Spatial prediction is to predict the values of the targeted variable, such as PM2.5 values and temperature, at arbitrary locations based on the collected geospatial data. It greatly affects the key research topics in geoscience in terms of obtaining heterogeneous spatial information (e.g., soil conditions, precipitation rates, wheat yields) for geographic modeling and decision-making at local, regional, and global scales. In situ data, collected by ground-level in situ sensors, and remote sensing data, collected by satellite or aircraft, are two important data sources for this task. In situ data are relatively accurate while sparse and unevenly distributed. Remote sensing data cover large spatial areas, but are coarse with low spatiotemporal resolution and prone to interference. How to synergize the complementary strength of these two data types is still a grand challenge. Moreover, it is difficult to model the unknown spatial predictive mapping while handling the tradeoff between spatial autocorrelation and heterogeneity. Third, representing spatial relations without substantial information loss is also a critical issue. To address these challenges, we propose a novel Heterogeneous Self-supervised Spatial Prediction (HSSP) framework that synergizes multi-source data by minimizing the inconsistency between in situ and remote sensing observations. We propose a new deep geometric spatial interpolation model as the prediction backbone that automatically interpolates the values of the targeted variable at unknown locations based on existing observations by taking into account both distance and orientation information. Our proposed interpolator is proven to both be the general form of popular interpolation methods and preserve spatial information. The spatial prediction is enhanced by a novel error-compensation framework to capture the prediction inconsistency due to spatial heterogeneity. Extensive experiments have been conducted on real-world datasets and demonstrated our model’s superiority in performance over state-of-the-art models.
{"title":"Deep Spatial Prediction via Heterogeneous Multi-source Self-supervision","authors":"Minxing Zhang, Dazhou Yu, Yun-Qing Li, Liang Zhao","doi":"10.1145/3605358","DOIUrl":"https://doi.org/10.1145/3605358","url":null,"abstract":"Spatial prediction is to predict the values of the targeted variable, such as PM2.5 values and temperature, at arbitrary locations based on the collected geospatial data. It greatly affects the key research topics in geoscience in terms of obtaining heterogeneous spatial information (e.g., soil conditions, precipitation rates, wheat yields) for geographic modeling and decision-making at local, regional, and global scales. In situ data, collected by ground-level in situ sensors, and remote sensing data, collected by satellite or aircraft, are two important data sources for this task. In situ data are relatively accurate while sparse and unevenly distributed. Remote sensing data cover large spatial areas, but are coarse with low spatiotemporal resolution and prone to interference. How to synergize the complementary strength of these two data types is still a grand challenge. Moreover, it is difficult to model the unknown spatial predictive mapping while handling the tradeoff between spatial autocorrelation and heterogeneity. Third, representing spatial relations without substantial information loss is also a critical issue. To address these challenges, we propose a novel Heterogeneous Self-supervised Spatial Prediction (HSSP) framework that synergizes multi-source data by minimizing the inconsistency between in situ and remote sensing observations. We propose a new deep geometric spatial interpolation model as the prediction backbone that automatically interpolates the values of the targeted variable at unknown locations based on existing observations by taking into account both distance and orientation information. Our proposed interpolator is proven to both be the general form of popular interpolation methods and preserve spatial information. The spatial prediction is enhanced by a novel error-compensation framework to capture the prediction inconsistency due to spatial heterogeneity. Extensive experiments have been conducted on real-world datasets and demonstrated our model’s superiority in performance over state-of-the-art models.","PeriodicalId":43641,"journal":{"name":"ACM Transactions on Spatial Algorithms and Systems","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49271670","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}
Recommending a Point of Interest (PoI) or a sequence of PoIs to visit based on user’s preferences and geo-locations has been one of the most popular applications of Location-Based Services (LBS). Variants have also been considered which take other factors into consideration, such as broader (implicit or explicit) semantic constraints as well as the limitations on the length of the trip. In this work, we present an efficient algorithmic solution to a novel query – PaDOC (Paths with Distance, Origin, and Category constraints) – which combines the generation of a path that (a) can be traversed within a user-specified budget (e.g., limit on distance), (b) starts at one of the user-specified origin locations (e.g., a hotel), and (c) contains PoIs from a user-specified list of PoI categories. We show that the problem of deciding whether such a path exists is an NP-hard problem. Based on a novel indexing structure, we propose two efficient algorithms for approximate PaDOC query processing based on both conservative and progressive distance estimations. We conducted extensive experiments over real, publicly available datasets, demonstrating the benefits of the proposed methodologies over straightforward solutions.
