Online-SVR for short-term traffic flow prediction under typical and atypical traffic conditions

By Manoel Castro-Neto, Youngseon Jeong, Myong Kee Jeong, Lee D. Han. Expert systems with applications, 2009

828 citations recorded by the source corpus.

Subfields: Building and Construction, Control and Systems Engineering, Transportation

View Paper: https://www.semanticscholar.org/paper/354817a97b1bd244ff18b4985c3a24bbe0c95559

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Building and Construction

1. Yu Zheng
2. Xing Xie
3. Yinhai Wang
4. Jing Yuan
5. Li Pan
6. Yongxue Tian
7. Guangzhong Sun
8. Zhifeng Bao

In Control and Systems Engineering

1. Li Pan
2. Yongxue Tian
3. Yinhai Wang
4. Weibin Zhang
5. Zhifeng Bao
6. A. K. Qin
7. Farhana Murtaza Choudhury
8. Baihua Zheng

In Transportation

1. Yu Zheng
2. Xing Xie
3. Jing Yuan
4. Guangzhong Sun
5. Junbo Zhang
6. Zhifeng Bao
7. Yunpeng Wang
8. Xiaolei Ma

Citations in the corpus

• Spatio-Temporal Self-Supervised Learning for Traffic Flow Prediction (2022, methodology): “• SVR (Castro-Neto et al. 2009): it is a regression model widely used for time series analysis.”
• Short-term traffic flow prediction based on spatio-temporal analysis and CNN deep learning (2019, methodology): “The insensitive coefficient epsilon, epsilon-SVM (Hong 2011; Zhang et al. 2016), and its improved algorithms online-SVR (Support Vector Regression) (Castro-Neto et al. 2009) and LS-SVR (Bhagwat and Maity 2012) have also been used for traffic prediction.”
• Deep Architecture for Traffic Flow Prediction: Deep Belief Networks With Multitask Learning (2014, methodology): “Some representative methods are artificial neural networks (NNs) [3], [24], support vector regression (SVR) [2], and local weighted learning (LWL) [23].”
• Supervised Weighting-Online Learning Algorithm for Short-Term Traffic Flow Prediction (2013, background): “Several short-term prediction methods for traffic flow, including artificial intelligence and optimization-based methods, have been proposed during the last several decades [1], [8], [9], [16], [17], [31], [32], [37].”
• A Survey on Modern Deep Neural Network for Traffic Prediction: Trends, Methods and Challenges (2020, methodology): “Other types of machine learning models aside from neural network were also used, such as the kNearest Neighbor [31], [32], [33] and the Support Vector Regression [34], [35], [36].”
• Predicting Short-Term Traffic Flow by Long Short-Term Memory Recurrent Neural Network (2015, methodology): “Four classic prediction models are chosen for comparison, which are Random Walk(RW), Support Vector Machine(SVM) [3], single hidden layer Feed Forward Neural Network(FFNN) and Stacked Autoencoder(SAE) [6].”
• Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction (2017, methodology): “More advanced models were employed, including support vector machines (SVM) [7], seasonal SVM [8], Online-SVM [9], and on-line sequential extreme learning machine [10], to promote prediction accuracy by capturing the high dynamics and sensitivity of traffic flow.”
• Driving with knowledge from the physical world (2011, background): “1 Traffic Estimation There are a few projects [1][2][9][11][12][25] aiming to learn historical traffic patterns, estimate real-time traffic flows and forecast future traffic conditions on some road segments in terms of floating car data [23], such as GPS trajectories as well as Wi-Fi and GSM signals”