Network data models are frequently used as a mechanism to solve wide range of problems typical for the GIS applications and transportation planning in particular. Because of their popularity and efficiency those models tend to grow in size and complexity. This growth however creates multiple scalability issues caused by the large number of network elements that have to be examined during the network traversal. In this paper we present an extension of our network model tailored towards improving the performance of hierarchical point to point solve operations. The proposed solution is based on introducing a new network edge type that we term hyperedges. We describe how hyperedges can be specified with a re-interpretation of our existing any-vertex connectivity policy on edges, discusses some modeling issues, and also provide insights of our implementation experience and the impact which those novel network elements have on the solve performance. Our solution is based on the existing database functionality (tables, joins, sorting algorithms) provided by a standard relational DBMS and has been implemented and tested and currently being shipped as a part of the ESRI ArcGIS 10.1 platform and all subsequent releases.
{"title":"Fast transportation network traversal with hyperedges: (industrial paper)","authors":"P. Bakalov, E. Hoel, Wee-Liang Heng","doi":"10.1145/2996913.2996991","DOIUrl":"https://doi.org/10.1145/2996913.2996991","url":null,"abstract":"Network data models are frequently used as a mechanism to solve wide range of problems typical for the GIS applications and transportation planning in particular. Because of their popularity and efficiency those models tend to grow in size and complexity. This growth however creates multiple scalability issues caused by the large number of network elements that have to be examined during the network traversal. In this paper we present an extension of our network model tailored towards improving the performance of hierarchical point to point solve operations. The proposed solution is based on introducing a new network edge type that we term hyperedges. We describe how hyperedges can be specified with a re-interpretation of our existing any-vertex connectivity policy on edges, discusses some modeling issues, and also provide insights of our implementation experience and the impact which those novel network elements have on the solve performance. Our solution is based on the existing database functionality (tables, joins, sorting algorithms) provided by a standard relational DBMS and has been implemented and tested and currently being shipped as a part of the ESRI ArcGIS 10.1 platform and all subsequent releases.","PeriodicalId":20525,"journal":{"name":"Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73759982","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}
Shrutilipi Bhattacharjee, Monidipa Das, S. Ghosh, S. Shekhar
Meteorological parameters are often considered as crucial factors for climatological pattern analysis. Predictions of these parameters have been studied extensively in the field of remote sensing and GIS. It is one of the most critical steps involved in most of the meteorological data mining process. Spatial interpolation is an efficient technique to yield minimal error in prediction. From existing literatures, it is evident that the land-use/land-cover (LULC) distribution of the terrain influences these parameters in a varying manner and it is important to model their behaviour for climatological analyses. However, this semantic LULC knowledge of the terrain is generally ignored in the prediction process of the meteorological parameters. Recently, we have proposed a new spatial interpolation technique, namely semantic kriging (SemK) [3,5,7], which considers the semantic LULC knowledge for land-atmospheric interaction modeling and incorporates it into the existing interpolation process for better accuracy. However, the a-priori correlation analysis of SemK ignores the effect of other nearby LULC classes on each other. This article presents a new variant of SemK, namely a-posterior probabilistic Bayesian SemK (BSemK), which extends the a-priori correlation analysis of SemK with a-posterior probabilistic analysis. The proposed approach provides more accurate estimation of the parameters. Experimentation with LST data advocates the efficacy of the proposed approach compared to the a-priori SemK and other existing interpolation techniques.
