sequence visualization based on aggregate information to analyze the behavior of an RNN's hidden state at the sentence-level. The usability and effectiveness of our method are demonstrated through case studies and reviews from domain experts.

In this paper, we introduce a visualization method that couples a trend chart with word clouds to illustrate temporal content evolutions in a set of documents. Specifically, we use a trend chart to encode the overall semantic evolution of document content over time. In our work, semantic evolution of a document collection is modeled by varied significance of document content, represented by a set of representative keywords, at different time points. At each time point, we also use a word cloud to depict the representative keywords. Since the words in a word cloud may vary one from another over time (e.g., words with increased importance), we use geometry meshes and an adaptive force-directed model to lay out word clouds to highlight the word differences between any two subsequent word clouds. Our method also ensures semantic coherence and spatial stability of word clouds over time. Our work is embodied in an interactive visual analysis system that helps users to perform text analysis and derive insights from a large collection of documents. Our preliminary evaluation demonstrates the usefulness and usability of our work.

With the growing adoption of machine learning techniques, there is a surge of research interest towards making machine learning systems more transparent and interpretable. Various visualizations have been developed to help model developers understand, diagnose, and refine machine learning models. However, a large number of potential but neglected users are the domain experts with little knowledge of machine learning but are expected to work with machine learning systems. In this paper, we present an interactive visualization technique to help users with little expertise in machine learning to understand, explore and validate predictive models. By viewing the model as a black box, we extract a standardized rule-based knowledge representation from its input-output behavior. Then, we design RuleMatrix, a matrix-based visualization of rules to help users navigate and verify the rules and the black-box model. We evaluate the effectiveness of RuleMatrix via two use cases and a usability study.

Parallel coordinates have been widely applied to visualize high-dimensional and multivariate data, discerning patterns within the data through visual clustering. However, the effectiveness of this technique on large data is reduced by edge clutter. In this paper, we present a novel framework to reduce edge clutter, consequently improving the effectiveness of visual clustering. We exploit curved edges and optimize the arrangement of these curved edges by minimizing their curvature and maximizing the parallelism of adjacent edges. The overall visual clustering is improved by adjusting the shape of the edges while keeping their relative order. The experiments on several representative datasets demonstrate the effectiveness of our approach.

No abstract

No abstract

Wheat bran was shown to provide protection against colorectal cancer in human intervention and animal studies. Our recent study showed, however, that antitumor activities of wheat bran from various wheat cultivars differed significantly even when wheat fiber was equal in diets. We hypothesized that phytochemical lignans in wheat bran may account for the differences among wheat cultivars in cancer prevention. The concentration of a major lignan, secoisolariciresinol diglycoside, was determined by HPLC in 4 selected wheat cultivars (i.e., Madison, Ernie, Betty, and Arapahoe). The lignan concentrations and their antitumor activities, previously determined in APC-Min mice, were correlated (r = 0.73, P < 0.02). The cancer preventive mechanisms of 2 prominent lignan metabolites (enterolactone and enterodiol) were further studied in human colonic cancer SW480 cells. Treatment with enterolactone and enterodiol, alone or in combination, at 0-40 micromol/L resulted in dose- and time-dependent decreases in cell numbers. Although the cytotoxicity as measured by trypan blue staining in adherent cells was not affected, DNA flow cytometric analysis indicated that the treatments induced cell cycle arrest at the S-phase. Western blot analysis for cyclin A, a required protein for S/G2 transition, showed that the cyclin A protein levels decreased after treatment with enterodiol or the combination of enterolactone and enterodiol at 40 micromol/L for 72 h. Apoptosis analysis by the terminal deoxynucleotidyl transferase-mediated dUTP nick end labeling assay showed an increased percentage of apoptotic cells in the floating cells after enterodiol alone or combined treatments. These results suggest for the first time that lignans may contribute, at least in part, to the cancer prevention by wheat bran observed in APC-Min mice. Inhibition of cancer cell growth by lignan metabolites seems to be mediated by cytostatic and apoptotic mechanisms.

The problem of formulating solutions immediately and comparing them rapidly for billboard placements has plagued advertising planners for a long time, owing to the lack of efficient tools for in-depth analyses to make informed decisions. In this study, we attempt to employ visual analytics that combines the state-of-the-art mining and visualization techniques to tackle this problem using large-scale GPS trajectory data. In particular, we present SmartAdP, an interactive visual analytics system that deals with the two major challenges including finding good solutions in a huge solution space and comparing the solutions in a visual and intuitive manner. An interactive framework that integrates a novel visualization-driven data mining model enables advertising planners to effectively and efficiently formulate good candidate solutions. In addition, we propose a set of coupled visualizations: a solution view with metaphor-based glyphs to visualize the correlation between different solutions; a location view to display billboard locations in a compact manner; and a ranking view to present multi-typed rankings of the solutions. This system has been demonstrated using case studies with a real-world dataset and domain-expert interviews. Our approach can be adapted for other location selection problems such as selecting locations of retail stores or restaurants using trajectory data.