{"title":"Distance, Origin and Category Constrained Paths","authors":"Xu Teng, Goce Trajcevski, Andreas Züfle","doi":"10.1145/3596601","DOIUrl":"https://doi.org/10.1145/3596601","url":null,"abstract":"Recommending a Point of Interest (PoI) or a sequence of PoIs to visit based on user’s preferences and geo-locations has been one of the most popular applications of Location-Based Services (LBS). Variants have also been considered which take other factors into consideration, such as broader (implicit or explicit) semantic constraints as well as the limitations on the length of the trip. In this work, we present an efficient algorithmic solution to a novel query – PaDOC (Paths with Distance, Origin, and Category constraints) – which combines the generation of a path that (a) can be traversed within a user-specified budget (e.g., limit on distance), (b) starts at one of the user-specified origin locations (e.g., a hotel), and (c) contains PoIs from a user-specified list of PoI categories. We show that the problem of deciding whether such a path exists is an NP-hard problem. Based on a novel indexing structure, we propose two efficient algorithms for approximate PaDOC query processing based on both conservative and progressive distance estimations. We conducted extensive experiments over real, publicly available datasets, demonstrating the benefits of the proposed methodologies over straightforward solutions.","PeriodicalId":43641,"journal":{"name":"ACM Transactions on Spatial Algorithms and Systems","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2023-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44010639","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}
Joachim Gudmundsson, John Pfeifer, Martin P. Seybold
We study the problem of sub-trajectory nearest-neighbor queries on polygonal curves under the continuous Fréchet distance. Given an n vertex trajectory P and an m vertex query trajectory Q, we seek to report a vertex-aligned sub-trajectory P′ of P that is closest to Q, i.e., P′ must start and end on contiguous vertices of P. Since in real data P typically contains a very large number of vertices, we focus on answering queries, without restrictions on P or Q, using only precomputed structures of 𝒪(n) size. We use three baseline algorithms from straightforward extensions of known work; however, they have impractical performance on realistic inputs. Therefore, we propose a new Hierarchical Simplification Tree (HST) data structure and an adaptive clustering-based query algorithm that efficiently explores relevant parts of P. The core of our query methods is a novel greedy-backtracking algorithm that solves the Fréchet decision problem using 𝒪(n+m) space and 𝒪O(nm) time in the worst case. Experiments on real and synthetic data show that our heuristic effectively prunes the search space and greatly reduces computations compared to baseline approaches.
