Volunteered geographic information such as that available in blogs, wikis, social networking sites, and community contributed photo collections is enabling new applications. This work investigates the use of georeferenced images from a popular photo sharing site for proximate sensing. In particular, we use computer vision and machine learning techniques to perform land cover classification based on the content of the georeferenced images. We evaluate the results using a ground truth dataset from the National Land Cover Database. We demonstrate that our approach can achieve upwards of 75% classification accuracy in a completely automated fashion.
{"title":"Proximate sensing using georeferenced community contributed photo collections","authors":"Daniel Leung, S. Newsam","doi":"10.1145/1629890.1629903","DOIUrl":"https://doi.org/10.1145/1629890.1629903","url":null,"abstract":"Volunteered geographic information such as that available in blogs, wikis, social networking sites, and community contributed photo collections is enabling new applications. This work investigates the use of georeferenced images from a popular photo sharing site for proximate sensing. In particular, we use computer vision and machine learning techniques to perform land cover classification based on the content of the georeferenced images. We evaluate the results using a ground truth dataset from the National Land Cover Database. We demonstrate that our approach can achieve upwards of 75% classification accuracy in a completely automated fashion.","PeriodicalId":107369,"journal":{"name":"Workshop on Location-based Social Networks","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130518576","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}
Recently, K-Nearest Neighbor(KNN) query processing over moving objects in road networks is becoming an interesting problem which has caught more and more researchers' attention. Distance pre-computation is an efficient approach for this problem. However, when the road network is large, this approach requires too much memory to use in some practical applications. In this paper, we present a simple and efficient pre-computation technique to solve this problem, with loss of some accuracy. In our pre-computation approach, we choose a proper representative nodes set R from road network G(V, E) (R is a subset of V) and compute the distance values of any pairs in R which are pre-computed. Since |R| ≪ |V|, our approach requires so less memory size that the KNN query can be processed in one common personal computer. Moreover, the approximation of distance value between any pairs in V is well bounded. The experimental results showed that this pre-computation technique yielded excellent performance with good approximation guarantee and high processing speed.
{"title":"An efficient pre-computation technique for approximation KNN search in road networks","authors":"Guangzhong Sun, Zhong Zhang, Jing Yuan","doi":"10.1145/1629890.1629899","DOIUrl":"https://doi.org/10.1145/1629890.1629899","url":null,"abstract":"Recently, K-Nearest Neighbor(KNN) query processing over moving objects in road networks is becoming an interesting problem which has caught more and more researchers' attention. Distance pre-computation is an efficient approach for this problem. However, when the road network is large, this approach requires too much memory to use in some practical applications. In this paper, we present a simple and efficient pre-computation technique to solve this problem, with loss of some accuracy. In our pre-computation approach, we choose a proper representative nodes set R from road network G(V, E) (R is a subset of V) and compute the distance values of any pairs in R which are pre-computed. Since |R| ≪ |V|, our approach requires so less memory size that the KNN query can be processed in one common personal computer. Moreover, the approximation of distance value between any pairs in V is well bounded. The experimental results showed that this pre-computation technique yielded excellent performance with good approximation guarantee and high processing speed.","PeriodicalId":107369,"journal":{"name":"Workshop on Location-based Social Networks","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115400145","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We have developed methods which can deal with the users' interaction without the conventional conscious searching manner. When a user generally performs map operations with certain information retrieval intentions (less-conscious), a system using our method can detect the specific operation sequences. For example, if the user performs zooming-in and centering operations, the user is narrowing down the search area to a certain location. We define such operation sequences as chunks. The system detects the chunks and uses them to analyze the user's operations and thereby detect the user's intentions. We have developed several prototype systems based on the proposed methods.
{"title":"Less-conscious information retrieval techniques for location based services","authors":"K. Sumiya","doi":"10.1145/1629890.1629905","DOIUrl":"https://doi.org/10.1145/1629890.1629905","url":null,"abstract":"We have developed methods which can deal with the users' interaction without the conventional conscious searching manner. When a user generally performs map operations with certain information retrieval intentions (less-conscious), a system using our method can detect the specific operation sequences. For example, if the user performs zooming-in and centering operations, the user is narrowing down the search area to a certain location. We define such operation sequences as chunks. The system detects the chunks and uses them to analyze the user's operations and thereby detect the user's intentions. We have developed several prototype systems based on the proposed methods.","PeriodicalId":107369,"journal":{"name":"Workshop on Location-based Social Networks","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127812175","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}
As the GPS-enabled mobile devices become extensively available, we are now given a chance to better understand human behaviors from a large amount of the GPS trajectories representing the mobile users' location histories. In this paper, we aim to establish a framework, which can jointly learn the user activities (what is the user doing) and profiles (what is the user's background, such as occupation, gender, age, etc.) from the GPS data. We will show that, learning user activities and learning user profiles can be beneficial to each other in nature, so we try to put them together and formulate a joint learning problem under a probabilistic collaborative filtering framework. In particular, for activity recognition, we manage to extract the location semantics from the raw GPS data and use it, together with the user profile, as the input; and we will output the corresponding activities of daily living. For user profile learning, we build a mobile social network among the users by modeling their similarities with the performed activities and known user backgrounds. Compared with the other work on solely learning user activities or profiles from GPS data, our approach is advantageous by exploiting the connections between the user activities and profiles for joint learning.
