Pub Date : 2022-06-10DOI: 10.5194/agile-giss-3-18-2022
Frederika Welle Donker, B. Van Loenen, C. Kessler, Natalie Küppers, Mark Panek, A. Mansourian, Pengxiang Zhou, G. Vancauwenberghe, H. Tomić, Karlo Kević
Abstract. The new concept of Open Spatial Data Infrastructures (Open SDIs) has emerged from an increased interest in open data initiatives together with national and international directives, such as the EU Open Data Directive (Directive (EU) 2019/1024), and the large investment of European public authorities in developing SDIs for sharing spatial data within public authorities. Open SDIs have the potential to boost reaching SDIs’ general aims and goals of facilitating the exchange and sharing of spatial data to support planning and decision-making by including public participation and increased openness in all aspects of SDIs, including Open SDI Education. The open SPatial data Infrastructure eDucation nEtwoRk (SPIDER) project aims to address Open SDI Education by particular emphasis on studying Active Learning and Teaching (ALT) methods for SDI education. This article provides a theoretical basis of ALT for SDI methodologies. We show in which way ALT practices were already implemented in SDI education at the Partner universities before the COVID-19 pandemic. We also describe how the pandemic functioned as a catalyst for implementing ALT practices to an online environment, and how students evaluated these practices. The outcomes of our research can serve as an inspiration for SDI education in other countries.
{"title":"Showcase of Active Learning and Teaching Practices in Spatial Data Infrastructure (SDI) Education","authors":"Frederika Welle Donker, B. Van Loenen, C. Kessler, Natalie Küppers, Mark Panek, A. Mansourian, Pengxiang Zhou, G. Vancauwenberghe, H. Tomić, Karlo Kević","doi":"10.5194/agile-giss-3-18-2022","DOIUrl":"https://doi.org/10.5194/agile-giss-3-18-2022","url":null,"abstract":"Abstract. The new concept of Open Spatial Data Infrastructures (Open SDIs) has emerged from an increased interest in open data initiatives together with national and international directives, such as the EU Open Data Directive (Directive (EU) 2019/1024), and the large investment of European public authorities in developing SDIs for sharing spatial data within public authorities. Open SDIs have the potential to boost reaching SDIs’ general aims and goals of facilitating the exchange and sharing of spatial data to support planning and decision-making by including public participation and increased openness in all aspects of SDIs, including Open SDI Education. The open SPatial data Infrastructure eDucation nEtwoRk (SPIDER) project aims to address Open SDI Education by particular emphasis on studying Active Learning and Teaching (ALT) methods for SDI education. This article provides a theoretical basis of ALT for SDI methodologies. We show in which way ALT practices were already implemented in SDI education at the Partner universities before the COVID-19 pandemic. We also describe how the pandemic functioned as a catalyst for implementing ALT practices to an online environment, and how students evaluated these practices. The outcomes of our research can serve as an inspiration for SDI education in other countries.\u0000","PeriodicalId":116168,"journal":{"name":"AGILE: GIScience Series","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125231644","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-10DOI: 10.5194/agile-giss-3-9-2022
Zilong Liu, K. Janowicz, Ling Cai, Rui Zhu, Gengchen Mai, Meilin Shi
Abstract. Geoparsing, the task of extracting toponyms from texts and associating them with geographic locations, has witnessed remarkable progress over the past years. However, despite its intrinsically geospatial nature, existing evaluations tend to focus on overall performance while paying little attention to its variation across geographic space. In this work, we attempt to answer the question whether geoparsing is solved or biased by conducting a spatially-explicit evaluation, namely an evaluation of the regional variability in geoparsing performance. Particularly, we will analyze the spatial autocorrelation underlying this regional variability. By performing hot and cold spot detection over results of several open-source geoparsers, we observe that none of them performs equally well across geographic space, and some are geographically biased towards some regions but against others. We also carry out a comparative experiment showing that stateof- the-art geoparsers developed with neural networks do not necessarily outperform the off-the-shelf tools across geographic space. To understand the implications behind this observed regional variability, we evaluate geographic biases involved in geoparsing research centered around data contribution and usage, algorithm design, and performance evaluations. Particularly, our spatially-explicit performance evaluation serves as an approach to evaluation bias mitigation in geoparsing.We conclude that previous performance evaluations published in the literature are overly optimistic, thus hiding the fact that geoparsing is far from solved, and geoparsers require debiasing in addition to further considerations when being applied to (geospatial) downstream tasks.
