{"title":"Proceedings of the 2nd ACM SIGSPATIAL Workshop on Recommendations for Location-based Services and Social Networks","authors":"","doi":"10.1145/3282825","DOIUrl":"https://doi.org/10.1145/3282825","url":null,"abstract":"","PeriodicalId":211655,"journal":{"name":"Proceedings of the 2nd ACM SIGSPATIAL Workshop on Recommendations for Location-based Services and Social Networks","volume":"171 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121716076","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}
E. Oliveira, Igo Ramalho Brilhante, J. A. F. de Macedo
In this article, we propose TrajectMe, an algorithm that solves the orienteering problem with hotel selection in several cities, taking advantage of the tourists' trajectories extracted from location-based services. This method is an extension of the state-of-the-art memetic-based algorithm. To this end, we collect data from Foursquare and Flickr location-based services, reconstruct the trajectories of tourists. Next, we build a hotel graph model (HGM) using a set of trajectories and a set of hotels to infer typical sequences of hotels and point of interest (PoI). The HGM is applied in the initialization phase and in the genetic operations of the memetic algorithm to provide good sequences of hotels, whereas the associated sequence of PoIs are improved by applying local search moves. We evaluate our proposal using a large and real dataset from three Italian cities using up to 1000 hotels. The results show that our approach is effective and outperforms the state-of-the-art when using large real datasets. Our approach is better than the baseline algorithm by up to 208% concerning the solution score and proved to be more profitable toward PoI visiting time, being 54% better than state-of-the-art.
{"title":"TrajectMe","authors":"E. Oliveira, Igo Ramalho Brilhante, J. A. F. de Macedo","doi":"10.1145/3282825.3282826","DOIUrl":"https://doi.org/10.1145/3282825.3282826","url":null,"abstract":"In this article, we propose TrajectMe, an algorithm that solves the orienteering problem with hotel selection in several cities, taking advantage of the tourists' trajectories extracted from location-based services. This method is an extension of the state-of-the-art memetic-based algorithm. To this end, we collect data from Foursquare and Flickr location-based services, reconstruct the trajectories of tourists. Next, we build a hotel graph model (HGM) using a set of trajectories and a set of hotels to infer typical sequences of hotels and point of interest (PoI). The HGM is applied in the initialization phase and in the genetic operations of the memetic algorithm to provide good sequences of hotels, whereas the associated sequence of PoIs are improved by applying local search moves. We evaluate our proposal using a large and real dataset from three Italian cities using up to 1000 hotels. The results show that our approach is effective and outperforms the state-of-the-art when using large real datasets. Our approach is better than the baseline algorithm by up to 208% concerning the solution score and proved to be more profitable toward PoI visiting time, being 54% better than state-of-the-art.","PeriodicalId":211655,"journal":{"name":"Proceedings of the 2nd ACM SIGSPATIAL Workshop on Recommendations for Location-based Services and Social Networks","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130186210","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 rapid growth of geotagged documents, top-k spatial keyword search queries (TkSKQ) have attracted a lot of attention and a number of spatio-textual indexes have been proposed. While some indexes support real-time updates over continuously generated documents, they do not support queries that simultaneously consider temporal relevance, textual similarity ranking and spatial location. Existing indexes also have limited capability to exploit parallelism. To address these issues, we introduce a novel parallel index, called Pastri (PArallel Spatio-Textual adaptive Ranking-based Index), which can be incrementally updated based on live spatio-textual document streams. Pastri uses a dynamic ranking scheme to retrieve the top-k objects that are most temporally relevant at the time of a query execution. We have built a system in which we integrate Pastri along with a persistent document store and several thread pools to exploit parallelism at various levels. Experimental evaluation demonstrates that our system can support high document update throughput and low latency with TkSKQ queries.
