Yurui Huang, Jie Zhang, HengDa Bao, Yang Yang, Jian Yang
Estimated time of arrival (ETA) is a very important factor in the transportation system. It has attracted increasing attentions and has been widely used as a basic service in navigation systems and intelligent transportation systems. In this paper, we propose a novel solution to the ETA estimation problem, which is an ensemble on tree models and neural networks. We proved the accuracy and robustness of the solution on the A/B list and finally won first place in the SIGSPATIAL 2021 GISCUP competition.
{"title":"Complementary Fusion of Deep Network and Tree Model for ETA Prediction","authors":"Yurui Huang, Jie Zhang, HengDa Bao, Yang Yang, Jian Yang","doi":"10.1145/3474717.3488237","DOIUrl":"https://doi.org/10.1145/3474717.3488237","url":null,"abstract":"Estimated time of arrival (ETA) is a very important factor in the transportation system. It has attracted increasing attentions and has been widely used as a basic service in navigation systems and intelligent transportation systems. In this paper, we propose a novel solution to the ETA estimation problem, which is an ensemble on tree models and neural networks. We proved the accuracy and robustness of the solution on the A/B list and finally won first place in the SIGSPATIAL 2021 GISCUP competition.","PeriodicalId":340759,"journal":{"name":"Proceedings of the 29th International Conference on Advances in Geographic Information Systems","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127118417","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}
We propose the combining of region connection calculi with nested hierarchical grids for representing spatial region data in the context of knowledge graphs, thereby avoiding reliance on vector representations. We present a resulting region calculus, and provide qualitative and formal evidence that this representation can be favorable with large data volumes in the context of knowledge graphs; in particular we study means of efficiently choosing which triples to store to minimize space requirements when data is represented this way, and we provide an algorithm for finding the smallest possible set of triples for this purpose including an asymptotic measure of the size of this set for a special case. We prove that a known constraint calculus is adequate for the reconstruction of all triples describing a region from such a pruned representation, but problematic for reasoning with hierarchical grids in general.
{"title":"Semantic Compression with Region Calculi in Nested Hierarchical Grids","authors":"Joseph Zalewski, P. Hitzler, K. Janowicz","doi":"10.1145/3474717.3483965","DOIUrl":"https://doi.org/10.1145/3474717.3483965","url":null,"abstract":"We propose the combining of region connection calculi with nested hierarchical grids for representing spatial region data in the context of knowledge graphs, thereby avoiding reliance on vector representations. We present a resulting region calculus, and provide qualitative and formal evidence that this representation can be favorable with large data volumes in the context of knowledge graphs; in particular we study means of efficiently choosing which triples to store to minimize space requirements when data is represented this way, and we provide an algorithm for finding the smallest possible set of triples for this purpose including an asymptotic measure of the size of this set for a special case. We prove that a known constraint calculus is adequate for the reconstruction of all triples describing a region from such a pruned representation, but problematic for reasoning with hierarchical grids in general.","PeriodicalId":340759,"journal":{"name":"Proceedings of the 29th International Conference on Advances in Geographic Information Systems","volume":"598 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116560806","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}
Samriddhi Singla, A. Eldawy, Tina Diao, Ayan Mukhopadhyay, E. Scudiero
Pre-processing spatial data for machine learning applications often includes combining different datasets into a form usable by the machine learning algorithms. Spatial data is generally available in two representations, raster and vector. The best data science and machine learning applications need to combine multiple datasets of both representations which is a data and compute intensive problem. This paper proposes a formal raster-vector join operator, Raptor Join, that can bridge the gap between raster and vector data. It is modeled as a relational join operator in Spark that can be easily combined with other operators, while also offering the advantage of in-situ processing. To implement the Raptor join operator efficiently, we propose a novel Flash index that has a low memory requirement and can process the entire operation with one data scan. We run an extensive experimental evaluation on large scale satellite data with up-to a trillion pixels, and big vector data with up-to hundreds of millions of segments and billions of points, and show that the proposed method can scale to big data with up-to three orders of magnitude performance gain over baselines.