{"title":"Geoparsing: Solved or Biased? An Evaluation of Geographic Biases in Geoparsing","authors":"Zilong Liu, K. Janowicz, Ling Cai, Rui Zhu, Gengchen Mai, Meilin Shi","doi":"10.5194/agile-giss-3-9-2022","DOIUrl":"https://doi.org/10.5194/agile-giss-3-9-2022","url":null,"abstract":"Abstract. Geoparsing, the task of extracting toponyms from texts and associating them with geographic locations, has witnessed remarkable progress over the past years. However, despite its intrinsically geospatial nature, existing evaluations tend to focus on overall performance while paying little attention to its variation across geographic space. In this work, we attempt to answer the question whether geoparsing is solved or biased by conducting a spatially-explicit evaluation, namely an evaluation of the regional variability in geoparsing performance. Particularly, we will analyze the spatial autocorrelation underlying this regional variability. By performing hot and cold spot detection over results of several open-source geoparsers, we observe that none of them performs equally well across geographic space, and some are geographically biased towards some regions but against others. We also carry out a comparative experiment showing that stateof- the-art geoparsers developed with neural networks do not necessarily outperform the off-the-shelf tools across geographic space. To understand the implications behind this observed regional variability, we evaluate geographic biases involved in geoparsing research centered around data contribution and usage, algorithm design, and performance evaluations. Particularly, our spatially-explicit performance evaluation serves as an approach to evaluation bias mitigation in geoparsing.We conclude that previous performance evaluations published in the literature are overly optimistic, thus hiding the fact that geoparsing is far from solved, and geoparsers require debiasing in addition to further considerations when being applied to (geospatial) downstream tasks.\u0000","PeriodicalId":116168,"journal":{"name":"AGILE: GIScience Series","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131047217","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-10DOI: 10.5194/agile-giss-3-37-2022
Marius Hogräfer, J. Grønbæk, Jana Puschmann, Sebastian Krog Knudsen, Hans-Jörg Schulz
Abstract. One of the challenges that GIS users in diverse, distributed teams face these days is being able to efficiently collaborate, both across workspaces and tools. To that end, we present MapBlender, a cybercartographic application that fosters geocollaboration by adapting a collaboration-first approach, placing users and their GIS tools on equal footing. MapBlender allows all connected users to share video feeds of their GIS tools and webcams, which can then be freely rearranged and re-sized, adopting simple and familiar interaction techniques from modern window managers. In addition, the rendering and translucency of these feeds can be adjusted, allowing users to align and analyze information across tools. We demonstrate the utility of MapBlender in a hybrid teaching scenario, wherein a representative of a software company uses our application to instruct co-located and remote learners from another company on the features of their GIS tool. MapBlender is publicly available under open source licenses and runs in the browser, with no local installation necessary. Thus, with MapBlender in place, one of our goals is to promote an HCI perspective on future work in geocollaboration.
{"title":"Enabling Collaborative Cybercartography with MapBlender","authors":"Marius Hogräfer, J. Grønbæk, Jana Puschmann, Sebastian Krog Knudsen, Hans-Jörg Schulz","doi":"10.5194/agile-giss-3-37-2022","DOIUrl":"https://doi.org/10.5194/agile-giss-3-37-2022","url":null,"abstract":"Abstract. One of the challenges that GIS users in diverse, distributed teams face these days is being able to efficiently collaborate, both across workspaces and tools. To that end, we present MapBlender, a cybercartographic application that fosters geocollaboration by adapting a collaboration-first approach, placing users and their GIS tools on equal footing. MapBlender allows all connected users to share video feeds of their GIS tools and webcams, which can then be freely rearranged and re-sized, adopting simple and familiar interaction techniques from modern window managers. In addition, the rendering and translucency of these feeds can be adjusted, allowing users to align and analyze information across tools. We demonstrate the utility of MapBlender in a hybrid teaching scenario, wherein a representative of a software company uses our application to instruct co-located and remote learners from another company on the features of their GIS tool. MapBlender is publicly available under open source licenses and runs in the browser, with no local installation necessary. Thus, with MapBlender in place, one of our goals is to promote an HCI perspective on future work in geocollaboration.\u0000","PeriodicalId":116168,"journal":{"name":"AGILE: GIScience Series","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134076938","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-10DOI: 10.5194/agile-giss-3-40-2022
Jérémy Kalsron, Jean Favreau, G. Touya
Abstract. Crossing an intersection is a challenge for visually impaired people. While tactile maps can be a medium for appropriating this complex space, they benefit from being complemented by audio information. In this paper we propose a data model to describe an intersection, the paths that allow to cross it, and their accessibility attributes. We also present methods to generate this model automatically from OpenStreetMap, by inferring missing data through graph analysis techniques. Finally, we present an implementation, the evaluation of which confirms the ability of the model to generate a compliant description for intersections with enough data.
