DeepSTN+: Context-Aware Spatial-Temporal Neural Network for Crowd Flow Prediction in Metropolis

Lin, Ziqian; Feng, Jie; Lu, Ziyang; Li, Yong; Jin, Depeng

doi:10.1609/aaai.v33i01.33011020

Cited by 206 publications

(87 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traffic prediction plays a key role in traffic management, and has received wide attention over the years. Essentially, traffic prediction aims at predicting future values of traffic conditions, such as taxi demand [17], traffic speed [11] and crowd flows [18]. Inspired by the ability of RNN to model the correlation of sequential data, RNNs [8,9] were adopted for traffic prediction problems.…”

Section: Related Workmentioning

confidence: 99%

“…Recently, several studies further considered spatial correlation by treating the traffic data as a regular image [17][18][19][20][21] or a graph [7,[9][10][11][12][13][14][22][23][24][25] with geographical attributes (e.g., distance, connectivity) among city regions, road segments, etc., to represent the spatial correlation. Among them, [17] proposed a local CNN method on the image to consider the correlation of taxi demand among spatially nearby city regions.…”

Section: Related Workmentioning

confidence: 99%

“…Among them, [17] proposed a local CNN method on the image to consider the correlation of taxi demand among spatially nearby city regions. [18] employed a ConvPlus model on the grid structure of city to model the long-range spatial dependency among the crowd flows in different regions. [7] employed a spectral graph convolution on the graph to extract the meaningful spatial features of road traffic speed.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

STP-TrellisNets: Spatial-Temporal Parallel TrellisNets for Metro Station Passenger Flow Prediction

Sun

Zhu

et al. 2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

Recent years have witnessed a drastic increase in the number of urban metro passengers, which inevitably causes the overcrowdedness in the metro systems of many cities. Clearly, an accurate prediction of passenger flows at metro stations is critical for a variety of metro system management operations, such as line scheduling and staff preallocation, that help alleviate such overcrowdedness. Thus, in this paper, we aim to address the problem of accurately predicting metro station passenger (MSP) flows. Similar to other traffic data, such as road traffic volume and highway speed, MSP flows are also spatial-temporal in nature. However, existing methods for other traffic prediction tasks are usually suboptimal to predict MSP flows due to MSP flows' unique spatial-temporal characteristics. As a result, we propose a novel deep learning framework STP-TrellisNets, which for the first time augments the newly-emerged temporal convolutional framework TrellisNet for spatial-temporal prediction. The temporal module of STP-TrellisNets (named CP-TrellisNets) employs two TrellisNets in serial to jointly capture the short-and long-term temporal correlation of MSP flows. In parallel to CP-TrellisNets, its spatial module (named GC-TrellisNet) adopts a novel transfer flow-based metric to characterize the spatial correlation among MSP flows, and implements multiple diffusion graph convolutional networks (DGCNs) in time-series order with their outputs connected to a TrellisNet to capture the dynamics of such spatial correlation. Clearly, GC-TrellisNet essentially integrates TrellisNet with graph convolution, and empowers TrellisNet with the ability to capture dynamic graph-structured correlation. We conduct extensive experiments with two large-scale real-world automated fare collection datasets, which contain respectively about 1.5 billion records in Shenzhen, China and 70 million records in Hangzhou, China. The experimental results demonstrate that STP-TrellisNets outperforms the state-of-the-art baselines. CCS CONCEPTS • Information systems → Spatial-temporal systems; Data mining; • Computing methodologies → Neural networks.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

STP-TrellisNets: Spatial-Temporal Parallel TrellisNets for Metro Station Passenger Flow Prediction

Sun

Zhu

et al. 2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

show abstract

“…Ziqian et al propose DeepSTN+, a deep learning-based convolutional model, to predict crowd flows in the metropolis. The spatial resolution in the study is about 20 km, while the time intervals are 30 minute and one hour, but the whole study areas are two cities, Beijing and New York [26]. The study [27] proposed DeepFlowFlex, a graph-based model to jointly predict inflows and outflows for each region of arbitrary shape and size in a city.…”

Section: Related Workmentioning

confidence: 99%

The Prediction of Finely-Grained Spatiotemporal Relative Human Population Density Distributions in China