{"title":"Improving Parallel Performance of Temporally Relevant Top-K Spatial Keyword Search","authors":"S. Ray, B. Nickerson","doi":"10.1145/3282825.3282830","DOIUrl":"https://doi.org/10.1145/3282825.3282830","url":null,"abstract":"With the rapid growth of geotagged documents, top-k spatial keyword search queries (TkSKQ) have attracted a lot of attention and a number of spatio-textual indexes have been proposed. While some indexes support real-time updates over continuously generated documents, they do not support queries that simultaneously consider temporal relevance, textual similarity ranking and spatial location. Existing indexes also have limited capability to exploit parallelism. To address these issues, we introduce a novel parallel index, called Pastri (PArallel Spatio-Textual adaptive Ranking-based Index), which can be incrementally updated based on live spatio-textual document streams. Pastri uses a dynamic ranking scheme to retrieve the top-k objects that are most temporally relevant at the time of a query execution. We have built a system in which we integrate Pastri along with a persistent document store and several thread pools to exploit parallelism at various levels. Experimental evaluation demonstrates that our system can support high document update throughput and low latency with TkSKQ queries.","PeriodicalId":211655,"journal":{"name":"Proceedings of the 2nd ACM SIGSPATIAL Workshop on Recommendations for Location-based Services and Social Networks","volume":"149 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129105645","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}
Madhuri Debnath, P. Tripathi, A. Biswas, R. Elmasri
There have been vast advances and rapid growth in Location based social networking (LBSN) services in recent years. Travel route recommendation is one of the most important applications in the LBSN services. Travel route recommendation provides users a sequence of POIs (Point of Interests) as a route to visit. In this paper, we propose to recommend time-aware and preference-aware travel routes consisting of a sequence of POI locations with corresponding time information. It helps users not only to explore interesting locations in a new city, but also it will help to plan the entire trip with those locations with the approximated time information under specific time constraints. First, we find the interesting POI locations that considers the following factors: User's categorical preferences, temporal activities and popularity of location. Then, we propose an efficient solution to generate travel routes with those locations including time to visit each location. These travel routes will inform users where to visit and when to visit. We evaluate the efficiency and effectiveness of our solution on a real life LBSN dataset.
{"title":"Preference Aware Travel Route Recommendation with Temporal Influence","authors":"Madhuri Debnath, P. Tripathi, A. Biswas, R. Elmasri","doi":"10.1145/3282825.3282829","DOIUrl":"https://doi.org/10.1145/3282825.3282829","url":null,"abstract":"There have been vast advances and rapid growth in Location based social networking (LBSN) services in recent years. Travel route recommendation is one of the most important applications in the LBSN services. Travel route recommendation provides users a sequence of POIs (Point of Interests) as a route to visit. In this paper, we propose to recommend time-aware and preference-aware travel routes consisting of a sequence of POI locations with corresponding time information. It helps users not only to explore interesting locations in a new city, but also it will help to plan the entire trip with those locations with the approximated time information under specific time constraints. First, we find the interesting POI locations that considers the following factors: User's categorical preferences, temporal activities and popularity of location. Then, we propose an efficient solution to generate travel routes with those locations including time to visit each location. These travel routes will inform users where to visit and when to visit. We evaluate the efficiency and effectiveness of our solution on a real life LBSN dataset.","PeriodicalId":211655,"journal":{"name":"Proceedings of the 2nd ACM SIGSPATIAL Workshop on Recommendations for Location-based Services and Social Networks","volume":"190 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134237226","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}
Keerti Banweer, Austin Graham, J. Ripberger, Nina L. Cesare, E. Nsoesie, Christan Earl Grant
Data from social media platforms such as Twitter can be used to analyze severe weather reports and foodborne illness outbreaks. Government officials use online reports for early estimation of the impact of catastrophes and to aid resource distribution. For online reports to be useful they must be geotagged, but location is often not available. Less then one percent of users share their location information and/or acquisition of significant sample of geolocation messages is prohibitively expensive. In this paper, we propose a multi-stage iterative model based on the popular matrix factorization technique. This algorithm uses the partial information and exploits the relationship of messages, location, and keywords to recommend locations for non-geotagged messages. We present this model for geotagging messages using recommender systems and discussion the potential applications and next steps in this work.
{"title":"Multi-stage Collaborative filtering for Tweet Geolocation","authors":"Keerti Banweer, Austin Graham, J. Ripberger, Nina L. Cesare, E. Nsoesie, Christan Earl Grant","doi":"10.1145/3282825.3282831","DOIUrl":"https://doi.org/10.1145/3282825.3282831","url":null,"abstract":"Data from social media platforms such as Twitter can be used to analyze severe weather reports and foodborne illness outbreaks. Government officials use online reports for early estimation of the impact of catastrophes and to aid resource distribution. For online reports to be useful they must be geotagged, but location is often not available. Less then one percent of users share their location information and/or acquisition of significant sample of geolocation messages is prohibitively expensive. In this paper, we propose a multi-stage iterative model based on the popular matrix factorization technique. This algorithm uses the partial information and exploits the relationship of messages, location, and keywords to recommend locations for non-geotagged messages. We present this model for geotagging messages using recommender systems and discussion the potential applications and next steps in this work.","PeriodicalId":211655,"journal":{"name":"Proceedings of the 2nd ACM SIGSPATIAL Workshop on Recommendations for Location-based Services and Social Networks","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131380751","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}
When users browse beautiful scenery photos uploaded on a social media website, they may have a passion to know about where those photos are taken so that they could view the similar sceneries when they go to the same spot. Advancement in computer vision technology enables the extraction of visual features from those images and the widespread of location-awareness devices makes image positioning possible with GPS coordinates or geo-tags (e.g., landmarks, place names). In this paper, we propose a novel method for image positioning by utilizing spatial analysis and computer vision techniques. A prototype system is implemented based on large-scale Flickr photos and a case-study of the Eiffel Tower is demonstrated. Both global and local visual features as well as the spatial context are utilized aiming at building a more accurate and efficient framework. The result illustrates that our approach can achieve a better accuracy compared with the baseline approach. To our knowledge, it is among the first researches that combine not only the visual features of photos, but also take the spatial context into consideration for the image geo-localization using high-density social media photos at the spatial scale of a landmark.
