基于改进长短时记忆神经网络自适应增强算法的多天气车辆分类方法*

doi:10.19562/j.chinasae.qcgc.2020.09.015

汽车工程 ›› 2020, Vol. 42 ›› Issue (9): 1248-1255.doi: 10.19562/j.chinasae.qcgc.2020.09.015

基于改进长短时记忆神经网络自适应增强算法的多天气车辆分类方法^*

李达^1,2,3, 张照生^1,2,3, 刘鹏^1,2,3, 王震坡^1,2,3, 董昊天¹

1.北京理工大学机械与车辆学院,北京 100081;
2.北京理工大学,电动车辆国家工程实验室,北京 100081;
3.北京市电动车辆协同创新中心,北京 100081

出版日期:2020-09-25 发布日期:2020-10-19
通讯作者: 张照生,讲师,硕士生导师,E-mail:zhangzhaosheng@bit.edu.cn
基金资助:
*国家自然科学基金(61703042)和国家重点研发计划(2018YFB0105700)资助。

Vehicle Classification Method in Multi-climates Based on Modified LSTM-AdaBoost Algorithm

Li Da^1,2,3, Zhang Zhaosheng^1,2,3, Liu Peng^1,2,3, Wang Zhenpo^1,2,3, Dong Haotian¹

1. School of Mechanical Engineering, Beijing Institute of Technology, Beijing 100081;
2. Beijing Institute of Technology, National Engineering Laboratory for Electric Vehicles, Beijing 100081;
3. Collaborative Innovation Center of Electric Vehicles in Beijing, Beijing 100081

Online:2020-09-25 Published:2020-10-19

摘要/Abstract

摘要： 针对目前国内外车辆分类效果不理想和受天气影响较大的问题,本文中提出一种基于改进长短时记忆神经网络自适应增强算法(LSTM-AdaBoost)的多天气车辆分类方法,并提出一种“多层网格法”以准确地确定LSTM的超参数。首先建立地磁车辆检测系统平台和车辆分类方法,然后分析基于改进LSTM-AdaBoost的车辆分类结果,并对不同车辆分类方法和不同天气下的分类准确率进行了对比。结果表明,与最邻近结点算法和反向传播神经网络算法相比,本文所提出的方法具有较高的准确率,最高分类准确率为92.2%。暴雨、雾霾和晴天3种天气中,暴雨时的分类准确率最低,但差别不大,最大相差3.9个百分点。

关键词: 车辆分类, 地磁信号, 长短时记忆神经网络自适应增强算法, 多天气

Abstract: In view of the poor results of existing domestic and oversea vehicle classification schemes and relatively significant effects of climate on them, a multi-climate vehicle classification method based on modified LSTM-AdaBoost (long short-term memory neural network-Adaptive boosting) algorithm is proposed, and a “multi-layer grid method” is also put forward to accurately determine the hyperparameters of LSTM. Firstly, the geomagnetic vehicle detection system and vehicle classification method are established. Then the results of vehicle classification based on modified LSTM-AdaBoost are analyzed, and the classification accuracies of different vehicle classification methods and different climates are compared. The results show that compared with K-nearest neighbor and BP neural network algorithms for classification, the proposed method has higher accuracy with a highest classification accuracy of 92.2%. Among three climates of torrential rain, haze and fine day, the classification accuracy in torrential rain is lowest, but the difference is rather small, 3.9 percentage points at most

Key words: vehicle classification, geomagnetic signal, LSTM-AdaBoost algorithm, multi-climate

李达, 张照生, 刘鹏, 王震坡, 董昊天. 基于改进长短时记忆神经网络自适应增强算法的多天气车辆分类方法^*[J]. 汽车工程, 2020, 42(9): 1248-1255.

Li Da, Zhang Zhaosheng, Liu Peng, Wang Zhenpo, Dong Haotian. Vehicle Classification Method in Multi-climates Based on Modified LSTM-AdaBoost Algorithm[J]. Automotive Engineering, 2020, 42(9): 1248-1255.

