پیش‌بینی کوتاه‌مدت سرعت ترافیک با استفاده از شبکه‌های عصبی بازگشتی (RNN)

توکلی, عماد; حاجی حسینلو, منصور

doi:10.22119/jte.2022.342446.2600

پیش‌بینی کوتاه‌مدت سرعت ترافیک با استفاده از شبکه‌های عصبی بازگشتی (RNN)

نوع مقاله : علمی - پژوهشی

نویسندگان

¹ کارشناسی ارشد، گروه مهندسی راه و ترابری، دانشکده مهندسی عمران، دانشگاه صنعتی خواجه نصیرالدین طوسی، تهران، ایران

² دانشیار، گروه مهندسی راه و ترابری، دانشکده مهندسی عمران، دانشگاه صنعتی‌خواجه‌ نصیرالدین‌طوسی، تهران، ایران

10.22119/jte.2022.342446.2600

چکیده

پیش بینی ترافیک، به عنوان بخش مهمی از سیستم‌های حمل و نقل هوشمند، نقش مهمی در نظارت بر وضعیت ترافیک ایفا می‌کند. با توجه به اینکه بسیاری از مطالعات کار پیش‌بینی سرعت ترافیک را با مدل‌های یادگیری عمیق انجام داده‌اند، همچنان پژوهشی بر روی پیش‌بین سرعت ترافیک در فصل‌های مختلف انجام نشده است.همچنین با توجه به تأثیرات مهم عوامل مکانی-زمانی و عملکرد عالی شبکه‌های عصبی بازگشتی (RNN) در زمینه تحلیل سری‌های زمانی، در این مقاله، یکی از شبکه‌های عصبی یادگیری عمیق که ویژگی‌های واحد بازگشتی گیتی تزریقی (FI_GRU) در داده‌های زمانی متوالی را ترکیب می‌کنند، پیشنهاد شده است. داده‌های مورد استفاده در این پژوهش از شبکه تجسم و ارزیابی فعال در شهر سیاتل ایالت متحده بدست آمده است. این پژوهش سه فصل بهار، تابستان و پاییز و چهار مدل یادگیری عمیق شامل LSTM وGRU و ConvLSTM و BiLSTM و یک مدل کم عمق SVM در سه گام زمانی ۵دقیقه، ۱۰دقیقه و۱۵ دقیقه باهم مقایسه کرده است، نتایج این تحقیق نشان می‌دهد، مدل پیشنهادی در فصل‌های مختلف اختلافی چشمگیری نداشته است، و همچنین چهار مدل یادگیری عمیق ومدل SVM ، در فصل‌های مختلف اختلاف قابل توجه نداشته‌اند ، نتایج دیگرنشان می‌دهد هرچه بازه گام‌های زمانی بیشتر می‌شود خطاها بیشتر و دقت مدل کاهش پیدا می‌کند، با توجه به نتایج بدست آمده دقت مدل FI-GRUنسبت به کمترین دقت مدل یادگیری عمیق (BiLSTM)۵۲/۰درصد بیشتر است، و دقت مدل پیشنهادی نسبت به مدل کم‌عمق (SVM) ۲۴/۱درصد بیشتر است و همچنین مدل پیشنهادی برای پیش‌بینی سرعت ترافیک در گام زمانی ۵ دقیقه ۴۴/۱درصد بهتر عمل کرده است.

کلیدواژه‌ها

20.1001.1.20086598.1402.15.1.10.8

عنوان مقاله [English]

Short-Term Prediction of Traffic Speed using Recurrent Neural Networks (RNN)

نویسندگان [English]

Emad Tavakoli ¹
Mansour Hadji Hosseinlou ²

¹ M.Ss., Civil Engineering Faculty, K.N. Toosi University of Technology, Tehran, Iran

² Associate Professor, Civil Engineering Faculty, K.N. Toosi University of Technology, Tehran, Iran

چکیده [English]

Traffic forecasting, as an important part of intelligent transportation systems, plays an important role in monitoring traffic conditions. Given that many studies have done traffic prediction work with deep learning models, no research has been done on traffic speed prediction in different chapters. Considering the important effects of spatio-temporal factors and the excellent performance of recursive neural networks in the field of time series analysis, in this paper, one of the deep learning neural networks that combine the characteristics of Giti recursive neural networks in consecutive time data is proposed. The data used in this study are obtained from the active visualization and evaluation network in Seattle, USA. This research has compared three seasons of spring, summer and autumn and four deep learning models including LSTM, GRU, ConvLSTM and BiLSTM and a shallow SVM model in three time steps of 5 minutes, 10 minutes and 15 minutes. The results of this research show that the results of the proposed model There was no significant difference in different seasons, and also the four deep learning models and the SVM model did not have significant differences in different seasons and these differences can be ignored. The other results show that as the interval of time steps increases, the errors increase and the accuracy of the model decreases. According to the obtained results, the accuracy of the FI-GRU model is 0.52% higher than the lowest accuracy of the deep learning model (BiLSTM), and the accuracy of the proposed model(SVM) is 1.24% higher than the shallow learning model, as well as the proposed model for predicting traffic speed. It has performed 44.1% better in the time step of 5 minutes.