{"title":"Joint learning user's activities and profiles from GPS data","authors":"V. Zheng, Yu Zheng, Qiang Yang","doi":"10.1145/1629890.1629894","DOIUrl":"https://doi.org/10.1145/1629890.1629894","url":null,"abstract":"As the GPS-enabled mobile devices become extensively available, we are now given a chance to better understand human behaviors from a large amount of the GPS trajectories representing the mobile users' location histories. In this paper, we aim to establish a framework, which can jointly learn the user activities (what is the user doing) and profiles (what is the user's background, such as occupation, gender, age, etc.) from the GPS data. We will show that, learning user activities and learning user profiles can be beneficial to each other in nature, so we try to put them together and formulate a joint learning problem under a probabilistic collaborative filtering framework. In particular, for activity recognition, we manage to extract the location semantics from the raw GPS data and use it, together with the user profile, as the input; and we will output the corresponding activities of daily living. For user profile learning, we build a mobile social network among the users by modeling their similarities with the performed activities and known user backgrounds. Compared with the other work on solely learning user activities or profiles from GPS data, our approach is advantageous by exploiting the connections between the user activities and profiles for joint learning.","PeriodicalId":107369,"journal":{"name":"Workshop on Location-based Social Networks","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122297492","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}
With the advent of ever more powerful mobile devices over recent years, an increasing wealth of technical functionalities has become ready for use at once. These were previously only available in separate specialized devices with limited functionality or non-mobile equipment. In addition, mobile platform providers have taken a more open approach, enabling community-members to develop applications for their platforms and to deliver them as readily consumable services to the public. Both trends combined have led to a significant increase in the number of innovative mobile applications. More recently, leveraging mobile users' geolocation for provision of services has become the focus of a number of organizations active in the field. In this paper we propose a solution that addresses some challenges when creating location based social networks and offering relevant services to participants in these networks. We have applied this solution in a use case with an Australian based transportation service provider.
{"title":"Overcoming challenges in delivering services to social networks in location centric scenarios","authors":"T. Lange, M. Kowalkiewicz, T. Springer, T. Raub","doi":"10.1145/1629890.1629910","DOIUrl":"https://doi.org/10.1145/1629890.1629910","url":null,"abstract":"With the advent of ever more powerful mobile devices over recent years, an increasing wealth of technical functionalities has become ready for use at once. These were previously only available in separate specialized devices with limited functionality or non-mobile equipment. In addition, mobile platform providers have taken a more open approach, enabling community-members to develop applications for their platforms and to deliver them as readily consumable services to the public. Both trends combined have led to a significant increase in the number of innovative mobile applications. More recently, leveraging mobile users' geolocation for provision of services has become the focus of a number of organizations active in the field. In this paper we propose a solution that addresses some challenges when creating location based social networks and offering relevant services to participants in these networks. We have applied this solution in a use case with an Australian based transportation service provider.","PeriodicalId":107369,"journal":{"name":"Workshop on Location-based Social Networks","volume":"47 20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117302375","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 paper describes a Location Based Social Network (LBSN) built upon activities that combine virtual and physical location. While many modern social networks are based in the virtual world and strengthen pre-existing connections, the CouchSurfing social network is built upon creating new face-to-face connections between members across the world. The network has connected travelers to cost-free lodging for over 5 years with over 1 million current members. Now it provides a large user database where each user is tagged with a location. This is useful for spatial data mining and knowledge discovery as recommendations about locations are left in user reviews of one another. These are drawn upon to find interesting locations and discover new places, people and activities. Techniques from the field of time geography are used with LBSN information about individual member location to show how spatiotemporal constraints combine the virtual and physical worlds. Additionally, mobile devices afford flexible utility for the LBSN and applications are presented that take advantage of this.
