Mobile devices are equipped with various sensors that continuously gather data about user activity and environmental conditions. Detecting anomalies in this sensor data is crucial for both health monitoring applications and technical quality control. This paper presents a novel framework, namely CLARA, that leverages Retrieval-Augmented Generation (RAG) with Large Language Models (LLMs) to detect anomalies in mobile device sensor data. Using the ExtraSensory dataset, which contains labeled sensor data from smartphones and smartwatches, we demonstrate how RAG enhances LLM-based anomaly detection by retrieving relevant historical patterns and domain knowledge to provide context-rich analysis. Our framework serves dual purposes: (1) providing health and lifestyle insights to end-users through anomaly detection in their daily activities and (2) offering manufacturers a tool for identifying technical sensor malfunctions during quality control processes. The framework delivers rich, contextual explanations of detected anomalies, making the results actionable for end-users and technical teams, addressing key industry challenges in sensor data analysis.

Walking is a fundamental mode of human movement and an essential component of urban mobility. However, traditional pedestrian navigation systems lack real-time sidewalk accessibility data, relying primarily on static maps that fail to reflect dynamic hazards, such as construction zones, obstructions, or uneven pavement. To address this gap, we present a sidewalk navigation system that integrates crowdsourced reports, adaptive routing, and AI-powered assistance. The system leverages OpenStreetMap (OSM) maps and real-time user contributions to dynamically adjust pedestrian routes based on reported obstacles, ensuring a safer and more efficient walking experience. In addition, a user-driven rating system validates sidewalk conditions, while an AI assistant powered by Large Language Models (LLMs) provides context-aware guidance, interactive navigation, and additional insights. The application also features turn-by-turn navigation with audio support, enhancing accessibility for many users. By combining real-time crowdsourced data, personalized routing, and AIenhanced navigation, our system addresses critical limitations in existing pedestrian navigation applications and provides a more interactive, adaptive, and user-driven approach to sidewalk accessibility.

Sensor networks are incredibly important. Versatile combinations of sensors are used in a wide array of applications, from urban sensing, to oceanographic sensing, to health and industrial sensing. Failures in individual sensors can have catastrophic consequences. Anomaly detection (AD) is essential to identify these failures and ensure the integrity and reliability of sensor data. This paper introduces a novel approach using Generative Adversarial Networks (GANs) to detect anomalies in time-series data collected from urban sensor networks. Our novel approach involves representing sensor readings as images in which sensor locations and readings are encoded into an image tensor, coupled with post-training the latency vector for more stable anomaly detection. This efficient representation enables GANs to learn whole networks of sensors globally and is capable of identifying differences in sensor data at a single-pixel level. Experimental results demonstrate the efficiency of this approach, where utilizing this approach flags nearly twice as many anomalous readings than without latency post-training.

This study presents a novel approach to designing a system for disability-aware sidewalk routing that considers the specific needs and preferences of individuals with mobility impairments. The study involves creating a multi-objective personalized routing service that uses multi-sensors and an artificial intelligence fusion approach to identify sidewalk distresses on a surface level. The preliminary model is used to rapidly deploy big spatial data management systems, providing the Department of Transportation (DoT) and Americans with Disabilities Act (ADA)-compliant services to various desired domains. This research contributes to the broader goal of creating smarter and more inclusive cities by harnessing technology to address the unique mobility requirements of all community members.

As the global transition towards renewable energy sources accelerates, solar power becomes an increasingly important solution. Identifying and understanding the current distribution of solar panel installations is crucial for future planning and decision-making process. This paper introduces SolarDetector, a transformer-based neural network model, which we developed and fine-tuned for the accurate detection of solar panels. It achieves 91.0% mIoU for the task of masking solar panels on SWISSIMAGE dataset.