کلیدواژه‌ها [English]

Traffic Speed Prediction
Deep Learning
GRU Neural Networks
LSTM Neural Network

مراجع

Song, Yongze, Xiangyu Wang, Graeme Wright, Dominique Thatcher, Peng Wu, and Pascal Felix. "Traffic volume prediction with segment-based regression kriging and its implementation in assessing the impact of heavy vehicles." Ieee transactions on intelligent transportation systems 20, no. 1 (2018): 232-243.

Xu, Chengcheng, Yong Wang, Pan Liu, Wei Wang, and Jie Bao. "Quantitative risk assessment of freeway crash casualty using high-resolution traffic data." Reliability Engineering & System Safety 169 (2018): 299-311.

Liu, Zhaobin, and Satish Sharma. "Statistical investigations of statutory holiday effects on traffic volumes." Transportation research record 1945, no. 1 (2006): 40-48.

Cetin, Mecit, and Gurcan Comert. "Short-term traffic flow prediction with regime switching models." Transportation Research Record 1965, no. 1 (2006): 23-31.

Kumar, S. Vasantha, and Lelitha Vanajakshi. "Short-term traffic flow prediction using seasonal ARIMA model with limited input data." European Transport Research Review 7, no. 3 (2015): 1-9.

Alajali, Walaa, Wei Zhou, Sheng Wen, and Yu Wang. "Intersection traffic prediction using decision tree models." Symmetry 10, no. 9 (2018): 386.

Yin, Shen, Yuchen Jiang, Yang Tian, and Okyay Kaynak. "A data-driven fuzzy information granulation approach for freight volume forecasting." IEEE Transactions on Industrial Electronics 64, no. 2 (2016): 1447-1456.

Kuang, Li, Han Yan, Yujia Zhu, Shenmei Tu, and Xiaoliang Fan. "Predicting duration of traffic accidents based on cost-sensitive Bayesian network and weighted K-nearest neighbor." Journal of Intelligent Transportation Systems 23, no. 2 (2019): 161-174.

Zhang, Weibin, Yaoyao Feng, Kai Lu, Yuhang Song, and Yinhai Wang. "Speed prediction based on a traffic factor state network model." IEEE Transactions on Intelligent Transportation Systems 22, no. 5 (2020): 3112-3122.

Lippi, Marco, Matteo Bertini, and Paolo Frasconi. "Short-term traffic flow forecasting: An experimental comparison of time-series analysis and supervised learning." IEEE Transactions on Intelligent Transportation Systems 14, no. 2 (2013): 871-882.

Jiang, Han, Yajie Zou, Shen Zhang, Jinjun Tang, and Yinhai Wang. "Short-term speed prediction using remote microwave sensor data: machine learning versus statistical model." Mathematical Problems in Engineering 2016 (2016).

Hinton, Geoffrey E., and Ruslan R. Salakhutdinov. "Reducing the dimensionality of data with neural networks." science 313, no. 5786 (2006): 504-507.

Huang, Wenhao, Guojie Song, Haikun Hong, and Kunqing Xie. "Deep architecture for traffic flow prediction: deep belief networks with multitask learning." IEEE Transactions on Intelligent Transportation Systems 15, no. 5 (2014): 2191-2201.

Lv, Yisheng, Yanjie Duan, Wenwen Kang, Zhengxi Li, and Fei-Yue Wang. "Traffic flow prediction with big data: a deep learning approach." IEEE Transactions on Intelligent Transportation Systems 16, no. 2 (2014): 865-873.

Zhang, Weibin, Yinghao Yu, Yong Qi, Feng Shu, and Yinhai Wang. "Short-term traffic flow prediction based on spatio-temporal analysis and CNN deep learning." Transportmetrica A: Transport Sc(2019).

Qu, Licheng, et al. "Features injected recurrent neural networks for short-term traffic speed prediction." Neurocomputing 451 (2021): 290-304.

Ma, Xiaolei, Zhimin Tao, Yinhai Wang, Haiyang Yu, and Yunpeng Wang. "Long short-term memory neural network for traffic speed prediction using remote microwave sensor data." Transportation Research Part C: Emerging Technologies 54 (2015): 187-197.

Tian, Yan, Kaili Zhang, Jianyuan Li, Xianxuan Lin, and Bailin Yang. "LSTM-based traffic flow prediction with missing data." Neurocomputing 318 (2018): 297-305.

