Keiichi Ochiai, Masayuki Terada, Makoto Hanashima, Hiroaki Sano, Y. Usuda
In a disaster situation, local and municipal governments need to distribute relief supplies and provide administrative support to evacuees. Although people are supposed to evacuate to evacuation shelters designated by local governments, some people take refuge at non-designated facilities, called non-designated evacuation shelters , due to unavoidable circumstances such as damages on the access routes to designated evacuation shelters. Upon occurrence of a disaster, therefore, it is necessary for the local governments to quickly find the locations of non-designated evacuation shelters. In this paper, we propose a method to detect non-designated evacuation shelters based on autoencoder (AE)-based anomaly detection using real-time population dynamics generated from operation data of cellular phone networks. We assume that reconstruction errors of an AE model include both the errors due to characteristic differences between locations and the errors due to anomalies in population dynamics. Thus, we propose to use the ratio of the reconstruction error before and after the earthquake to determine the threshold of anomaly detection. We evaluate the performance of the proposed method on data from three actual earthquakes in Japan. The evaluation results show that our reconstruction-error-based approach can achieve better accuracy for the actual disaster data compared to a baseline method that exploits statistical anomaly detection.
{"title":"Detection of Non-designated Evacuation Shelters from Real-time Population Dynamics using Autoencoder-based Anomaly Detection","authors":"Keiichi Ochiai, Masayuki Terada, Makoto Hanashima, Hiroaki Sano, Y. Usuda","doi":"10.1145/3643679","DOIUrl":"https://doi.org/10.1145/3643679","url":null,"abstract":"\u0000 In a disaster situation, local and municipal governments need to distribute relief supplies and provide administrative support to evacuees. Although people are supposed to evacuate to evacuation shelters designated by local governments, some people take refuge at non-designated facilities, called\u0000 non-designated evacuation shelters\u0000 , due to unavoidable circumstances such as damages on the access routes to designated evacuation shelters. Upon occurrence of a disaster, therefore, it is necessary for the local governments to quickly find the locations of non-designated evacuation shelters. In this paper, we propose a method to detect non-designated evacuation shelters based on autoencoder (AE)-based anomaly detection using real-time population dynamics generated from operation data of cellular phone networks. We assume that reconstruction errors of an AE model include both the errors due to characteristic differences between locations and the errors due to anomalies in population dynamics. Thus, we propose to use the ratio of the reconstruction error before and after the earthquake to determine the threshold of anomaly detection. We evaluate the performance of the proposed method on data from three actual earthquakes in Japan. The evaluation results show that our reconstruction-error-based approach can achieve better accuracy for the actual disaster data compared to a baseline method that exploits statistical anomaly detection.\u0000","PeriodicalId":43641,"journal":{"name":"ACM Transactions on Spatial Algorithms and Systems","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2024-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140489925","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Recommendation system concentrates on quickly matching products to consumer’s needs which plays a major role in improving user experiences and increase conversion rate. Travel recommendation has become a hot topic in both industry and academia with the development of the tourism industry. Nevertheless, the selection of travel products entails careful consideration of various geographical factors, such as departure and destination. Meanwhile, due to the limitation of finance and time, users browse and purchase travel products less frequently than they do for traditional products, which leads to data sparsity problem in representation learning. To solve these challenges, a novel model named GHGCL (short for G eography-aware H eterogeneous G raph C ontrastive L earning) is proposed for recommending travel products. Concretely, we model the travel recommender system as an heterogeneous information network with geographical information, and capture diverse user preferences from local and high-order structures. Especially, we design two kinds of contrastive learning tasks for better user and travel product representation learning. The multi-view contrastive learning aims to bridge the gap between network schema and meta-path view representations. The meta-path contrastive learning focuses on modeling the coarse-grained commonality between different meta-paths from the perspective of different geographical factors, i.e., departure and destination. We assess the performance of GHGCL by performing a series of experiments on a real-world dataset and the results clearly verify its superiority as compared to the baseline methods.
