Accurate prediction of water quality and quantity is crucial for sustainable development and human well-being. However, existing data-driven methods often suffer from spatial biases in model performance due to heterogeneous data, limited observations, and noisy sensor data. To overcome these challenges, we propose Fair-Graph, a novel graph-based recurrent neural network that leverages interrelated knowledge from multiple rivers to predict water flow and temperature within large-scale stream networks. Additionally, we introduce node-specific graph masks for information aggregation and adaptation to enhance prediction over heterogeneous river segments. To reduce performance disparities across river segments, we introduce a centralized coordination strategy that adjusts training priorities for segments. We evaluate the prediction of water temperature within the Delaware River Basin, and the prediction of streamflow using simulated data from U.S. National Water Model in the Houston River network. The results showcase improvements in predictive performance and highlight the proposed model's ability to maintain spatial fairness over different river segments.

Over a century separates initial lead service lateral installations from the federal regulation of lead in drinking water. As such, municipalities often do not have adequate information describing installations of lead plumbing. Municipalities thus face challenges such as reducing exposure to lead in drinking water, spreading scarce resources for gathering information, adopting short-term protection measures (e.g., providing filters), and developing longer-term prevention strategies (e.g., replacing lead laterals). Given the spatial and temporal patterns to properties, machine learning is seen as a useful tool to reduce uncertainty in decision making by authorities when addressing lead in water. The Pittsburgh Water and Sewer Authority (PWSA) is currently addressing these challenges in Pittsburgh and this paper describes the development and application of a model predicting high tap water concentrations (> 15 ppb) for PWSA customers. The model was developed using spatial cross validation to support PWSA’s interest in applying predictions in areas without training data. The model’s AUROC is 71.6% and primarily relies on publicly available property tax assessment data and indicators of lateral material collected by PWSA as they meet regulatory requirements.

In this paper, we propose a method for predicting the distributions of people’s trajectories on the road network throughout a city. Specifically, we predict the number of people who will move from one area to another, their probable trajectories, and the corresponding likelihoods of those trajectories in the near future, such as within an hour. With this prediction, we will identify the hot road segments where potential traffic jams might occur and reveal the formation of those traffic jams. Accurate predictions of human trajectories at a city level in real time is challenging due to the uncertainty of people’s spatial and temporal mobility patterns, the complexity of a city level’s road network, and the scale of the data. To address these challenges, this paper proposes a method which includes several major components: (1) a model for predicting movements between neighboring areas, which combines both latent and explicit features that may influence the movements; (2) different methods to estimate corresponding flow trajectory distributions in the road network; (3) a MapReduce-based distributed algorithm to simulate large-scale trajectory distributions under real-time constraints. We conducted two case studies with taxi data collected from Beijing and New York City and systematically evaluated our method.

The proliferation of data acquisition devices like 3D laser scanners had led to the burst of large-scale spatial terrain data which imposes many challenges to spatial data analysis and computation. With the advent of several emerging cloud technologies, a natural and cost-effective approach to managing such large-scale data is to store and process such datasets in a publicly hosted cloud service using modern distributed computing paradigms such as MapReduce. For several key spatial data analysis and computation problems, polygon retrieval is a fundamental operation which is often computed under real-time constraints. However, existing sequential algorithms fail to meet this demand effectively given that terrain data in recent years have witnessed an unprecedented growth in both volume and rate. In this work, we present a MapReduce-based parallel polygon retrieval algorithm which aims at minimizing the IO and CPU loads of the map and reduce tasks during spatial data processing. Our proposed algorithm first hierarchically indexes the spatial terrain data using a quad-tree index, with the help of which, a significant amount of data is filtered out in the pre-processing stage based on the query object. In addition, a prefix tree based on the quad-tree index is built to query the relationship between the terrain data and query area in real time which leads to significant savings in both I/O load and CPU time. The performance of the proposed techniques is evaluated in a Hadoop cluster and the results demonstrate that the proposed techniques are scalable and lead to more than 35% reduction in execution time of the polygon retrieval operation over existing distributed algorithms.

