Pub Date : 2023-07-06DOI: 10.1080/13658816.2023.2229894
J. Huck, J. Whyatt, G. Davies, John Dixon, Brendan Sturgeon, Bree Hocking, C. Tredoux, N. Jarman, Dominic Bryan
Abstract The problem of mapping regions with socially-derived boundaries has been a topic of discussion in the GIS literature for many years. Fuzzy approaches have frequently been suggested as solutions, but none have been adopted. This is likely due to difficulties associated with determining suitable membership functions, which are often as arbitrary as the crisp boundaries that they seek to replace. This paper presents a novel approach to fuzzy geographical modelling that replaces the membership function with a possibility distribution that is estimated using Bayesian inference. In this method, data from multiple sources are combined to estimate the degree to which a given location is a member of a given set and the level of uncertainty associated with that estimate. The Fuzzy Bayesian Inference approach is demonstrated through a case study in which census data are combined with perceptual and behavioural evidence to model the territory of two segregated groups (Catholics and Protestants) in Belfast, Northern Ireland, UK. This novel method provides a robust empirical basis for the use of fuzzy models in GIS, and therefore has applications for mapping a range of socially-derived and otherwise vague boundaries.
{"title":"Fuzzy Bayesian inference for mapping vague and place-based regions: a case study of sectarian territory","authors":"J. Huck, J. Whyatt, G. Davies, John Dixon, Brendan Sturgeon, Bree Hocking, C. Tredoux, N. Jarman, Dominic Bryan","doi":"10.1080/13658816.2023.2229894","DOIUrl":"https://doi.org/10.1080/13658816.2023.2229894","url":null,"abstract":"Abstract The problem of mapping regions with socially-derived boundaries has been a topic of discussion in the GIS literature for many years. Fuzzy approaches have frequently been suggested as solutions, but none have been adopted. This is likely due to difficulties associated with determining suitable membership functions, which are often as arbitrary as the crisp boundaries that they seek to replace. This paper presents a novel approach to fuzzy geographical modelling that replaces the membership function with a possibility distribution that is estimated using Bayesian inference. In this method, data from multiple sources are combined to estimate the degree to which a given location is a member of a given set and the level of uncertainty associated with that estimate. The Fuzzy Bayesian Inference approach is demonstrated through a case study in which census data are combined with perceptual and behavioural evidence to model the territory of two segregated groups (Catholics and Protestants) in Belfast, Northern Ireland, UK. This novel method provides a robust empirical basis for the use of fuzzy models in GIS, and therefore has applications for mapping a range of socially-derived and otherwise vague boundaries.","PeriodicalId":14162,"journal":{"name":"International Journal of Geographical Information Science","volume":"37 1","pages":"1765 - 1786"},"PeriodicalIF":5.7,"publicationDate":"2023-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42303638","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-27DOI: 10.1080/13658816.2023.2213869
Vicente Tang, M. Painho
Abstract The use of social media and location-based networks through GPS-enabled devices provides geospatial data for a plethora of applications in urban studies. However, the extent to which information found in geo-tagged social media activity corresponds to the spatial context is still a topic of debate. In this article, we developed a framework aimed at retrieving the thematic and spatial relationships between content originated from space-based (Twitter) and place-based (Google Places and OSM) sources of geographic user-generated content based on topics identified by the embedding-based BERTopic model. The contribution of the framework lies on the combination of methods that were selected to improve previous works focused on content-location relationships. Using the city of Lisbon (Portugal) to test our methodology, we first applied the embedding-based topic model to aggregated textual data coming from each source. Results of the analysis evidenced the complexity of content-location relationships, which are mostly based on thematic profiles. Nonetheless, the framework can be employed in other cities and extended with other metrics to enrich the research aimed at exploring the correlation between online discourse and geography.