{"title":"CrossroadsDescriber – Automatic Textual Description of OpenStreetMap Intersections","authors":"Jérémy Kalsron, Jean Favreau, G. Touya","doi":"10.5194/agile-giss-3-40-2022","DOIUrl":"https://doi.org/10.5194/agile-giss-3-40-2022","url":null,"abstract":"Abstract. Crossing an intersection is a challenge for visually impaired people. While tactile maps can be a medium for appropriating this complex space, they benefit from being complemented by audio information. In this paper we propose a data model to describe an intersection, the paths that allow to cross it, and their accessibility attributes. We also present methods to generate this model automatically from OpenStreetMap, by inferring missing data through graph analysis techniques. Finally, we present an implementation, the evaluation of which confirms the ability of the model to generate a compliant description for intersections with enough data.\u0000","PeriodicalId":116168,"journal":{"name":"AGILE: GIScience Series","volume":"41 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133293651","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-10DOI: 10.5194/agile-giss-3-4-2022
Jean Favreau, Jérémy Kalsron
Abstract. The increase of accessibility and pedestrian data in geographic databases such as OpenStreetMap brings with it the possibility to find a number of applications for pedestrian users.The way in which different urban spaces are crossed obviously depends on their nature. In particular, crossing an intersection is not the same as walking along a street. Intersections are particularly complex areas, where crossing is almost mandatory, often with several possible routes.Although there are various works in the literature that are interested in locating these intersections in a road network, to our knowledge there is no work that deals with the precise segmentation of intersections at the scale of pedestrian use.In this article, we propose an approach that allows us to segment the OpenStreetMap street network at the pedestrian level, by precisely identifying the boundaries between intersections and other spaces.By combining the geometry, topology and semantics of the urban automobile network of OpenStreetMap, we propose an algorithm for locating elementary intersections, and then successively assembling them in a multi-scale approach, in order to obtain the intersections as they are considered by pedestrians during their movements. In particular, our approach relies on the elements that constitute the boundaries of these intersections, such as pedestrian crossings and traffic lights.After presenting an implementation of this approach, we offer a number of results that illustrate the robustness of the proposed approach.
{"title":"What are intersections for pedestrian users?","authors":"Jean Favreau, Jérémy Kalsron","doi":"10.5194/agile-giss-3-4-2022","DOIUrl":"https://doi.org/10.5194/agile-giss-3-4-2022","url":null,"abstract":"Abstract. The increase of accessibility and pedestrian data in geographic databases such as OpenStreetMap brings with it the possibility to find a number of applications for pedestrian users.The way in which different urban spaces are crossed obviously depends on their nature. In particular, crossing an intersection is not the same as walking along a street. Intersections are particularly complex areas, where crossing is almost mandatory, often with several possible routes.Although there are various works in the literature that are interested in locating these intersections in a road network, to our knowledge there is no work that deals with the precise segmentation of intersections at the scale of pedestrian use.In this article, we propose an approach that allows us to segment the OpenStreetMap street network at the pedestrian level, by precisely identifying the boundaries between intersections and other spaces.By combining the geometry, topology and semantics of the urban automobile network of OpenStreetMap, we propose an algorithm for locating elementary intersections, and then successively assembling them in a multi-scale approach, in order to obtain the intersections as they are considered by pedestrians during their movements. In particular, our approach relies on the elements that constitute the boundaries of these intersections, such as pedestrian crossings and traffic lights.After presenting an implementation of this approach, we offer a number of results that illustrate the robustness of the proposed approach.\u0000","PeriodicalId":116168,"journal":{"name":"AGILE: GIScience Series","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132580513","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-10DOI: 10.5194/agile-giss-3-26-2022
Golan Ben-Dor, A. Ogulenko, Ido Klein, I. Benenson
Abstract. Transportation Network Companies (TNC), like Uber, Lyft, and VIA, started their activities a decade ago with a far-reaching hope that Mobility-On-Demand (MOD) transportation services would decelerate or even stop the ever-growing congestion. However, it didn't happen; the negative incentives, like congestion charges and higher parking prices, seem to be the only policy tools for influencing congestion and associated negative externalities like pollution and noise. The question is whether we can establish socially acceptable congestion charges and parking prices that will effectively reduce the arrivals and traffic in highly congested areas and become the background for the future MOD arrangement? We employ the MATSim agent-based simulation model (Horni et al., 2016) of multi-modal traffic in Jerusalem Metropolitan Area (JMA) to address this problem. We investigate whether the combination of congestion and parking prices can force drivers to use Public Transport (PT), thus reducing arrivals with the private cars into the center of the city. The model study demonstrates that a reasonable charge of 7–12€ for entering the city center could decrease arrivals by 25%. From the transport policy point of view, the effects of congestion charges and parking prices are different – the increase in the congestion charges decreases arrivals. In contrast, the increase in parking prices decreases the dwell time. We discuss the policy consequences of employing each of the two mechanisms.