{"title":"Prediction of meteorological parameters: an a-posteriori probabilistic semantic kriging approach","authors":"Shrutilipi Bhattacharjee, Monidipa Das, S. Ghosh, S. Shekhar","doi":"10.1145/2996913.2996968","DOIUrl":"https://doi.org/10.1145/2996913.2996968","url":null,"abstract":"Meteorological parameters are often considered as crucial factors for climatological pattern analysis. Predictions of these parameters have been studied extensively in the field of remote sensing and GIS. It is one of the most critical steps involved in most of the meteorological data mining process. Spatial interpolation is an efficient technique to yield minimal error in prediction. From existing literatures, it is evident that the land-use/land-cover (LULC) distribution of the terrain influences these parameters in a varying manner and it is important to model their behaviour for climatological analyses. However, this semantic LULC knowledge of the terrain is generally ignored in the prediction process of the meteorological parameters. Recently, we have proposed a new spatial interpolation technique, namely semantic kriging (SemK) [3,5,7], which considers the semantic LULC knowledge for land-atmospheric interaction modeling and incorporates it into the existing interpolation process for better accuracy. However, the a-priori correlation analysis of SemK ignores the effect of other nearby LULC classes on each other. This article presents a new variant of SemK, namely a-posterior probabilistic Bayesian SemK (BSemK), which extends the a-priori correlation analysis of SemK with a-posterior probabilistic analysis. The proposed approach provides more accurate estimation of the parameters. Experimentation with LST data advocates the efficacy of the proposed approach compared to the a-priori SemK and other existing interpolation techniques.","PeriodicalId":20525,"journal":{"name":"Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75484207","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}
What is the relationship between urban form and citizens' well-being? In this paper, we propose a quantitative approach to help answer this question, inspired by theories developed within the fields of architecture and population health. The method extracts a rich set of metrics of urban form and well-being from openly accessible datasets. Using linear regression analysis, we identify a model which can explain 30% of the variance of well-being when applied to Greater London, UK. Outcomes of this research can inform the discussion on how to design cities which foster the well-being of their residents.
{"title":"City form and well-being: what makes London neighborhoods good places to live?","authors":"A. Venerandi, G. Quattrone, L. Capra","doi":"10.1145/2996913.2997011","DOIUrl":"https://doi.org/10.1145/2996913.2997011","url":null,"abstract":"What is the relationship between urban form and citizens' well-being? In this paper, we propose a quantitative approach to help answer this question, inspired by theories developed within the fields of architecture and population health. The method extracts a rich set of metrics of urban form and well-being from openly accessible datasets. Using linear regression analysis, we identify a model which can explain 30% of the variance of well-being when applied to Greater London, UK. Outcomes of this research can inform the discussion on how to design cities which foster the well-being of their residents.","PeriodicalId":20525,"journal":{"name":"Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76983300","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}
Ridesharing is an emerging travel mode that reduces the total amount of traffic on the road by combining people's travels together. While present ridesharing algorithms are trip-based, this paper aims to achieve significantly higher matching chances by a novel, activity-based algorithm. The algorithm expands the potential destination choice set by considering alternative destinations that are within given space-time budgets and would provide a similar activity function as the originals. In order to address the increased combinatorial complexity of trip chains, the paper introduces an efficient space-time filter on the foundations of time geography to search for accessible resources. Globally optimal matching is achieved by binary linear programming. The ridesharing algorithm is tested with a series of realistic scenarios of different population sizes. The encouraging results demonstrate that the matching rate by activity-based ridesharing is significantly increased from the baseline scenario of traditional trip-based ridesharing.