{"title":"Utilizing Reverse Viewshed Analysis in Image Geo-Localization","authors":"Yuhao Kang, Song Gao, Yunlei Liang","doi":"10.1145/3282825.3282828","DOIUrl":"https://doi.org/10.1145/3282825.3282828","url":null,"abstract":"When users browse beautiful scenery photos uploaded on a social media website, they may have a passion to know about where those photos are taken so that they could view the similar sceneries when they go to the same spot. Advancement in computer vision technology enables the extraction of visual features from those images and the widespread of location-awareness devices makes image positioning possible with GPS coordinates or geo-tags (e.g., landmarks, place names). In this paper, we propose a novel method for image positioning by utilizing spatial analysis and computer vision techniques. A prototype system is implemented based on large-scale Flickr photos and a case-study of the Eiffel Tower is demonstrated. Both global and local visual features as well as the spatial context are utilized aiming at building a more accurate and efficient framework. The result illustrates that our approach can achieve a better accuracy compared with the baseline approach. To our knowledge, it is among the first researches that combine not only the visual features of photos, but also take the spatial context into consideration for the image geo-localization using high-density social media photos at the spatial scale of a landmark.","PeriodicalId":211655,"journal":{"name":"Proceedings of the 2nd ACM SIGSPATIAL Workshop on Recommendations for Location-based Services and Social Networks","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116252038","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}
Location Based Services (LBS) powered apps generate a massive amount of GPS trajectory data everyday. Because many of these trajectories are similar, if not exactly the same, (e.g., people traveling together or taking the same route everyday), there is a significant amount of redundancy in the data generated. This redundant data increases storage cost and network bandwidth cost. In order to counteract this and efficiently provide the LBS, LBS providers are considering trajectory similarity computation. There are several methods reported in the literature regarding similarity in GPS trajectories, which directly work on data in the plaintext format. However, computing trajectory similarity traditionally introduces privacy and security concerns among users since the number of incidents of the privacy breaches is on the rise. Hence, researchers have recently come up with innovative ways to perform trajectory similarity operations in the encrypted domain, without revealing the actual data. These approaches increase privacy and boost user confidence, which results in more customers for LBS providers. In this paper, we review various methods proposed in the plaintext domain and in the encrypted domain for secured trajectory comparison. We also discuss potential methods for encrypted domain computing that can be used in the domain of trajectory similarity and list the open research challenges.
{"title":"Secure Computing of GPS Trajectory Similarity: A Review","authors":"Akshay Chandra Pesara, Vikram Patil, P. Atrey","doi":"10.1145/3282825.3282832","DOIUrl":"https://doi.org/10.1145/3282825.3282832","url":null,"abstract":"Location Based Services (LBS) powered apps generate a massive amount of GPS trajectory data everyday. Because many of these trajectories are similar, if not exactly the same, (e.g., people traveling together or taking the same route everyday), there is a significant amount of redundancy in the data generated. This redundant data increases storage cost and network bandwidth cost. In order to counteract this and efficiently provide the LBS, LBS providers are considering trajectory similarity computation. There are several methods reported in the literature regarding similarity in GPS trajectories, which directly work on data in the plaintext format. However, computing trajectory similarity traditionally introduces privacy and security concerns among users since the number of incidents of the privacy breaches is on the rise. Hence, researchers have recently come up with innovative ways to perform trajectory similarity operations in the encrypted domain, without revealing the actual data. These approaches increase privacy and boost user confidence, which results in more customers for LBS providers. In this paper, we review various methods proposed in the plaintext domain and in the encrypted domain for secured trajectory comparison. We also discuss potential methods for encrypted domain computing that can be used in the domain of trajectory similarity and list the open research challenges.","PeriodicalId":211655,"journal":{"name":"Proceedings of the 2nd ACM SIGSPATIAL Workshop on Recommendations for Location-based Services and Social Networks","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116516208","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：