{"title":"The Raptor Join Operator for Processing Big Raster + Vector Data","authors":"Samriddhi Singla, A. Eldawy, Tina Diao, Ayan Mukhopadhyay, E. Scudiero","doi":"10.1145/3474717.3483971","DOIUrl":"https://doi.org/10.1145/3474717.3483971","url":null,"abstract":"Pre-processing spatial data for machine learning applications often includes combining different datasets into a form usable by the machine learning algorithms. Spatial data is generally available in two representations, raster and vector. The best data science and machine learning applications need to combine multiple datasets of both representations which is a data and compute intensive problem. This paper proposes a formal raster-vector join operator, Raptor Join, that can bridge the gap between raster and vector data. It is modeled as a relational join operator in Spark that can be easily combined with other operators, while also offering the advantage of in-situ processing. To implement the Raptor join operator efficiently, we propose a novel Flash index that has a low memory requirement and can process the entire operation with one data scan. We run an extensive experimental evaluation on large scale satellite data with up-to a trillion pixels, and big vector data with up-to hundreds of millions of segments and billions of points, and show that the proposed method can scale to big data with up-to three orders of magnitude performance gain over baselines.","PeriodicalId":340759,"journal":{"name":"Proceedings of the 29th International Conference on Advances in Geographic Information Systems","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122488991","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}
One of the most popular applications of Location Based Services (LBS) is recommending a Point of Interest (POI) based on user's preferences and geo-locations. However, the existing approaches have not tackled the problem of jointly determining: (a) a sequence of POIs that can be traversed within certain budget (i.e., limit on distance) and simultaneously provide a high-enough diversity; and (b) recommend the best origin (i.e., the hotel) for a given user, so that the desired route of POIs can be traversed within the specified constraints. In this work, we take a first step towards identifying this new problem and formalizing it as a novel type of a query. Subsequently, we present naïve solutions and experimental observations over a real-life datasets, illustrating the trade-offs in terms of (dis)associating the initial location from the rest of the POIs.
{"title":"Semantically Diverse Paths with Range and Origin Constraints","authors":"Xu Teng, Goce Trajcevski, Andreas Züfle","doi":"10.1145/3474717.3483985","DOIUrl":"https://doi.org/10.1145/3474717.3483985","url":null,"abstract":"One of the most popular applications of Location Based Services (LBS) is recommending a Point of Interest (POI) based on user's preferences and geo-locations. However, the existing approaches have not tackled the problem of jointly determining: (a) a sequence of POIs that can be traversed within certain budget (i.e., limit on distance) and simultaneously provide a high-enough diversity; and (b) recommend the best origin (i.e., the hotel) for a given user, so that the desired route of POIs can be traversed within the specified constraints. In this work, we take a first step towards identifying this new problem and formalizing it as a novel type of a query. Subsequently, we present naïve solutions and experimental observations over a real-life datasets, illustrating the trade-offs in terms of (dis)associating the initial location from the rest of the POIs.","PeriodicalId":340759,"journal":{"name":"Proceedings of the 29th International Conference on Advances in Geographic Information Systems","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122702190","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}
Hanxiang Hao, Sriram Baireddy, Kevin J. LaTourette, Latisha R. Konz, Moses W. Chan, M. Comer, E. Delp
Automatic building segmentation is an important task for satellite imagery analysis and scene understanding. Most existing segmentation methods focus on the case where the images are taken from directly overhead (i.e., low off-nadir/viewing angle). These methods often fail to provide accurate results on satellite images with larger off-nadir angles due to the higher noise level and lower spatial resolution. In this paper, we propose a method that is able to provide accurate building segmentation for satellite imagery captured from a large range of off-nadir angles. Based on Bayesian deep learning, we explicitly design our method to learn the data noise via aleatoric and epistemic uncertainty modeling. Satellite image metadata (e.g., off-nadir angle and ground sample distance) is also used in our model to further improve the result. We show that with uncertainty modeling and metadata injection, our method achieves better performance than the baseline method, especially for noisy images taken from large off-nadir angles1.
{"title":"Improving Building Segmentation Using Uncertainty Modeling and Metadata Injection","authors":"Hanxiang Hao, Sriram Baireddy, Kevin J. LaTourette, Latisha R. Konz, Moses W. Chan, M. Comer, E. Delp","doi":"10.1145/3474717.3483918","DOIUrl":"https://doi.org/10.1145/3474717.3483918","url":null,"abstract":"Automatic building segmentation is an important task for satellite imagery analysis and scene understanding. Most existing segmentation methods focus on the case where the images are taken from directly overhead (i.e., low off-nadir/viewing angle). These methods often fail to provide accurate results on satellite images with larger off-nadir angles due to the higher noise level and lower spatial resolution. In this paper, we propose a method that is able to provide accurate building segmentation for satellite imagery captured from a large range of off-nadir angles. Based on Bayesian deep learning, we explicitly design our method to learn the data noise via aleatoric and epistemic uncertainty modeling. Satellite image metadata (e.g., off-nadir angle and ground sample distance) is also used in our model to further improve the result. We show that with uncertainty modeling and metadata injection, our method achieves better performance than the baseline method, especially for noisy images taken from large off-nadir angles1.","PeriodicalId":340759,"journal":{"name":"Proceedings of the 29th International Conference on Advances in Geographic Information Systems","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128519830","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 paper, we demonstrate how to conduct OD analysis based on big taxi trajectory data with XStar in an efficient manner. XStar, originally developed by the first author, is a standalone software system dedicated to trajectory-data users with little programming skills and affordable computing devices. Since its release in Jan. 2019, it has received downloads of over 4000 by May 2021.