摘要十年前，Uber、Lyft和VIA等交通网络公司(TNC)就开始了他们的活动，希望按需出行(MOD)运输服务能够减缓甚至阻止日益严重的拥堵。然而，这并没有发生;负面激励措施，如拥堵费和更高的停车费，似乎是影响拥堵和相关的负面外部性(如污染和噪音)的唯一政策工具。问题是，我们能否订立社会可接受的交通挤塞费和泊车费，以有效减少高度挤塞地区的抵港人数和交通流量，并作为日后交通运输署安排的背景?我们采用基于MATSim代理的耶路撒冷大都市区(JMA)多模式交通仿真模型(Horni et al.， 2016)来解决这个问题。我们研究了拥堵和停车价格的结合是否会迫使司机使用公共交通工具，从而减少私家车进入市中心的数量。模型研究表明，进入市中心收取7-12欧元的合理费用可能会减少25%的入境人数。从交通政策的角度来看，拥堵费和停车费的影响是不同的——拥堵费的增加会减少到达的车辆。相反，停车价格的上涨减少了停留时间。我们将讨论采用这两种机制的政策后果。
{"title":"Modeling the Effect of Congestion Charge and Parking Pricing on Urban Traffic: Example of Jerusalem","authors":"Golan Ben-Dor, A. Ogulenko, Ido Klein, I. Benenson","doi":"10.5194/agile-giss-3-26-2022","DOIUrl":"https://doi.org/10.5194/agile-giss-3-26-2022","url":null,"abstract":"Abstract. Transportation Network Companies (TNC), like Uber, Lyft, and VIA, started their activities a decade ago with a far-reaching hope that Mobility-On-Demand (MOD) transportation services would decelerate or even stop the ever-growing congestion. However, it didn't happen; the negative incentives, like congestion charges and higher parking prices, seem to be the only policy tools for influencing congestion and associated negative externalities like pollution and noise. The question is whether we can establish socially acceptable congestion charges and parking prices that will effectively reduce the arrivals and traffic in highly congested areas and become the background for the future MOD arrangement? We employ the MATSim agent-based simulation model (Horni et al., 2016) of multi-modal traffic in Jerusalem Metropolitan Area (JMA) to address this problem. We investigate whether the combination of congestion and parking prices can force drivers to use Public Transport (PT), thus reducing arrivals with the private cars into the center of the city. The model study demonstrates that a reasonable charge of 7–12€ for entering the city center could decrease arrivals by 25%. From the transport policy point of view, the effects of congestion charges and parking prices are different – the increase in the congestion charges decreases arrivals. In contrast, the increase in parking prices decreases the dwell time. We discuss the policy consequences of employing each of the two mechanisms.\u0000","PeriodicalId":116168,"journal":{"name":"AGILE: GIScience Series","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115457139","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-10DOI: 10.5194/agile-giss-3-1-2022
T. Bartoschek, A. Schwering
Abstract. GIS have been coined as a support to thinking and learning spatially. In particular spatial learning in real environments can be supported by Geotechnologies as location-based games. We investigate how the use of a custom map-based geocaching game influences the individual development of spatial abilities and sketch mapping. We present a cross-cultural study with primary school children consisting of two spatial ability tests and a sketch map task in a pre- and post-test setting. Improvements were found in mental rotation and sketch map perspective, individual differences in culture and gender decreased for the experimental group. We conclude with a discussion of prospects and problems of integrating this type of GIS into education and learning.