The proliferation of data acquisition devices like 3D laser scanners had led to the burst of large-scale spatial terrain data which imposes many challenges to spatial data analysis and computation. With the advent of several emerging collaborative cloud technologies, a natural and cost-effective app

Personalized routing counts on traveler’s preferences which are usually based on different criteria, such as shortest, fastest, least traffic, or less expensive (e.g., less fuel cost, toll free). However, people are increasingly becoming concerned about the adverse health effects of exposure to air pollution in chosen routes. Exposures to elevated air pollution concentrations particularly endanger children, pregnant women, elderly people, and people with asthma and other respiratory conditions. Choosing routes with least air pollution exposure (APE) is seen as one approach to minimize the level of pollution exposed, which is a major public health issue. Routing algorithms use weights on segments of road networks to find optimum routes. While existing weights are commonly distance and time, among a few others, there is currently no weight based on APE to compute least APE routes. In this paper, we present a weight function that computes weight based on APE. Two different approaches, geostatistical and non-geostatistical, were used to compute APE weight. Each approach was evaluated, and the results indicate that the APE weight is suitable for computing least APE routes.

With the advanced capabilities of mobile devices and the success of car navigation systems, interest in pedestrian navigation systems is on the rise. A critical component of any navigation system is a map database, which represents a network (e.g., road networks for car navigation) and supports key functionality such as map display, geocoding, and routing. Road networks, mainly due to the popularity of car navigation systems, are well defined and publicly available. However, in pedestrian navigation systems, as well as other applications including urban planning and physical activity studies, road networks do not adequately represent the paths that pedestrians usually travel. Currently, there is a void in literatures discussing the challenges, methods, and best practices for pedestrian network map generation. This coupled with the increased demand for pedestrian networks is the prime motivation for development of new approaches and algorithms to automatically generating pedestrian networks. Three approaches, network buffering, using existing road networks, collaborative mapping, using Global Positioning System (GPS) traces collected by volunteers, and image processing, using high-resolution satellite and laser imageries, were implemented and evaluated with a pedestrian network baseline as a ground truth. The results of the experiments indicate that these three approaches, while differing in complexity and outcome, are viable for automatic pedestrian network map generation. The recommendation of a suitable approach for generating pedestrian networks for a given set of sources and requirements is provided.

Modern navigation systems/services are computationally sophisticated gadgets capable of assisting people with mobility in locations where digital road network maps are available. However, despite much advancements in navigation systems/services, they fall short of handling common constraints (e.g.,

Although in-car navigation systems are becoming commonplace, cars travelling in urban canyon areas still suffer from poor positional accuracy and limited visibility of GPS satellites due to signal blockage. As a result, map matching accuracy and navigation performance may not reach the required leve

Accidents on roads are one of the main causes of human loss and damages to property every day and anywhere that vehicles travel. Communications-based approaches to reducing highway accidents include vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communications. However, while V2V and V

Geocoding is an uncertain process that associates an address or a place name with geographic coordinates. Traditionally, geocoding is performed locally on a stand-alone computer with the geocoding tools usually bundled in GIS software packages. The use of such tools requires skillful operators who know about the issues of geocoding, that is, reference databases and complicated geocoding interpolation techniques. These days, with the advancement in the Internet and Web services technologies, online geocoding provides its functionality to the Internet users with ease; thus, they are often unaware of such issues. With an increasing number of online geocoding services, which differ in their reference databases, the geocoding algorithms, and the strategy for dealing with inputs and outputs, it is crucial for the service requestors to realize the quality of the geocoded results of each service before choosing one for their applications. This is primarily because any errors associated with the geocoded addresses will be propagated to subsequent decisions, activities, modeling, and analysis. This article examines the quality of five online geocoding services: Geocoder.us, Google, MapPoint, MapQuest, and Yahoo!. The quality of each geocoding service is evaluated with three metrics: match rate, positional accuracy, and similarity. A set of addresses from the US Environmental Protection Agency (EPA) database were used as a baseline. The results were statistically analyzed with respect to different location characteristics. The outcome of this study reveals the differences among the online geocoding services on the quality of their geocoding results and it can be used as a general guideline for selecting a suitable service that matches an application's needs.

The increasing capabilities of mobile devices and their mobile positioning technologies have shown great promise in location-enabled applications such as navigation systems. One of the essential components of a navigation system is a spatial database as it provides the base data to perform navigatio

Considering the growth of wireless communication and mobile positioning technologies, location-based services (LBSs) have been generating increasing research interest in recent years. One of the critical issues for the deployment of LBS applications is how to reconcile their quality of service with

We propose a location-based query anonymization technique, LBS (k, T)-anonymization, that ensures anonymity of user's query in a specific time window against what we call known user attack. We distinguish between our technique and related work on k-anonymity for LBSs by showing that they target different privacy inference attacks. Also, we analyze the inconsistency of the existing predominant approach with the original definition of k-anonymity and its implications on the anonymization. Finally, we present an evaluation framework that assess the applicability and performance of the proposed technique using an evaluation framework.