推荐系统专注于根据消费者的需求快速匹配产品，在改善用户体验和提高转化率方面发挥着重要作用。随着旅游业的发展，旅游推荐已成为业界和学术界的热门话题。然而，旅游产品的选择需要仔细考虑出发地和目的地等各种地理因素。同时，由于资金和时间的限制，用户浏览和购买旅游产品的频率低于传统产品，这就导致了表示学习中的数据稀疏问题。为了解决这些难题，我们提出了一种名为 GHGCL（G eography-aware H eterogeneous G raph C ontrastive L earning 的缩写）的新型旅游产品推荐模型。具体来说，我们将旅游推荐系统建模为一个具有地理信息的异构信息网络，并从本地和高阶结构中捕捉用户的不同偏好。特别是，我们设计了两种对比学习任务，以便更好地学习用户和旅游产品的表征。多视图对比学习旨在弥合网络模式和元路径视图表征之间的差距。元路径对比学习侧重于从不同地理因素（即出发地和目的地）的角度对不同元路径之间的粗粒度共性进行建模。我们在真实世界的数据集上进行了一系列实验，评估了 GHGCL 的性能，结果清楚地验证了它与基线方法相比的优越性。
{"title":"Geography-aware Heterogeneous Graph Contrastive Learning for Travel Recommendation","authors":"Lei Chen, Jie Cao, Weichao Liang, Qiaolin Ye","doi":"10.1145/3641277","DOIUrl":"https://doi.org/10.1145/3641277","url":null,"abstract":"\u0000 Recommendation system concentrates on quickly matching products to consumer’s needs which plays a major role in improving user experiences and increase conversion rate. Travel recommendation has become a hot topic in both industry and academia with the development of the tourism industry. Nevertheless, the selection of travel products entails careful consideration of various geographical factors, such as departure and destination. Meanwhile, due to the limitation of finance and time, users browse and purchase travel products less frequently than they do for traditional products, which leads to data sparsity problem in representation learning. To solve these challenges, a novel model named GHGCL (short for\u0000 G\u0000 eography-aware\u0000 H\u0000 eterogeneous\u0000 G\u0000 raph\u0000 C\u0000 ontrastive\u0000 L\u0000 earning) is proposed for recommending travel products. Concretely, we model the travel recommender system as an heterogeneous information network with geographical information, and capture diverse user preferences from local and high-order structures. Especially, we design two kinds of contrastive learning tasks for better user and travel product representation learning. The multi-view contrastive learning aims to bridge the gap between network schema and meta-path view representations. The meta-path contrastive learning focuses on modeling the coarse-grained commonality between different meta-paths from the perspective of different geographical factors,\u0000 i.e.,\u0000 departure and destination. We assess the performance of GHGCL by performing a series of experiments on a real-world dataset and the results clearly verify its superiority as compared to the baseline methods.\u0000","PeriodicalId":43641,"journal":{"name":"ACM Transactions on Spatial Algorithms and Systems","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2024-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139607734","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mingliang Hou, Feng Xia, Xin Chen, V. Saikrishna, Honglong Chen
Understanding and managing public transportation systems require capturing complex spatio-temporal correlations within datasets. Existing studies often use predefined graphs in graph learning frameworks, neglecting shifted spatial and long-term temporal correlations, which are crucial in practical applications. To address these problems, we propose a novel bus station profiling framework to automatically infer the spatio-temporal correlations and capture the shifted spatial and long-term temporal correlations in the public transportation dataset. The proposed framework adopts and advances the graph learning structure through the following innovative ideas: (1) Designing an adaptive graph learning mechanism to capture the interactions between spatio-temporal correlations rather than relying on pre-defined graphs; (2) Modeling shifted correlation in shifted spatial graphs to learn fine-grained spatio-temporal features; (3) Employing self-attention mechanism to learn the long-term temporal correlations preserved in public transportation data. We conduct extensive experiments on three real-world datasets and exploit the learned profiles of stations for the station passenger flow prediction task. Experimental results demonstrate that the proposed framework outperforms all baselines under different settings and can produce meaningful bus station profiles.