Zheng

Zhang

2020

IEEE Access

View full text Add to dashboard Cite

China's transportation industry has been experiencing huge changes and the travelling frequency of citizens becomes higher and higher and more and more diversified in a short time period. The analysis and deep research on the short-term change of population density in the city-level spatial resolution are worthy of further exploration. In this study, we first used two linear regression models to build relationships between the 2010 census density, predicted 2020 census density and the Tencent density respectively to test the usability of Tencent positioning data. The Pearson's correlation coefficients r 0.58 (p<0.01) and 0.54 (p<0.01) demonstrates good positive correlations between the ground truth (census data) and the geographic spatiotemporal big data (Tencent positioning data), which could be used to represent the relative human population density distribution in China. Then we use the human population distribution based on the Tencent positioning dataset of China in every hour of the first 21 days, to predict the hourly distribution in the next week by seasonal autoregressive-integrated-moving-average (SARIMA) and a convolutional long short-term memory (ConvLSTM) models respectively, with the 50×50 km of spatial resolution. The total average of the ConvLSTM model's Root Mean Square Error (RMSE) is 139.0, while the SARIMA's one is three times greater than the value. And the coefficient of determination (R 2) values of ConvLSTM model is higher than 0.9, while the other ones are about 0.78. Comparing the two results in both time and space concludes that: the evaluation results reflected by RMSE and R 2 showed that the two models are both suitable for the prediction of Tencent density distribution in finely-grained time and space. Nevertheless, the predicted density correlated much better with the tested data at temporal and spatial scales when using ConvLSTM compared to SARIMA, and the capability of prediction in space by ConvLSTM model is more stable. INDEX TERMS Prediction, human population density distribution, SARIMA, ConvLSTM, Tencent positioning data, deep learning, Geographic spatiotemporal big data. Zhi Zheng received a BSc degree in Urban Planning from Peking University, China, in 2016. He is currently pursuing the Ph.D. degree in China academy of science and now a visiting student in National University of Singapore. His research interests include regional development, global production networks, GIS and Remote sensing.

show abstract

“…[30,31] simulated and predicted large-scale human mobility under big disaster (earthquake) situation. Furthermore, in addition to trajectory-based methods, by aggregating citywide crowd density into mesh-grids, [16,23,37,43,44] predicted citywide crowd in-flow and out-flow by using Convolution Neural Network (CNN) to capture the spatial dependencies among the mesh-grids. Cityprophet [18] predicted city-scale irregularity about crowd density using transit app logs.…”

Section: Urban Computingmentioning

confidence: 99%

DualSIN

Chen

Jiang

Yang

et al. 2020

Proceedings of the 28th International Conference on Advances in Geographic Information Systems

View full text Add to dashboard Cite

Nowadays, GPS devices have increased explosively and produced huge amounts of trajectory data related to people's outgoing. Through those big location data, many researches aim to analyze human mobility for urban development, such as human movement prediction/modeling, POI (Point-Of-Interest) recommendation. However, trajectory data only contains timestamp and location information. The intention of human movement is not explicit so that it is hard to understand why people go to somewhere. The intention prior to the activity could be of great significance for analyzing and predicting human mobility, which has not been taken into consideration by the existing researches until the present. Thus, in this study, we propose a brand-new concept called human intentional mobility, aiming to employ intention information to predict people's outgoing. We carefully utilize user's search query to sense his intention as well as the intensity. For instance, if a user searches a certain POI for many times in a short period, it will represent a relatively high intention to go there. Then, to fully utilize this intention representation for predicting whether user will visit searched POI or not, we specially design Dual Sequential Interaction Network (DualSIN) as a novel and unique deep-learning model, which can effectively capture the sophisticated interactions among two kinds of sequential information (i.e., search sequence and mobility sequence) and typical categorical information (i.e., user attributes). Last, we evaluate our model on real-world dataset collected from Yahoo! Japan portal application, and demonstrate that it can achieve superior satisfactory performances to the-state-of-the-art models on multiple POI search queries. CCS CONCEPTS • Information systems → Recommender systems; Information systems applications; • Human-centered computing → * Equal contribution.

show abstract

DeepSTN+: Context-Aware Spatial-Temporal Neural Network for Crowd Flow Prediction in Metropolis

Cited by 206 publications

References 15 publications

STP-TrellisNets: Spatial-Temporal Parallel TrellisNets for Metro Station Passenger Flow Prediction

STP-TrellisNets: Spatial-Temporal Parallel TrellisNets for Metro Station Passenger Flow Prediction

The Prediction of Finely-Grained Spatiotemporal Relative Human Population Density Distributions in China

DualSIN

Contact Info

Product

Resources

About