{"title":"Geotechnology-based Spatial Learning: The Effects on Spatial Abilities and Sketch Maps in an Inter-Cultural Study","authors":"T. Bartoschek, A. Schwering","doi":"10.5194/agile-giss-3-1-2022","DOIUrl":"https://doi.org/10.5194/agile-giss-3-1-2022","url":null,"abstract":"Abstract. GIS have been coined as a support to thinking and learning spatially. In particular spatial learning in real environments can be supported by Geotechnologies as location-based games. We investigate how the use of a custom map-based geocaching game influences the individual development of spatial abilities and sketch mapping. We present a cross-cultural study with primary school children consisting of two spatial ability tests and a sketch map task in a pre- and post-test setting. Improvements were found in mental rotation and sketch map perspective, individual differences in culture and gender decreased for the experimental group. We conclude with a discussion of prospects and problems of integrating this type of GIS into education and learning.\u0000","PeriodicalId":116168,"journal":{"name":"AGILE: GIScience Series","volume":"436 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122805099","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-10DOI: 10.5194/agile-giss-3-19-2022
Nina Wiedemann, Henry Martin, M. Raubal
Abstract. Planning and operations in urban spaces are strongly affected by human mobility behavior. A better understanding of individual mobility is key to improve transportation systems and to guide the allocation of public space. Previous studies have discovered statistical laws of travel distances, but the topology of movement between places has received little attention. We propose to employ network modelling methods to analyze the effect of spatial and context attributes on individual movement patterns. The perspective of mobility as a network allows to explicitly regard dyadic dependencies of sequential location visits. Here, we consider two methods developed for social networks and provide a formulation of mobility networks to justify their applicability. First, we use the Multiple Regression Quadratic Assignment Procedure to test hypotheses on the influence of location attributes on mobility behavior. Secondly, Stochastic Actor-Oriented Models are applied to model the evolution of mobility networks over time. As a proof-of-concept study, we transform data from one GNSS-based and one check-in based dataset into mobility networks and present results from both methods. We find relations that appear for a majority of samples and thus seem inherent to mobility networks. The differences between individuals and the available datasets are further quantified and discussed. We conclude that the transfer of network modeling methods is an interesting opportunity to study network-related phenomena in geographic information science.
{"title":"Unlocking social network analysis methods for studying human mobility","authors":"Nina Wiedemann, Henry Martin, M. Raubal","doi":"10.5194/agile-giss-3-19-2022","DOIUrl":"https://doi.org/10.5194/agile-giss-3-19-2022","url":null,"abstract":"Abstract. Planning and operations in urban spaces are strongly affected by human mobility behavior. A better understanding of individual mobility is key to improve transportation systems and to guide the allocation of public space. Previous studies have discovered statistical laws of travel distances, but the topology of movement between places has received little attention. We propose to employ network modelling methods to analyze the effect of spatial and context attributes on individual movement patterns. The perspective of mobility as a network allows to explicitly regard dyadic dependencies of sequential location visits. Here, we consider two methods developed for social networks and provide a formulation of mobility networks to justify their applicability. First, we use the Multiple Regression Quadratic Assignment Procedure to test hypotheses on the influence of location attributes on mobility behavior. Secondly, Stochastic Actor-Oriented Models are applied to model the evolution of mobility networks over time. As a proof-of-concept study, we transform data from one GNSS-based and one check-in based dataset into mobility networks and present results from both methods. We find relations that appear for a majority of samples and thus seem inherent to mobility networks. The differences between individuals and the available datasets are further quantified and discussed. We conclude that the transfer of network modeling methods is an interesting opportunity to study network-related phenomena in geographic information science.\u0000","PeriodicalId":116168,"journal":{"name":"AGILE: GIScience Series","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116737215","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-10DOI: 10.5194/agile-giss-3-36-2022
Yunya Gao, Getachew Workineh Gella, Nianhua Liu
Abstract. This research assessed the influences of four band combinations and three types of pretrained weights on the performance of semantic segmentation in extracting refugee dwelling footprints of the Kule refugee camp in Ethiopia during a dry season and a wet season from very high spatial resolution imagery. We chose a classical network, U-Net with VGG16 as a backbone, for all segmentation experiments. The selected band combinations include 1) RGBN (Red, Green, Blue, and Near Infrared), 2) RGB, 3) RGN, and 4) RNB. The three types of pretrained weights are 1) randomly initialized weights, 2) pretrained weights from ImageNet, and 3) weights pretrained on data from the Bria refugee camp in the Central African Republic). The results turn out that three-band combinations outperform RGBN bands across all types of weights and seasons. Replacing the B or G band with the N band can improve the performance in extracting dwellings during the wet season but cannot bring improvement to the dry season in general. Pretrained weights from ImageNet achieve the best performance. Weights pretrained on data from the Bria refugee camp produced the lowest IoU and Recall values.
