Short-Term Prediction of Passenger Demand in Multi-Zone Level: Temporal Convolutional Neural Network With Multi-Task Learning
The DOI matches its Crossref record; 34 of the 34 references it cites were found in a registry or an index.
Abstract
Accurate short-term passenger demand prediction contributes to the coordination of traffic supply and demand. This paper proposes an end-to-end multi-task learning temporal convolutional neural network (MTL-TCNN) to predict the short-term passenger demand in a multi-zone level. Along with a feature selector named spatiotemporal dynamic time warping (ST-DTW) algorithm, this proposed MTL-TCNN is quite qualified for the multi-task prediction problem with the consideration of spatiotemporal correlations. Then, based on the car-calling demand data from Didi Chuxing, Chengdu, China, and taxi demand data from the New York City, the numerical results show that the MTL-TCNN outperforms both classic methods (i.e., historical average (HA),v-support vector machine (v-SVM), and XGBoost) and the state-of-the-art deep learning approaches [e.g., long short-term memory (LSTM) and convolutional LSTM (ConvLSTM)] in both the single task learning (STL) and multi-task learning (MTL) scenarios. In summary, the proposed MTL-TCNN with the ST-DTW algorithm is a promising method for short-term passenger demand prediction in a multi-zone level.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 2×
“Inspired by these successful applications aforementioned, this study will propose a novel deep learning structure named multi-task learning temporal convolutional neural network (MTL-TCNN) with residual mappings [7] to predict the short-term passenger demand in a multi-zone level.”
BackgroundMethodHochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
XGBoost: A Scalable Tree Boosting System
Chen, T., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939785 · Cited by 54,569 · cited 1×
“3) XGBoost: XGBoost is a scalable machine learning sys-tem for tree boosting [40].”
MethodDeep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1412.3555 · Cited by 11,008 · cited 1×
“Wu et al. [26] proposed a deep learning based traffic flow prediction model with a CNN layer to learn spatial features and two Gated Recurrent Unit (GRU) layers [27] to capture temporal features of traffic flow.”
MethodA Computer Movie Simulating Urban Growth in the Detroit Region
Tobler, W. R. (1970) · Economic Geography · doi:10.2307/143141 · Cited by 9,719 · cited 1×
“Inspired by the First Law of Geography - “near things are more related than distant things” [37], this study considers spatial impacts when calculating the correlations between various tasks.”
Method(2012) · Cited by 8,009
WaveNet: a generative model for raw audio
Oord, A. V. D., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kalchbrenner, N., Senior, A., & Kavukcuoglu, K. (2016) · arXiv · doi:10.48550/arxiv.1609.03499 · Cited by 4,911 · cited 2×
“However, recent evidence indicates that some novel CNN based architectures can outperform RNN based ones in the fields of audio synthesis and machine translation [29], [30].”
BackgroundAn Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
Bai, S., Kolter, J. Z., & Koltun, V. (2018) · arXiv · doi:10.48550/arxiv.1803.01271 · Cited by 4,655 · cited 2×
“However, a large filter size k could cause the model non-convergence problem [30], which will worsen the prediction accuracy.”
BackgroundTraffic Flow Prediction With Big Data: A Deep Learning Approach
Lv, Y., Duan, Y., Kang, W., Li, Z., & Wang, F.-Y. (2014) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2014.2345663 · Cited by 3,000 · cited 1×
“[12] proposed a deep learning based stacked autoencoder (SAE) model to capture spatial and temporal correlations in the traffic flow prediction.”
BackgroundDeep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction
Zhang, J., Zheng, Y., & Qi, D. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.10735 · Cited by 2,282 · cited 1×
“[18] utilized a residual CNN to predict the citywide crowd flow.”
MethodMa, X., Tao, Z., Wang, Y., Yu, H., & Wang, Y. (2015) · Transportation Research Part C: Emerging Technologies · doi:10.1016/j.trc.2015.03.014 · Cited by 2,191 · cited 1×
“[19] employed LSTM to capture the temporal characteristics for the traffic speed prediction.”
