Numerous important applications rely on detailed trajectory data. Yet, unfortunately, trajectory datasets are typically sparse with large spatial and temporal gaps between each two points, which is a major hurdle for their accuracy. This paper presents Kamel; a scalable trajectory imputation system that inserts additional realistic trajectory points, boosting the accuracy of trajectory applications. Kamel maps the trajectory imputation problem to finding the missing word problem; a classical problem in the natural language processing (NLP) community. This allows employing the widely used BERT model for trajectory imputation. However, BERT, as is, does not lend itself to the special characteristics of trajectories. Hence, Kamel starts from BERT, but then adds spatial-awareness to its operations, adjusts trajectory data to be closer to the nature of language data, and adds multipoint imputation ability to it; all encapsulated in one system. Experimental results based on real datasets show that Kamel significantly outperforms its competitors and is applicable to city-scale trajectories, large gaps, and tight accuracy thresholds.

Trajectory-based applications have acquired significant attention in several areas, including transportation (e.g., mapping and routing, traffic monitoring and forecasting), location-based service (e.g., recommendations), health (e.g., contact tracing), and urban planning. However, building such applications is still cumbersome due to the lack of unified frameworks to tackle the underlying trajectory problems, including trajectory similarity search, trajectory imputation, classification, prediction, and simplification. Despite the fact that all of these problems deal with the same trajectory data, each of the proposed solutions in the literature (e.g., see [7, 10] for surveys) is entirely designed to solve one problem of interest. This makes it hard to have a unified efficient and practical framework that is capable of supporting most (if not all) trajectory problems.

Trajectory-based applications have acquired significant attention over the past decade with the rising size of trajectory data generated by users. However, building trajectory-based applications is still cumbersome due to the lack of unified frameworks to tackle the underlying trajectory analysis challenges. Inspired by the tremendous success of the BERT deep learning model in solving various NLP tasks, our vision is to have a BERT-like system for a myriad of trajectory analysis operations. We envision that in a few years, we will have such system, where no one needs to worry again about each specific trajectory analysis operation. Whether it is trajectory imputation, similarity, clustering, or whatever, it would be one system that researchers, developers, and practitioners can deploy to get high accuracy for their trajectory operations.

Road network queries (e.g., shortest path, range, and k-NN) hinge on the road network quality, which, un-fortunately, suffer from all sorts of inaccuracy. Given that OpenStreetMap (OSM) has been the de facto open-source map for a myriad of widely used applications, this demo presents RASED; a publicly available scalable dashboard to interactively monitor and analyze billions of OSM updates worldwide. RASED provides the necessary infrastructure that is immensely needed by map analyzers to understand and assess the map quality for anywhere in the world, which is a measure of the query accuracy.

Understanding the evolution and changes of digital road networks and how it resembles the true physical road network, have been a rich area of study within map analyzers, urban planners, and transportation communities. The main focus was to study OpenStreetMap (OSM) as the most commonly used platform for worldwide digital road networks, and is deemed even more accurate than commercial maps. However, all such studies have been localized to small areas of interest, mainly due to the large scale of the whole OSM road network. This paper presents RASED; a publicly available scalable dashboard to interactively monitor and analyze the evolution of all OSM road network. Using RASED, map analyzers can query and visualize various statistics about the road network daily changes worldwide, which would give a better understanding of the status of map quality and stability anywhere in the world. RASED relies on daily and monthly offline precomputations, accessed via a hierarchical temporal index structure. Experimental results show that RASED queries are always supported in the order of milliseconds, regardless of how large is the query temporal window, which allows highly interactive map analysis.

This demo presents QARTA; an open-source full-fledged system for highly accurate and scalable map services. QARTA employs machine learning techniques to: (a) construct its own highly accurate map in terms of both map topology and edge weights, and (b) calibrate its query answers based on contextual information, including transportation modality, underlying algorithm, and time of day/week. The demo is based on actual deployment of QARTA in all Taxis in the State of Qatar and in the third-largest food delivery company in the country, and receiving hundreds of thousands of daily API calls with a real-time response time. Audience will be able to interact with the demo through various scenarios that show QARTA map and query accuracy as well as internals of QARTA.