{"title":"Origin-destination (OD) analysis based on big taxi trajectory data with XStar (Demo Paper)","authors":"Xiang Li, Yijun He","doi":"10.1145/3474717.3483925","DOIUrl":"https://doi.org/10.1145/3474717.3483925","url":null,"abstract":"In this paper, we demonstrate how to conduct OD analysis based on big taxi trajectory data with XStar in an efficient manner. XStar, originally developed by the first author, is a standalone software system dedicated to trajectory-data users with little programming skills and affordable computing devices. Since its release in Jan. 2019, it has received downloads of over 4000 by May 2021.","PeriodicalId":340759,"journal":{"name":"Proceedings of the 29th International Conference on Advances in Geographic Information Systems","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130071118","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}
Estimated time of arrival (ETA) is an important task in Intelligent Transportation Systems. Usually, the task involves a large amount of spatial-temporal data and is affected by different factors such as route distance, road capacity, traffic lights, and the real-time traffic condition. Real-time traffic conditions are highly uncertain and dynamic, which makes ETA challenging. For this reason, we propose an ETA model that incorporates the task of traffic condition prediction. Specifically, we introduce a Geo-Attention Network that combines a geo-location encoder and the geo-attentioned graph convolution to predict traffic conditions. Then, we use convolution network and recurrent neural network to capture the spatial and temporal correlations. Finally, we learn to estimate the arrival time and the traffic conditions simultaneously in a multi-task learning component. Extensive experiments have been carried out on the large-scale floating car data provided by GISCUP 2021, and excellent results have been achieved.
{"title":"Geo-Attention Network for Traffic Condition Prediction and Travel Time Estimation","authors":"Jie Li, Wanyi Zhou, Zebin Chen, Yue-jiao Gong","doi":"10.1145/3474717.3488383","DOIUrl":"https://doi.org/10.1145/3474717.3488383","url":null,"abstract":"Estimated time of arrival (ETA) is an important task in Intelligent Transportation Systems. Usually, the task involves a large amount of spatial-temporal data and is affected by different factors such as route distance, road capacity, traffic lights, and the real-time traffic condition. Real-time traffic conditions are highly uncertain and dynamic, which makes ETA challenging. For this reason, we propose an ETA model that incorporates the task of traffic condition prediction. Specifically, we introduce a Geo-Attention Network that combines a geo-location encoder and the geo-attentioned graph convolution to predict traffic conditions. Then, we use convolution network and recurrent neural network to capture the spatial and temporal correlations. Finally, we learn to estimate the arrival time and the traffic conditions simultaneously in a multi-task learning component. Extensive experiments have been carried out on the large-scale floating car data provided by GISCUP 2021, and excellent results have been achieved.","PeriodicalId":340759,"journal":{"name":"Proceedings of the 29th International Conference on Advances in Geographic Information Systems","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133982230","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}
The GISCUP 2021 focuses on estimated time of arrival (ETA) which is widely used in various industries such as Transportation and Mobility. In this paper, we describe the 6th-place-solution that uses positional features hierarchically from wide to narrow and other statistical features for predictions with GBDT. Especially for narrow features, graph-embedding features are generated by extending node2vec to make it easier to handle large amounts of data. This solution got MAPE score of 12.478 as the final score.
{"title":"Hierarchical Positional Approach for ETA Prediction","authors":"Tomoki Saito, Shinichi Tanimoto, Fumihiko Takahashi","doi":"10.1145/3474717.3488240","DOIUrl":"https://doi.org/10.1145/3474717.3488240","url":null,"abstract":"The GISCUP 2021 focuses on estimated time of arrival (ETA) which is widely used in various industries such as Transportation and Mobility. In this paper, we describe the 6th-place-solution that uses positional features hierarchically from wide to narrow and other statistical features for predictions with GBDT. Especially for narrow features, graph-embedding features are generated by extending node2vec to make it easier to handle large amounts of data. This solution got MAPE score of 12.478 as the final score.","PeriodicalId":340759,"journal":{"name":"Proceedings of the 29th International Conference on Advances in Geographic Information Systems","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127857017","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-related forecasting plays a critical role in determining transportation policy, unlike traditional approaches, which can only make decisions based on statistical results or historical experience. Through machine learning, we are able to capture the potential interactions between urban dynamics and find their mutual interactions in a spatial context. However, despite a plethora of traffic-related studies, few works have explored predicting the impact of congestion. Therefore, this paper focuses on predicting how a car accident leads to traffic congestion, especially the length of time it takes for the congestion to occur. Accordingly, we propose a novel model named Dual-Attention Multi-Scale Graph Convolutional Networks (DAMGNet) to address this issue. In this proposed model, heterogeneous data such as accident information, urban dynamics, and various highway network characteristics are considered and combined. Next, the context encoder encodes the accident data, and the spatial encoder captures the hidden features between multi-scale Graph Convolutional Networks (GCNs). With our designed dual attention mechanism, the DAMGNet model is able to effectively learn the correlation between features. The evaluations conducted on a real-world dataset prove that our DAMGNet has a significant improvement in RMSE and MAE over other comparative methods.