{"title":"Content-location relationships: a framework to explore correlations between space-based and place-based user-generated content","authors":"Vicente Tang, M. Painho","doi":"10.1080/13658816.2023.2213869","DOIUrl":"https://doi.org/10.1080/13658816.2023.2213869","url":null,"abstract":"Abstract The use of social media and location-based networks through GPS-enabled devices provides geospatial data for a plethora of applications in urban studies. However, the extent to which information found in geo-tagged social media activity corresponds to the spatial context is still a topic of debate. In this article, we developed a framework aimed at retrieving the thematic and spatial relationships between content originated from space-based (Twitter) and place-based (Google Places and OSM) sources of geographic user-generated content based on topics identified by the embedding-based BERTopic model. The contribution of the framework lies on the combination of methods that were selected to improve previous works focused on content-location relationships. Using the city of Lisbon (Portugal) to test our methodology, we first applied the embedding-based topic model to aggregated textual data coming from each source. Results of the analysis evidenced the complexity of content-location relationships, which are mostly based on thematic profiles. Nonetheless, the framework can be employed in other cities and extended with other metrics to enrich the research aimed at exploring the correlation between online discourse and geography.","PeriodicalId":14162,"journal":{"name":"International Journal of Geographical Information Science","volume":"37 1","pages":"1840 - 1871"},"PeriodicalIF":5.7,"publicationDate":"2023-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44570584","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-01DOI: 10.1080/13658816.2023.2219288
Jie Yang, Qiliang Liu, Min Deng
Abstract The presence of global spatial autocorrelation usually leads to the spurious identification of spatial hotspots and hinders the identification of local hotspots. Despite the use of statistical methods to address global spatial autocorrelation in spatial hotspot detection, accurately modeling global spatial autocorrelation structure without the stationarity assumption of spatial processes is difficult. To overcome this challenge, we fitted the global spatial autocorrelation structure from a geometric perspective and identified the optimal global spatial autocorrelation structure by analyzing the variances in spatial data. Hotspots were detected from the residuals obtained by removing the global spatial autocorrelation structure from the original dataset. We upgraded a weighted moving average method based on binomial coefficients (Yang Chizhong filtering) to fit the global spatial autocorrelation structure for field-like geographic phenomena. A variance decay indicator, based on the variance in the original and filtered data, was used to identify the optimal global spatial autocorrelation structure. Yang Chizhong filtering does not require a spatial stationarity assumption and can preserve local autocorrelation structures in the residuals as much as possible. Experimental results showed that hotspot detection methods combined with Yang Chizhong filtering can effectively reduce type-I and -II errors in the results and discover implicit and valuable urban hotspots.
{"title":"Spatial hotspot detection in the presence of global spatial autocorrelation","authors":"Jie Yang, Qiliang Liu, Min Deng","doi":"10.1080/13658816.2023.2219288","DOIUrl":"https://doi.org/10.1080/13658816.2023.2219288","url":null,"abstract":"Abstract The presence of global spatial autocorrelation usually leads to the spurious identification of spatial hotspots and hinders the identification of local hotspots. Despite the use of statistical methods to address global spatial autocorrelation in spatial hotspot detection, accurately modeling global spatial autocorrelation structure without the stationarity assumption of spatial processes is difficult. To overcome this challenge, we fitted the global spatial autocorrelation structure from a geometric perspective and identified the optimal global spatial autocorrelation structure by analyzing the variances in spatial data. Hotspots were detected from the residuals obtained by removing the global spatial autocorrelation structure from the original dataset. We upgraded a weighted moving average method based on binomial coefficients (Yang Chizhong filtering) to fit the global spatial autocorrelation structure for field-like geographic phenomena. A variance decay indicator, based on the variance in the original and filtered data, was used to identify the optimal global spatial autocorrelation structure. Yang Chizhong filtering does not require a spatial stationarity assumption and can preserve local autocorrelation structures in the residuals as much as possible. Experimental results showed that hotspot detection methods combined with Yang Chizhong filtering can effectively reduce type-I and -II errors in the results and discover implicit and valuable urban hotspots.","PeriodicalId":14162,"journal":{"name":"International Journal of Geographical Information Science","volume":"37 1","pages":"1787 - 1817"},"PeriodicalIF":5.7,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49653836","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-01DOI: 10.1080/13658816.2023.2217443
B. Chen, Yuhua Luo, Yu Zhang, Tao Jia, Hui-Ping Chen, Jianya Gong, Qingquan Li
Abstract Clustering the trajectories of vehicles moving on road networks is a key data mining technique for understanding human mobility patterns, as well as their interactions with urban environments. The development of efficient and scalable trajectory clustering algorithms, however, still faces challenges because of the computational costs when measuring similarities among a large number of network-constrained trajectories. To address this problem, a novel trajectory clustering framework based on the well-developed Density-Based Spatial Clustering of Applications with Noise (DBSCAN) approach is proposed. This proposed framework accurately quantifies similarities using a trajectory representation of continuous polylines in the space and time dimensions, and does not require trajectory discretization. Further, the proposed framework utilizes the space-time buffering concept to formulate -neighborhood queries that directly retrieve the -neighbors of trajectories and thus avoids computing a trajectory similarity matrix. State-of-the-art trajectory databases and index structures are incorporated to further improve trajectory clustering performance. A comprehensive case study was carried out using an open dataset of 20,161 trajectories. Results show that the proposed framework efficiently executed trajectory clustering on the large test dataset within 3 min. This was approximately 2,700 times faster than existing DBSCAN algorithms.