{"title":"On Practical Nearest Sub-Trajectory Queries under the Fréchet Distance","authors":"Joachim Gudmundsson, John Pfeifer, Martin P. Seybold","doi":"10.1145/3587426","DOIUrl":"https://doi.org/10.1145/3587426","url":null,"abstract":"We study the problem of sub-trajectory nearest-neighbor queries on polygonal curves under the continuous Fréchet distance. Given an n vertex trajectory P and an m vertex query trajectory Q, we seek to report a vertex-aligned sub-trajectory P′ of P that is closest to Q, i.e., P′ must start and end on contiguous vertices of P. Since in real data P typically contains a very large number of vertices, we focus on answering queries, without restrictions on P or Q, using only precomputed structures of 𝒪(n) size. We use three baseline algorithms from straightforward extensions of known work; however, they have impractical performance on realistic inputs. Therefore, we propose a new Hierarchical Simplification Tree (HST) data structure and an adaptive clustering-based query algorithm that efficiently explores relevant parts of P. The core of our query methods is a novel greedy-backtracking algorithm that solves the Fréchet decision problem using 𝒪(n+m) space and 𝒪O(nm) time in the worst case. Experiments on real and synthetic data show that our heuristic effectively prunes the search space and greatly reduces computations compared to baseline approaches.","PeriodicalId":43641,"journal":{"name":"ACM Transactions on Spatial Algorithms and Systems","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2023-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46249414","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}
Anup Adhikari, Leen-Kiat Soh, Deepti Joshi, A. Samal, Regina Werum
Prior research suggests that the timing and location of social unrest may be influenced by similar unrest activities in another nearby region, potentially causing a spread of unrest activities across space and time. In this paper, we model the spread of social unrest across time and space using a novel approach, grounded in agent-based modeling (ABM). In it, regions (geographic polygons) are represented as agents that transition from one state to another based on changes in their environment. Our approach involves (1) creating a vector for each region/agent based on socio-demographic, infrastructural, economic, geographic, and environmental (SIEGE) factors, (2) formulating a neighborhood distance function to identify an agent's neighbors based on geospatial distance and SIEGE proximity, (3) designing transition probability equations based on two distinct compartmental models—i.e., the Susceptible-Infected-Recovered (SIR) and the Susceptible-Infected-Susceptible (SIS) models, and (4) building a ground truth for evaluating the simulations. We use ABM to determine the individualized probabilities of each region/agent to transition from one state to another. The models are tested using the districts of three states in India as agents at a monthly scale for 2016-2019. For ground truth of unrest events, we use the Armed Conflict Location and Event Data (ACLED) dataset. Our findings include that (1) the transition probability equations are viable, (2) the agent-based modeling of the spread of social unrest is feasible while treating regions as agents (Brier's score < 0.25 for two out of three regions), and (3) the SIS model performs comparatively better than the SIR model.
{"title":"Agent Based Modeling of the Spread of Social Unrest Using Infectious Disease Models","authors":"Anup Adhikari, Leen-Kiat Soh, Deepti Joshi, A. Samal, Regina Werum","doi":"10.1145/3587463","DOIUrl":"https://doi.org/10.1145/3587463","url":null,"abstract":"Prior research suggests that the timing and location of social unrest may be influenced by similar unrest activities in another nearby region, potentially causing a spread of unrest activities across space and time. In this paper, we model the spread of social unrest across time and space using a novel approach, grounded in agent-based modeling (ABM). In it, regions (geographic polygons) are represented as agents that transition from one state to another based on changes in their environment. Our approach involves (1) creating a vector for each region/agent based on socio-demographic, infrastructural, economic, geographic, and environmental (SIEGE) factors, (2) formulating a neighborhood distance function to identify an agent's neighbors based on geospatial distance and SIEGE proximity, (3) designing transition probability equations based on two distinct compartmental models—i.e., the Susceptible-Infected-Recovered (SIR) and the Susceptible-Infected-Susceptible (SIS) models, and (4) building a ground truth for evaluating the simulations. We use ABM to determine the individualized probabilities of each region/agent to transition from one state to another. The models are tested using the districts of three states in India as agents at a monthly scale for 2016-2019. For ground truth of unrest events, we use the Armed Conflict Location and Event Data (ACLED) dataset. Our findings include that (1) the transition probability equations are viable, (2) the agent-based modeling of the spread of social unrest is feasible while treating regions as agents (Brier's score < 0.25 for two out of three regions), and (3) the SIS model performs comparatively better than the SIR model.","PeriodicalId":43641,"journal":{"name":"ACM Transactions on Spatial Algorithms and Systems","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2023-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47931483","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 problem of point set registration (PSR) on images obtained using a group of unmanned aerial vehicles (UAVs) is addressed in this article. UAVs are given a flight plan each, which they execute autonomously. A flight plan consists of a series of GPS coordinates and altitudes that indicate where the UAV stops and hovers momentarily to capture an image of stationary targets on ground. A PSR algorithm is proposed that, given any two images and corresponding GPS coordinates and altitude, estimates the overlap between the images, identifies targets in the overlapping area, and matches these targets according to the geometric patterns they form. The algorithm estimates the overlap considering the error in UAVs’ locations due to wind, and it differentiates similar geometrical patterns by their GPS location. The algorithm is evaluated using the percentage of targets in the overlapping area that are matched correctly and the percentage of overlapping images matched correctly. The target-matching rate achieved using only the GPS locations of targets varied from 44% to 55% for target densities that varied from 6.4 down to 3.2 targets/m2. The proposed algorithm achieved target-matching rates of 48% to 87%. Well-known algorithms for PSR achieved lower rates on average.
