A Sequential Convolution Network for Population Flow Prediction with Explicitly Correlation Modelling

Lin, Ziqian; Tong, Xia; Sun, Fangmiao; Guo, Diansheng; Li, Yong

doi:10.24963/ijcai.2020/185

Cited by 17 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 1 shows the performance of the proposed method as compared to all other baseline models. Note that the absolute value of the metrics is relatively high compared to existing works such as [3,14,15]. This is because most of the existing works aim to predict the crowd flows, that is, the number of people who move to the other regions in the corresponding time intervals.…”

Section: Performance Comaprisonmentioning

confidence: 98%

See 1 more Smart Citation

Attention-based Contextual Multi-View Graph Convolutional Networks for Short-term Population Prediction

Kubota¹,

Ohira²,

Shimizu³

2022

Preprint

View full text Add to dashboard Cite

Short-term future population prediction is a crucial problem in urban computing. Accurate future population prediction can provide rich insights for urban planners or developers. However, predicting the future population is a challenging task due to its complex spatiotemporal dependencies. Many existing works have attempted to capture spatial correlations by partitioning a city into grids and using Convolutional Neural Networks (CNN). However, CNN merely captures spatial correlations by using a rectangle filter; it ignores urban environmental information such as distribution of railroads and location of POI. Moreover, the importance of those kinds of information for population prediction differs in each region and is affected by contextual situations such as weather conditions and day of the week. To tackle this problem, we propose a novel deep learning model called Attention-based Contextual Multi-View Graph Convolutional Networks (ACMV-GCNs). We first construct multiple graphs based on urban environmental information, and then ACMV-GCNs captures spatial correlations from various views with graph convolutional networks. Further, we add an attention module to consider the contextual situations when leveraging urban environmental information for future population prediction. Using statistics population count data collected through mobile phones, we demonstrate that our proposed model outperforms baseline methods. In addition, by visualizing weights calculated by an attention module, we show that our model learns an efficient way to utilize urban environment information without any prior knowledge. CCS CONCEPTS• Human-centered computing → Ubiquitous and mobile computing; • Computing methodologies → Artificial intelligence.

show abstract

Section: Performance Comaprisonmentioning

confidence: 98%

“…Therefore, some researchers have leveraged machine learning algorithms, which have achieved great success in various fields, to apply them in spatiotemporal prediction problems [3,7,9,18]. The two popular models mainly used for spatiotemporal data analysis are Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN).…”

Section: Introductionmentioning

confidence: 99%

Attention-based Contextual Multi-View Graph Convolutional Networks for Short-term Population Prediction

Kubota¹,

Ohira²,

Shimizu³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Regarding temporal correlation, recurrent neural networks have been a widely used choice, where the inputs are usually at a fixed granularity. For example, Feng et al (2020) sliced the spatiotemporal data by hour and used neural networks to capture the temporal correlations. Lin et al (2020) extracted features by day and proposed an attention mechanism to learn the contributions of daily data features to future data.…”

Section: Related Workmentioning

confidence: 99%

Spatiotemporal Data Prediction Model Based on a Multi-Layer Attention Mechanism

Jiang

Han

Zhang

et al. 2022

International Journal of Data Warehousing and Mining

View full text Add to dashboard Cite

Spatiotemporal data prediction is of great significance in the fields of smart cities and smart manufacturing. Current spatiotemporal data prediction models heavily rely on traditional spatial views or single temporal granularity, which suffer from missing knowledge, including dynamic spatial correlations, periodicity, and mutability. This paper addresses these challenges by proposing a multi-layer attention-based predictive model. The key idea of this paper is to use a multi-layer attention mechanism to model the dynamic spatial correlation of different features. Then, multi-granularity historical features are fused to predict future spatiotemporal data. Experiments on real-world data show that the proposed model outperforms six state-of-the-art benchmark methods.

show abstract

“…Besides, many studies [21-23, 31, 36, 37] combined the CNNs with RNNs to capture the dynamic ST dependencies. In addition, [4,42] exploited the flow transitions between regions as auxiliary features to boost the predictive performance. One problem is that, these studies are inefficient to capture the global spatial dependencies, since they rely on large receptive fields achieved by stacking many convolution layers.…”

Section: Related Work 61 Grid-based Urban Flow Predictionmentioning

confidence: 99%

Fine-Grained Urban Flow Prediction

Liang

Ouyang

Sun

et al. 2021

Proceedings of the Web Conference 2021

View full text Add to dashboard Cite

Urban flow prediction benefits smart cities in many aspects, such as traffic management and risk assessment. However, a critical prerequisite for these benefits is having fine-grained knowledge of the city. Thus, unlike previous works that are limited to coarse-grained data, we extend the horizon of urban flow prediction to fine granularity which raises specific challenges: 1) the predominance of inter-grid transitions observed in fine-grained data makes it more complicated to capture the spatial dependencies among grid cells at a global scale; 2) it is very challenging to learn the impact of external factors (e.g., weather) on a large number of grid cells separately. To address these two challenges, we present a Spatio-Temporal Relation Network (STRN) to predict fine-grained urban flows. First, a backbone network is used to learn high-level representations for each cell. Second, we present a Global Relation Module (GloNet) that captures global spatial dependencies much more efficiently compared to existing methods. Third, we design a Meta Learner that takes external factors and land functions (e.g., POI density) as inputs to produce meta knowledge and boost model performances. We conduct extensive experiments on two real-world datasets. The results show that STRN reduces the errors by 7.1% to 11.5% compared to the state-of-the-art method while using much fewer parameters. Moreover, a cloud-based system called UrbanFlow 3.0 has been deployed to show the practicality of our approach.

show abstract

A Sequential Convolution Network for Population Flow Prediction with Explicitly Correlation Modelling

Cited by 17 publications

References 11 publications

Attention-based Contextual Multi-View Graph Convolutional Networks for Short-term Population Prediction

Attention-based Contextual Multi-View Graph Convolutional Networks for Short-term Population Prediction

Spatiotemporal Data Prediction Model Based on a Multi-Layer Attention Mechanism

Fine-Grained Urban Flow Prediction

Contact Info

Product

Resources

About