{"title":"Dual-Attention Multi-Scale Graph Convolutional Networks for Highway Accident Delay Time Prediction","authors":"I-Ying Wu, Fandel Lin, Hsun-Ping Hsieh","doi":"10.1145/3474717.3484259","DOIUrl":"https://doi.org/10.1145/3474717.3484259","url":null,"abstract":"Traffic-related forecasting plays a critical role in determining transportation policy, unlike traditional approaches, which can only make decisions based on statistical results or historical experience. Through machine learning, we are able to capture the potential interactions between urban dynamics and find their mutual interactions in a spatial context. However, despite a plethora of traffic-related studies, few works have explored predicting the impact of congestion. Therefore, this paper focuses on predicting how a car accident leads to traffic congestion, especially the length of time it takes for the congestion to occur. Accordingly, we propose a novel model named Dual-Attention Multi-Scale Graph Convolutional Networks (DAMGNet) to address this issue. In this proposed model, heterogeneous data such as accident information, urban dynamics, and various highway network characteristics are considered and combined. Next, the context encoder encodes the accident data, and the spatial encoder captures the hidden features between multi-scale Graph Convolutional Networks (GCNs). With our designed dual attention mechanism, the DAMGNet model is able to effectively learn the correlation between features. The evaluations conducted on a real-world dataset prove that our DAMGNet has a significant improvement in RMSE and MAE over other comparative methods.","PeriodicalId":340759,"journal":{"name":"Proceedings of the 29th International Conference on Advances in Geographic Information Systems","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124287823","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}
Daichi Amagata, Shohei Tsuruoka, Yusuke Arai, T. Hara
Due to the proliferation of GPS-enabled mobile devices and IoT environments, location-based services are generating a large number of objects that contain both spatial and keyword information, and spatial-keyword databases are receiving much attention. This paper addresses the problem of top-k spatial-keyword similarity join, which outputs k object pairs with the highest similarity. This query is a primitive operator for important applications, including duplicate detection, recommendation, and clustering. The main bottleneck of the top-k spatial-keyword similarity join is to compute the similarity of a given object pair. To avoid this computation as much as possible, a state-of-the-art algorithm utilizes a filter that can skip the exact similarity computation of a given pair. However, this algorithm suffers from a loose threshold at the first stage, a high filtering cost, and the impossibility of filtering many pairs in a batch. We propose Feat-SKSJ, which removes these drawbacks and quickly outputs the exact result. Extensive experiments on real datasets show that Feat-SKSJ is significantly faster than the state-of-the-art algorithm.
{"title":"Feat-SKSJ: Fast and Exact Algorithm for Top-k Spatial-Keyword Similarity Join","authors":"Daichi Amagata, Shohei Tsuruoka, Yusuke Arai, T. Hara","doi":"10.1145/3474717.3483629","DOIUrl":"https://doi.org/10.1145/3474717.3483629","url":null,"abstract":"Due to the proliferation of GPS-enabled mobile devices and IoT environments, location-based services are generating a large number of objects that contain both spatial and keyword information, and spatial-keyword databases are receiving much attention. This paper addresses the problem of top-k spatial-keyword similarity join, which outputs k object pairs with the highest similarity. This query is a primitive operator for important applications, including duplicate detection, recommendation, and clustering. The main bottleneck of the top-k spatial-keyword similarity join is to compute the similarity of a given object pair. To avoid this computation as much as possible, a state-of-the-art algorithm utilizes a filter that can skip the exact similarity computation of a given pair. However, this algorithm suffers from a loose threshold at the first stage, a high filtering cost, and the impossibility of filtering many pairs in a batch. We propose Feat-SKSJ, which removes these drawbacks and quickly outputs the exact result. Extensive experiments on real datasets show that Feat-SKSJ is significantly faster than the state-of-the-art algorithm.","PeriodicalId":340759,"journal":{"name":"Proceedings of the 29th International Conference on Advances in Geographic Information Systems","volume":"198 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124441420","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：