Maps provide various sources of information. An important example of such information is textual labels such as cities, neighborhoods, and street names. Although we treat this information as facts, and despite the massive effort done by providers to continuously improve their accuracy, this data is far from perfect. Discrepancies in textual labels rendered on the map are one of the major sources of inconsistencies across map providers. These discrepancies can have significant impacts on the reliability of the derived information and decision-making processes. Thus, it is important to validate the accuracy and consistency in such data. Most providers treat this data as their propriety data and it is not available to the public, thus we cannot compare the data directly. To address these challenges, we introduce a novel computer vision-based approach for automatically extracting and classifying labels based on the visual characteristics of the label, which indicates its category based on the format convention used by the specific map provider. Based on the extracted data, we detect the degree of discrepancies across map providers. We consider three map providers: Bing Maps, Google Maps, and OpenStreetMaps. The neural network we develop classifies the text labels with an accuracy up to 93% in all providers. We leverage our system to analyze randomly selected regions in different markets. The studied markets are USA, Germany, France, and Brazil. Experimental results and statistical analysis reveal the amount of discrepancies across map providers per region. We calculate the Jaccard distance between the extracted text sets for each pair of map providers, which represents the discrepancy percentage. Discrepancies percentages as high as 90% were found in some markets.

The coronavirus outbreak is first and foremost a human calamity, severely affecting the health of millions of people around the globe. It is also having a significant impact on the national and global economy. As this crisis has a two-sided negative impact, health, and economy, this makes it hard to manage. A full lockdown of the society can help control the spread of the infection. However, the economy will suffer significantly. On the other side, allowing normal life activities will protect the growth of the economy. But, it will decisively increase the spread of the infection, and consequently, cause a collapse in the whole medical system. In response to the COVID-19 pandemic, this paper presents the development of a real-time crisis management system that is able to holistically control the country’s resources at both micro and macro levels. The ultimate goal of this system is to assure the harmonic balance between crucial actions needed for the containment of the coronavirus spread and at the same time protect the national economy from the negative impacts caused by these actions. To achieve this goal, the system will privately monitor users’ geo-social interactions to assist in applying a reasonable social distance when it is needed. The system will alert the people who were in interaction with an infected person or area and recommend the appropriate health care provider. In addition to the fine crafted mobile and web interfaces, the proposed system will be equipped with a set of infrastructures such as data warehousing, data mining, maps, and dashboards. These tools will facilitate heterogeneous data management and analytics to efficiently handle the COVID-19 pandemic crisis at various levels of the decision-making process. We present the proposed crisis management system which can significantly contribute to winning the battle with COVID-19.

Map service providers are working hard to maintain high-quality maps service to more than three billion digital maps users. As each provider presents its unique routing engine and road network graph (RNG) mapping techniques, inconsistencies in services provided are inevitable. These inconsistencies may be of two types- (1) inconsistencies in RNG, including missing or shifted road segments, missing turn restriction, or mislabeled road attributes; or (2) inconsistencies in routing service arising from the unique routing algorithm (RA). Discovering those inconsistencies would improve the routing services efficiency. This paper presents a system, named GeoDart, that compares publicly available routing data from the APIs of Bing Maps, Google Maps, and OpenStreetMaps (OSM) to automatically discover discrepancies. The system categorizes the detected discrepancies based on (1) routing data such as distance, duration, and route geometry, (2) the attributes of the road segments, and (3) the connectivity and turn restrictions of the RNG. Equipped with an ensemble of Multi-Layer Perception (MLP) and Support Vector Machine Classifiers (SVC), GeoDart can efficiently discover and classify maps discrepancies. Through its graphical interface, the GeoDart system enables users such as professional editors and cartographers to visually inspect, identify, and correct map discrepancies mutually across the three engines.

Routing engines and navigation services are among the top applications that take advantage of the OpenStreetMap (OSM) collaborative project. With that said, it is key for the underlying road network data provided by the OSM public geographic datasets to be as accurate as possible for these services to work correctly. This means that road networks must be fully connected, and constraints such as turn restrictions, road directionality, and correct road classification must be respected. However, being an open-license project with around 7 million users and a daily average of about 3.5 million map changes, errors in the data are far from lacking. Issues like misclassified road segments, incorrect connections and gaps in road networks are fairly common, and they pose a complex yet notable obstacle that jeopardizes the accuracy and reliability of routing services that rely on the OSM data. This paper presents a system named OSMRunner developed to tackle and remedy all sorts of connectivity errors in OSM graphs. The system automatically detects connectivity errors that otherwise require an extensive manual process to discover. It is designed to achieve full connectivity in any area of the OSM road network. User input is made available via a friendly graphical user interface that allows visual error investigation, fix suggestions, and easy access to editing tools.

