. Analysis of vehicle fuel consumption under different driving methods[J]. Traffic Energy Saving and Environmental Protection,2011(1):31—34. (In Chinese)

WANG W S,XI J Q,CHEN H Y. Modeling and recognizing driver behavior based on driving data:a survey [J]. Mathematical Problems in Engineering,2014(1):1—20.

CHU D F,DENG Z J,HE Y,et al. Curve speed model for driver assistance based on driving style classification [J]. IET Intelligent Transport Systems,2017,11(8):501—510.

QIND T,ZHAN S,ZENG Y P,et al. Hybrid vehicle energy management strategy based on driving style recognition[J]. Journal of Mechanical Engineering,2016,52(8):162—169.(In Chinese)

CHEN J R,WU Y F,WU B. Driver behavior spectrum analysis method based on vehicle driving data [J]. Computer Applications, 2018,38(7):92—98.(In Chinese)

SHI B,XU L,HU J,et al. Evaluating driving styles by normalizing

KOH D W,KANG H B. Smartphone-based modeling and detection of aggressiveness reactions in senior drivers[C]//2015 IEEE Intelligent Vehicles Symposium(IV). Seoul,South Korea:IEEE,2015: 12—17.

JIN H,LI M. A study on the driving style recognition in the vehicle starting condition based on the modified Fisher discrimination [J]. Journal of Beijing Institute of Technology,2020,(3):262—266. (In Chinese)

BENDER A,AGAMENNONI G,WARD J R,et al. An unsupervised approach for inferring driver behavior from naturalistic driving data [J]. IEEE Transactions on Intelligent Transportation Systems, 2015,16(6):3325—3336.

GUARDIOLA C,PLA B,REIG A. Modelling driving behavior and its impact on the energy management problem in hybrid electric vehicles[J]. International Journal of Computer Mathematics,2014,91 (1):147—156.

AOUDE G S,DESARAJU V R,STEPHENS L H,et al. Driver behavior classification at intersections and validation on large naturalistic data set [J]. IEEE Transactions on Intelligent Transportation Systems,2012,13(2):724—736.

KARGINOVA N,BYTTNER S,SVENSSON M. Data-driven methods for classification of driving styles in buses [J]. SAE Technical Paper,2012-01-0744.

CHANDRASIRI N P,NAWA K,ISHII A. Driving skill classification in curve driving scenes using machine learning[J]. Journal of Modern Transportation,2016,24(3):196—206.

WU J P,DU Y M,QI G Q,et al. Leveraging longitudinal driving behavior data with data mining techniques for driving style analysis [J]. IET Intelligent Transport Systems,2015,9(8):792—801.

DEUTSCH H P. Principle component analysis: derivatives and internal models [M]. Basingstroke:Palgrave Macmillan,2004:793- 804.


Refbacks

  • There are currently no refbacks.