{"title":"Efficient and scalable DBSCAN framework for clustering continuous trajectories in road networks","authors":"B. Chen, Yuhua Luo, Yu Zhang, Tao Jia, Hui-Ping Chen, Jianya Gong, Qingquan Li","doi":"10.1080/13658816.2023.2217443","DOIUrl":"https://doi.org/10.1080/13658816.2023.2217443","url":null,"abstract":"Abstract Clustering the trajectories of vehicles moving on road networks is a key data mining technique for understanding human mobility patterns, as well as their interactions with urban environments. The development of efficient and scalable trajectory clustering algorithms, however, still faces challenges because of the computational costs when measuring similarities among a large number of network-constrained trajectories. To address this problem, a novel trajectory clustering framework based on the well-developed Density-Based Spatial Clustering of Applications with Noise (DBSCAN) approach is proposed. This proposed framework accurately quantifies similarities using a trajectory representation of continuous polylines in the space and time dimensions, and does not require trajectory discretization. Further, the proposed framework utilizes the space-time buffering concept to formulate -neighborhood queries that directly retrieve the -neighbors of trajectories and thus avoids computing a trajectory similarity matrix. State-of-the-art trajectory databases and index structures are incorporated to further improve trajectory clustering performance. A comprehensive case study was carried out using an open dataset of 20,161 trajectories. Results show that the proposed framework efficiently executed trajectory clustering on the large test dataset within 3 min. This was approximately 2,700 times faster than existing DBSCAN algorithms.","PeriodicalId":14162,"journal":{"name":"International Journal of Geographical Information Science","volume":"37 1","pages":"1693 - 1727"},"PeriodicalIF":5.7,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46911449","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-24DOI: 10.1080/13658816.2023.2193969
T. Bayer, I. Kolingerová, Marek Celonk, J. Lysák
Abstract This paper introduces a new simplification method providing high-quality contour lines derived from the 3D point cloud, minimizing their energy. It combines the simplification potential and the splines with the generalized axial symmetry. Generating results similar to the topological skeleton, it applies to large-scale maps (1:5000–1:25,000). It significantly improves all geometric and shape parameters of contour lines, namely in flatter areas. Extensive cartographic testing on high spatial density point clouds using 17 invariants is performed. The outcomes indicate the significant potential of the proposed method. The simplified contour lines preserve the given vertical error, lie within the vertical buffer, are parallel, aesthetically pleasing, and have similar spacing; their artificial oscillations are significantly reduced. Unlike complex generalization methods, the proposed solution does not interfere with the DTM but performs only a correction of the cartographic representation of contour lines.
{"title":"Simplification of contour lines, based on axial splines, with high-quality results","authors":"T. Bayer, I. Kolingerová, Marek Celonk, J. Lysák","doi":"10.1080/13658816.2023.2193969","DOIUrl":"https://doi.org/10.1080/13658816.2023.2193969","url":null,"abstract":"Abstract This paper introduces a new simplification method providing high-quality contour lines derived from the 3D point cloud, minimizing their energy. It combines the simplification potential and the splines with the generalized axial symmetry. Generating results similar to the topological skeleton, it applies to large-scale maps (1:5000–1:25,000). It significantly improves all geometric and shape parameters of contour lines, namely in flatter areas. Extensive cartographic testing on high spatial density point clouds using 17 invariants is performed. The outcomes indicate the significant potential of the proposed method. The simplified contour lines preserve the given vertical error, lie within the vertical buffer, are parallel, aesthetically pleasing, and have similar spacing; their artificial oscillations are significantly reduced. Unlike complex generalization methods, the proposed solution does not interfere with the DTM but performs only a correction of the cartographic representation of contour lines.","PeriodicalId":14162,"journal":{"name":"International Journal of Geographical Information Science","volume":"37 1","pages":"1520 - 1554"},"PeriodicalIF":5.7,"publicationDate":"2023-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43891523","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-23DOI: 10.1080/13658816.2023.2214592
Stephen Law, Rikuo Hasegawa, Brooks Paige, C. Russell, Andrew Elliott
Abstract We propose a new form of plausible counterfactual explanation designed to explain the behaviour of computer vision systems used in urban analytics that make predictions based on properties across the entire image, rather than specific regions of it. We illustrate the merits of our approach by explaining computer vision models used to analyse street imagery, which are now widely used in GeoAI and urban analytics. Such explanations are important in urban analytics as researchers and practioners are increasingly reliant on it for decision making. Finally, we perform a user study that demonstrate our approach can be used by non-expert users, who might not be machine learning experts, to be more confident and to better understand the behaviour of image-based classifiers/regressors for street view analysis. Furthermore, the method can potentially be used as an engagement tool to visualise how public spaces can plausibly look like. The limited realism of the counterfactuals is a concern which we hope to improve in the future.