As any other type of data, GPS traces contain noise, anomaly, and sometimes unexpected values. Normally, researchers and data engineers analysts would start dealing with GPS data by removing those noises and outliers. However, in this work, we take the opposite direction. We focus on analyzing those unexpected values rather than discarding them. Interestingly, we discovered useful findings from an insight look at the noise in GPS trajectories. The intuition behind those discoveries is that when unexpected GPS readings are observed several times around a specific location, we study the nature of that location rather than thrown away those reading. By doing so, we are able to tell the type of area around those readings. For example, we can infer that a driver is passing by a tall building or through a forest based on the pattern of noise in the GPS readings. We are also able to question the quality of the underlying road map. Our findings and discoveries are based on the analysis of real GPS data for the Microsoft shuttles.

In this demo, we present a system for managing location uncertainty in moving objects' data and refining their uncertain trajectories. Therefore, users are able to query objects' past, present, and predicted location more precisely. In the absence of precise location data, i.e. exact lat and long, the uncertain location is defined by an uncertainty region that overlaps multiple nodes in the underlying road network graph. Imprecise location comes from various causes such as inaccurate GPS readings, cloaked region for privacy, or communication issues. The main idea is to find a maximum likelihood connected path of nodes across consecutive regions of uncertainty. By doing so, we narrow down the possible paths and hence prune out a considerable number of nodes in the uncertain regions which in turn leads to a smaller and more precise region. Finally, using the latest location data received from a given object, following refinements, we predict its future movements. Due to the uncertain nature of the problem, there are always multiple possible locations for a moving object. This is only amplified when we try to predict future movements. The refinement steps narrow down possible locations significantly and hence reduces the computation cost. During the demo, the audience will be able to interact with the system to define the size of the uncertainty region, examine the refinement process, and visually experience how the system narrows down the possible locations of the objects' past, current, and future trajectory segments.

GPS data is noisy by nature. A typical location-based service would start by filtering out the noise from the raw GPS points that are generated by moving objects. Once the locations of the objects are identified, the location-based service is provided. In this paper, we decide not to throw away the noise. Instead, we consider the noise as an asset. We analyze the various noise patterns under different conditions and region characteristics. More specifically, we focus on one example where a lot of GPS noise is experienced; which is urban canyons. We believe that learning the GPS noise patterns in a supervised environment enables us to discover knowledge about new areas or areas where we have little knowledge. This paper is based on the analysis of GPS traces that are collected from the shuttle service within the Microsoft campuses around Seattle, Washington.

It is a fact that there are tons of GPS traces generated every minute by the millions of in-road vehicles over the world. Naturally, those traces contain imprecise readings, and most of the time they include noise and outliers. Therefore, there is a real need for a tool to allow users, companies, and researchers to get a deep insight into those raw traces and discover potential knowledge out of it. This knowledge would uncover the quality level of the GPS traces and, indeed, the quality level of the underlying map. It would also help discover interesting facts about the surrounding environment such as the type and height of buildings, the landscape cover, the weather conditions, and the nature of businesses and activities. This demo presents a system that allows users to interactively explore their collected GPS traces. Users can visually inspect the precision of their raw GPS traces, and snap these traces to the underlying road network map. Furthermore, users have the ability to clean their traces by applying various types of spatio-temporal filters. Users can perform noise analysis and produce statistics over regions of interest on the map. Last but not least, the system gives suggestions or guesses on the surrounding environment by comparing the perceived noise patterns to a database of pre-stored noise patterns. For the demo purpose, the system is initially populated with a rich data set of trajectories generated from the Microsoft shuttle service around the Greater Area of Seattle.

