Raimundo F. Dos Santos

Advances in GML for Geospatial Applications

This paper presents a study of Geography Markup Language (GML), the issues that arise from using GML for spatial applications, including storage, parsing, querying and visualization, as well as the use of GML for mobile devices and web services. GML is a modeling language developed by the Open Geospatial Consortium (OGC) as a medium of uniform geographic data storage and exchange among diverse applications. Many new XML-based languages are being developed as open standards in various areas of application. It would be beneficial to integrate such languages with GML during the developmental stages, taking full advantage of a non-proprietary universal standard. As GML is a relatively new language still in development, data processing techniques need to be refined further in order for GML to become a more efficient medium for geospatial applications.

A GRAPH-BASED APPROACH TO DETECT ABNORMAL SPATIAL POINTS AND REGIONS

Spatial outliers are the spatial objects whose nonspatial attribute values are quite different from those of their spatial neighbors. Identification of spatial outliers is an important task for data mining researchers and geographers. A number of algorithms have been developed to detect spatial anomalies in meteorological images, transportation systems, and contagious disease data. In this paper, we propose a set of graph-based algorithms to identify spatial outliers. Our method first constructs a graph based on k-nearest neighbor relationship in spatial domain, assigns the differences of nonspatial attribute as edge weights, and continuously cuts high-weight edges to identify isolated points or regions that are much dissimilar to their neighboring objects. The proposed algorithms have three major advantages compared with other existing spatial outlier detection methods: accurate in detecting both point and region outliers, capable of avoiding false outliers, and capable of computing the local outlierness of an object within subgraphs. We present time complexity of the algorithms, and show experiments conducted on US housing and Census data to demonstrate the effectiveness of the proposed approaches.

Forecasting location-based events with spatio-temporal storytelling

Storytelling, the act of connecting entities through relationships, provides an intuitive platform for exploratory analysis. This paper combines storytelling and Spatio-logical Inference (SLI) to generate rules of interaction among entities and measure how well they forecast a real-world event. The proposed algorithm first takes as input the probability of prior occurrences of events along with their spatial distances. It calculates their soft truths, i.e., the belief they have indeed been observed with certainty. Subsequently, the algorithm applies a relaxed form of logical conjunction and disjunction to compute a distance to satisfaction for each rule. The rules of lowest distances represent the best forecasts. Extensive experiments with social unrest in Afghanistan show that storytelling and SLI can outperform common probabilistic approaches by as much as 30% in terms of precision and 13% in terms of recall.

DAREonline: A Web-Based Domain Engineering Tool

DAREonline is a web-based tool for domain engineering. It supports the DARE framework in a centralized platform-independent environment. Our approach leverages concepts of Service-Oriented Architecture (SOA) to aggregate data and functionality from diverse sources that can be helpful in domain engineering. In this paper, we describe DAREonlines1 architecture and implementation, and its use in a graduate course on software design and quality. Initial results indicate that DAREonline can be a valuable resource for domain analysts and can achieve acceptance at similar levels to DARE COTS.

The big data of violent events: algorithms for association analysis using spatio-temporal storytelling

This paper proposes three methods of association analysis that address two challenges of Big Data: capturing relatedness among real-world events in high data volumes, and modeling similar events that are described disparately under high data variability. The proposed methods take as input a set of geotemporally-encoded text streams about violent events called “storylines”. These storylines are associated for two purposes: to investigate if an event could occur again, and to measure influence, i.e., how one event could help explain the occurrence of another. The first proposed method, Distance-based Bayesian Inference, uses spatial distance to relate similar events that are described differently, addressing the challenge of high variability. The second and third methods, Spatial Association Index and Spatio-logical Inference, measure the influence of storylines in different locations, dealing with the high-volume challenge. Extensive experiments on social unrest in Mexico and wars in the Middle East showed that these methods can achieve precision and recall as high as 80 % in retrieval tasks that use both keywords and geospatial information as search criteria. In addition, the experiments demonstrated high effectiveness in uncovering real-world storylines for exploratory analysis.

A framework for intelligence analysis using spatio-temporal storytelling

Social media have ushered in alternative modalities to propagate news and developments rapidly. Just as traditional IR matured to modeling storylines from search results, we are now at a point to study how stories organize and evolve in additional mediums such as Twitter, a new frontier for intelligence analysis. This study takes as input news articles as well as social media feeds and extracts and connects entities into interesting storylines not explicitly stated in the underlying data. First, it proposes a novel method of spatio-temporal analysis on induced concept graphs that models storylines propagating through spatial regions in a time sequence. Second, it describes a method to control search space complexity by providing regions of exploration. And third, it describes ConceptRank as a ranking strategy that differentiates strongly-typed connections from weakly-bound ones. Extensive experiments on the Boston Marathon Bombings of April 15, 2013 as well as socio-political and medical events in Latin America, the Middle East, and the United States demonstrate storytelling’s high application potential, showcasing its use in event summarization and association analysis that identifies events before they hit the newswire.

DERIV: distributed brand perception tracking framework

Determining user’s perception of a brand in short periods of time has become crucial for business. Distilling brand perception directly from people’s comments in social media has promise. Current techniques for determining brand perception, such as surveys of handpicked users by mail, in person, phone or online, are time consuming and increasingly inadequate. The DERIV system distills storylines from open data representing direct consumer voice into a brand perception. The framework summarizes perception of a brand in comparison to peer brands with in-memory distributed algorithms utilizing supervised machine learning techniques. Experiments performed with open data and models built with storylines of known peer brands show the technique as highly scalable and accurate in capturing brand perception from vast amounts of social data compared to sentiment analysis.

DERIV: Distributed In-Memory Brand Perception Tracking Framework

Social media captures voice of customers at a rapid pace. Consumer perception of a brand is crucial to its success. Current techniques for measuring brand perception using lengthy surveys of handpicked users in person, by mail, phone or online are time consuming and increasingly inadequate. A more effective technique to measure brand perception is to interpret customer voice directly from social media and other open data. In this work we present DERIV, a DistributEd, in-memoRy framework for trackIng consumer Voice based on a brand perception measure using storylines generated from open data. The framework measures perception of a brand in comparison to peer brands with in-memory distributed algorithms utilizing supervised machine learning techniques. Experiments performed with open data and models built with storylines of known peer brands show the technique as highly accurate and effective in capturing brand perception.

Towards ontological similarity for spatial hierarchies

Ontological structures provide a rich hierarchy of concepts and relationships that are helpful in exploratory analysis. Ontologies, however, are often categorical, which introduces ambiguity, and makes numerical analysis difficult. Adding to the problem is the fact that as the number of ontological concepts increases so does computational complexity for a variety of analytical tasks. In this paper, we propose both spatial and ontological co-occurrence as a means to derive similarity among categorical values. More specifically, we devise a method that combines entity location as well as categorical frequency into a numerical measure of similarity for any pair of categorical values. In addition, we show how different ontological levels can hide or uncover information content while influencing the number of processed categorical values. We provide experiments that demonstrate the effectiveness of our approach.

A framework for the expansion of spatial features based on semantic footprints

Geographic feature expansion is a common task in Geographic Information Systems (GIS). Identifying and integrating geographic features is a challenging task since many of their spatial and non-spatial properties are described in different sources. We tackle this expansion problem by defining semantic footprints as a measure of similarity among features. Furthermore, we propose three quantifiers of semantic similarity: spatial, dimensional, and ontological affinity. We show how these measures dilute, concentrate, harden, or concede the feature space, and provide useful insights into the semantic relationships of the spatial entities. Experiments demonstrate the effectiveness of our approach in semantically associating the most appropriate spatial features.