{"title":"Adaptive Spatio-Temporal Graph Learning for Bus Station Profiling","authors":"Mingliang Hou, Feng Xia, Xin Chen, V. Saikrishna, Honglong Chen","doi":"10.1145/3636459","DOIUrl":"https://doi.org/10.1145/3636459","url":null,"abstract":"Understanding and managing public transportation systems require capturing complex spatio-temporal correlations within datasets. Existing studies often use predefined graphs in graph learning frameworks, neglecting shifted spatial and long-term temporal correlations, which are crucial in practical applications. To address these problems, we propose a novel bus station profiling framework to automatically infer the spatio-temporal correlations and capture the shifted spatial and long-term temporal correlations in the public transportation dataset. The proposed framework adopts and advances the graph learning structure through the following innovative ideas: (1) Designing an adaptive graph learning mechanism to capture the interactions between spatio-temporal correlations rather than relying on pre-defined graphs; (2) Modeling shifted correlation in shifted spatial graphs to learn fine-grained spatio-temporal features; (3) Employing self-attention mechanism to learn the long-term temporal correlations preserved in public transportation data. We conduct extensive experiments on three real-world datasets and exploit the learned profiles of stations for the station passenger flow prediction task. Experimental results demonstrate that the proposed framework outperforms all baselines under different settings and can produce meaningful bus station profiles.","PeriodicalId":43641,"journal":{"name":"ACM Transactions on Spatial Algorithms and Systems","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2023-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138591142","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Forecasting spatio-temporal correlated time series of sensor values is crucial in urban applications, such as air pollution alert, biking resource management, and intelligent transportation systems. While recent advances exploit graph neural networks (GNN) to better learn spatial and temporal dependencies between sensors, they cannot model time-evolving spatio-temporal correlation (STC) between sensors, and require pre-defined graphs, which are neither always available nor totally reliable, and target at only a specific type of sensor data at one time. Moreover, since the form of time-series fluctuation is varied across sensors, a model needs to learn fluctuation modulation. To tackle these issues, in this work, we propose a novel GNN-based model, Attention-adjusted Graph Spatio-Temporal Network (AGSTN). In AGSTN, multi-graph convolution with sequential learning is developed to learn time-evolving STC. Fluctuation modulation is realized by a proposed attention adjustment mechanism. Experiments on three sensor data, air quality, bike demand, and traffic flow, exhibit that AGSTN outperforms the state-of-the-art methods.
{"title":"Forecasting Urban Sensory Values through Learning Attention-adjusted Graph Spatio-Temporal Networks","authors":"Yi-Ju Lu, Cheng-Te Li","doi":"10.1145/3635140","DOIUrl":"https://doi.org/10.1145/3635140","url":null,"abstract":"Forecasting spatio-temporal correlated time series of sensor values is crucial in urban applications, such as air pollution alert, biking resource management, and intelligent transportation systems. While recent advances exploit graph neural networks (GNN) to better learn spatial and temporal dependencies between sensors, they cannot model time-evolving spatio-temporal correlation (STC) between sensors, and require pre-defined graphs, which are neither always available nor totally reliable, and target at only a specific type of sensor data at one time. Moreover, since the form of time-series fluctuation is varied across sensors, a model needs to learn fluctuation modulation. To tackle these issues, in this work, we propose a novel GNN-based model, Attention-adjusted Graph Spatio-Temporal Network (AGSTN). In AGSTN, multi-graph convolution with sequential learning is developed to learn time-evolving STC. Fluctuation modulation is realized by a proposed attention adjustment mechanism. Experiments on three sensor data, air quality, bike demand, and traffic flow, exhibit that AGSTN outperforms the state-of-the-art methods.","PeriodicalId":43641,"journal":{"name":"ACM Transactions on Spatial Algorithms and Systems","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2023-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138603321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Guojiang Shen, Juntao Wang, Xiangjie Kong, Zhanhao Ji, Bing Zhu, Tie Qiu
As a significant part of traffic accident prevention, abnormal driving behavior recognition has been receiving extensive attention. However, the granularity of existing abnormal driving behavior recognition is mostly at road-level, and these methods’ high complexity leads to high overhead on training and recognition. In this article, we propose a deformation gated recurrent network for lane-level abnormal driving behavior recognition. Firstly, we use conditional random field model to calculate the lane change necessity of the vehicle, which helps us to distinguish whether the lane-changing behavior is reasonable. Secondly, we propose deformation gated recurrent network (DF-GRN) and trajectory entropy to capture the implicit relationship between trajectories and shorten recognition time. Finally, we get classified results including aggressive, distracted and normal driving behavior from the network. Distracted and aggressive behavior will be marked as anomaly. The effectiveness and real-time nature of the network are verified by experiments on Hangzhou and Chengdu location datasets.