Maps services are ubiquitous in widely used applications including navigation systems, ride sharing, and items/food delivery. Though there are plenty of efforts to support such services through designing more efficient algorithms, we believe that efficiency is no longer a bottleneck to these services. Instead, it is the accuracy of the underlying road network and query result. This paper presents QARTA; an open-source full-fledged system for highly accurate and scalable map services. QARTA employs machine learning techniques to construct its own highly accurate map, not only in terms of map topology but more importantly, in terms of edge weights. QARTA also employs machine learning techniques to calibrate its query answers based on contextual information, including transportation modality, location, and time of day/week. QARTA is currently deployed in all Taxis and the third largest food delivery company in the State of Qatar, replacing the commercial map service that was in use, and responding in real-time to hundreds of thousands of daily API calls. Experimental evaluation of QARTA shows its comparable or higher accuracy than commercial services.

High quality data is crucial for many applications but real-life data is often dirty. Unfortunately, automated solutions are often not trustable and are thus seldom employed in practice. In real-world scenarios, it is often necessary to resort to manual cleaning for obtaining pristine data. Existing human-in-the-loop solutions, such as Trifacta and OpenRefine, typically involve a single user. This is often error-prone, limited to a single-person expertise, and cannot scale with the ever growing volume, variety and veracity of data.

The current explosion in spatial data raises the need for efficient spatial analysis tools to extract useful information from such data. However, existing tools are neither generic nor scalable when dealing with big spatial data. This demo presents Flash ; a framework for generic and scalable spatial data analysis, with a special focus on spatial probabilistic graphical modelling (SPGM). Flash exploits Markov Logic Networks (MLN) to express SPGM as a set of declarative logical rules. In addition, it provides spatial variations of the scalable RDBMS-based learning and inference techniques of MLN to efficiently perform SPGM predictions. To show Flash effectiveness, we demonstrate three applications that use Flash in their SPGM: (1) Bird monitoring, (2) Safety analysis, and (3) Land use change tracking.

Predicting the presence or absence of spatial phenomena has been of great interest to scientists pursuing research in several applications including epidemic diseases detection, species occurrence prediction and earth observation. In this operation, a geographical space is divided by a two-dimensional grid, where the prediction (i.e, either 0 or 1) is performed at each cell in the grid. A common approach to solve this problem is to build spatial logistic regression models (a.k.a autologistic models) that estimate the prediction at any location based on a set of predictors (i.e., features) at this location and predictions from neighboring locations. Unfortunately, existing methods to build autologistic models are computationally expensive and do not scale up for large-scale grid data (e.g., fine-grained satellite images). This paper introduces TurboReg, a scalable framework to build autologistic models for predicting large-scale spatial phenomena. TurboReg considers both the accuracy and efficiency aspects when learning the regression model parameters. TurboReg is built on top of Markov Logic Network (MLN), a scalable statistical learning framework, where its internals and data structures are optimized to process spatial data. A set of experiments using large real and synthetic data show that TurboReg achieves at least three orders of magnitude performance gain over existing methods while preserving the model accuracy.

This demo presents Sya; the first full-fledged spatial probabilistic knowledge base construction system. Sya is a comprehensive extension to the DeepDive system that enables exploiting the spatial relationships between extracted relations during the knowledge base construction process, and hence results in a better knowledge base output. Sya runs existing DeepDive programs as is, yet, it extracts more accurate relations than DeepDive when dealing with input data that have spatial attributes. Sya employs a simple spatial high-level language, a rule-based spatial SQL query engine, a spatially-indexed probabilistic graphical model, and an adapted spatial statistical inference technique to infer the factual scores of relations. We demonstrate a real system prototype of Sya, showing a case study of constructing a crime knowledge base. The demonstration shows to the audience the internal steps of building the knowledge base, as well as a comparison with the output of DeepDive.