参考文献

[1] XU X J, LIU Y, WANG W, et al. ITS-frame: a framework for multi-aspect analysis in the field of intelligent transportation systems[J]. IEEE Transactions on Intelligent Transportation Systems,2019,20(8):2893-2902.
[2] LI Q, WANG F, WANG J F, et al. LSTM-based SQL injection detection method for intelligent transportation system[J]. IEEE Transactions on Vehicular Technology,2019,68(5):4182-4191.
[3] ZHANG J, WANG F Y, WANG K, et al. Data-driven intelligent transportation systems: a survey[J]. IEEE Transactions on Intelligent Transportation Systems,2011,12(4):1624-1639.
[4] 文学志,方巍,郑钰辉.一种基于类Haar特征和改进AdaBoost分类器的车辆识别算法[J].电子学报,2011,39(5):1121- 1126.
[5] LI X X, YU L Y, CHANG D L, et al. Dual cross-entropy loss for small-sample fine-grained vehicle classification[J]. IEEE Transactions on Vehicular Technology,2019,68(5):4204-4212.
[6] MA Z Y, CHANG D L, XIE J Y, et al. Fine-grained vehicle classification with channel max pooling modified CNNs[J]. IEEE Transactions on Vehicular Technology,2019,68(4):3224-3233.
[7] WANG X C, ZHANG W W, WU X C, et al. Real-time vehicle type classification with deep convolutional neural networks[J]. Journal of Real-Time Image Processing,2017,16(1):5-14.
[8] TAGHVAEEYAN S, RAJAMANI R. Portable roadside sensors for vehicle counting, classification, and speed measurement[J]. IEEE Transactions on Intelligent Transportation Systems,2014,15(1):73- 83.
[9] YANG B, LEI Y Q. Vehicle detection and classification for low-speed congested traffic with anisotropic magnetoresistive sensor[J]. IEEE Sensors Journal,2015,15(2):1132-1138.
[10] 王卿.基于磁传感器的交通车辆检测与分类研究[D].苏州:苏州大学,2017.
[11] 温美玲.基于磁阻传感器的交通信息感知算法研究[D].西安:长安大学,2016.
[12] XIE Y, LIANG R Y, LIANG Z L, et al. Speech emotion classification using attention-based LSTM[J]. IEEE-Acm Transactions on Audio Speech and Language Processing,2019,27(11):1675- 1685.
[13] FISCHER T, KRAUSS C. Deep learning with long short-term memory networks for financial market predictions[J]. European Journal of Operational Research,2018,270(2):654-669.
[14] ZAZO R, LOZANO-DIEZ A, GONZALEZ-DOMINGUEZ J, et al. Language identification in short utterances using long short-term memory recurrent neural networks[J]. Plos One,2016,11(1).
[15] SUTSKEVER I. Training recurrent neural networks[D]. Toronto: University of Toronto,2013.
[16] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation,1997,9(8):1735-1780.
[17] GERS F A, SCHMIDHUBER J, CUMMINS F. Learning to forget: continual prediction with LSTM[J]. Neural Computation,2000,12(10):2451-2471.
[18] GERS F A, SCHMIDHUBER J. Recurrent nets that time and count[C]. Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, Como, Italy,2000:189- 194.
[19] FREUND Y, SCHAPIRE R E. Game theory, on-line prediction and boosting[C]. Proceedings of the ninth annual conference on computational learning theory, Desenzano del Garda, Italy,1996:325-332.
[20] SCHMIDHUBER J. Deep learning in neural networks: an overview[J]. Neural Networks,2015,61:85-117.
[21] 余浥.基于地磁的路边停车场车辆检测系统研究[D].哈尔滨:哈尔滨工程大学,2017.

基于改进长短时记忆神经网络自适应增强算法的多天气车辆分类方法^*

Vehicle Classification Method in Multi-climates Based on Modified LSTM-AdaBoost Algorithm

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

Metrics

本文评价

推荐阅读 10