{"title":"Deformation Gated Recurrent Network for Lane-Level Abnormal Driving Behavior Recognition","authors":"Guojiang Shen, Juntao Wang, Xiangjie Kong, Zhanhao Ji, Bing Zhu, Tie Qiu","doi":"10.1145/3635141","DOIUrl":"https://doi.org/10.1145/3635141","url":null,"abstract":"As a significant part of traffic accident prevention, abnormal driving behavior recognition has been receiving extensive attention. However, the granularity of existing abnormal driving behavior recognition is mostly at road-level, and these methods’ high complexity leads to high overhead on training and recognition. In this article, we propose a deformation gated recurrent network for lane-level abnormal driving behavior recognition. Firstly, we use conditional random field model to calculate the lane change necessity of the vehicle, which helps us to distinguish whether the lane-changing behavior is reasonable. Secondly, we propose deformation gated recurrent network (DF-GRN) and trajectory entropy to capture the implicit relationship between trajectories and shorten recognition time. Finally, we get classified results including aggressive, distracted and normal driving behavior from the network. Distracted and aggressive behavior will be marked as anomaly. The effectiveness and real-time nature of the network are verified by experiments on Hangzhou and Chengdu location datasets.","PeriodicalId":43641,"journal":{"name":"ACM Transactions on Spatial Algorithms and Systems","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2023-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138606562","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-01Epub Date: 2023-11-20DOI: 10.1145/3569087
Sina Shaham, Gabriel Ghinita, Ritesh Ahuja, John Krumm, Cyrus Shahabi
Mobile apps that use location data are pervasive, spanning domains such as transportation, urban planning and healthcare. Important use cases for location data rely on statistical queries, e.g., identifying hotspots where users work and travel. Such queries can be answered efficiently by building histograms. However, precise histograms can expose sensitive details about individual users. Differential privacy (DP) is a mature and widely-adopted protection model, but most approaches for DP-compliant histograms work in a data-independent fashion, leading to poor accuracy. The few proposed data-dependent techniques attempt to adjust histogram partitions based on dataset characteristics, but they do not perform well due to the addition of noise required to achieve DP. In addition, they use ad-hoc criteria to decide the depth of the partitioning. We identify density homogeneity as a main factor driving the accuracy of DP-compliant histograms, and we build a data structure that splits the space such that data density is homogeneous within each resulting partition. We propose a self-tuning approach to decide the depth of the partitioning structure that optimizes the use of privacy budget. Furthermore, we provide an optimization that scales the proposed split approach to large datasets while maintaining accuracy. We show through extensive experiments on large-scale real-world data that the proposed approach achieves superior accuracy compared to existing approaches.
{"title":"HTF: Homogeneous Tree Framework for Differentially-Private Release of Large Geospatial Datasets with Self-Tuning Structure Height.","authors":"Sina Shaham, Gabriel Ghinita, Ritesh Ahuja, John Krumm, Cyrus Shahabi","doi":"10.1145/3569087","DOIUrl":"10.1145/3569087","url":null,"abstract":"<p><p>Mobile apps that use location data are pervasive, spanning domains such as transportation, urban planning and healthcare. Important use cases for location data rely on statistical queries, e.g., identifying hotspots where users work and travel. Such queries can be answered efficiently by building histograms. However, precise histograms can expose sensitive details about individual users. Differential privacy (DP) is a mature and widely-adopted protection model, but most approaches for DP-compliant histograms work in a data-independent fashion, leading to poor accuracy. The few proposed data-dependent techniques attempt to adjust histogram partitions based on dataset characteristics, but they do not perform well due to the addition of noise required to achieve DP. In addition, they use ad-hoc criteria to decide the depth of the partitioning. We identify <i>density homogeneity</i> as a main factor driving the accuracy of DP-compliant histograms, and we build a data structure that splits the space such that data density is homogeneous within each resulting partition. We propose a self-tuning approach to decide the depth of the partitioning structure that optimizes the use of privacy budget. Furthermore, we provide an optimization that scales the proposed split approach to large datasets while maintaining accuracy. We show through extensive experiments on large-scale real-world data that the proposed approach achieves superior accuracy compared to existing approaches.</p>","PeriodicalId":43641,"journal":{"name":"ACM Transactions on Spatial Algorithms and Systems","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10881200/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44219469","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Huiqun Huang, Suining He, Xi Yang, Mahan Tabatabaie