Much research has recently been devoted to developing approaches, techniques, and technologies which assist people with navigation within buildings. Routing is an essential technique often requested by users prior to real-time navigation, providing them with appropriate routes within buildings. A survey of the literature reveals indoor routing approaches primarily based on shortest distance or fastest travel time as the main criteria. However, such routing criteria that are common in outdoor navigation may not be as applicable to indoor navigation. Presenting users with appropriate indoor routes could be beneficial to many users in various situations. For example, people with physical, cognitive, or sensory impairments may need routes that take into account their special needs as well as preferences rather than ones that are shortest or fastest. In this paper, we present a new ontology and an algorithm (ONALIN) that provides routing for individuals with various needs and preferences. To this end, ONALIN takes the ADA (American disability act) standards, among other requirements, into consideration. An indoor routing algorithm based on this ontology is presented and analyzed in detail where it first finds feasible routes with respect to the special needs of the users and then from those will select the comfortable routes.

Protein function is a dynamic property closely related to the conformational mechanisms of protein structure in its physiological environment. To understand and control the function of target proteins, it becomes increasingly important to develop methods and tools for predicting collective motions at the molecular level. In this article, we review computational methods for predicting conformational dynamics and discuss software tools for data analysis. In particular, we discuss a high-throughput, web-based system called iGNM for protein structural dynamics. iGNM contains a database of protein motions for more than 20 000 PDB structures and supports online calculations for newly deposited PDB structures or user-modified structures. iGNM allows dynamics analysis of protein structures ranging from enzymes to large complexes and assemblies, and enables the exploration of protein sequence-structure-dynamics-function relations.

UNLABELLED: TMpro is a transmembrane (TM) helix prediction algorithm that uses language processing methodology for TM segment identification. It is primarily based on the analysis of statistical distributions of properties of amino acids in transmembrane segments. This article describes the availability of TMpro on the internet via a web interface. The key features of the interface are: (i) output is generated in multiple formats including a user-interactive graphical chart which allows comparison of TMpro predicted segment locations with other labeled segments input by the user, such as predictions from other methods. (ii) Up to 5000 sequences can be submitted at a time for prediction. (iii) TMpro is available as a web server and is published as a web service so that the method can be accessed by users as well as other services depending on the need for data integration. AVAILABILITY: http://linzer.blm.cs.cmu.edu/tmpro/ (web server and help), http://blm.sis.pitt.edu:8080/axis/services/TMProFetcherService (web service).

MOTIVATION: The knowledge of protein structure is not sufficient for understanding and controlling its function. Function is a dynamic property. Although protein structural information has been rapidly accumulating in databases, little effort has been invested to date toward systematically characterizing protein dynamics. The recent success of analytical methods based on elastic network models, and in particular the Gaussian Network Model (GNM), permits us to perform a high-throughput analysis of the collective dynamics of proteins. RESULTS: We computed the GNM dynamics for 20 058 structures from the Protein Data Bank, and generated information on the equilibrium dynamics at the level of individual residues. The results are stored on a web-based system called iGNM and configured so as to permit the users to visualize or download the results through a standard web browser using a simple search engine. Static and animated images for describing the conformational mobility of proteins over a broad range of normal modes are accessible, along with an online calculation engine available for newly deposited structures. A case study of the dynamics of 20 non-homologous hydrolases is presented to illustrate the utility of the iGNM database for identifying key residues that control the cooperative motions and revealing the connection between collective dynamics and catalytic activity.

Location-Based Services (LBSs) utilize information about users' locations through location-aware mobile devices to provide services, such as nearest features of interest, they request. This is a common strategy in LBSs and although it is needed and benefits the users, there are additional benefits when future locations (e.g., locations at later times) are predicted. One major advantage of location prediction is that it provides LBSs with extended resources, mainly time, to improve system reliability which in return increases the users' confidence and the demand for LBSs. However, much of the current location prediction research is focused on generalized location models, where the geographic extent is divided into regular-shape cells. These models are not suitable for certain LBSs whose objective is to compute and present on-road services, because a cell may contain several roads while the computation and delivery of a service may require the exact road on which the user is driving. We propose a new model, called Predictive Location Model (PLM), to predict locations in LBSs with road-level granularities. The premise of PLM is geometrical and topological techniques allowing users to receive timely and desired services.