NoSQL data-stores are commonly used to provide flexibility and availability for big data handling. However, there is a lack of comprehensive studies about which NoSQL data-store performs the best from the two scalability aspects, (scale-up, and scale-out), in a distributed and parallel processing environment. This paper compares the popular NoSQL data-stores (Cassandra, HBase, and MongoDB) and analyzes the resulting performance. Our experiments measure throughput, latency, and run-time of the evaluated data-stores on a big data set that consist of standard benchmarking workloads. Our results provide that the performance of each NoSQL data-store varies according to two main factors, (a) the type of executed operation, (read, scan, update, write, and insert), and (b) the level of distribution.

Locating spatial data sources for a specific area of interest (AOI) is a difficult task, because of constantly updating server locations (URLs), specific layer location changes within that server location, and the relative unpopularity of a specific spatial data source. The proposed system, named Pine attempts to remedy the issue using automatic, yet user-led discovery of data sources by utilizing a web plug-in that discovers spatial data sources as users browse the web. The web plug-in has a two-fold function, (1) immediately presenting the spatial data source and all of the layers contained within that server discovered by the plug-in, (2) sending those layers and servers into a centralized, search-able repository that is accessible via the web. By utilizing the users browsing habits, and their machines as the discoverers of spatial data, Pine avoids the very high computational overhead of discovery of spatial data sources from a central server using a web crawling approach. As with any user-contributed data set, Pine must get users to actually contribute to the central repository, and it achieves this by including functionality that is useful to the user on its own by displaying a search-able list in the web plug-in of spatial data sources that the user has discovered themselves, a previously difficult task. The system implements a push based approach for discovering data sources, as the plug-in sends the data directly to the central repository, it is always up to date with the newest data sources discovered by any of the many instances of the web plug-in running on users computers

This poster presents the PreGo system for smart touring services. PreGo is smart in the sense that it enables its users to consider many preferences, (e.g., distance, travel time, services, attractions, safety), in their routing queries. The recommended route is completely personalized based on each user's weights for each of the routing preferences.

Connected moving objects with location sensors form the world of the Internet of Moving Things. This world includes people, animals, vehicles, drones, and vessels, to name a few. The conventional spatial libraries including Microsoft SQL Server Spatial (SqlSpatial) are primarily developed to evaluate spatial operations on stationary things. When it comes to real-world applications for the Internet of Moving Things that require realtime tracking and processing, the limitations of these libraries float to the surface. Unfortunately, the SqlSpatial library has very limited operations in this domain. This paper presents the Reactive eXtension Spatial (RxSpatial) library developed to provide real-time processing of spatio-temporal operations on moving objects connected through the Internet of Things. The superiority of the RxSpatial over the basic SqlSpatial is demonstrated throughout extensive experimental evaluations on real and synthetic data sets.

In smart cities, commuters have the opportunities for smart routing that may enable selecting a route with less car accidents, or one that is more scenic, or perhaps a straight and flat route. Such smart personalization requires a data management framework that goes beyond a static road network graph. This paper introduces PreGo, a novel system developed to provide real time personalized routing. The recommended routes by PreGo are smart and personalized in the sense of being (1) adjustable to individual users preferences, (2) subjective to the trip start time, and (3) sensitive to changes of the road conditions. Extensive experimental evaluation using real and synthetic data demonstrates the efficiency of the PreGo system.

Faced with the continuously increasing scale of data and expectation on response time, complex deep learning technologies, though highly accurate, present two non-rival challenges: a large amount of training data makes a model impossible to be built in short time and intolerable time-cost prohibits acceptable real-time responses. In this research we focus on improving the accuracy and efficiency of the handwritten digit recognition problem. We chose this problem because it is regarded as the prototype of a lot of complex recognition and classification problems. The success of classification of the handwritten digit dataset can be extended further to other advanced areas. The Convolutional Neural Network (CNN) is implemented to do the recognition. We further improved the accuracy by adding elastic distortion to the input data, which helps the model better select the features. In addition we implement distributed computing to reduce the time cost. The training process is divided and a final model is formulated by the combination of each trained model. The results shows two facts: the elastic distortion helped the CNN model to improve the accuracy by 7-10%; and the distributed computing method reduced the training time consumption by about 50%.