{"title":"Point Set Registration for Target Localization Using Unmanned Aerial Vehicles","authors":"Dhruvil Darji, G. Vejarano","doi":"10.1145/3586575","DOIUrl":"https://doi.org/10.1145/3586575","url":null,"abstract":"The problem of point set registration (PSR) on images obtained using a group of unmanned aerial vehicles (UAVs) is addressed in this article. UAVs are given a flight plan each, which they execute autonomously. A flight plan consists of a series of GPS coordinates and altitudes that indicate where the UAV stops and hovers momentarily to capture an image of stationary targets on ground. A PSR algorithm is proposed that, given any two images and corresponding GPS coordinates and altitude, estimates the overlap between the images, identifies targets in the overlapping area, and matches these targets according to the geometric patterns they form. The algorithm estimates the overlap considering the error in UAVs’ locations due to wind, and it differentiates similar geometrical patterns by their GPS location. The algorithm is evaluated using the percentage of targets in the overlapping area that are matched correctly and the percentage of overlapping images matched correctly. The target-matching rate achieved using only the GPS locations of targets varied from 44% to 55% for target densities that varied from 6.4 down to 3.2 targets/m2. The proposed algorithm achieved target-matching rates of 48% to 87%. Well-known algorithms for PSR achieved lower rates on average.","PeriodicalId":43641,"journal":{"name":"ACM Transactions on Spatial Algorithms and Systems","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2023-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43431179","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}
This special issue contains extended versions of the best papers from the 2020 ACM SIGSPATIAL conference. Five papers have been recommended by the program committee co-chairs of the conference: Professors Yan Huang (North Texas University), Shawn Newsam (University of California, Merced), and Li Xiong (Emory University). These papers have received the highest ranks by the conference’s program committee members, and have also been endorsed by the PC co-chairs. Authors of all five conference papers have extended their papers and have submitted the extended versions for possible publication in ACM TSAS. To qualify for publication in ACM TSAS, one im-portant criterion is that the extended version includes at least 30% new material over the published conference version of the paper. The reviewers and the editorial board of ACM TSAS are the ones to decide on this issue, as well as assess the significance of the newly added material. Another im-portant criterion is that these extended versions should not have been published formerly in any other publication venue. To speed up the review process
{"title":"Editorial: Special Issue on the Best Papers from the 2020 ACM SIGSPATIAL Conference","authors":"Walid G. Aref","doi":"10.1145/3573198","DOIUrl":"https://doi.org/10.1145/3573198","url":null,"abstract":"This special issue contains extended versions of the best papers from the 2020 ACM SIGSPATIAL conference. Five papers have been recommended by the program committee co-chairs of the conference: Professors Yan Huang (North Texas University), Shawn Newsam (University of California, Merced), and Li Xiong (Emory University). These papers have received the highest ranks by the conference’s program committee members, and have also been endorsed by the PC co-chairs. Authors of all five conference papers have extended their papers and have submitted the extended versions for possible publication in ACM TSAS. To qualify for publication in ACM TSAS, one im-portant criterion is that the extended version includes at least 30% new material over the published conference version of the paper. The reviewers and the editorial board of ACM TSAS are the ones to decide on this issue, as well as assess the significance of the newly added material. Another im-portant criterion is that these extended versions should not have been published formerly in any other publication venue. To speed up the review process","PeriodicalId":43641,"journal":{"name":"ACM Transactions on Spatial Algorithms and Systems","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2023-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41918737","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}
Aparajita Haldar, Shuang Wang, G. Demirci, Joe Oakley, H. Ferhatosmanoğlu