{"title":"Explaining holistic image regressors and classifiers in urban analytics with plausible counterfactuals","authors":"Stephen Law, Rikuo Hasegawa, Brooks Paige, C. Russell, Andrew Elliott","doi":"10.1080/13658816.2023.2214592","DOIUrl":"https://doi.org/10.1080/13658816.2023.2214592","url":null,"abstract":"Abstract We propose a new form of plausible counterfactual explanation designed to explain the behaviour of computer vision systems used in urban analytics that make predictions based on properties across the entire image, rather than specific regions of it. We illustrate the merits of our approach by explaining computer vision models used to analyse street imagery, which are now widely used in GeoAI and urban analytics. Such explanations are important in urban analytics as researchers and practioners are increasingly reliant on it for decision making. Finally, we perform a user study that demonstrate our approach can be used by non-expert users, who might not be machine learning experts, to be more confident and to better understand the behaviour of image-based classifiers/regressors for street view analysis. Furthermore, the method can potentially be used as an engagement tool to visualise how public spaces can plausibly look like. The limited realism of the counterfactuals is a concern which we hope to improve in the future.","PeriodicalId":14162,"journal":{"name":"International Journal of Geographical Information Science","volume":" ","pages":""},"PeriodicalIF":5.7,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49547376","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-15DOI: 10.1080/13658816.2023.2206890
Cyrill Delfgou, Nikolaos Bakogiannis, P. Laube
Abstract Digital map processing promises computational methods for the extraction of geographic features from scanned historical maps. Such workflows are error prone, with potential spatial uncertainty arising from the initial map production, the processing of the feature extraction, and the eventual application and use of the extracted features. This paper investigates several types of uncertainty emerging the extraction of hydrological features from historical topographic maps for the monitoring of change in ecological indicators describing river ecosystems, such as shoreline length, river sinuosity or number of river nodes and islands. Computational procedures have been developed to simulate various typical, expected sources of error. In a series of experiments investigating three different typical river types, the errors were systematically varied and increased using Monte Carlo simulation whilst studying the errors’ impacts on the derived ecological indicators. The results suggest that production-oriented uncertainties emerging the initial map generalization and simplification process have bigger impacts than processing-oriented uncertainties, such as errors from manual digitizing. The results further indicate that the derivation of ecological indicators from braided rivers is more error prone than from straight or meandering rivers, and that topological indicators such as river sinuosity are more robust than indicators derived from the features’ geometry.