Internet traffic measurement and analysis have long been used to characterize network usage and user behaviors, but face the problem of scalability under the explosive growth of Internet traffic and high-speed access. In this paper, we present Hobbits, a Hadoop and Hive based traffic analysis system that performs Internet Protocol (IP) and Transport Control Protocol (TCP) analysis of large-sized Internet traffic in a scalable manner. Our experimental evaluation on real datasets confirms that Hobbits outperforms previous solutions in terms of both job completion time and storage efficiency.

A few decades ago, the Internet was created. Since then, searching for information and services has increased exponentially. With the introduction of GPS-enabled devices, a special type of search appeared offering location-aware services. These services customize search results based on users' location. This includes, but not limited to, (1) service finding, e.g., "find the nearest pizza restaurant", (2) routing, e.g., "obtain the shortest path from a user's home to the airport", (3) transportation, e.g., "what are the bus links to get a user from downtown to the mall", and (4) monitoring, e.g., "alert a parent if their child school-bus deviates from its regular route". Though new hardware and software technologies such as smart watches, voice search, and big-data platforms have been introduced and widely used, each single type of the above services has benefited very little from these technologies. On the local level of each service (the micro level), a full-fledged view is still missing. On the global level of all service types (the macro level), all Location-aware services are still acting as isolated islands and a global optimized service is not available. This paper presents our vision of how to provide an integrated macro location-aware service that acts harmoniously, and how each micro service can be further improved by better incorporation of novel technologies. We also overview the key challenges associated with these suggested improvements. Then, we highlight the potential value-added by the application of our vision.

The spatial libraries that have been developed by Microsoft, IBM and Oracle have substantially changed the capabilities of geospatial computing. These libraries implement several functionalities that include intersection, distance, and area for various geospatial objects. These libraries came out to address a wealth of use cases that were challenging in that era. As time goes by, GPS devices and location-aware mobile technologies increased the demand for geospatial computing, in general, and for real time geostreaming, in particular. Existing commercial spatial libraries were originally designed to support operations on stationary objects with limited or no capabilities for moving objects. In this paper, we introduce the RxSpatial library, a real time reactive spatial library for spatiotemporal stream query processing. RxSpatial provides, (1) a front-end, which is a programming interface for developers who are familiar with the Microsoft. NET Reactive framework and the Microsoft SQL Server Spatial Library, and (2) a back-end for processing spatial operations in a streaming fashion. RxSpatial provides the programming convenience at the front end and the query processing efficiency at the back end.

Existing routing services calculate the best route from source to destination over a road network graph. Most commercial routing services offer the best route in terms of either the shortest travel distance or the shortest travel time (with or without considering current traffic conditions). While travel distance and travel time are crucial route preferences for the commuter, other preferences are equally, or even more, important. Examples of other route preferences include fuel consumption, gas emissions, road safety, points of interest along the route, construction activities, open shops and restaurants. While some route preferences are static (e.g., travel distance and points of interests), other route preferences are dynamic and vary according to the time of the day (e.g., traffic-dependent travel time and the number of open shops/restaurants). Volunteered Geographic information (VGI) has been proposed as an approach to collect massive amounts of route information and, more specifically, the time varying parameters. This demo presents PreGo, a time-dependent multi-preference routing engine. During the demo, audience would interact with the PreGo routing engine to (1) find the optimal route w.r.t. The user's personal preferences for a given start time, (2) dynamically obtain the best start time for a trip given a set of preferences, (3) feed the system with VGI and examine their effect on the chosen route at real time, and (4) examine the correctness and efficiency of the PreGo selected routes compared to routes chosen by other commercial systems.

Current commercial spatial libraries implemented strong support on functionalities like intersection, distance, and area for various stationary geospatial objects. The missing point is the support for moving object. Performing moving object real-time location tracking and computation on server side of GIS application is challenging because of high user volume of moving object to track, time complexity of analysis and computation, and requirement of real-timing. In this Demo, we present the RxSpatial, a real time reactive spatial library that consists of (1) a front-end, a programming interface for developers who are familiar with the Reactive framework and the Microsoft Spatial Library, and (2) a back-end for processing spatial operations in a streaming fashion. Then we provide the demonstration scenarios that show how RxSpatial is employed in real-world applications. The demonstration scenarios include criminal activity tracking, collaborative vehicle system, performance analysis and an interactive internal inspection.