{"title":"Activity-based ridesharing: increasing flexibility by time geography","authors":"Yaoli Wang, Ronny J. Kutadinata, S. Winter","doi":"10.1145/2996913.2997002","DOIUrl":"https://doi.org/10.1145/2996913.2997002","url":null,"abstract":"Ridesharing is an emerging travel mode that reduces the total amount of traffic on the road by combining people's travels together. While present ridesharing algorithms are trip-based, this paper aims to achieve significantly higher matching chances by a novel, activity-based algorithm. The algorithm expands the potential destination choice set by considering alternative destinations that are within given space-time budgets and would provide a similar activity function as the originals. In order to address the increased combinatorial complexity of trip chains, the paper introduces an efficient space-time filter on the foundations of time geography to search for accessible resources. Globally optimal matching is achieved by binary linear programming. The ridesharing algorithm is tested with a series of realistic scenarios of different population sizes. The encouraging results demonstrate that the matching rate by activity-based ridesharing is significantly increased from the baseline scenario of traditional trip-based ridesharing.","PeriodicalId":20525,"journal":{"name":"Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85775764","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}
Abhinandan Nath, K. Fox, Kamesh Munagala, P. Agarwal
We propose parallel algorithms in the massively parallel communication (MPC) model (e.g. MapReduce) for processing large terrain elevation data (represented as a 3D point cloud) that are too big to fit on one machine. In particular, given a set S of 3D points that is distributed across multiple machines, we present a simple randomized algorithm to construct a TIN DEM of S by computing the Delaunay triangulation of the xy-projections of points in S, which is also stored across multiple machines. With high probability, the algorithm works in O(1) rounds and the total work performed is O(n log n). Next, we describe an efficient algorithm in the MPC model for computing the contour tree of the resulting DEM. Under some assumptions on the input, the algorithm works in O(1) rounds and the total work performed is O(n log n).
{"title":"Massively parallel algorithms for computing TIN DEMs and contour trees for large terrains","authors":"Abhinandan Nath, K. Fox, Kamesh Munagala, P. Agarwal","doi":"10.1145/2996913.2996952","DOIUrl":"https://doi.org/10.1145/2996913.2996952","url":null,"abstract":"We propose parallel algorithms in the massively parallel communication (MPC) model (e.g. MapReduce) for processing large terrain elevation data (represented as a 3D point cloud) that are too big to fit on one machine. In particular, given a set S of 3D points that is distributed across multiple machines, we present a simple randomized algorithm to construct a TIN DEM of S by computing the Delaunay triangulation of the xy-projections of points in S, which is also stored across multiple machines. With high probability, the algorithm works in O(1) rounds and the total work performed is O(n log n). Next, we describe an efficient algorithm in the MPC model for computing the contour tree of the resulting DEM. Under some assumptions on the input, the algorithm works in O(1) rounds and the total work performed is O(n log n).","PeriodicalId":20525,"journal":{"name":"Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80347768","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}
A Group Nearest Neighbor (GNN) query finds a point of interest (POI) that minimizes the aggregate distance for a group of users. In current systems, users have to reveal their exact, often sensitive locations to issue a GNN query. This calls for private GNN queries. However, existing methods for private GNN queries either are computationally too expensive for mobile phones or cannot resist sophisticated attacks. Our approach can efficiently and effectively process an important variant of private GNN queries: queries that minimize the maximum distance for any user in the group. To achieve high efficiency we develop a distributed multi-party private protocol to compute the maximum function. Our method exploits geometric constraints to prune POIs and avoids unnecessary data disclosure. In contrast to current state of the art multi-party private protocols, our proposed protocol does not rely on cryptography and has a fast runtime. Importantly, a user does not have to provide a location directly, even in imprecise form.