{"title":"A case for space: physical and virtual location requirements in the CouchSurfing social network","authors":"Edward Pultar, M. Raubal","doi":"10.1145/1629890.1629909","DOIUrl":"https://doi.org/10.1145/1629890.1629909","url":null,"abstract":"This paper describes a Location Based Social Network (LBSN) built upon activities that combine virtual and physical location. While many modern social networks are based in the virtual world and strengthen pre-existing connections, the CouchSurfing social network is built upon creating new face-to-face connections between members across the world. The network has connected travelers to cost-free lodging for over 5 years with over 1 million current members. Now it provides a large user database where each user is tagged with a location. This is useful for spatial data mining and knowledge discovery as recommendations about locations are left in user reviews of one another. These are drawn upon to find interesting locations and discover new places, people and activities. Techniques from the field of time geography are used with LBSN information about individual member location to show how spatiotemporal constraints combine the virtual and physical worlds. Additionally, mobile devices afford flexible utility for the LBSN and applications are presented that take advantage of this.","PeriodicalId":107369,"journal":{"name":"Workshop on Location-based Social Networks","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125787311","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}
H. Karimi, Benjamin Zimmerman, Alper Ozcelik, Duangduen Asavasuthirakul
Location-Based Services (LBSs) and Social Networks (SN) have been developed independently with different technologies and for different purposes. However, due to their success with respect to the demand for them and for the reason that they overlap in utilizing "location" information in some applications and services, location-based social networks (LBSNs) are emerging. In this paper, we present a LBSN which is focused on navigation experience and sharing called Social Navigation Network (SoNavNet). Starting with an ontology, the details of SoNavNet, including architecture and functions, are provided and a prototype SoNavNet to demonstrate the capabilities and features of LBSNs is presented.
{"title":"SoNavNet: a framework for social navigation networks","authors":"H. Karimi, Benjamin Zimmerman, Alper Ozcelik, Duangduen Asavasuthirakul","doi":"10.1145/1629890.1629908","DOIUrl":"https://doi.org/10.1145/1629890.1629908","url":null,"abstract":"Location-Based Services (LBSs) and Social Networks (SN) have been developed independently with different technologies and for different purposes. However, due to their success with respect to the demand for them and for the reason that they overlap in utilizing \"location\" information in some applications and services, location-based social networks (LBSNs) are emerging. In this paper, we present a LBSN which is focused on navigation experience and sharing called Social Navigation Network (SoNavNet). Starting with an ontology, the details of SoNavNet, including architecture and functions, are provided and a prototype SoNavNet to demonstrate the capabilities and features of LBSNs is presented.","PeriodicalId":107369,"journal":{"name":"Workshop on Location-based Social Networks","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126428506","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}
People's activity sequences such as eat at a restaurant after 2 hours of shopping, contains rich semantic information. This information can be explored for a broad range of applications and services. However, it is impractical to ask a large number of people to record their daily activities. As the increasing popularity of GPS-enabled mobile devices, a huge amount of trajectories which show people's movement behaviors have been acquiring. The natural link between activities and traveling motivates us to investigate a novel approach to automatically extract sequences of activities from large set of trajectory data. Intuitively, activities can only happen when trajectory is geographically near for a proper period of time for these activities, such as 30 minutes for dining in a restaurant. In this work, the concepts influence and influence duration are proposed to capture the intuition. We also propose two algorithms to join large set of trajectories with activities with duplication reuse techniques. We conduct comprehensive empirical studies to evaluate the two algorithms with synthetic data set generated from real world POIs and road networks.
{"title":"From trajectories to activities: a spatio-temporal join approach","authors":"Kexin Xie, K. Deng, Xiaofang Zhou","doi":"10.1145/1629890.1629897","DOIUrl":"https://doi.org/10.1145/1629890.1629897","url":null,"abstract":"People's activity sequences such as eat at a restaurant after 2 hours of shopping, contains rich semantic information. This information can be explored for a broad range of applications and services. However, it is impractical to ask a large number of people to record their daily activities. As the increasing popularity of GPS-enabled mobile devices, a huge amount of trajectories which show people's movement behaviors have been acquiring. The natural link between activities and traveling motivates us to investigate a novel approach to automatically extract sequences of activities from large set of trajectory data. Intuitively, activities can only happen when trajectory is geographically near for a proper period of time for these activities, such as 30 minutes for dining in a restaurant. In this work, the concepts influence and influence duration are proposed to capture the intuition. We also propose two algorithms to join large set of trajectories with activities with duplication reuse techniques. We conduct comprehensive empirical studies to evaluate the two algorithms with synthetic data set generated from real world POIs and road networks.","PeriodicalId":107369,"journal":{"name":"Workshop on Location-based Social Networks","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133571402","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}
Due to the recent development of mobile computing and communication network technologies, information services for mobile phone users and car navigation systems have becomeof some importance. Since these mobile devices have limited display sizes, we often need to select carefully the appropriate information to be presented to the user. However, it is not easy to select the "appropriate" information because users have different contexts and preferences. In this paper, we present an approach to recommending items such as restaurants to a mobile user taking into account his current location and preferences. In our framework, a user initially provides a profile, which records preferences as relative orders within predefined categories such as food types and prices. We then select items to be recommended from the database based on the user's profile as well as the current location. To select good items, we extend the notion of spatial skyline queries to incorporate not only distance information but also categorical preference information. Based on the proposed approach, a prototype system has been implemented in a small mobile PC containing a small embedded RDBMS. The facilities of the RDBMS, such as spatial indexes, were used to process our skyline queries effectively.