Accurate citywide crowd activity prediction (CAP) can enable proactive crowd mobility management and timely responses to urban events, which has become increasingly important for a myriad of smart city planning and management purposes. However, complex correlations across the crowd activities, spatial and temporal urban environment features and their interactive dependencies, and relevant external factors (e.g., weather conditions) make it highly challenging to predict crowd activities accurately in terms of different venue categories (for instance, venues related to dining, services, and residence) and varying degrees (e.g., daytime and nighttime). To address the above concerns, we propose STICAP, a citywide spatio-temporal interactive crowd activity prediction approach. In particular, STICAP takes in the location-based social network check-in data (e.g., from Foursquare/Gowalla) as the model inputs, and forecasts the crowd activity within each time step for each venue category. Furthermore, we have integrated multiple levels of temporal discretization to interactively capture the relations with historical data. Then three parallel Residual Spatial Attention Networks (RSAN) in the Spatial Attention Component exploit the hourly, daily, and weekly spatial features of crowd activities, which are further fused and processed by the Temporal Attention Component for interactive CAP. Along with other external factors such as weather conditions and holidays, STICAP adaptively and accurately forecasts the final crowd activities per venue category, enabling potential activity recommendation and other smart city applications. Extensive experimental studies based on three different real-word crowd activity datasets have demonstrated that our proposed STICAP outperforms the baseline and state-of-the-art algorithms in CAP accuracy, with an average error reduction of 35.02%
{"title":"STICAP: Spatio-Temporal Interactive Attention for Citywide Crowd Activity Prediction","authors":"Huiqun Huang, Suining He, Xi Yang, Mahan Tabatabaie","doi":"10.1145/3603375","DOIUrl":"https://doi.org/10.1145/3603375","url":null,"abstract":"Accurate citywide crowd activity prediction (CAP) can enable proactive crowd mobility management and timely responses to urban events, which has become increasingly important for a myriad of smart city planning and management purposes. However, complex correlations across the crowd activities, spatial and temporal urban environment features and their interactive dependencies, and relevant external factors (e.g., weather conditions) make it highly challenging to predict crowd activities accurately in terms of different venue categories (for instance, venues related to dining, services, and residence) and varying degrees (e.g., daytime and nighttime). To address the above concerns, we propose STICAP, a citywide spatio-temporal interactive crowd activity prediction approach. In particular, STICAP takes in the location-based social network check-in data (e.g., from Foursquare/Gowalla) as the model inputs, and forecasts the crowd activity within each time step for each venue category. Furthermore, we have integrated multiple levels of temporal discretization to interactively capture the relations with historical data. Then three parallel Residual Spatial Attention Networks (RSAN) in the Spatial Attention Component exploit the hourly, daily, and weekly spatial features of crowd activities, which are further fused and processed by the Temporal Attention Component for interactive CAP. Along with other external factors such as weather conditions and holidays, STICAP adaptively and accurately forecasts the final crowd activities per venue category, enabling potential activity recommendation and other smart city applications. Extensive experimental studies based on three different real-word crowd activity datasets have demonstrated that our proposed STICAP outperforms the baseline and state-of-the-art algorithms in CAP accuracy, with an average error reduction of 35.02%","PeriodicalId":43641,"journal":{"name":"ACM Transactions on Spatial Algorithms and Systems","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138621022","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Editorial: Special Issue on the Best Papers from the 2021 ACM SIGSPATIAL Conference","authors":"W. Aref","doi":"10.1145/3632619","DOIUrl":"https://doi.org/10.1145/3632619","url":null,"abstract":"","PeriodicalId":43641,"journal":{"name":"ACM Transactions on Spatial Algorithms and Systems","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139198239","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Traffic data forecasting has become an integral part of the intelligent traffic system. Great efforts are spent developing tools and techniques to estimate traffic flow patterns. Many existing approaches lack the ability to model the complex and dynamic spatio-temporal relations in the traffic data, which are crucial in capturing the traffic dynamic. In this work, we propose a novel adaptive joint spatio-temporal graph learning network (AJSTGL) for traffic data forecasting. The proposed model utilizes static and adaptive graph learning modules to capture the static and dynamic spatial traffic patterns and optimize the graph learning process. A sequence-to-sequence fusion model is proposed to learn the temporal correlation and combine the output of multiple parallelized encoders. We also develop a spatio-temporal graph transformer module to complement the sequence-to-sequence fusion module by dynamically capturing the time-evolving node relations in long-term intervals. Experiments on three large-scale traffic flow datasets demonstrate that our model could outperform other state-of-the-art baseline methods.