组最近邻(Group Nearest Neighbor, GNN)查询查找一个兴趣点(point of interest, POI)，使一组用户的总距离最小。在目前的系统中，用户必须透露他们的准确位置，通常是敏感的位置，才能发出GNN查询。这将调用私有GNN查询。然而，现有的私人GNN查询方法要么对移动电话来说计算成本太高，要么无法抵御复杂的攻击。我们的方法可以高效地处理私有GNN查询的一个重要变体:最小化组中任何用户的最大距离的查询。为了提高效率，我们开发了一个分布式多方私有协议来计算最大函数。我们的方法利用几何约束来修剪poi并避免不必要的数据泄露。与当前最先进的多方私有协议相比，我们提出的协议不依赖于密码学，并且具有快速的运行时间。重要的是，用户不必直接提供位置，即使是不精确的形式。
{"title":"Location privacy for group meetups","authors":"A. K. M. M. R. Khan, L. Kulik, E. Tanin","doi":"10.1145/2996913.2996966","DOIUrl":"https://doi.org/10.1145/2996913.2996966","url":null,"abstract":"A Group Nearest Neighbor (GNN) query finds a point of interest (POI) that minimizes the aggregate distance for a group of users. In current systems, users have to reveal their exact, often sensitive locations to issue a GNN query. This calls for private GNN queries. However, existing methods for private GNN queries either are computationally too expensive for mobile phones or cannot resist sophisticated attacks. Our approach can efficiently and effectively process an important variant of private GNN queries: queries that minimize the maximum distance for any user in the group. To achieve high efficiency we develop a distributed multi-party private protocol to compute the maximum function. Our method exploits geometric constraints to prune POIs and avoids unnecessary data disclosure. In contrast to current state of the art multi-party private protocols, our proposed protocol does not rely on cryptography and has a fast runtime. Importantly, a user does not have to provide a location directly, even in imprecise form.","PeriodicalId":20525,"journal":{"name":"Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81347842","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}
Lamia Belouaer, David Brosset, Christophe Claramunt
The representation of human knowledge extracted from navigations in natural environments is still a research challenge for spatial cognition and computer science. When acting in natural environments people often use verbal route descriptions or sketch maps to transmit their knowledge of the environment, and some of the actions performed. The research developed in this paper introduces a modeling and computational approach using verbal descriptions of human navigating in a natural environment. The objective is to extract the semantic and spatial knowledge emerging from the verbal route descriptions. A formal and semantic model is introduced with a series of rules that merge different route descriptions. The semantic network constructed presents a global view of the route descriptions, and is used to generate a map representation from them. The whole approach is illustrated by a case study.
{"title":"From verbal route descriptions to sketch maps in natural environments","authors":"Lamia Belouaer, David Brosset, Christophe Claramunt","doi":"10.1145/2996913.2997003","DOIUrl":"https://doi.org/10.1145/2996913.2997003","url":null,"abstract":"The representation of human knowledge extracted from navigations in natural environments is still a research challenge for spatial cognition and computer science. When acting in natural environments people often use verbal route descriptions or sketch maps to transmit their knowledge of the environment, and some of the actions performed. The research developed in this paper introduces a modeling and computational approach using verbal descriptions of human navigating in a natural environment. The objective is to extract the semantic and spatial knowledge emerging from the verbal route descriptions. A formal and semantic model is introduced with a series of rules that merge different route descriptions. The semantic network constructed presents a global view of the route descriptions, and is used to generate a map representation from them. The whole approach is illustrated by a case study.","PeriodicalId":20525,"journal":{"name":"Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91415811","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}
In this work we introduce an anisotropic density-based clustering algorithm. It outperforms DBSCAN and OPTICS for the detection of anisotropic spatial point patterns and performs equally well in cases that do not explicitly benefit from an anisotropic perspective. ADCN has the same time complexity as DBSCAN and OPTICS, namely O(n log n) when using a spatial index, O(n2) otherwise.
{"title":"ADCN: an anisotropic density-based clustering algorithm","authors":"Gengchen Mai, K. Janowicz, Yingjie Hu, Song Gao","doi":"10.1145/2996913.2996940","DOIUrl":"https://doi.org/10.1145/2996913.2996940","url":null,"abstract":"In this work we introduce an anisotropic density-based clustering algorithm. It outperforms DBSCAN and OPTICS for the detection of anisotropic spatial point patterns and performs equally well in cases that do not explicitly benefit from an anisotropic perspective. ADCN has the same time complexity as DBSCAN and OPTICS, namely O(n log n) when using a spatial index, O(n2) otherwise.","PeriodicalId":20525,"journal":{"name":"Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89901673","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}
Paras Mehta, Dimitrios Skoutas, Dimitris Sacharidis, A. Voisard
Large amounts of user-generated content are posted daily on the Web, including textual, spatial and temporal information. Exploiting this content to detect, analyze and monitor events and topics that have a potentially large span in space and time requires efficient retrieval and ranking based on criteria including all three dimensions. In this paper, we introduce a novel type of spatial-temporal-keyword query that combines keyword search with the task of maximizing the spatio-temporal coverage and diversity of the returned top-f results. We first describe a baseline algorithm based on related search results diversification problems. Then, we develop an efficient approach which exploits a hybrid spatial-temporal-keyword index to drastically reduce query execution time. To that end, we extend two state-of-the- art indices for top-f spatio-textual queries and describe how our proposed approach can be applied on top of them. We evaluate the efficiency of our algorithms by conducting experiments on two large, real-world datasets containing geotagged tweets and photos.
