The widespread use of smart mobile devices has resulted in a massive accumulation of trajectory data by service providers. The analysis of human trajectories, particularly semantic location information, has opened up avenues for discovering common social behavior and enhancing social connections, leading to a range of applications such as friend recommendations and product suggestions. However, the exponential growth of trajectory information generated every day presents significant challenges for existing trajectory analysis algorithms, which are no longer capable of delivering timely analysis results. To address this issue, we propose a highly efficient algorithm that can recommend social communities for new users in real time by leveraging knowledge gained from large-scale semantic trajectories. Specifically, we develop a novel two-branch deep neural network model that extracts semantic meanings at different levels of granularity from human trajectories and uncovers the hidden relationship between trajectories and social communities. We then utilize this model to perform instant social community recommendations. Our experimental results have demonstrated that our approach is not only significantly faster than traditional trajectory analysis algorithms in terms of social community recommendation, but also preserves high prediction accuracy with F1-score above 97%.
{"title":"Social Community Recommendation based on Large-scale Semantic Trajectory Analysis Using Deep Learning","authors":"Chao Cai, Wei Jiang, Dan Lin","doi":"10.1145/3609956.3609957","DOIUrl":"https://doi.org/10.1145/3609956.3609957","url":null,"abstract":"The widespread use of smart mobile devices has resulted in a massive accumulation of trajectory data by service providers. The analysis of human trajectories, particularly semantic location information, has opened up avenues for discovering common social behavior and enhancing social connections, leading to a range of applications such as friend recommendations and product suggestions. However, the exponential growth of trajectory information generated every day presents significant challenges for existing trajectory analysis algorithms, which are no longer capable of delivering timely analysis results. To address this issue, we propose a highly efficient algorithm that can recommend social communities for new users in real time by leveraging knowledge gained from large-scale semantic trajectories. Specifically, we develop a novel two-branch deep neural network model that extracts semantic meanings at different levels of granularity from human trajectories and uncovers the hidden relationship between trajectories and social communities. We then utilize this model to perform instant social community recommendations. Our experimental results have demonstrated that our approach is not only significantly faster than traditional trajectory analysis algorithms in terms of social community recommendation, but also preserves high prediction accuracy with F1-score above 97%.","PeriodicalId":274777,"journal":{"name":"Proceedings of the 18th International Symposium on Spatial and Temporal Data","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123480078","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}
Multi-sensor spatiotemporal satellite images have become crucial for monitoring the geophysical characteristics of the Earth’s environment. However, clouds often obstruct the view from the optical sensors mounted on satellites and therefore degrade the quality of spectral, spatial, and temporal information. Though cloud imputation with the rise of deep learning research has provided novel ways to reconstruct the cloud-contaminated regions, many learning-based methods still lack the capability of harmonizing the differences between similar spectral bands across multiple sensors. To cope with the inter-sensor inconsistency of overlapping bands in different optical sensors, we propose a novel harmonization-guided residual network to impute the areas under clouds. We present a knowledge-guided harmonization model that maps the reflectance response from one satellite collection to another based on the spectral distribution of the cloud-free pixels. The harmonized cloud-free image is subsequently exploited in the intermediate layers as an additional input, paired with a custom loss function that considers image reconstruction quality and inter-sensor consistency jointly during training. To demonstrate the performance of our model, we conducted extensive experiments on a multi-sensor remote sensing imagery benchmark dataset consisting of widely used Landsat-8 and Sentinel-2 images. Compared to the state-of-the-art methods, results show at least a 22.35% improvement in MSE.
{"title":"Harmonization-guided deep residual network for imputing under clouds with multi-sensor satellite imagery","authors":"Xian Yang, Yifan Zhao, Ranga Raju Vatsavai","doi":"10.1145/3609956.3609967","DOIUrl":"https://doi.org/10.1145/3609956.3609967","url":null,"abstract":"Multi-sensor spatiotemporal satellite images have become crucial for monitoring the geophysical characteristics of the Earth’s environment. However, clouds often obstruct the view from the optical sensors mounted on satellites and therefore degrade the quality of spectral, spatial, and temporal information. Though cloud imputation with the rise of deep learning research has provided novel ways to reconstruct the cloud-contaminated regions, many learning-based methods still lack the capability of harmonizing the differences between similar spectral bands across multiple sensors. To cope with the inter-sensor inconsistency of overlapping bands in different optical sensors, we propose a novel harmonization-guided residual network to impute the areas under clouds. We present a knowledge-guided harmonization model that maps the reflectance response from one satellite collection to another based on the spectral distribution of the cloud-free pixels. The harmonized cloud-free image is subsequently exploited in the intermediate layers as an additional input, paired with a custom loss function that considers image reconstruction quality and inter-sensor consistency jointly during training. To demonstrate the performance of our model, we conducted extensive experiments on a multi-sensor remote sensing imagery benchmark dataset consisting of widely used Landsat-8 and Sentinel-2 images. Compared to the state-of-the-art methods, results show at least a 22.35% improvement in MSE.","PeriodicalId":274777,"journal":{"name":"Proceedings of the 18th International Symposium on Spatial and Temporal Data","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121838390","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}
Significant increase in high-resolution satellite data requires more productive analysis methods to benefit data scientists. Interactive exploration is essential to productivity since it keeps the user engaged by providing quick responses. This paper addresses the progressive zonal statistics problem that given big satellite data, an aggregate function, and a set of query polygons, zonal statistics computes the aggregate function for each query polygon over raster data. Efficiently querying complex polygons, reading high resolution pixels and process multiple polygons simultaneously are three main challenges. This work introduces Viper, an interactive exploration pipeline to overcome these challenges and achieve requirements. Viper uses a raster-vector index to bootstrap the answer with an accurate result in a short time. Then, it progressively refines the answer using a priority processing algorithm to produce the final answer. Experiments on large-scale real data show that Viper can reach 90% accuracy or higher up-to two orders of magnitude faster than baseline algorithms.
{"title":"Viper: Interactive Exploration of Large Satellite Data✱✱","authors":"Zhuocheng Shang, A. Eldawy","doi":"10.1145/3609956.3609966","DOIUrl":"https://doi.org/10.1145/3609956.3609966","url":null,"abstract":"Significant increase in high-resolution satellite data requires more productive analysis methods to benefit data scientists. Interactive exploration is essential to productivity since it keeps the user engaged by providing quick responses. This paper addresses the progressive zonal statistics problem that given big satellite data, an aggregate function, and a set of query polygons, zonal statistics computes the aggregate function for each query polygon over raster data. Efficiently querying complex polygons, reading high resolution pixels and process multiple polygons simultaneously are three main challenges. This work introduces Viper, an interactive exploration pipeline to overcome these challenges and achieve requirements. Viper uses a raster-vector index to bootstrap the answer with an accurate result in a short time. Then, it progressively refines the answer using a priority processing algorithm to produce the final answer. Experiments on large-scale real data show that Viper can reach 90% accuracy or higher up-to two orders of magnitude faster than baseline algorithms.","PeriodicalId":274777,"journal":{"name":"Proceedings of the 18th International Symposium on Spatial and Temporal Data","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130268564","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}
{"title":"Proceedings of the 18th International Symposium on Spatial and Temporal Data","authors":"","doi":"10.1145/3609956","DOIUrl":"https://doi.org/10.1145/3609956","url":null,"abstract":"","PeriodicalId":274777,"journal":{"name":"Proceedings of the 18th International Symposium on Spatial and Temporal Data","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130528796","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：