Predictive queries on moving objects offer an important category of location-aware services based on the objects' expected future locations. A wide range of applications utilize this type of services, e.g., traffic management systems, location-based advertising, and ride sharing systems. This paper proposes a novel index structure, named Predictive tree (P-tree), for processing predictive queries against moving objects on road networks. The predictive tree: (1) provides a generic infrastructure for answering the common types of predictive queries including predictive point, range, KNN, and aggregate queries, (2) updates the probabilistic prediction of the object's future locations dynamically and incrementally as the object moves around on the road network, and (3) provides an extensible mechanism to customize the probability assignments of the object's expected future locations, with the help of user defined functions. The proposed index enables the evaluation of predictive queries in the absence of the objects' historical trajectories. Based solely on the connectivity of the road network graph and assuming that the object follows the shortest route to destination, the predictive tree determines the reachable nodes of a moving object within a specified time window T in the future. The predictive tree prunes the space around each moving object in order to reduce computation, and increase system efficiency. Tunable threshold parameters control the behavior of the predictive trees by trading the maximum prediction time and the details of the reported results on one side for the computation and memory overheads on the other side. The predictive tree is integrated in the context of the iRoad system in two different query processing modes, namely, the precomputed query result mode, and the on-demand query result mode. Extensive experimental results based on large scale real and synthetic datasets confirm that the predictive tree achieves better accuracy compared to the existing related work, and scales up to support a large number of moving objects and heavy predictive query workloads.

In this seminar, we address spatial predictive queries both in Euclidian spaces and over road networks. We provide a definition for various types of spatial predictive queries, describe current research trends, and envision future directions. We present practical application scenarios and emphasize the roadblocks that are holding industry back from the commercialization of spatial predictive queries. This seminar targets audience in mobile data management, spatiotemporal query processing, mobile crowd sourcing, and tracking of moving objects.

This demo presents the Panda system for efficient support of a wide variety of predictive spatio-temporal queries. These queries are widely used in several applications including traffic management, location-based advertising, and store finders. Panda targets long-term query prediction as it relies on adapting a long-term prediction function to: (a) scale up to large number of moving objects, and (b) support predictive queries. Panda does not only aim to predict the query answer, but, it also aims to predict the incoming queries such that parts of the query answer can be precomputed before the query arrival. Panda maintains a tunable threshold that achieves a trade-off between the predictive query response time and the system overhead in precomputing the query answer. Equipped with a Graphical User Interface (GUI), audience can explore the Panda demo through issuing predictive queries over a moving set of objects on a map. In addition, they are able to follow the execution of such queries through an eye on the Panda execution engine.

Road-network data compression reduces the size of the network to occupy lesser storage with the aim to fit small form-factor routing devices, mobile devices, or embedded systems. Compression (1) reduces the storage cost of memory and disks, and (2) reduces the I/O and communication overhead. There are several road network compression techniques proposed in literature. These techniques are evaluated by their compression ratios. However, none of these techniques takes into consideration the possibility that the generated compressed data can be used directly in map-matching. Map-matching is an essential component of routing services that matches a measured latitude and longitude of an object to an edge in the road network graph. In this paper, we propose a novel compression technique, named COMA, that significantly reduces the size of a given road network data. Another advantage of the proposed technique is that it enables the generated compressed road network graph to be used directly in map-matching without a need to decompress it beforehand. COMA smartly deletes those nodes and edges that will not affect neither the graph connectivity nor the accuracy of map-matching objects' location. COMA is equipped with an adjustable parameter, termed conflict factor C, by which location-based services can achieve a trade-off between the compression gain and map-matching accuracy. Extensive experimental evaluation on real road network data demonstrates competitive performance on compression-ratio and the high mapmatching accuracy achieved by the proposed technique.