Current approaches for modeling propagation in networks (e.g., of diseases, computer viruses, rumors) cannot adequately capture temporal properties such as order/duration of evolving connections or dynamic likelihoods of propagation along connections. Temporal models on evolving networks are crucial in applications that need to analyze dynamic spread. For example, a disease spreading virus has varying transmissibility based on interactions between individuals occurring with different frequency, proximity, and venue population density. Similarly, propagation of information having a limited active period, such as rumors, depends on the temporal dynamics of social interactions. To capture such behaviors, we first develop the Temporal Independent Cascade (T-IC) model with a spread function that efficiently utilizes a hypergraph-based sampling strategy and dynamic propagation probabilities. We prove this function to be submodular, with guarantees of approximation quality. This enables scalable analysis on highly granular temporal networks where other models struggle, such as when the spread across connections exhibits arbitrary temporally evolving patterns. We then introduce the notion of “reverse spread” using the proposed T-IC processes, and develop novel solutions to identify both sentinel/detector nodes and highly susceptible nodes. Extensive analysis on real-world datasets shows that the proposed approach significantly outperforms the alternatives in modeling both if and how spread occurs, by considering evolving network topology alongside granular contact/interaction information. Our approach has numerous applications, such as virus/rumor/influence tracking. Utilizing T-IC, we explore vital challenges of monitoring the impact of various intervention strategies over real spatio-temporal contact networks where we show our approach to be highly effective.
{"title":"Temporal Cascade Model for Analyzing Spread in Evolving Networks","authors":"Aparajita Haldar, Shuang Wang, G. Demirci, Joe Oakley, H. Ferhatosmanoğlu","doi":"10.1145/3579996","DOIUrl":"https://doi.org/10.1145/3579996","url":null,"abstract":"Current approaches for modeling propagation in networks (e.g., of diseases, computer viruses, rumors) cannot adequately capture temporal properties such as order/duration of evolving connections or dynamic likelihoods of propagation along connections. Temporal models on evolving networks are crucial in applications that need to analyze dynamic spread. For example, a disease spreading virus has varying transmissibility based on interactions between individuals occurring with different frequency, proximity, and venue population density. Similarly, propagation of information having a limited active period, such as rumors, depends on the temporal dynamics of social interactions. To capture such behaviors, we first develop the Temporal Independent Cascade (T-IC) model with a spread function that efficiently utilizes a hypergraph-based sampling strategy and dynamic propagation probabilities. We prove this function to be submodular, with guarantees of approximation quality. This enables scalable analysis on highly granular temporal networks where other models struggle, such as when the spread across connections exhibits arbitrary temporally evolving patterns. We then introduce the notion of “reverse spread” using the proposed T-IC processes, and develop novel solutions to identify both sentinel/detector nodes and highly susceptible nodes. Extensive analysis on real-world datasets shows that the proposed approach significantly outperforms the alternatives in modeling both if and how spread occurs, by considering evolving network topology alongside granular contact/interaction information. Our approach has numerous applications, such as virus/rumor/influence tracking. Utilizing T-IC, we explore vital challenges of monitoring the impact of various intervention strategies over real spatio-temporal contact networks where we show our approach to be highly effective.","PeriodicalId":43641,"journal":{"name":"ACM Transactions on Spatial Algorithms and Systems","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2023-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42833303","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}
K. K. Qin, Yongli Ren, Wei Shao, Brennan Lake, Filippo Privitera, Flora D. Salim
Sparsity is a common issue in many trajectory datasets, including human mobility data. This issue frequently brings more difficulty to relevant learning tasks, such as trajectory imputation and prediction. Nowadays, little existing work simultaneously deals with imputation and prediction on human trajectories. This work plans to explore whether the learning process of imputation and prediction could benefit from each other to achieve better outcomes. And the question will be answered by studying the coexistence patterns between missing points and observed ones in incomplete trajectories. More specifically, the proposed model develops an imputation component based on the self-attention mechanism to capture the coexistence patterns between observations and missing points among encoder-decoder layers. Meanwhile, a recurrent unit is integrated to extract the sequential embeddings from newly imputed sequences for predicting the following location. Furthermore, a new implementation called Imputation Cycle is introduced to enable gradual imputation with prediction enhancement at multiple levels, which helps to accelerate the speed of convergence. The experimental results on three different real-world mobility datasets show that the proposed approach has significant advantages over the competitive baselines across both imputation and prediction tasks in terms of accuracy and stability.