{"title":"Adaptive Joint Spatio-Temporal Graph Learning Network for Traffic Data Forecasting","authors":"Tianyi Wang, Shu-Ching Chen","doi":"10.1145/3634913","DOIUrl":"https://doi.org/10.1145/3634913","url":null,"abstract":"Traffic data forecasting has become an integral part of the intelligent traffic system. Great efforts are spent developing tools and techniques to estimate traffic flow patterns. Many existing approaches lack the ability to model the complex and dynamic spatio-temporal relations in the traffic data, which are crucial in capturing the traffic dynamic. In this work, we propose a novel adaptive joint spatio-temporal graph learning network (AJSTGL) for traffic data forecasting. The proposed model utilizes static and adaptive graph learning modules to capture the static and dynamic spatial traffic patterns and optimize the graph learning process. A sequence-to-sequence fusion model is proposed to learn the temporal correlation and combine the output of multiple parallelized encoders. We also develop a spatio-temporal graph transformer module to complement the sequence-to-sequence fusion module by dynamically capturing the time-evolving node relations in long-term intervals. Experiments on three large-scale traffic flow datasets demonstrate that our model could outperform other state-of-the-art baseline methods.","PeriodicalId":43641,"journal":{"name":"ACM Transactions on Spatial Algorithms and Systems","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2023-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139219549","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Transportation between satellite cities or inside the city center has always been a crucial factor in contributing to a better quality of life. This article focuses on multi-criteria distributed and competitive route planning for stationary resources in regions where neither real-time nor historical availability of the targeted resource is accessible. We propose an inference-than-planning approach, with an availability inference for stationary resources in areas with no sensor coverage and a distributed routing where no information is shared among agents. We leverage the inferred availability and network structure in the searching space to suggest a two-stage algorithm with three relaxing policies: adjacent cruising, on-orbital annealing, and orbital transitioning. We take two publicly accessible parking-slot datasets from San Francisco and Melbourne for evaluation. Overall results show that the proposed availability inference model can retain decent performance. Furthermore, our proposed routing algorithm maintains the quality of solutions by achieving the Pareto-optimal between searching experience and resource utilization among baseline and state-of-the-art methods under various circumstances.
{"title":"Exploiting Network Structure in Multi-criteria Distributed and Competitive Stationary-resource Searching","authors":"Fandel Lin, Hsun-Ping Hsieh","doi":"10.1145/3569937","DOIUrl":"https://doi.org/10.1145/3569937","url":null,"abstract":"Transportation between satellite cities or inside the city center has always been a crucial factor in contributing to a better quality of life. This article focuses on multi-criteria distributed and competitive route planning for stationary resources in regions where neither real-time nor historical availability of the targeted resource is accessible. We propose an inference-than-planning approach, with an availability inference for stationary resources in areas with no sensor coverage and a distributed routing where no information is shared among agents. We leverage the inferred availability and network structure in the searching space to suggest a two-stage algorithm with three relaxing policies: adjacent cruising, on-orbital annealing, and orbital transitioning. We take two publicly accessible parking-slot datasets from San Francisco and Melbourne for evaluation. Overall results show that the proposed availability inference model can retain decent performance. Furthermore, our proposed routing algorithm maintains the quality of solutions by achieving the Pareto-optimal between searching experience and resource utilization among baseline and state-of-the-art methods under various circumstances.","PeriodicalId":43641,"journal":{"name":"ACM Transactions on Spatial Algorithms and Systems","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2023-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139258484","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：