scholarly journals ADST: Forecasting Metro Flow Using Attention-Based Deep Spatial-Temporal Networks with Multi-Task Learning

Sensors ◽  
2020 ◽  
Vol 20 (16) ◽  
pp. 4574
Author(s):  
Hongwei Jia ◽  
Haiyong Luo ◽  
Hao Wang ◽  
Fang Zhao ◽  
Qixue Ke ◽  
...  
Keyword(s):  
Traffic Management ◽  
Weather Conditions ◽  
Research Field ◽  
Superior Performance ◽  
Multi Scale ◽  
Passenger Flow ◽  
Task Learning ◽  
Temporal Correlations ◽  
Flow Prediction ◽  
Attentional Mechanism

Passenger flow prediction has drawn increasing attention in the deep learning research field due to its great importance in traffic management and public safety. The major challenge of this essential task lies in multiple spatiotemporal correlations that exhibit complex non-linear correlations. Although both the spatial and temporal perspectives have been considered in modeling, most existing works have ignored complex temporal correlations or underlying spatial similarity. In this paper, we identify the unique spatiotemporal correlation of urban metro flow, and propose an attention-based deep spatiotemporal network with multi-task learning (ADST-Net) at a citywide level to predict the future flow from historical observations. ADST-Net uses three independent channels with the same structure to model the recent, daily-periodic and weekly-periodic complicated spatiotemporal correlations, respectively. Specifically, each channel uses the framework of residual networks, the rectified block and the multi-scale convolutions to mine spatiotemporal correlations. The residual networks can effectively overcome the gradient vanishing problem. The rectified block adopts an attentional mechanism to automatically reweigh measurements at different time intervals, and the multi-scale convolutions are used to extract explicit spatial relationships. ADST-Net also introduces an external embedding mechanism to extract the influence of external factors on flow prediction, such as weather conditions. Furthermore, we enforce multi-task learning to utilize transition passenger flow volume prediction as an auxiliary task during the training process for generalization. Through this model, we can not only capture the steady trend, but also the sudden changes of passenger flow. Extensive experimental results on two real-world traffic flow datasets demonstrate the obvious improvement and superior performance of our proposed algorithm compared with state-of-the-art baselines.

scholarly journals Passenger Flow Prediction Using Smart Card Data from Connected Bus System Based on Interpretable XGBoost

2022 ◽  
Vol 2022 ◽  
pp. 1-13
Author(s):  
Liang Zou ◽  
Sisi Shu ◽  
Xiang Lin ◽  
Kaisheng Lin ◽  
Jiasong Zhu ◽  
...  
Keyword(s):  
Traffic Management ◽  
Prediction Accuracy ◽  
Nearest Neighbor ◽  
Important Variable ◽  
Management Control ◽  
Learning Models ◽  
Time Step ◽  
Passenger Flow ◽  
Temporal Correlations ◽  
Flow Prediction

Bus passenger flow prediction is a critical component of advanced transportation information system for public traffic management, control, and dispatch. With the development of artificial intelligence, many previous studies attempted to apply machine learning models to extract comprehensive correlations from transit networks to improve passenger flow prediction accuracy, given that the variety and volume of traffic data have been easily obtained. The passenger flow on a station is highly affected by various factors such as the previous time step, peak hours or nonpeak hours, and extracting the key features from the data is essential for a passenger flow prediction model. Although the neural networks, k -nearest neighbor, and some deep learning models have been adopted to mine the temporal correlations of the passenger flow data, the lack of interpretability of the influenced variables is still a big problem. Classical tree-based models can mine the correlations between variables and rank the importance of each variable. In this study, we presented a method to extract passenger flow of different routes on the station and implemented a XGBoost model to find the contributions of variables to the prediction of passenger flow. Comparing to benchmark models, the proposed model can reach state-of-the-art prediction accuracy and computational efficiency on the real-world dataset. Moreover, the XGBoost model can interpret the predicted results. It can be seen that period is the most important variable for the passenger flow prediction, and so the management of buses during peak hours should be improved.

scholarly journals Analysis of Space-Time Variation of Passenger Flow and Commuting Characteristics of Residents Using Smart Card Data of Nanjing Metro

2019 ◽  
Vol 11 (18) ◽  
pp. 4989 ◽  
Author(s):  
Wei Yu ◽  
Hua Bai ◽  
Jun Chen ◽  
Xingchen Yan
Keyword(s):  
Intelligent Transportation Systems ◽  
Traffic Management ◽  
Rapid Development ◽  
Weather Conditions ◽  
Transportation Systems ◽  
Space Time ◽  
Smart Cards ◽  
The Sustainable Development ◽  
Passenger Flow ◽  
Challenges And Opportunities

