Spatial–Temporal Convolutional Model for Urban Crowd Density Prediction Based on Mobile-Phone Signaling Data

Fu, Xiao; Yu, Guanyi; Liu, Zhiyuan

doi:10.1109/tits.2021.3131337

Cited by 20 publications

(5 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The application of such micro dynamic models as Cellular Automata Model and Multi-Agent System has created a method for predicting the spatialtemporal distribution and activity of urban population based on dynamics (Dorff et al, 2021;Kontou et al, 2018;Qbouche & Rhoulami, 2022). It brings the decision-making and transfer of micro agents into the scope of modelling, and tries to explain the impact and changes of local interaction on the overall system by establishing a transfer function of its own state and domain state (Fu, Yu & Liu, 2021). However, the complexity and confusion of population activities are relatively higher, so the simple and subjective conversion rules based on the mathematical statistical model will oversimplify the whole dynamic process (Ghadi et al, 2022).…”

Section: Methods For Population Activity Prediction Based On Dynamicsmentioning

confidence: 99%

Spatial–Temporal Distribution Prediction Method of Urban Population Density through Behaviour–Environment Agent Model（BEM）

Yang¹,

Shi²,

Yi³

et al. 2022

Preprint

View full text Add to dashboard Cite

Based on the interrelationship between the built environment and spatial–temporal distribution of population density, this paper proposes a method to predict the spatial–temporal distribution of urban population density using the depth residual network model (ResNet) of neural network. This study used the time-sharing data of mobile phone users provided by the China Mobile Communications Corporation to predict the time–space sequence of the steady-state distribution of population density. Firstly, 40 prediction databases were constructed according to the characteristics of built environment and the spatial–temporal distribution of population density. Thereafter, the depth residual model ResNet was used as the basic framework to construct the behaviour–environment agent model (BEM) for model training and prediction. Finally, the average percentage error index was used to evaluate the prediction results. The results revealed that the accuracy rate of prediction results reached 76.92% in the central urban area of the verification case. The proposed method can be applied to prevent urban public safety incidents and alleviate pandemics. Moreover, this method can be practically applied to enable the construction of a “smart city” for improving the efficient allocation of urban resources and traffic mobility.

show abstract

Section: Methods For Population Activity Prediction Based On Dynamicsmentioning

confidence: 99%

Spatial–Temporal Distribution Prediction Method of Urban Population Density through Behaviour–Environment Agent Model（BEM）

Yang¹,

Shi²,

Yi³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Furno et al discover that functional differences between regions are not only dependent on trajectories but also relate to the time of duration and arrival [13]. In addition, Fu et al propose a novel spatial-temporal convolutional model based on mobile-phone signaling data, which can analyze the difference between areas by extracting the density and location of crowds [14].…”

Section: Related Workmentioning

confidence: 99%

Exploring the regional function in Shanghai and New York City

Yu,

Wu,

Wang

2024

International Conference on Smart Transportation and City Engineering (STCE 2023)

View full text Add to dashboard Cite

The exponential growth of data in the modern city makes it possible to calculate the dissimilitude between different urban regions. Most recent studies divide the city by analyzing satellite or social media data, which suffer from poor resolution and timeliness. In this paper, we propose a statistical model named Power-law Dirichlet Allocation (PDA) to determine the function of each region by applying taxi trajectories and Points-of-Interest (POIs). We conduct extensive experiments using the dataset of Shanghai and New York City to verify the reasonability of our method.

show abstract

“…On this basis, more work focuses on refining the extra factors existing in traffic flow so as to improve the accuracy of the model in predicting future traffic flow trends. STC-CDPM [12] analyzes the trajectory of the flow of real people and extracts the extra activity features based on the POI attributes of the areas passing through during the flow, and combines them with the flow features. STUaNet [15] aims to reduce the uncertainty between the predicted value of the traffic flow and the actual data by quantifying the uncertainty of external additional influencing factors and the uncertainty caused by the variation in urban traffic changes.…”

Section: Related Workmentioning

confidence: 99%

“…Over time, traffic flow changes in a city's periphery will affect traffic flow in the core, and accurately identifying potential connections between these areas will improve the accuracy of modeling future traffic flow predictions. The graph convolution model [12][13][14][15][16] uses convolution and superposition of time and space to predict future traffic trends based on past continuous flow maps and other influencing factors. However, most of the current work is biased towards analyzing the impact of various environmental factors on local traffic flow [14,15].…”

Section: Introductionmentioning

confidence: 99%

Multi-Scale Non-Local Spatio-Temporal Information Fusion Networks for Multi-Step Traffic Flow Forecasting

Lu,

Chen,

Teng

2024

IJGI

View full text Add to dashboard Cite

Traffic flow prediction is a crucial research area in traffic management. Accurately predicting traffic flow in each area of the city over the long term can enable city managers to make informed decisions regarding the allocation of urban transportation resources in the future. The existing traffic flow prediction models either give insufficient attention to the interactions of long-lasting spatio-temporal regions or extract spatio-temporal features in a single scale, which ignores the identification of traffic flow patterns at various scales. In this paper, we present a multi-scale spatio-temporal information fusion model using non-local networks, which fuses traffic flow pattern features at multiple scales in space and time, complemented by non-local networks to construct the global direct dependence relationship between local areas and the entire region of the city in space and time in the past. The proposed model is evaluated through experiments and is shown to outperform existing benchmark models in terms of prediction performance.

show abstract

Spatial–Temporal Convolutional Model for Urban Crowd Density Prediction Based on Mobile-Phone Signaling Data

Cited by 20 publications

References 40 publications

Spatial–Temporal Distribution Prediction Method of Urban Population Density through Behaviour–Environment Agent Model（BEM）

Spatial–Temporal Distribution Prediction Method of Urban Population Density through Behaviour–Environment Agent Model（BEM）

Exploring the regional function in Shanghai and New York City

Multi-Scale Non-Local Spatio-Temporal Information Fusion Networks for Multi-Step Traffic Flow Forecasting

Contact Info

Product

Resources

About