Education, Science, Technology, Innovation and Life
Open Access
Sign In

Analysis of urban vehicle driving mode based on deep-learning method

Download as PDF

DOI: 10.23977/autml.2024.050107 | Downloads: 2 | Views: 78

Author(s)

Su Zhou 1,2, Yang Jiao 1, Jianhua Gao 1, Xiaoman Liu 1

Affiliation(s)

1 College of Automotive Studies, Tongji University, Shanghai, China
2 China-Germany Institute, Tongji University, Shanghai, China

Corresponding Author

Su Zhou

ABSTRACT

In view of the data processing difficulties in the data collection of vehicle driving behavior, the neural network structures of FCN, ResNet, LSTM and Bi-LSTM are designed and optimized. Then, ResNet and Bi-LSTM with better performance were selected for model fusion, which improved the overall performance of the model. Finally, different degrees of error disturbance are added to the test set to verify the anti-interference and generalization ability of the fusion model. The results show that the classification accuracy of the model does not decline when there is 5% disturbance in the data, maintains a high level of performance, avoids the problem of high-dimensional features after the One-hot coding, realizes the same batch training of variable length samples, and improves the efficiency of model training.

KEYWORDS

Driving behavior recognition, automatic driving, deep learning, neural network, model fusion

CITE THIS PAPER

Su Zhou, Yang Jiao, Jianhua Gao, Xiaoman Liu, Analysis of urban vehicle driving mode based on deep-learning method. Automation and Machine Learning (2024) Vol. 5: 50-61. DOI: http://dx.doi.org/10.23977/autml.2024.050107.

REFERENCES

[1] Ahmed Mobyen Uddin,Begum Shahina. Convolutional Neural Network for Driving Maneuver Identification Based on Inertial Measurement Unit (IMU) and Global Positioning System (GPS) [J]. Frontiers in Sustainable Cities, 2020.
[2] Lattanzi Emanuele, Castellucci Giacomo,Freschi Valerio. Improving Machine Learning Identification of Unsafe Driver Behavior by Means of Sensor Fusion[J]. Applied Sciences, 2020, 10(18).
[3] Gerdes A. Driver manoeuvre recognition[C]//Proc. 13th World Congress on ITS. 2006.
[4] Xie F, Wang R J, Shen S B, Sun R, Zhang B, Liu X X. Detecting driving behaviors by smartphone inertial sensors based on multi-feature convolutional neural network[J]. Journal of Chinese Inertial Technology, 2019,27(03):288-294.
[5] Chu J H, Zhang S, Tang W H, Lyu W. Driving Behavior Recognition Method Based on Tutor-Student Network[J]. Laser & Optoelectronics Progress, 2020,57(06):211-218.
[6] Xue Q W, Jiang Y M, Lu J. Risky Driving Behavior Recognition based on Trajectory Data[J]. China Journal of Highway and Transport, 2020,33(06):84-94.
[7] Zhan W, Sun L, Wang D, et al. Interaction dataset: An international, adversarial and cooperative motion dataset in interactive driving scenarios with semantic maps [J]. arXiv preprint arXiv:1910.03088, 2019.
[8] Potdar K, Pardawala T S, Pai C D. A comparative study of categorical variable encoding techniques for neural network classifiers [J]. International journal of computer applications, 2017, 175(4): 7-9.
[9] Tan M S, Lyu X, Ding L, Li X J, Deep denoising autoencoder anomaly detection method based on elastic net[J]. Computer Engineering and Design, 2020,41(06):1516-1521.
[10] Goutte C, Gaussier E. A probabilistic interpretation of precision, recall and F-score, with implication for evaluation[C]//European conference on information retrieval. Springer, Berlin, Heidelberg, 2005: 345-359
[11] Powers D M W. Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation [J]. arXiv preprint arXiv:2010.16061
[12] Kotsiantis S, Kanellopoulos D, Pintelas P. Handling imbalanced datasets: A review [J]. GESTS International Transactions on Computer Science and Engineering, 2006, 30(1): 25-36
[13] Sola J, Sevilla J. Importance of input data normalization for the application of neural networks to complex industrial problems [J]. IEEE Transactions on nuclear science, 1997, 44(3): 1464-1468.
[14] Chen Y C, Liu W. Opinion extraction and clustering of students’ teaching evaluation text based on sentiment analysis[J]. Journal of Computer Applications, 2020,40(S1):113-117.
[15] Tao Z L, Song G G, Huang X L. Survey of Crucial Technologies on CTR Prediction[J]. Journal of Communication University of China (Science and Technology), 2019,26(06):72-75+79.

Downloads: 1643
Visits: 69083

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.