This paper demonstrates Taghreed; a full-fledged system for efficient and scalable querying, analyzing, and visualizing geotagged microblogs, such as tweets. Taghreed supports a wide variety of queries on all microblogs attributes. In addition, it is able to manage a large number (billions) of microblogs for relatively long periods, e.g., months. Taghreed consists of four main components: (1) indexer, (2) query engine, (3) recovery manager, and (4) visualizer. Taghreed indexer efficiently digests incoming microblogs with high arrival rates in light main-memory indexes. When the memory becomes full, the memory contents are flushed to disk indexes which are managing billions of microblogs efficiently. On memory failure, the recovery manager restores the memory contents from backup copies. Taghreed query engine consists of two modules: a query optimizer and a query processor. The query optimizer generates an optimized query plan to be executed by the query processor to provide low query responses. Taghreed visualizer features to its users a wide variety of spatiotemporal queries and presents the answers on a map-based user interface that allows an interactive exploration. Taghreed is the first system that addresses all these challenges collectively for geotagged microblogs data. The system is demonstrated based on real system implementation through different scenarios that show system functionality and internals.

This paper presents Taghreed; a full-fledged system for efficient and scalable querying, analyzing, and visualizing geotagged microblogs, e.g., tweets. Taghreed supports arbitrary queries on a large number (Billions) of microblogs that go up to several months in the past. Taghreed consists of four main components: (f) Indexer, (2) query engine, (3) recovery manager, and (4) visualizer. Taghreed indexer efficiently digests incoming microblogs with high arrival rates in light memory-resident indexes. When the memory becomes full, a flushing policy manager transfers the memory contents to disk indexes which are managing Billions of microblogs for several months. On memory failure, the recovery manager restores the system status from replicated copies for the main-memory content. Taghreed query engine consists of two modules: a query optimizer and a query processor. The query optimizer generates an optimal query plan to be executed by the query processor through efficient retrieval techniques to provide low query response, i.e., order of milli-seconds. Taghreed visualizer allows end users to issue a wide variety of spatio-temporal queries. Then, it graphically presents the answers and allows interactive exploration through them. Taghreed is the first system that addresses all these challenges collectively for microblogs data. In the paper, each system component is described in detail.

In the last few years, Twitter data has become so popular that it is used in a rich set of new applications, e.g., real-time event detection, demographic analysis, and news extraction. As user-generated data, the plethora of Twitter data motivates several analysis tasks that make use of activeness of 271+ Million Twitter users. This demonstration presents VisCAT; a tool for aggregating and visualizing categorical attributes in Twitter data. VisCAT outputs visual reports that provide spatial analysis through interactive map-based visualization for categorical attributes---such as tweet language or source operating system---at different zoom levels. The visual reports are built based on user-selected data in arbitrary spatial and temporal ranges. For this data, VisCAT employs a hierarchical spatial data structure to materialize the count of each category at multiple spatial levels. We demonstrate VisCAT, using real Twitter dataset. The demonstration includes use cases on tweet language and tweet source attributes in the region of Gulf Arab states, which can be used for deducing thoughtful conclusions on demographics and living levels in local societies.

Twitter is one of the most popular social networks where people use to tweet about their opinions, feelings, desires, ...etc. One of the most important and consistent behaviors of Twitter users is posting a plethora of tweets about events of different types, e.g., Oscars celebration, soccer games, and natural disasters. For such kind of event-specific tweets, geotagged tweets grab the biggest attention because all events by nature have a spatial extent. For example, while Boston Marathon explosions were going on, in April 2013, users rush to Twitter seeking tweets from the marathon location. Thus, within a large project called Taghreed for comprehensive real-time and offline analysis and visualization for Twitter data (see www.gistic.org/taghreed), we are working on a module that aims to semi-automate the task of visually analyzing event-specific tweets, for arbitrary events, over the spatial and temporal dimensions. In this poster, we present our on-going work on this module and discuss three of its use cases. We also discuss our future plans to extend the module for larger data sizes and make it interactive while the events are going-on.