MethodUnderstanding the Effective Receptive Field in Deep Convolutional Neural Networks
Luo, W., Li, Y., Urtasun, R., & Zemel, R. (2017) · arXiv · doi:10.48550/arxiv.1701.04128 · Cited by 1,575 · cited 1×
“is introduced to represent the capability of CNN to cover the inputs in the input sequence [31].”
BackgroundMa, X., Dai, Z., He, Z., Ma, J., Wang, Y., & Wang, Y. (2017) · Sensors · doi:10.3390/s17040818 · Cited by 1,409 · cited 1×
“[17] converted traffic speed dynamics to images, based on which CNN was”
BackgroundDeep Multi-View Spatial-Temporal Network for Taxi Demand Prediction
Yao, H., Wu, F., Ke, J., Tang, X., Jia, Y., Lu, S., Gong, P., Ye, J., & Li, Z. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11836 · Cited by 1,173
Deep Architecture for Traffic Flow Prediction: Deep Belief Networks With Multitask Learning
Huang, W., Song, G., Hong, H., & Xie, K. (2014) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2014.2311123 · Cited by 1,139 · cited 1×
“[13] predicted traffic flow via a two-layer deep learning structure, i.”
BackgroundDeep learning for short-term traffic flow prediction
Polson, N. G., & Sokolov, V. O. (2017) · Transportation Research Part C: Emerging Technologies · doi:10.1016/j.trc.2017.02.024 · Cited by 1,015 · cited 1×
“Polson and Sokolov [16] predicted traffic flow by a deep learning model composed of a linear model and a sequence of tanh layers, which is able to capture spatiotemporal dependencies of traffic flow in an urban area.”
BackgroundA hybrid deep learning based traffic flow prediction method and its understanding
Wu, Y., Tan, H., Qin, L., Ran, B., & Jiang, Z. (2018) · Transportation Research Part C: Emerging Technologies · doi:10.1016/j.trc.2018.03.001 · Cited by 798 · cited 1×
“[26] proposed a deep learning based traffic flow prediction model with a CNN layer to learn spatial features and two Gated Recurrent Unit (GRU) layers [27] to capture temporal features of traffic flow.”
MethodKe, J., Zheng, H., Yang, H., & Chen, X. (. (2017) · Transportation Research Part C: Emerging Technologies · doi:10.1016/j.trc.2017.10.016 · Cited by 726 · cited 3×
“Meanwhile, inspired by the previous studies [2], [5], Time variables (including time-of-day and day-of-week) are incorporated in the model by one-hot encoding, which are also treated as the auxiliary variables (c.f., Fig.”
BackgroundMethodPredicting Taxi–Passenger Demand Using Streaming Data
Moreira-Matias, L., Gama, J., Ferreira, M., Mendes-Moreira, J., & Damas, L. (2013) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2013.2262376 · Cited by 721 · cited 1×
“Moreira-Matias et al. [9] incorporated the time varying passion model and autoregressive integrated moving average (ARIMA) to predict the taxi demand.”
BackgroundSpatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks
Yu, H., Wu, Z., Wang, S., Wang, Y., & Ma, X. (2017) · Sensors · doi:10.3390/s17071501 · Cited by 618 · cited 1×
“[25]”
T-Finder: A Recommender System for Finding Passengers and Vacant Taxis
Yuan, N. J., Zheng, Y., Zhang, L., & Xie, X. (2013) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2012.153 · Cited by 432 · cited 1×
“[8] presented a probabilistic approach to model”
Deep Learning: A Generic Approach for Extreme Condition Traffic Forecasting
Yu, R., Li, Y., Shahabi, C., Demiryurek, U., & Liu, Y. (2017) · Proceedings of the 2017 SIAM International Conference on Data Mining · doi:10.1137/1.9781611974973.87 · Cited by 412 · cited 1×
“[20] applied LSTM and a stacked autoencoder to describe the temporal relations for the traffic state prediction”
MethodKoesdwiady, A., Soua, R., & Karray, F. (2016) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2016.2585575 · Cited by 367 · cited 1×
“[14] incorporated a DBN and a decision-level data fusion scheme to predict traffic flow with weather information.”