{"title":"Skyline queries based on user locations and preferences for making location-based recommendations","authors":"K. Kodama, Yuichi Iijima, G. Xi, Y. Ishikawa","doi":"10.1145/1629890.1629893","DOIUrl":"https://doi.org/10.1145/1629890.1629893","url":null,"abstract":"Due to the recent development of mobile computing and communication network technologies, information services for mobile phone users and car navigation systems have becomeof some importance. Since these mobile devices have limited display sizes, we often need to select carefully the appropriate information to be presented to the user. However, it is not easy to select the \"appropriate\" information because users have different contexts and preferences.\u0000 In this paper, we present an approach to recommending items such as restaurants to a mobile user taking into account his current location and preferences. In our framework, a user initially provides a profile, which records preferences as relative orders within predefined categories such as food types and prices. We then select items to be recommended from the database based on the user's profile as well as the current location. To select good items, we extend the notion of spatial skyline queries to incorporate not only distance information but also categorical preference information.\u0000 Based on the proposed approach, a prototype system has been implemented in a small mobile PC containing a small embedded RDBMS. The facilities of the RDBMS, such as spatial indexes, were used to process our skyline queries effectively.","PeriodicalId":107369,"journal":{"name":"Workshop on Location-based Social Networks","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117112367","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}
Driven by travel demand, the distribution and density of taxi passenger pick-up and drop-off points reflect the attractiveness of an area and thus, can be used to find out hot spots and the movement of human flow, to benefit location-based services (LBS) and transport planning, etc. There exist some point pattern analysis (PPA) methods can facilitate the analysis. But most of them lack of the ability to integrate with location-based data in geo-visualization environment. We build an interactive visualization system based on mashup technique to contain diverse analysis data and applications under one framework. Two PPA methods--Kernel Density Estimation (KDE) and Agglomerative Hierarchical Clustering (AHC) are used to discover the hot spots. Microsoft Virtual Earth is used as data integration and visualization platform by combining with some other web techniques, to display analysis results in both static and dynamic effect. This study on one hand represents a novel application of vehicle trajectory data, reveals urban hot spots and traffic pattern, and addresses data integration and geo-visualization issues on the other hand. Preliminary attempt can benefit LBS and LBSN (Location-based Social Network) related web applications.
{"title":"Visualizing hot spot analysis result based on mashup","authors":"Han dong Wang, H. Zou, Y. Yue, Qingquan Li","doi":"10.1145/1629890.1629900","DOIUrl":"https://doi.org/10.1145/1629890.1629900","url":null,"abstract":"Driven by travel demand, the distribution and density of taxi passenger pick-up and drop-off points reflect the attractiveness of an area and thus, can be used to find out hot spots and the movement of human flow, to benefit location-based services (LBS) and transport planning, etc. There exist some point pattern analysis (PPA) methods can facilitate the analysis. But most of them lack of the ability to integrate with location-based data in geo-visualization environment. We build an interactive visualization system based on mashup technique to contain diverse analysis data and applications under one framework. Two PPA methods--Kernel Density Estimation (KDE) and Agglomerative Hierarchical Clustering (AHC) are used to discover the hot spots. Microsoft Virtual Earth is used as data integration and visualization platform by combining with some other web techniques, to display analysis results in both static and dynamic effect. This study on one hand represents a novel application of vehicle trajectory data, reveals urban hot spots and traffic pattern, and addresses data integration and geo-visualization issues on the other hand. Preliminary attempt can benefit LBS and LBSN (Location-based Social Network) related web applications.","PeriodicalId":107369,"journal":{"name":"Workshop on Location-based Social Networks","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121986831","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：