A Sample-Rebalanced Outlier-Rejected $k$ -Nearest Neighbor Regression Model for Short-Term Traffic Flow Forecasting

Short-term traffic flow forecasting is a fundamental and challenging task due to the stochastic dynamics of the traffic flow, which is often imbalanced and noisy. This paper presents a sample-rebalanced and outlier-rejected $k$ -nearest neighbor regression model for short-term traffic flow forecasting. In this model, we adopt a new metric for the evolutionary traffic flow patterns, and reconstruct balanced training sets by relative transformation to tackle the imbalance issue. Then, we design a hybrid model that considers both local and global information to address the limited size of the training samples. We employ four real-world benchmark datasets often used in such tasks to evaluate our model. Experimental results show that our model outperforms state-of-the-art parametric and non-parametric models.

[1]  Mehdi Khashei,et al.  A novel hybridization of artificial neural networks and ARIMA models for time series forecasting , 2011, Appl. Soft Comput..

[2]  Maurizio Filippone,et al.  A comparative evaluation of outlier detection algorithms: Experiments and analyses , 2018, Pattern Recognit..

[3]  Fei Guo,et al.  Constructing odd-variable RSBFs with optimal algebraic immunity, good nonlinearity and good behavior against fast algebraic attacks , 2019, Discret. Appl. Math..

[4]  Jie Cao,et al.  A multivariate short-term traffic flow forecasting method based on wavelet analysis and seasonal time series , 2018, Applied Intelligence.

[5]  Tharam S. Dillon,et al.  Optimized Configuration of Exponential Smoothing and Extreme Learning Machine for Traffic Flow Forecasting , 2019, IEEE Transactions on Industrial Informatics.

[6]  Fei-Yue Wang,et al.  Traffic Flow Prediction With Big Data: A Deep Learning Approach , 2015, IEEE Transactions on Intelligent Transportation Systems.

[7]  Gang Xiong,et al.  A k-nearest neighbor locally weighted regression method for short-term traffic flow forecasting , 2012, 2012 15th International IEEE Conference on Intelligent Transportation Systems.

[8]  Dazhi Jiang,et al.  Hybrid dual Kalman filtering model for short‐term traffic flow forecasting , 2019, IET Intelligent Transport Systems.

[9]  Liu Zhang,et al.  Translation Equivalence of Boolean Functions Expressed by Primitive Element , 2019, IEICE Trans. Fundam. Electron. Commun. Comput. Sci..

[10]  Minghui Ma,et al.  Short-Term Passenger Flow Prediction in Urban Public Transport: Kalman Filtering Combined K-Nearest Neighbor Approach , 2019, IEEE Access.

[11]  Yanyan Xu,et al.  Short-term traffic volume prediction using classification and regression trees , 2013, 2013 IEEE Intelligent Vehicles Symposium (IV).

[12]  Ashish Ghosh,et al.  Integration of deep feature extraction and ensemble learning for outlier detection , 2019, Pattern Recognit..

[13]  Daniel Cohen-Or,et al.  Outlier Detection for Robust Multi-Dimensional Scaling , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Gang Wang,et al.  Gaussian field consensus: A robust nonparametric matching method for outlier rejection , 2018, Pattern Recognit..

[15]  Feng Xia,et al.  Shared Subway Shuttle Bus Route Planning Based on Transport Data Analytics , 2018, IEEE Transactions on Automation Science and Engineering.

[16]  Zhanxing Zhu,et al.  Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting , 2017, IJCAI.

[17]  Billy M. Williams,et al.  Modeling and Forecasting Vehicular Traffic Flow as a Seasonal ARIMA Process: Theoretical Basis and Empirical Results , 2003, Journal of Transportation Engineering.

[18]  Guoqiang Han,et al.  Quantitative analysis of patients with celiac disease by video capsule endoscopy: A deep learning method , 2017, Comput. Biol. Medicine.

[19]  Danyang Li,et al.  Spatiotemporal Traffic Flow Prediction with KNN and LSTM , 2019, Journal of Advanced Transportation.

[20]  Chen-Chia Chuang,et al.  IPFCM Clustering Algorithm Under Euclidean and Hausdorff Distance Measure for Symbolic Interval Data , 2019, International Journal of Fuzzy Systems.

[21]  Gurcan Comert,et al.  An Online Change-Point-Based Model for Traffic Parameter Prediction , 2013, IEEE Transactions on Intelligent Transportation Systems.

[22]  Jianwei Chen,et al.  Factorization Meets Neural Networks: A Scalable and Efficient Recommender for Solving the New User Problem , 2020, IEEE Access.

[23]  Du Xin,et al.  A hybrid ensemble learning framework for basketball outcomes prediction , 2019, Physica A: Statistical Mechanics and its Applications.

[24]  Zhirui Ye,et al.  Short‐Term Traffic Volume Forecasting Using Kalman Filter with Discrete Wavelet Decomposition , 2007, Comput. Aided Civ. Infrastructure Eng..

[25]  Edward J. Ciaccio,et al.  Celiac Disease Detection From Videocapsule Endoscopy Images Using Strip Principal Component Analysis , 2019, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[26]  Xuelong Li,et al.  Joint Learning of Fuzzy k-Means and Nonnegative Spectral Clustering With Side Information , 2019, IEEE Transactions on Image Processing.

