Ross Maciejewski

Spatiotemporal social media analytics for abnormal event detection and examination using seasonal-trend decomposition

Recent advances in technology have enabled social media services to support space-time indexed data, and internet users from all over the world have created a large volume of time-stamped, geo-located data. Such spatiotemporal data has immense value for increasing situational awareness of local events, providing insights for investigations and understanding the extent of incidents, their severity, and consequences, as well as their time-evolving nature. In analyzing social media data, researchers have mainly focused on finding temporal trends according to volume-based importance. Hence, a relatively small volume of relevant messages may easily be obscured by a huge data set indicating normal situations. In this paper, we present a visual analytics approach that provides users with scalable and interactive social media data analysis and visualization including the exploration and examination of abnormal topics and events within various social media data sources, such as Twitter, Flickr and YouTube. In order to find and understand abnormal events, the analyst can first extract major topics from a set of selected messages and rank them probabilistically using Latent Dirichlet Allocation. He can then apply seasonal trend decomposition together with traditional control chart methods to find unusual peaks and outliers within topic time series. Our case studies show that situational awareness can be improved by incorporating the anomaly and trend examination techniques into a highly interactive visual analysis process.

A Visual Analytics Approach to Understanding Spatiotemporal Hotspots

As data sources become larger and more complex, the ability to effectively explore and analyze patterns among varying sources becomes a critical bottleneck in analytic reasoning. Incoming data contain multiple variables, high signal-to-noise ratio, and a degree of uncertainty, all of which hinder exploration, hypothesis generation/exploration, and decision making. To facilitate the exploration of such data, advanced tool sets are needed that allow the user to interact with their data in a visual environment that provides direct analytic capability for finding data aberrations or hotspots. In this paper, we present a suite of tools designed to facilitate the exploration of spatiotemporal data sets. Our system allows users to search for hotspots in both space and time, combining linked views and interactive filtering to provide users with contextual information about their data and allow the user to develop and explore their hypotheses. Statistical data models and alert detection algorithms are provided to help draw user attention to critical areas. Demographic filtering can then be further applied as hypotheses generated become fine tuned. This paper demonstrates the use of such tools on multiple geospatiotemporal data sets.

Structuring Feature Space: A Non-Parametric Method for Volumetric Transfer Function Generation

The use of multi-dimensional transfer functions for direct volume rendering has been shown to be an effective means of extracting materials and their boundaries for both scalar and multivariate data. The most common multi-dimensional transfer function consists of a two-dimensional (2D) histogram with axes representing a subset of the feature space (e.g., value vs. value gradient magnitude), with each entry in the 2D histogram being the number of voxels at a given feature space pair. Users then assign color and opacity to the voxel distributions within the given feature space through the use of interactive widgets (e.g., box, circular, triangular selection). Unfortunately, such tools lead users through a trial-and-error approach as they assess which data values within the feature space map to a given area of interest within the volumetric space. In this work, we propose the addition of non-parametric clustering within the transfer function feature space in order to extract patterns and guide transfer function generation. We apply a non-parametric kernel density estimation to group voxels of similar features within the 2D histogram. These groups are then binned and colored based on their estimated density, and the user may interactively grow and shrink the binned regions to explore feature boundaries and extract regions of interest. We also extend this scheme to temporal volumetric data in which time steps of 2D histograms are composited into a histogram volume. A three-dimensional (3D) density estimation is then applied, and users can explore regions within the feature space across time without adjusting the transfer function at each time step. Our work enables users to effectively explore the structures found within a feature space of the volume and provide a context in which the user can understand how these structures relate to their volumetric data. We provide tools for enhanced exploration and manipulation of the transfer function, and we show that the initial transfer function generation serves as a reasonable base for volumetric rendering, reducing the trial-and-error overhead typically found in transfer function design.

Volume Estimation Using Food Specific Shape Templates in Mobile Image-Based Dietary Assessment.

As obesity concerns mount, dietary assessment methods for prevention and intervention are being developed. These methods include recording, cataloging and analyzing daily dietary records to monitor energy and nutrient intakes. Given the ubiquity of mobile devices with built-in cameras, one possible means of improving dietary assessment is through photographing foods and inputting these images into a system that can determine the nutrient content of foods in the images. One of the critical issues in such the image-based dietary assessment tool is the accurate and consistent estimation of food portion sizes. The objective of our study is to automatically estimate food volumes through the use of food specific shape templates. In our system, users capture food images using a mobile phone camera. Based on information (i.e., food name and code) determined through food segmentation and classification of the food images, our system choose a particular food template shape corresponding to each segmented food. Finally, our system reconstructs the three-dimensional properties of the food shape from a single image by extracting feature points in order to size the food shape template. By employing this template-based approach, our system automatically estimates food portion size, providing a consistent method for estimation food volume.

