Wan D. Bae

A Mobile Data Analysis Framework for Environmental Health Decision Support

Relations between negative health effects like asthma and lung cancer and elevated levels of the environmental factors, such as air pollution, tobacco smoke and humidity, have been detected in several large scale exposure studies. Thus, public health care and service systems require the ability to track, monitor, store, and analyze individual moving trajectories along with several environmental conditions the individual is exposed to in order to identify meaningful relationships among theses data and derive conclusions for environmental health decision support. With continued advances in information technology, patients can be monitored with numerous intelligent devices. Sensors can be integrated into their mobile devices such as smart phones for continuous health assistance and disease attack prevention. However, researchers must overcome many challenges, such as data acquisition, data scales and data uncertainty, in order to develop a real-time health monitoring system. In this paper, we propose a system framework for modeling and analyzing individual exposure to environmental triggers of asthma attacks. The proposed system can provide a tool to develop more accurate asthma prevention and care plans enabled by real-time patient monitoring and communication through alerts for potential environmental triggers.

The tornado model: uncertainty model for continuously changing data

To support emerging database applications that deal with continuously changing (or moving) data objects (CCDOs), such as vehicles, RFIDs, and multi-stimuli sensors, one requires an efficient data management system that can store, update, and retrieve large sets of CCDOs. Although actual CCDOs can continuously change over time, computer systems cannot deal with continuously occurring infinitesimal changes. Thus, in the data management system, each objects spatiotemporal values are associated with a certain degree of uncertainty at virtually every point in time, and the queries are mostly processed over estimates characterizing the uncertainty. The smaller the uncertainty is, the better the query performance becomes. The paper proposes a sophisticated asymmetric uncertainty model, called the Tornado Model, which can effectively represent, process, and minimize the data uncertainty for a wide variety of CCDO database applications.

Web data retrieval: solving spatial range queries using k-nearest neighbor searches

As Geographic Information Systems (GIS) technologies have evolved, more and more GIS applications and geospatial data are available on the web. Spatial objects in a given query range can be retrieved using spatial range query − one of the most widely used query types in GIS and spatial databases. However, it can be challenging to retrieve these data from various web applications where access to the data is only possible through restrictive web interfaces that support certain types of queries. A typical scenario is the existence of numerous business web sites that provide their branch locations through a limited “nearest location” web interface. For example, a chain restaurant’s web site such as McDonalds can be queried to find some of the closest locations of its branches to the user’s home address. However, even though the site has the location data of all restaurants in, for example, the state of California, it is difficult to retrieve the entire data set efficiently due to its restrictive web interface. Considering that k-Nearest Neighbor (k-NN) search is one of the most popular web interfaces in accessing spatial data on the web, this paper investigates the problem of retrieving geospatial data from the web for a given spatial range query using only k-NN searches. Based on the classification of k-NN interfaces on the web, we propose a set of range query algorithms to completely cover the rectangular shape of the query range (completeness) while minimizing the number of k-NN searches as possible (efficiency). We evaluated the efficiency of the proposed algorithms through statistical analysis and empirical experiments using both synthetic and real data sets.

Optimizing map labeling of point features based on an onion peeling approach

Map labeling of point features is the problem of placing text labels to correspond- ing point features on a map in a way that minimizes overlaps while satisfying basic rules for the quality. This is a critical problem in the application of cartography and geographical information systems (GIS). In this paper we study the fundamental issues related to map labeling of point features and develop a new genetic algorithm to solve this problem. We adopt a method called convex onion peeling and utilize it in our proposed convex onion peeling genetic algorithm (COPGA )t o efficiently manage map labels of point features. The proposed algorithm takes advantage of a convex onion peeling structure to achieve better map label initialization and to enhance the evolutionary process. The performance of the proposed algorithm was evaluated through extensive experiments on both synthetic and real datasets. In experiments with an implementation of our algorithm using OpenMap, the results show that our genetic algorithm, based on convex onion peeling, is an efficient, robust, and extensible algorithm for automated map labeling of point features.

An interactive framework for raster data spatial joins

Many Geographic Information Systems (GIS) handle large geospatial datasets stored in raster representation. Spatial joins over raster data are important queries in GIS for data analysis and decision support. However, evaluating spatial joins can be very time intensive due to the size of these datasets. In this paper we propose a new interactive framework that allows users to get approximate answers in near instantaneous time, thus allowing for truly interactive data exploration. Our method utilizes two proposed statistical approaches: probabilistic join and sampling based join. Our probabilistic join method provides speedup of two orders of magnitude with no correctness guarantee, while our sampling based method provides an order of magnitude improvement over the full quad-tree join and also provides running confidence intervals. We propose a framework that combines the two approaches to allow end users to tradeoff speed versus bounded accuracy. The two approaches are evaluated empirically with real and synthetic datasets.