[27]  Yunpeng Wang,et al.  Long short-term memory neural network for traffic speed prediction using remote microwave sensor data , 2015 .

[28]  Jan H. van Schuppen,et al.  Prediction of Traffic Flow at the Boundary of a Motorway Network , 2014, IEEE Transactions on Intelligent Transportation Systems.

[29]  Jin Xin Cao,et al.  Traffic volume forecasting based on radial basis function neural network with the consideration of traffic flows at the adjacent intersections , 2014 .

[30]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[31]  Teresa Pamuła,et al.  Impact of Data Loss for Prediction of Traffic Flow on an Urban Road Using Neural Networks , 2019, IEEE Transactions on Intelligent Transportation Systems.

[32]  Zuduo Zheng,et al.  Short-term traffic volume forecasting : a k-nearest neighbor approach enhanced by constrained linearly sewing principle component algorithm , 2014 .

[33]  Xianlun Tang,et al.  Application of Bidirectional Recurrent Neural Network Combined With Deep Belief Network in Short-Term Load Forecasting , 2019, IEEE Access.

[34]  Xiangchen Li.  The symmetric intersection design and traffic control optimization , 2018 .

[35]  Hareton K. N. Leung,et al.  Hybrid $k$ -Nearest Neighbor Classifier , 2016, IEEE Transactions on Cybernetics.

[36]  Kup-Sze Choi,et al.  CNN in CT Image Segmentation: Beyond Loss Function for Exploiting Ground Truth Images , 2020, 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI).

[37]  Guoqiang Han,et al.  A Learning-Based Multimodel Integrated Framework for Dynamic Traffic Flow Forecasting , 2019, Neural Processing Letters.

[38]  Jianhua Guo,et al.  Adaptive Kalman filter approach for stochastic short-term traffic flow rate prediction and uncertainty quantification , 2014 .

[39]  Kaigui Bian,et al.  Hybrid Multi-metric K-Nearest Neighbor Regression for Traffic Flow Prediction , 2015, 2015 IEEE 18th International Conference on Intelligent Transportation Systems.

[40]  Z. Kassas,et al.  A Closed-Loop Map-Matching Approach for Ground Vehicle Navigation in GNSS-Denied Environments using Signals of Opportunity , 2018 .

[41]  Qian Chen,et al.  SVRGSA: a hybrid learning based model for short‐term traffic flow forecasting , 2019, IET Intelligent Transport Systems.

[42]  Teng Zhou,et al.  PSO-ELM: A Hybrid Learning Model for Short-Term Traffic Flow Forecasting , 2020, IEEE Access.

[43]  Guoqiang Han,et al.  δ-agree AdaBoost stacked autoencoder for short-term traffic flow forecasting , 2017, Neurocomputing.

[44]  Wenhu Tang,et al.  Deep Learning for Daily Peak Load Forecasting–A Novel Gated Recurrent Neural Network Combining Dynamic Time Warping , 2019, IEEE Access.

[45]  Paolo Frasconi,et al.  Short-Term Traffic Flow Forecasting: An Experimental Comparison of Time-Series Analysis and Supervised Learning , 2013, IEEE Transactions on Intelligent Transportation Systems.

[46]  Jing Qin,et al.  Noise-Identified Kalman Filter for Short-Term Traffic Flow Forecasting , 2019, 2019 15th International Conference on Mobile Ad-Hoc and Sensor Networks (MSN).

[47]  Yindong CHEN,et al.  Balanced Odd-Variable RSBFs with Optimum AI, High Nonlinearity and Good Behavior against FAAs , 2019, IEICE Trans. Fundam. Electron. Commun. Comput. Sci..

[48]  Yunpeng Wang,et al.  A spatiotemporal correlative k-nearest neighbor model for short-term traffic multistep forecasting , 2016 .

[49]  Yanru Zhang,et al.  A hybrid short-term traffic flow forecasting method based on spectral analysis and statistical volatility model , 2014 .

[50]  Yiwen Xu,et al.  Adaptive Multi-Kernel SVM With Spatial–Temporal Correlation for Short-Term Traffic Flow Prediction , 2019, IEEE Transactions on Intelligent Transportation Systems.

[51]  Pascal Vincent,et al.  K-Local Hyperplane and Convex Distance Nearest Neighbor Algorithms , 2001, NIPS.

[52]  Tharam S. Dillon,et al.  Neural-Network-Based Models for Short-Term Traffic Flow Forecasting Using a Hybrid Exponential Smoothing and Levenberg–Marquardt Algorithm , 2012, IEEE Transactions on Intelligent Transportation Systems.

[53]  Junjie Yang,et al.  A noise-immune Kalman filter for short-term traffic flow forecasting , 2019 .

[54]  M.A. Masnadi-Shirazi,et al.  Arima model for network traffic prediction and anomaly detection , 2008, 2008 International Symposium on Information Technology.

[55]  Kaichao Wu,et al.  A probability and integrated learning based classification algorithm for high-level human emotion recognition problems , 2020 .

[56]  Yan Li,et al.  Time-Series Representation and Clustering Approaches for Sharing Bike Usage Mining , 2019, IEEE Access.