Zhao, Zheng, Weihai Chen, Xingming Wu, Peter CY Chen, and Jingmeng Liu. "LSTM network: a deep learning approach for short-term traffic forecast." IET Intelligent Transport Systems 11, no. 2 (2017): 68-75.

Chen, Deqi, Xuedong Yan, Shurong Li, Xiaobing Liu, and Liwei Wang. "Long Short-Term Memory Neural Network for Traffic Speed Prediction of Urban Expressways Using Floating Car Data." In Green Connected Automated Transportation and Safety, pp. 773-787. Springer, Singapore, 2022.

Dai, Guowen, Changxi Ma, and Xuecai Xu. "Short-term traffic flow prediction method for urban road sections based on space–time analysis and GRU." IEEE Access 7 (2019): 143025-143035.

Ma, Dongfang, Bowen Sheng, Sheng Jin, Xiaolong Ma, and Peng Gao. "Short-term traffic flow forecasting by selecting appropriate predictions based on pattern matching." IEEE Access 6 (2018): 75629-75638.

Saleh, Khaled, Mohammed Hossny, and Saeid Nahavandi. "Contextual recurrent predictive model for long-term intent prediction of vulnerable road users." IEEE Transactions on Intelligent Transportation Systems 21, no. 8 (2019): 3398-3408.

Abduljabbar, Rusul L., Hussein Dia, and Pei-Wei Tsai. "Development and evaluation of bidirectional LSTM freeway traffic forecasting models using simulation data." Scientific reports 11, no. 1 (2021): 1-16.

Cheng, Wei, Jiang-lin Li, Hai-Cheng Xiao, and Li-na Ji. "Combination predicting model of traffic congestion index in weekdays based on LightGBM-GRU." Scientific reports 12, no. 1 (2022): 1-13.

Bin, Mu, and Zhen Lin. "GCN model combined with Bi-GRU for traffic prediction." In 2nd International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2022), vol. 12259, pp. 613-618. SPIE, 2022.

Zhang, Hong, Xiaoming Wang, Jie Cao, Minan Tang, and Yirong Guo. "A multivariate short-term traffic flow forecasting method based on wavelet analysis and seasonal time series." Applied Intelligence 48, no. 10 (2018): 3827-3838.

Luo, Xianglong, Danyang Li, and Shengrui Zhang. "Traffic flow prediction during the holidays based on DFT and SVR." Journal of Sensors 2019 (2019).

Liu, Meiyu, and Jing Shi. "A cellular automata traffic flow model combined with a BP neural network based microscopic lane changing decision model." Journal of Intelligent Transportation Systems 23, no. 4 (2019): 309-318.

Luo, Xianglong, Danyang Li, Yu Yang, and Shengrui Zhang. "Spatiotemporal traffic flow prediction with KNN and LSTM." Journal of Advanced Transportation 2019 (2019).

An, Jiyao, Li Fu, Meng Hu, Weihong Chen, and Jiawei Zhan. "A novel fuzzy-based convolutional neural network method to traffic flow prediction with uncertain traffic accident information." Ieee Access 7 (2019): 20708-20722.

Rumelhart, David E., Geoffrey E. Hinton, and Ronald J. Williams. Learning internal representations by error propagation. California Univ San Diego La Jolla Inst for Cognitive Science, 1985.

Chherawala, Youssouf, Partha Pratim Roy, and Mohamed Cheriet. "Feature set evaluation for offline handwriting recognition systems: application to the recurrent neural network model." IEEE transaction (2015).

Yao, Zengwei, Zihao Wang, Weihuang Liu, Yaqian Liu, and Jiahui Pan. "Speech emotion recognition using fusion of three multi-task learning-based classifiers: HSF-DNN, MS-CNN and LLD-RNN." Speech Communication 120 (2020): 11-19.

FRANÇOIS CHOLLET, (Deep Learning with Python), Toni Arritola, (2017).

Nazar, Kamal, and Max A. Bramer. "Concept dispersion, feature interaction and their effect on particular sources of bias in machine learning." Knowledge-Based Systems 11, no. 5-6 (1998): 275-283.

Wu, Kai, Jing Liu, Penghui Liu, and Shanchao Yang. "Time series prediction using sparse autoencoder and high-order fuzzy cognitive maps." IEEE transactions on fuzzy systems 28, no. 12 (2019): 3110-3121.

Vlachas, Pantelis R., Jaideep Pathak, Brian R. Hunt, Themistoklis P. Sapsis, Michelle Girvan, Edward Ott, and Petros Koumoutsakos. "Backpropagation algorithms and reservoir computing in recurrent neural networks for the forecasting of complex spatiotemporal dynamics." Neural Networks 126 (2020): 191-217.