We demonstrate a novel location aware services framework termed COMA for efficient compression and map-matching of road-network graph data. Key innovations include working demonstration of a new compression algorithm to eliminate nodes and edges that do not affect graph connectivity while ensuring object location map-matching accuracy. The demonstration features: (1) Algorithm to leverage compressed versions of road-network graphs for map-matching of objects locations to correct road edges without decompression, (2) Upwards of 75% compression ratio implying significant savings for road network data transmission costs, a key constraint for internet of things (IOT) devices, and (3) Use of a new controllable parameter, termed conflict factor C, whereby location aware services can trade the compression efficiency with map-matching accuracy at varying granularity. In addition to above features the demonstration features an extensible framework that enables experimentation and comparison between various compression and map-matching algorithms in a rich interactive interface. In this paper we outline data management challenges for location aware services using various scenarios for compression of a real road-network map of a large region of United States, along with both real and synthetic moving object trajectories distributed over this map. We describe the COMA framework through its map-based Graphical User Interface, ability to select the area of interest from the road-network map, and submit a compression request. COMA can export and save the compact versions of the selected area in different formats and plot the compressed graph over the original map for visual inspection to study the differences between compressed and uncompressed versions and various related statistics.

Traditional routing services aim to save driving time by recommending the shortest path, in terms of distance or time, to travel from a start location to a given destination. However, these methods are relatively static and to a certain extent rely on traffic patterns under relatively normal conditions to calculate and recommend an appropriate route. As such, they do not necessarily translate effectively during severe weather events such as tornadoes. In these scenarios, the guiding principal is not, optimize for travel time, but rather, optimize for survivability of the event, i.e., can we recommend an evacuation route to those users inside the hazardous areas. In this demo, we present a framework for routing services for evacuating and avoiding real world severe weather threats that is able to: (1) Identify the users inside the dangerous region of a severe weather event (2) Recommend an evacuation route to guide the users out to a safe destination or shelter (3) Assure the recommended route to be one of the shortest paths after excluding the risky area (4) Maintain the flow of traffic by normalizing the evacuation on the possible safe routes. During the demo, attendees will be able to use the system interactively through its graphical user interface within a number of different scenarios. They will be able to locate the severe weather events on real time basis in any area in USA and examine detailed information about each event, to issue an evacuation query from an existing dangerous area by identifying a destination location and receiving the routing direction on their mobile devices, to issue an avoidance routing query to ask for a shortest path that avoids the dangerous region, to have an inside look into the internal system components and finally, to evaluate the overall system performance.

This demo presents the iRoad framework for evaluating predictive queries on moving objects for road networks. The main promise of the iRoad system is to support a variety of common predictive queries including predictive point query, predictive range query, predictive KNN query, and predictive aggregate query. The iRoad framework is equipped with a novel data structure, named reachability tree, employed to determine the reachable nodes for a moving object within a specified future time Τ. In fact, the reachability tree prunes the space around each object in order to significantly reduce the computation time. So, iRoad is able to scale up to handle real road networks with millions of nodes, and it can process heavy workloads on large numbers of moving objects. During the demo, audience will be able to interact with iRoad through a well designed Graphical User Interface to issue different types of predictive queries on a real road network, to obtain the predictive heatmap of the area of interest, to follow the creation and the dynamic update of the reachability tree around a specific moving object, and finally to examine the system efficiency and scalability.

This paper presents the Panda system for efficient support of a wide variety of predictive spatio-temporal queries that are widely used in several applications including traffic management, location-based advertising, and ride sharing. Unlike previous attempts in supporting predictive queries, Panda targets long-term query prediction as it relies on adapting a well-designed long-term prediction function to: (a) scale up to large number of moving objects, and (b) support large number of predictive queries. As a means of scalability, Panda smartly precomputes parts of the most frequent incoming predictive queries, which significantly reduces the query response time. Panda employs a tunable threshold that achieves a trade-off between query response time and the maintenance cost of precomptued answers. Experimental results, based on large data sets, show that Panda is scalable, efficient, and as accurate as its underlying prediction function.