{"title":"Coverage and diversity aware top-k query for spatio-temporal posts","authors":"Paras Mehta, Dimitrios Skoutas, Dimitris Sacharidis, A. Voisard","doi":"10.1145/2996913.2996941","DOIUrl":"https://doi.org/10.1145/2996913.2996941","url":null,"abstract":"Large amounts of user-generated content are posted daily on the Web, including textual, spatial and temporal information. Exploiting this content to detect, analyze and monitor events and topics that have a potentially large span in space and time requires efficient retrieval and ranking based on criteria including all three dimensions. In this paper, we introduce a novel type of spatial-temporal-keyword query that combines keyword search with the task of maximizing the spatio-temporal coverage and diversity of the returned top-f results. We first describe a baseline algorithm based on related search results diversification problems. Then, we develop an efficient approach which exploits a hybrid spatial-temporal-keyword index to drastically reduce query execution time. To that end, we extend two state-of-the- art indices for top-f spatio-textual queries and describe how our proposed approach can be applied on top of them. We evaluate the efficiency of our algorithms by conducting experiments on two large, real-world datasets containing geotagged tweets and photos.","PeriodicalId":20525,"journal":{"name":"Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91341061","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}
Junbo Zhang, Yu Zheng, Dekang Qi, Ruiyuan Li, Xiuwen Yi
Advances in location-acquisition and wireless communication technologies have led to wider availability of spatio-temporal (ST) data, which has unique spatial properties (i.e. geographical hierarchy and distance) and temporal properties (i.e. closeness, period and trend). In this paper, we propose a Deep-learning-based prediction model for Spatio-Temporal data (DeepST). We leverage ST domain knowledge to design the architecture of DeepST, which is comprised of two components: spatio-temporal and global. The spatio-temporal component employs the framework of convolutional neural networks to simultaneously model spatial near and distant dependencies, and temporal closeness, period and trend. The global component is used to capture global factors, such as day of the week, weekday or weekend. Using DeepST, we build a real-time crowd flow forecasting system called UrbanFlow1. Experiment results on diverse ST datasets verify DeepST's ability to capture ST data's spatio-temporal properties, showing the advantages of DeepST beyond four baseline methods.
{"title":"DNN-based prediction model for spatio-temporal data","authors":"Junbo Zhang, Yu Zheng, Dekang Qi, Ruiyuan Li, Xiuwen Yi","doi":"10.1145/2996913.2997016","DOIUrl":"https://doi.org/10.1145/2996913.2997016","url":null,"abstract":"Advances in location-acquisition and wireless communication technologies have led to wider availability of spatio-temporal (ST) data, which has unique spatial properties (i.e. geographical hierarchy and distance) and temporal properties (i.e. closeness, period and trend). In this paper, we propose a Deep-learning-based prediction model for Spatio-Temporal data (DeepST). We leverage ST domain knowledge to design the architecture of DeepST, which is comprised of two components: spatio-temporal and global. The spatio-temporal component employs the framework of convolutional neural networks to simultaneously model spatial near and distant dependencies, and temporal closeness, period and trend. The global component is used to capture global factors, such as day of the week, weekday or weekend. Using DeepST, we build a real-time crowd flow forecasting system called UrbanFlow1. Experiment results on diverse ST datasets verify DeepST's ability to capture ST data's spatio-temporal properties, showing the advantages of DeepST beyond four baseline methods.","PeriodicalId":20525,"journal":{"name":"Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90432178","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：