{"title":"Uncertainty analysis of geodata derived from digital map processing","authors":"Cyrill Delfgou, Nikolaos Bakogiannis, P. Laube","doi":"10.1080/13658816.2023.2206890","DOIUrl":"https://doi.org/10.1080/13658816.2023.2206890","url":null,"abstract":"Abstract Digital map processing promises computational methods for the extraction of geographic features from scanned historical maps. Such workflows are error prone, with potential spatial uncertainty arising from the initial map production, the processing of the feature extraction, and the eventual application and use of the extracted features. This paper investigates several types of uncertainty emerging the extraction of hydrological features from historical topographic maps for the monitoring of change in ecological indicators describing river ecosystems, such as shoreline length, river sinuosity or number of river nodes and islands. Computational procedures have been developed to simulate various typical, expected sources of error. In a series of experiments investigating three different typical river types, the errors were systematically varied and increased using Monte Carlo simulation whilst studying the errors’ impacts on the derived ecological indicators. The results suggest that production-oriented uncertainties emerging the initial map generalization and simplification process have bigger impacts than processing-oriented uncertainties, such as errors from manual digitizing. The results further indicate that the derivation of ecological indicators from braided rivers is more error prone than from straight or meandering rivers, and that topological indicators such as river sinuosity are more robust than indicators derived from the features’ geometry.","PeriodicalId":14162,"journal":{"name":"International Journal of Geographical Information Science","volume":"37 1","pages":"1667 - 1691"},"PeriodicalIF":5.7,"publicationDate":"2023-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48762390","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-12DOI: 10.1080/13658816.2023.2209811
D. Murakami, N. Tsutsumida, T. Yoshida, T. Nakaya, Binbin Lu, P. Harris
Abstract Although geographically weighted Poisson regression (GWPR) is a popular regression for spatially indexed count data, its development is relatively limited compared to that found for linear geographically weighted regression (GWR), where many extensions (e.g. multiscale GWR, scalable GWR) have been proposed. The weak development of GWPR can be attributed to the computational cost and identification problem in the underpinning Poisson regression model. This study proposes linearized GWPR (L-GWPR) by introducing a log-linear approximation into the GWPR model to overcome these bottlenecks. Because the L-GWPR model is identical to the Gaussian GWR model, it is free from the identification problem, easily implemented, computationally efficient, and offers similar potential for extension. Specifically, L-GWPR does not require a double-loop algorithm, which makes GWPR slow for large samples. Furthermore, we extended L-GWPR by introducing ridge regularization to enhance its stability (regularized L-GWPR). The results of the Monte Carlo experiments confirmed that regularized L-GWPR estimates local coefficients accurately and computationally efficiently. Finally, we compared GWPR and regularized L-GWPR through a crime analysis in Tokyo.
{"title":"A linearization for stable and fast geographically weighted Poisson regression","authors":"D. Murakami, N. Tsutsumida, T. Yoshida, T. Nakaya, Binbin Lu, P. Harris","doi":"10.1080/13658816.2023.2209811","DOIUrl":"https://doi.org/10.1080/13658816.2023.2209811","url":null,"abstract":"Abstract Although geographically weighted Poisson regression (GWPR) is a popular regression for spatially indexed count data, its development is relatively limited compared to that found for linear geographically weighted regression (GWR), where many extensions (e.g. multiscale GWR, scalable GWR) have been proposed. The weak development of GWPR can be attributed to the computational cost and identification problem in the underpinning Poisson regression model. This study proposes linearized GWPR (L-GWPR) by introducing a log-linear approximation into the GWPR model to overcome these bottlenecks. Because the L-GWPR model is identical to the Gaussian GWR model, it is free from the identification problem, easily implemented, computationally efficient, and offers similar potential for extension. Specifically, L-GWPR does not require a double-loop algorithm, which makes GWPR slow for large samples. Furthermore, we extended L-GWPR by introducing ridge regularization to enhance its stability (regularized L-GWPR). The results of the Monte Carlo experiments confirmed that regularized L-GWPR estimates local coefficients accurately and computationally efficiently. Finally, we compared GWPR and regularized L-GWPR through a crime analysis in Tokyo.","PeriodicalId":14162,"journal":{"name":"International Journal of Geographical Information Science","volume":"37 1","pages":"1818 - 1839"},"PeriodicalIF":5.7,"publicationDate":"2023-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46221205","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-08DOI: 10.1080/13658816.2023.2204345
Xiaorui Yan, T. Pei, Hua Shu, Ci Song, Mingbo Wu, Zidong Fang, Jie Chen
Abstract A geographical flow (hereafter flow) is defined as a movement between locations at two different times. A group of spatiotemporal flows can be viewed as a cluster if their origins and destinations are both spatiotemporally concentrated. Identifying spatiotemporal flow clusters may help reveal underlying spatiotemporal mobility trends or intensive relationships between regions. Despite recent advances in flow clustering methods, most only consider spatial attributes and ignore temporal information, and may fail to differentiate space-close but time-separated clusters. To this end, we derive global and local versions of the Spatiotemporal Flow L-function, extended from the classical L-function for points, and thereby construct a clustering method. First, the global version is utilized to check whether flow data contain clusters and estimate the spatial and temporal scales of the clusters. The local version is then employed to extract the clusters with the estimated scales. Experiments of simulated data demonstrate that our method outperforms three state-of-the-art methods in identifying spatiotemporal flow clusters with arbitrary shapes and different densities and reducing subjectivity in the parameter selection process. A case study with taxi data shows that our method reveals residents’ spatiotemporal moving patterns, including rush-hour commuting and whole-daytime transferring among railway stations.