{"title":"Multiple-level Point Embedding for Solving Human Trajectory Imputation with Prediction","authors":"K. K. Qin, Yongli Ren, Wei Shao, Brennan Lake, Filippo Privitera, Flora D. Salim","doi":"10.1145/3582427","DOIUrl":"https://doi.org/10.1145/3582427","url":null,"abstract":"Sparsity is a common issue in many trajectory datasets, including human mobility data. This issue frequently brings more difficulty to relevant learning tasks, such as trajectory imputation and prediction. Nowadays, little existing work simultaneously deals with imputation and prediction on human trajectories. This work plans to explore whether the learning process of imputation and prediction could benefit from each other to achieve better outcomes. And the question will be answered by studying the coexistence patterns between missing points and observed ones in incomplete trajectories. More specifically, the proposed model develops an imputation component based on the self-attention mechanism to capture the coexistence patterns between observations and missing points among encoder-decoder layers. Meanwhile, a recurrent unit is integrated to extract the sequential embeddings from newly imputed sequences for predicting the following location. Furthermore, a new implementation called Imputation Cycle is introduced to enable gradual imputation with prediction enhancement at multiple levels, which helps to accelerate the speed of convergence. The experimental results on three different real-world mobility datasets show that the proposed approach has significant advantages over the competitive baselines across both imputation and prediction tasks in terms of accuracy and stability.","PeriodicalId":43641,"journal":{"name":"ACM Transactions on Spatial Algorithms and Systems","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2023-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44100779","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}
Eman Bin Khunayn, Hairuo Xie, S. Karunasekera, K. Ramamohanarao
Spatial simulations have been widely used to study real-world environments, such as transportation systems. Applications like prediction and analysis of transportation require the simulation to handle millions of objects while running faster than real time. Running such large-scale simulation requires high computational power, which can be provided through parallel distributed computing. Implementations of parallel distributed spatial simulations usually follow a bulk synchronous parallel (BSP) model to ensure the correctness of simulation. The processing in BSP is divided into iterations of computation and communication, running on multiple workers, followed by a global barrier synchronisation to ensure that all communications are concluded. Unfortunately, the BSP model is plagued by the straggler problem, where a delay in any worker slows down the entire simulation. Stragglers may occur for many reasons, including imbalanced workload distribution or communication and synchronisation delays. The straggler problem can become more severe with increasing parallelism and continuous change of workload distribution among workers. This article proposes methods to dynamically mitigate stragglers and tackle communication delays. The proposed strategies can rebalance the workload distribution during simulation. These methods employ the spatial properties of the simulated environments to combine a flexible synchronisation model with decentralised dynamic load balancing and on-demand resource allocation. All proposed methods are implemented and evaluated using a microscopic traffic simulator as an example of large-scale spatial simulations. We run traffic simulations for Melbourne, Beijing and New York with different straggler scenarios. Our methods significantly improve simulation performance compared to advanced methods such as global dynamic load balancing.