MobiS: a distributed paradigm of mobile sensor data analytics for evaluating environmental exposures

Continued advances and cost reduction in personal mobile devices such as smart phones made them widely used in daily-life practices. Mobile devices can be integrated with a growing set of cheap powerful embedded sensors that enable the emergence of mobile sensing applications, including healthcare, environmental monitoring and transportation. As the size of the sensor data continuously grows, managing the data becomes increasingly difficult using traditional database systems. This paper proposes a new framework for large-scale continuously changing mobile sensor data analysis. We discuss the emerging environmental sensing paradigms and opportunities to apply HBase and MapReduce for managing multiple sensor data in the environmental exposome domain. Moreover, we provide an architectural framework and present a concrete use case with a set of data models, spatio-temporal queries, and MapReduce functions.

IRSJ: incremental refining spatial joins for interactive queries in GIS

An increasing number of emerging web database applications deal with large georeferenced data sets. However, exploring these large data sets through spatial queries can be very time and resource intensive. The need for interactive spatial queries has arisen in many applications such as Geographic Information Systems (GIS) for efficient decision-support. In this paper, we propose a new interactive spatial query processing technique for GIS. We present a family of the Incremental Refining Spatial Join (IRSJ) algorithms that can be used to report incrementally refined running estimates for aggregate queries while simultaneously displaying the actual query result tuples of the data sets sampled so far. Our goal is to minimize the time until an acceptably accurate estimate of the query result is available (to users) measured by a confidence interval. Our approach enables more interactive data exploration and analysis. While similar work has been done in relational databases, to the best of our knowledge, this is the first work using this approach in GIS. We investigate and evaluate different sampling methodologies through extensive experimental performance comparisons. Experiments on both real and synthetic data show an order of magnitude response time improvement relative to the final answer obtained when using a full R-tree join. We also show the impact of different index structures on the performance of our algorithms using three known sampling methods.

An interactive framework for spatial joins: a statistical approach to data analysis in GIS

Many Geographic Information Systems (GIS) handle a large volume of geospatial data. Spatial joins over two or more geospatial datasets are very common operations in GIS for data analysis and decision support. However, evaluating spatial joins can be very time intensive due to the size of datasets. In this paper, we propose an interactive framework that provides faster approximate answers of spatial joins. The proposed framework utilizes two statistical methods: probabilistic join and sampling based join. The probabilistic join method provides speedup of two orders of magnitude with no correctness guarantee, while the sampling based method provides an order of magnitude improvement over the full indexing tree joins of datasets and also provides running confidence intervals. The framework allows users to trade-off speed versus bounded accuracy, hence it provides truly interactive data exploration. The two methods are evaluated empirically with real and synthetic datasets.

Convex onion peeling genetic algorithm: an efficient solution to map labeling of point-feature

Map labeling of point-feature is the problem of placing text labels to corresponding point features on a map in a way that minimizes overlaps while satisfying basic rules for the quality. This problem is a critical problem in the applications of cartography and Geographical Information Systems (GIS). In this paper we study the fundamental issues related to map labeling of point-feature and develop a new genetic algorithm to solve this problem. We adopt a data structure called convex onion peeling and utilize it in our proposed Convex Onion Peeling Genetic Algorithm (COPGA) to efficiently manage point features. We evaluated the performance of the proposed algorithm through extensive experiments on both synthetic and real datasets. The experimental results show that our genetic algorithm based on the convex onion peeling structure is an efficient, robust and extensible algorithm for automated map labeling of point-feature.

An incremental refining spatial join algorithm for estimating query results in GIS

Geographic information systems (GIS) must support large georeferenced data sets. Due to the size of these data sets finding exact answers to spatial queries can be very time consuming. We present an incremental refining spatial join algorithm that can be used to report query result estimates while simultaneously provide incrementally refined confidence intervals for these estimates. Our approach allows for more interactive data exploration. While similar work has been done in relational databases, to the best of our knowledge this is the first work using this approach in GIS. We investigate different sampling methodologies and evaluate them through extensive experimental performance comparisons. Experiments on real and synthetic data show an order of magnitude response time improvement relative to the exact answer obtained when using the R-tree join.