MethodReal-Time Prediction of Taxi Demand Using Recurrent Neural Networks
Xu, J., Rahmatizadeh, R., Boloni, L., & Turgut, D. (2018) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2017.2755684 · Cited by 300 · cited 1×
“Xu et al. [11] employed LSTM and mixture density networks to carry out the citywide taxi demand prediction.”
BackgroundThe Symmetric Time-Warping Problem : From Continuous to Discrete
Kruskall, J. B. (1983) · Cited by 274
Tong, Y., Chen, Y., Zhou, Z., Chen, L., Wang, J., Yang, Q., Ye, J., & Lv, W. (2017) · Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/3097983.3098018 · Cited by 271 · cited 1×
“[6] proposed a unified linear regression model with high-dimensional features to capture spatiotemporal dependencies during the passenger demand prediction.”
BackgroundOptimized Structure of the Traffic Flow Forecasting Model With a Deep Learning Approach
Yang, H.-F., Dillon, T. S., & Chen, Y.-P. P. (2017) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2016.2574840 · Cited by 263 · cited 1×
“[15] applied a stacked autoencoder Levenberg-Marquardt model to build a deep learning architecture for the traffic flow prediction.”
MethodDeepSD: Supply-Demand Prediction for Online Car-Hailing Services Using Deep Neural Networks
Wang, D., Cao, W., Li, J., & Ye, J. (2017) · 2017 IEEE 33rd International Conference on Data Engineering (ICDE) · doi:10.1109/icde.2017.83 · Cited by 197 · cited 2×
“Meanwhile, inspired by the previous studies [2], [5], Time variables (including time-of-day and day-of-week) are incorporated in the model by one-hot encoding, which are also treated as the auxiliary variables (c.f., Fig.”
BackgroundMethodPredicting Multi-step Citywide Passenger Demands Using Attention-based Neural Networks
Zhou, X., Shen, Y., Zhu, Y., & Huang, L. (2018) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3159652.3159682 · Cited by 168 · cited 1×
“[3] employed convolutional long shortterm memory (ConvLSTM) to capture spatial and temporal relations for the short-term passenger demand prediction.”
MethodDong, N., Huang, H., & Zheng, L. (2015) · Accident Analysis & Prevention · doi:10.1016/j.aap.2015.05.018 · Cited by 167 · cited 1×
“[39], v-SVM is employed here.”
Self-citationMapping to Cells: A Simple Method to Extract Traffic Dynamics from Probe Vehicle Data
He, Z., Zheng, L., Chen, P., & Guan, W. (2017) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.12251 · Cited by 102 · cited 1×
“years [21], [22].”
Self-citationA Framework for Passengers Demand Prediction and Recommendation
Zhang, K., Feng, Z., Chen, S., Huang, K., & Wang, G. G. (2016) · IEEE International Conference on Services Computing · doi:10.1109/scc.2016.51 · Cited by 78 · cited 1×
“Zhang et al. [10] utilized an exponential weighted moving average (EWMA) method to predict passenger demand hotspots so as to provide the recommendations for taxi drivers.”
MethodSelf-citationAdaptive Pooling in Multi-instance Learning for Web Video Annotation
Liu, D., Zhou, Y., Sun, X., Zha, Z.-J., & Zeng, W. (2017) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2017.46 · Cited by 46 · cited 1×
“A spatial adaptive max pooling [33] (i.”
Metadata
- Authors
- Zhang, K., Liu, Z., & Zheng, L.
- Venue
- IEEE Transactions on Intelligent Transportation Systems
- Published
- 2020-04
- Volume
- 21
- Issue
- 4
- Pages
- 1480-1490
- ISSN
- 1524-9050 (ISSN-L)
- 1558-0016
- OpenAlex
- W2946782700
- Cited by
- 170
- References
- 34
- FWCI
- 13.80
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.