{"title":"Assessing the Influences of Band Selection and Pretrained Weights on Semantic-Segmentation-Based Refugee Dwelling Extraction from Satellite Imagery","authors":"Yunya Gao, Getachew Workineh Gella, Nianhua Liu","doi":"10.5194/agile-giss-3-36-2022","DOIUrl":"https://doi.org/10.5194/agile-giss-3-36-2022","url":null,"abstract":"Abstract. This research assessed the influences of four band combinations and three types of pretrained weights on the performance of semantic segmentation in extracting refugee dwelling footprints of the Kule refugee camp in Ethiopia during a dry season and a wet season from very high spatial resolution imagery. We chose a classical network, U-Net with VGG16 as a backbone, for all segmentation experiments. The selected band combinations include 1) RGBN (Red, Green, Blue, and Near Infrared), 2) RGB, 3) RGN, and 4) RNB. The three types of pretrained weights are 1) randomly initialized weights, 2) pretrained weights from ImageNet, and 3) weights pretrained on data from the Bria refugee camp in the Central African Republic). The results turn out that three-band combinations outperform RGBN bands across all types of weights and seasons. Replacing the B or G band with the N band can improve the performance in extracting dwellings during the wet season but cannot bring improvement to the dry season in general. Pretrained weights from ImageNet achieve the best performance. Weights pretrained on data from the Bria refugee camp produced the lowest IoU and Recall values.\u0000","PeriodicalId":116168,"journal":{"name":"AGILE: GIScience Series","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116892118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-10DOI: 10.5194/agile-giss-3-8-2022
Hiroyuki Kaneko, T. Osaragi
Abstract. In the field of facility planning, the analysis of pedestrian trajectories using laser sensor-based behavior monitoring technologies is a proven way to improve our understanding of the behavioral features of foot-travelers. While these technologies can gather large volumes of trajectory data, the analysis of such data is a chaotic and complicated task and creates a large workload if it must be interpreted visually by human analysts. Hence, a method is needed for automatically extracting the features and their separate components from pedestrian trajectories and patterns. This study proposes just such a method based on a Restricted Boltzmann machine, a machine learning tool, to automatically extract and classify the latent features of pedestrian trajectories. Our method was applied to data taken in the outpatient waiting area of a hospital and the machine learning generated results were compared to those of visual classifications by human analysts. It was shown to be functional for classifying trajectories by orientation, stopping location and walking speed, and was considered effective for furnishing rough classifications resembling the intuition-based classifications of a human analyst.
{"title":"Classifying pedestrian trajectories by Machine learning using laser sensor data","authors":"Hiroyuki Kaneko, T. Osaragi","doi":"10.5194/agile-giss-3-8-2022","DOIUrl":"https://doi.org/10.5194/agile-giss-3-8-2022","url":null,"abstract":"Abstract. In the field of facility planning, the analysis of pedestrian trajectories using laser sensor-based behavior monitoring technologies is a proven way to improve our understanding of the behavioral features of foot-travelers. While these technologies can gather large volumes of trajectory data, the analysis of such data is a chaotic and complicated task and creates a large workload if it must be interpreted visually by human analysts. Hence, a method is needed for automatically extracting the features and their separate components from pedestrian trajectories and patterns. This study proposes just such a method based on a Restricted Boltzmann machine, a machine learning tool, to automatically extract and classify the latent features of pedestrian trajectories. Our method was applied to data taken in the outpatient waiting area of a hospital and the machine learning generated results were compared to those of visual classifications by human analysts. It was shown to be functional for classifying trajectories by orientation, stopping location and walking speed, and was considered effective for furnishing rough classifications resembling the intuition-based classifications of a human analyst.\u0000","PeriodicalId":116168,"journal":{"name":"AGILE: GIScience Series","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130346988","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：