Stippling by example

In this work, we focus on stippling as an artistic style and discuss our technique for capturing and reproducing stipple features unique to an individual artist. We employ a texture synthesis algorithm based on the gray-level co-occurrence matrix (GLCM) of a texture field. This algorithm uses a texture similarity metric to generate stipple textures that are perceptually similar to input samples, allowing us to better capture and reproduce stipple distributions. First, we extract example stipple textures representing various tones in order to create an approximate tone map used by the artist. Second, we extract the stipple marks and distributions from the extracted example textures, generating both a lookup table of stipple marks and a texture representing the stipple distribution. Third, we use the distribution of stipples to synthesize similar distributions with slight variations using a numerical measure of the error between the synthesized texture and the example texture as the basis for replication. Finally, we apply the synthesized stipple distribution to a 2D grayscale image and place stipple marks onto the distribution, thereby creating a stippled image that is statistically similar to images created by the example artist.

Understanding Twitter data with TweetXplorer

In the era of big data it is increasingly difficult for an analyst to extract meaningful knowledge from a sea of information. We present TweetXplorer, a system for analysts with little information about an event to gain knowledge through the use of effective visualization techniques. Using tweets collected during Hurricane Sandy as an example, we will lead the reader through a workflow that exhibits the functionality of the system.

Visual analytics decision support environment for epidemic modeling and response evaluation

In modeling infectious diseases, scientists are studying the mechanisms by which diseases spread, predicting the future course of the outbreak, and evaluating strategies applied to control an epidemic. While recent work has focused on accurately modeling disease spread, less work has been performed in developing interactive decision support tools for analyzing the future course of the outbreak and evaluating potential disease mitigation strategies. The absence of such tools makes it difficult for researchers, analysts and public health officials to evaluate response measures within outbreak scenarios. As such, our research focuses on the development of an interactive decision support environment in which users can explore epidemic models and their impact. This environment provides a spatiotemporal view where users can interactively utilize mitigative response measures and observe the impact of their decision over time. Our system also provides users with a linked decision history visualization and navigation tool that support the simultaneous comparison of mortality and infection rates corresponding to different response measures at different points in time.

Forecasting Hotspots—A Predictive Analytics Approach

Current visual analytics systems provide users with the means to explore trends in their data. Linked views and interactive displays provide insight into correlations among people, events, and places in space and time. Analysts search for events of interest through statistical tools linked to visual displays, drill down into the data, and form hypotheses based upon the available information. However, current systems stop short of predicting events. In spatiotemporal data, analysts are searching for regions of space and time with unusually high incidences of events (hotspots). In the cases where hotspots are found, analysts would like to predict how these regions may grow in order to plan resource allocation and preventative measures. Furthermore, analysts would also like to predict where future hotspots may occur. To facilitate such forecasting, we have created a predictive visual analytics toolkit that provides analysts with linked spatiotemporal and statistical analytic views. Our system models spatiotemporal events through the combination of kernel density estimation for event distribution and seasonal trend decomposition by loess smoothing for temporal predictions. We provide analysts with estimates of error in our modeling, along with spatial and temporal alerts to indicate the occurrence of statistically significant hotspots. Spatial data are distributed based on a modeling of previous event locations, thereby maintaining a temporal coherence with past events. Such tools allow analysts to perform real-time hypothesis testing, plan intervention strategies, and allocate resources to correspond to perceived threats.

Measuring Stipple Aesthetics in Hand-Drawn and Computer-Generated Images

When people compare a computer-generated illustration to a hand-drawn illustration of the same object, they usually perceive differences. This seems to indicate that the two kinds of images follow different aesthetic principles. To explore and explain these differences, the authors compare texture stippling in hand-drawn and computer-generated illustrations, using image-processing analysis techniques.

Spatial Text Visualization Using Automatic Typographic Maps

We present a method for automatically building typographic maps that merge text and spatial data into a visual representation where text alone forms the graphical features. We further show how to use this approach to visualize spatial data such as traffic density, crime rate, or demographic data. The technique accepts a vector representation of a geographic map and spatializes the textual labels in the space onto polylines and polygons based on user-defined visual attributes and constraints. Our sample implementation runs as a Web service, spatializing shape files from the OpenStreetMap project into typographic maps for any region.