The rapid development of cities has brought new challenges and opportunities to traditional traffic management. The usage of smart cards promotes the upgrading of intelligent transportation systems, and also produces considerable big data. As an important part of the urban comprehensive transportation system, Nanjing metro has more than 1 million inbound and outbound records of traffic smart cards used by residents every day. How to process these traffic data and present them visually is an urgent problem in modern traffic management. In this study, five working days with normal weather conditions in Nanjing were selected, and the swiping records of the smart cards were extracted, and the space–time characteristics were analyzed. In terms of time analysis, this research analyzed the 24-h fluctuation of daily average passenger flow, peak hour coefficient of passenger flow, 24-h fluctuation of passenger flow on different metro lines, passenger flow intensity on different metro lines and passenger flow comparison at different stations. In spatial analysis, this study uses thermodynamic charts to represent the inflow and outflow of passengers at different stations during early and evening peak periods. The analysis results and visualized images directly reflect the area where Nanjing metro congestion is located, and also shows the commuting characteristics of residents. It can solve the problem of urban congestion, carry out the rational layout of urban functional areas, and promote the sustainable development of people and cities.

scholarly journals Pedestrian Detection at Night in Infrared Images Using an Attention-Guided Encoder-Decoder Convolutional Neural Network

2020 ◽  
Vol 10 (3) ◽  
pp. 809 ◽  
Author(s):  
Yunfan Chen ◽  
Hyunchul Shin
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Pedestrian Detection ◽  
Weather Conditions ◽  
Superior Performance ◽  
Low Resolution ◽  
Feature Maps ◽  
Camera System ◽  
Ir Camera ◽  
Multi Scale

Pedestrian-related accidents are much more likely to occur during nighttime when visible (VI) cameras are much less effective. Unlike VI cameras, infrared (IR) cameras can work in total darkness. However, IR images have several drawbacks, such as low-resolution, noise, and thermal energy characteristics that can differ depending on the weather. To overcome these drawbacks, we propose an IR camera system to identify pedestrians at night that uses a novel attention-guided encoder-decoder convolutional neural network (AED-CNN). In AED-CNN, encoder-decoder modules are introduced to generate multi-scale features, in which new skip connection blocks are incorporated into the decoder to combine the feature maps from the encoder and decoder module. This new architecture increases context information which is helpful for extracting discriminative features from low-resolution and noisy IR images. Furthermore, we propose an attention module to re-weight the multi-scale features generated by the encoder-decoder module. The attention mechanism effectively highlights pedestrians while eliminating background interference, which helps to detect pedestrians under various weather conditions. Empirical experiments on two challenging datasets fully demonstrate that our method shows superior performance. Our approach significantly improves the precision of the state-of-the-art method by 5.1% and 23.78% on the Keimyung University (KMU) and Computer Vision Center (CVC)-09 pedestrian dataset, respectively.

scholarly journals Precipitation Modeling for Extreme Weather Based on Sparse Hybrid Machine Learning and Markov Chain Random Field in a Multi-Scale Subspace

Water ◽  
2021 ◽  
Vol 13 (9) ◽  
pp. 1241
Author(s):  
Ming-Hsi Lee ◽  
Yenming J. Chen
Keyword(s):  
Machine Learning ◽  
Markov Chain ◽  
Random Field ◽  
Long Range ◽  
Weather Conditions ◽  
Extreme Weather ◽  
Prediction Algorithm ◽  
Learning Method ◽  
Multi Scale ◽  
Hybrid Machine

This paper proposes to apply a Markov chain random field conditioning method with a hybrid machine learning method to provide long-range precipitation predictions under increasingly extreme weather conditions. Existing precipitation models are limited in time-span, and long-range simulations cannot predict rainfall distribution for a specific year. This paper proposes a hybrid (ensemble) learning method to perform forecasting on a multi-scaled, conditioned functional time series over a sparse l1 space. Therefore, on the basis of this method, a long-range prediction algorithm is developed for applications, such as agriculture or construction works. Our findings show that the conditioning method and multi-scale decomposition in the parse space l1 are proved useful in resisting statistical variation due to increasingly extreme weather conditions. Because the predictions are year-specific, we verify our prediction accuracy for the year we are interested in, but not for other years.

Decision Support System for Advanced Traffic Management Through Data Fusion

2002 ◽  
Vol 1804 (1) ◽  
pp. 173-178 ◽  
Author(s):  
Lawrence A. Klein ◽  
Ping Yi ◽  
Hualiang Teng
Keyword(s):  
Data Fusion ◽  
Traffic Management ◽  
Information Sources ◽  
Partial Information ◽  
Weather Conditions ◽  
Field Testing ◽  
Traffic Operations ◽  
Dempster Shafer Theory ◽  
Classification Technique ◽  
Shafer Theory

The Dempster–Shafer theory for data fusion and mining in support of advanced traffic management is introduced and tested. Dempste–Shafer inference is a statistically based classification technique that can be applied to detect traffic events that affect normal traffic operations. It is useful when data or information sources contribute partial information about a scenario, and no single source provides a high probability of identifying the event responsible for the received information. The technique captures and combines whatever information is available from the data sources. Dempster’s rule is applied to determine the most probable event—as that with the largest probability based on the information obtained from all contributing sources. The Dempster–Shafer theory is explained and its implementation described through numerical examples. Field testing of the data fusion technique demonstrated its effectiveness when the probability masses, which quantify the likelihood of the postulated events for the scenario, reflect current traffic and weather conditions.

Sign in / Sign up

Export Citation Format

Share Document