{"title":"Dynamic Straggler Mitigation for Large-Scale Spatial Simulations","authors":"Eman Bin Khunayn, Hairuo Xie, S. Karunasekera, K. Ramamohanarao","doi":"10.1145/3578933","DOIUrl":"https://doi.org/10.1145/3578933","url":null,"abstract":"Spatial simulations have been widely used to study real-world environments, such as transportation systems. Applications like prediction and analysis of transportation require the simulation to handle millions of objects while running faster than real time. Running such large-scale simulation requires high computational power, which can be provided through parallel distributed computing. Implementations of parallel distributed spatial simulations usually follow a bulk synchronous parallel (BSP) model to ensure the correctness of simulation. The processing in BSP is divided into iterations of computation and communication, running on multiple workers, followed by a global barrier synchronisation to ensure that all communications are concluded. Unfortunately, the BSP model is plagued by the straggler problem, where a delay in any worker slows down the entire simulation. Stragglers may occur for many reasons, including imbalanced workload distribution or communication and synchronisation delays. The straggler problem can become more severe with increasing parallelism and continuous change of workload distribution among workers. This article proposes methods to dynamically mitigate stragglers and tackle communication delays. The proposed strategies can rebalance the workload distribution during simulation. These methods employ the spatial properties of the simulated environments to combine a flexible synchronisation model with decentralised dynamic load balancing and on-demand resource allocation. All proposed methods are implemented and evaluated using a microscopic traffic simulator as an example of large-scale spatial simulations. We run traffic simulations for Melbourne, Beijing and New York with different straggler scenarios. Our methods significantly improve simulation performance compared to advanced methods such as global dynamic load balancing.","PeriodicalId":43641,"journal":{"name":"ACM Transactions on Spatial Algorithms and Systems","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44275670","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}
Yan-Min Luo, C. Leong, Shuhai Jiao, F. Chung, Wenjie Li, Guoping Liu
Cities are very complex systems. Representing urban regions are essential for exploring, understanding, and predicting properties and features of cities. The enrichment of multi-modal urban big data has provided opportunities for researchers to enhance urban region embedding. However, existing works failed to develop an integrated pipeline that fully utilizes effective and informative data sources within geographic units. In this article, we regard a geo-tile as a geographic unit and propose a multi-modal and multi-stage representation learning framework, namely Geo-Tile2Vec, for urban analytics, especially for urban region properties identification. Specifically, in the early stage, geo-tile embeddings are firstly inferred through dynamic mobility events which are combinations of point-of-interest (POI) data and trajectory data by a Word2Vec-like model and metric learning. Then, in the latter stage, we use static street-level imagery to further enrich the embedding information by metric learning. Lastly, the framework learns distributed geo-tile embeddings for the given multi-modal data. We conduct experiments on real-world urban datasets. Four downstream tasks, i.e., main POI category classification task, main land use category classification task, restaurant average price regression task, and firm number regression task, are adopted for validating the effectiveness of the proposed framework in representing geo-tiles. Our proposed framework can significantly improve the performances of all downstream tasks. In addition, we also demonstrate that geo-tiles with similar urban region properties are geometrically closer in the vector space.
{"title":"Geo-Tile2Vec: A Multi-Modal and Multi-Stage Embedding Framework for Urban Analytics","authors":"Yan-Min Luo, C. Leong, Shuhai Jiao, F. Chung, Wenjie Li, Guoping Liu","doi":"10.1145/3571741","DOIUrl":"https://doi.org/10.1145/3571741","url":null,"abstract":"Cities are very complex systems. Representing urban regions are essential for exploring, understanding, and predicting properties and features of cities. The enrichment of multi-modal urban big data has provided opportunities for researchers to enhance urban region embedding. However, existing works failed to develop an integrated pipeline that fully utilizes effective and informative data sources within geographic units. In this article, we regard a geo-tile as a geographic unit and propose a multi-modal and multi-stage representation learning framework, namely Geo-Tile2Vec, for urban analytics, especially for urban region properties identification. Specifically, in the early stage, geo-tile embeddings are firstly inferred through dynamic mobility events which are combinations of point-of-interest (POI) data and trajectory data by a Word2Vec-like model and metric learning. Then, in the latter stage, we use static street-level imagery to further enrich the embedding information by metric learning. Lastly, the framework learns distributed geo-tile embeddings for the given multi-modal data. We conduct experiments on real-world urban datasets. Four downstream tasks, i.e., main POI category classification task, main land use category classification task, restaurant average price regression task, and firm number regression task, are adopted for validating the effectiveness of the proposed framework in representing geo-tiles. Our proposed framework can significantly improve the performances of all downstream tasks. In addition, we also demonstrate that geo-tiles with similar urban region properties are geometrically closer in the vector space.","PeriodicalId":43641,"journal":{"name":"ACM Transactions on Spatial Algorithms and Systems","volume":null,"pages":null},"PeriodicalIF":1.9,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43264800","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：