This paper presents a novel identification method of driver steering characteristics based on backpropagation neural network. First, a driving simulator is built to collect required driving data. After careful analysis, three feature parameters that reflect driver steering characteristics are determined, including the average steering wheel angular speed, the standard deviation of the steering wheel angle, and the average vehicle longitudinal speed. Then, steering feature parameter vectors are extracted from raw data and clustered by the K-means algorithm. According to the clustering result, driver steering characteristics are divided into three types: cautious, average, and aggressive. Subsequently, a backpropagation neural network with two hidden layers is designed and trained to identify the types of feature parameter vectors. Verification results show that the established backpropagation neural network has high identification accuracy and good generalization ability for the identification of driver steering characteristics.
WangJZhangLZhangD, et al. An adaptive longitudinal driving assistance system based on driver characteristics. IEEE T Intell Transp2013; 14: 1–12.
2.
SahayadhasASundarajKMurugappanM. Detecting driver drowsiness based on sensors: a review. Sensors2012; 12: 16937–16953.
3.
RongbenWLieGBingliangT, et al. Monitoring mouth movement for driver fatigue or distraction with one camera. In: Proceedings of the 7th international IEEE conference on intelligent transportation systems, Washington, DC, 3–6 October 2004, pp.314–319. New York: IEEE.
4.
BergasaLMNuevoJSoteloMA, et al. Real-time system for monitoring driver vigilance. IEEE T Intell Transp2006; 7: 63–77.
5.
LeeSJJoJJungHG, et al. Real-time gaze estimator based on driver’s head orientation for forward collision warning system. IEEE T Intell Transp2011; 12: 254–267.
6.
ParkSJLimHK. Characteristics of elderly driver’s driving behavior and cognition under unexpected event using driving simulator. SAE paper 2011-01-0552, 2001.
7.
ZhaoXFangRRongJ, et al. Experiment study on comprehensive evaluation method of driving fatigue based on physiological signals. J Beijing Univ Technol2011; 37: 1511–1516.
8.
ZhangCWangHFuR. Automated detection of driver fatigue based on entropy and complexity measures. IEEE T Intell Transp2014; 15: 168–177.
9.
LópezJOPinillaACC. Driver behavior classification model based on an intelligent driving diagnosis system. In: 2012 15th international IEEE conference on intelligent transportation systems (ITSC), Anchorage, AK, 16–19 September 2012, pp.894–899. New York: IEEE.
ChiRWangJYangF, et al. A forward collision warning algorithm based on driver characteristics. In: Proceedings of the ICCTP 2010: integrated transportation systems: green, intelligent, reliable, Beijing, China, 4–8 August 2010, pp.640–652. Reston, VA: ASCE.
12.
AbdulWWenTGKamaruddinN. Understanding driver behavior using multi-dimensional CMAC. In: 2007 6th international conference on information, communications & signal processing, Singapore, 10–13 December 2007, pp.1–5. New York: IEEE.
13.
LuJFilevDPrakah-AsanteK, et al. From vehicle stability control to intelligent personal minder: real-time vehicle handling limit warning and driver style characterization. In: 2009 CIVVS ‘09 IEEE workshop on computational intelligence in vehicles and vehicular systems, Nashville, TN, 30 March–2 April 2009, pp.43–50. New York: IEEE/
14.
XiGQunY. Driver–vehicle–environment closed-loop simulation of handling and stability using fuzzy control theory. Vehicle Syst Dyn1994; 23: 172–181.
15.
YoshidaHNagaiMKamadaT, et al. Experiment and design of advanced brake assist system for active interface vehicle based on driver’s gas pedal operation. Rev Automot Eng2005; 26: 237–243.
16.
FujisawaMHasegawaTIshiiT, et al. Apparatus and method for automobile control using a control characteristic which can be adjusted by the driver. Patent 5,467,277, USA, 1995.
17.
BallGHHallDJ. A clustering technique for summarizing multivariate data. Behav Sci1967; 12: 153–155.
18.
Montazeri-GhMFotouhiANaderpourA. Driving patterns clustering based on driving features analysis. Proc IMechE, Part C: J Mechanical Engineering Science2011; 225: 1301–1317.
19.
GurudathNRileyHB. Drowsy driving detection by EEG analysis using wavelet transform and K-means clustering. Procedia Comput Sci2014; 34: 400–409.
20.
PengJGuoYFuR, et al. Multi-parameter prediction of drivers’ lane-changing behaviour with neural network model. Appl Ergon2015; 50: 207–217.
21.
ZhangXZhaoXRongJ. A study of individual characteristics of driving behavior based on Hidden Markov Model. Sens Transducer J2014; 167: 194–202.
22.
HamadaRKuboTIkedaK, et al. A comparative study of time series modeling for driving behavior towards prediction. In: 2013 Asia-Pacific Signal and Information Processing Association annual summit and conference 2013, Kaohsiung, 29 October–1 November 2013, pp.1–4. New York: IEEE.
23.
FernandezSItoT. Driver classification for intelligent transportation systems using fuzzy logic. In: 2016 IEEE 19th international conference on intelligent transportation systems (ITSC), Rio de Janeiro, Brazil, 1–4 November 2016, pp.1212–1216. New York: IEEE.
24.
LiJChengJ-HShiJ-Y, et al. Brief introduction of back propagation (BP) neural network algorithm and its improvement. In: JinDLinS. (eds) Advances in computer science and information engineering. Berlin: Springer, 2012, pp.553–558.
25.
Cheng-hanL. Realization of BP network based on neural network tool kit in MATLAB. Comput Simul2004; 5: 109–111.