{"title":"Spatiotemporal Flow L-function: a new method for identifying spatiotemporal clusters in geographical flow data","authors":"Xiaorui Yan, T. Pei, Hua Shu, Ci Song, Mingbo Wu, Zidong Fang, Jie Chen","doi":"10.1080/13658816.2023.2204345","DOIUrl":"https://doi.org/10.1080/13658816.2023.2204345","url":null,"abstract":"Abstract A geographical flow (hereafter flow) is defined as a movement between locations at two different times. A group of spatiotemporal flows can be viewed as a cluster if their origins and destinations are both spatiotemporally concentrated. Identifying spatiotemporal flow clusters may help reveal underlying spatiotemporal mobility trends or intensive relationships between regions. Despite recent advances in flow clustering methods, most only consider spatial attributes and ignore temporal information, and may fail to differentiate space-close but time-separated clusters. To this end, we derive global and local versions of the Spatiotemporal Flow L-function, extended from the classical L-function for points, and thereby construct a clustering method. First, the global version is utilized to check whether flow data contain clusters and estimate the spatial and temporal scales of the clusters. The local version is then employed to extract the clusters with the estimated scales. Experiments of simulated data demonstrate that our method outperforms three state-of-the-art methods in identifying spatiotemporal flow clusters with arbitrary shapes and different densities and reducing subjectivity in the parameter selection process. A case study with taxi data shows that our method reveals residents’ spatiotemporal moving patterns, including rush-hour commuting and whole-daytime transferring among railway stations.","PeriodicalId":14162,"journal":{"name":"International Journal of Geographical Information Science","volume":"37 1","pages":"1615 - 1639"},"PeriodicalIF":5.7,"publicationDate":"2023-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45152182","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Different types of roads in complex road networks may run side-by-side or across in 2D or 3D spaces, which causes mismatched segments using existing online map-matching algorithms. A driving scenario that represents the driving environment can inform map-matching algorithms. Images from vehicle cameras contain extensive information about driving scenarios, such as surrounding key objects. This research utilized vehicle images and developed an object-based method to classify driving scenarios (Object-Based Driving-Scenario Classification: OBDSC) to calculate the probabilities of the current image in predefined types of driving scenarios. We implemented an online map-matching algorithm with the OBDSC method (OMM-OBDSC) to obtain optimal matching segments. The algorithm was tested on nine trajectories and OpenStreetMap data in Shanghai and compared with five benchmark algorithms in terms of the match rate, recall and accuracy. The OBDSC method is also applied to the benchmark algorithms to verify the effectiveness of map matching. The results show that our algorithm outperforms the benchmark algorithms with both the original interval and downsampled intervals (96.6%, 96.5%, 93.7% on average with 1–20 s intervals for the three metrics, respectively). The average match rate has improved by 8.9% for all benchmark algorithms after the addition of the OBDSC method.
{"title":"Online map-matching assisted by object-based classification of driving scenario","authors":"Hangbin Wu, Sheng-Min Huang, Chen Fu, Sha Xu, Junhua Wang, Weizhou Huang, Chongxing Liu","doi":"10.1080/13658816.2023.2206877","DOIUrl":"https://doi.org/10.1080/13658816.2023.2206877","url":null,"abstract":"Abstract Different types of roads in complex road networks may run side-by-side or across in 2D or 3D spaces, which causes mismatched segments using existing online map-matching algorithms. A driving scenario that represents the driving environment can inform map-matching algorithms. Images from vehicle cameras contain extensive information about driving scenarios, such as surrounding key objects. This research utilized vehicle images and developed an object-based method to classify driving scenarios (Object-Based Driving-Scenario Classification: OBDSC) to calculate the probabilities of the current image in predefined types of driving scenarios. We implemented an online map-matching algorithm with the OBDSC method (OMM-OBDSC) to obtain optimal matching segments. The algorithm was tested on nine trajectories and OpenStreetMap data in Shanghai and compared with five benchmark algorithms in terms of the match rate, recall and accuracy. The OBDSC method is also applied to the benchmark algorithms to verify the effectiveness of map matching. The results show that our algorithm outperforms the benchmark algorithms with both the original interval and downsampled intervals (96.6%, 96.5%, 93.7% on average with 1–20 s intervals for the three metrics, respectively). The average match rate has improved by 8.9% for all benchmark algorithms after the addition of the OBDSC method.","PeriodicalId":14162,"journal":{"name":"International Journal of Geographical Information Science","volume":"37 1","pages":"1872 - 1907"},"PeriodicalIF":5.7,"publicationDate":"2023-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44266951","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}