DGCNN: A convolutional neural network over large-scale labeled graphs.

Exploiting graph-structured data has many real applications in domains including natural language semantics, programming language processing, and malware analysis. A variety of methods has been developed to deal with such data. However, learning graphs of large-scale, varying shapes and sizes is a big challenge for any method. In this paper, we propose a multi-view multi-layer convolutional neural network on labeled directed graphs (DGCNN), in which convolutional filters are designed flexibly to adapt to dynamic structures of local regions inside graphs. The advantages of DGCNN are that we do not need to align vertices between graphs, and that DGCNN can process large-scale dynamic graphs with hundred thousands of nodes. To verify the effectiveness of DGCNN, we conducted experiments on two tasks: malware analysis and software defect prediction. The results show that DGCNN outperforms the baselines, including several deep neural networks.

Beyond Low-Rank Representations: Orthogonal clustering basis reconstruction with optimized graph structure for multi-view spectral clustering.

Low-Rank Representation (LRR) is arguably one of the most powerful paradigms for Multi-view spectral clustering, which elegantly encodes the multi-view local graph/manifold structures into an intrinsic low-rank self-expressive data similarity embedded in high-dimensional space, to yield a better graph partition than their single-view counterparts. In this paper we revisit it with a fundamentally different perspective by discovering LRR as essentially a latent clustered orthogonal projection based representation winged with an optimized local graph structure for spectral clustering; each column of the representation is fundamentally a cluster basis orthogonal to others to indicate its members, which intuitively projects the view-specific feature representation to be the one spanned by all orthogonal basis to characterize the cluster structures. Upon this finding, we propose our technique with the following: (1) We decompose LRR into latent clustered orthogonal representation via low-rank matrix factorization, to encode the more flexible cluster structures than LRR over primal data objects; (2) We convert the problem of LRR into that of simultaneously learning orthogonal clustered representation and optimized local graph structure for each view; (3) The learned orthogonal clustered representations and local graph structures enjoy the same magnitude for multi-view, so that the ideal multi-view consensus can be readily achieved. The experiments over multi-view datasets validate its superiority, especially over recent state-of-the-art LRR models.

Visualization of temporal patterns in patient record data.

Visualization contributes to a variety of tasks, from reviewing individual patient records to helping researchers assess data quality, find patients of interest, review temporal patterns and anomalies, or understand differences between cohorts. We review some of visualization techniques developed at the University of Maryland.

Current and Evolving Methods to Visualize Biological Data in Cancer Research.

Although the measurements of clinical outcomes for cancer treatments have become diverse and complex, there remains a need for clear, easily interpreted representations of patients' experiences. With oncology trials increasingly reporting non-time-to-event outcomes, data visualization has evolved to incorporate parameters such as responses to therapy, duration and degree of response, and novel representations of underlying tumor biology. We review both commonly used and newly developed methods to display outcomes in oncology, with a focus on those that have evolved to represent complex datasets.

From chalkboard, slides, and paper to e-learning: How computing technologies have transformed anatomical sciences education.

Until the late-twentieth century, primary anatomical sciences education was relatively unenhanced by advanced technology and dependent on the mainstays of printed textbooks, chalkboard- and photographic projection-based classroom lectures, and cadaver dissection laboratories. But over the past three decades, diffusion of innovations in computer technology transformed the practices of anatomical education and research, along with other aspects of work and daily life. Increasing adoption of first-generation personal computers (PCs) in the 1980s paved the way for the first practical educational applications, and visionary anatomists foresaw the usefulness of computers for teaching. While early computers lacked high-resolution graphics capabilities and interactive user interfaces, applications with video discs demonstrated the practicality of programming digital multimedia linking descriptive text with anatomical imaging. Desktop publishing established that computers could be used for producing enhanced lecture notes, and commercial presentation software made it possible to give lectures using anatomical and medical imaging, as well as animations. Concurrently, computer processing supported the deployment of medical imaging modalities, including computed tomography, magnetic resonance imaging, and ultrasound, that were subsequently integrated into anatomy instruction. Following its public birth in the mid-1990s, the World Wide Web became the ubiquitous multimedia networking technology underlying the conduct of contemporary education and research. Digital video, structural simulations, and mobile devices have been more recently applied to education. Progressive implementation of computer-based learning methods interacted with waves of ongoing curricular change, and such technologies have been deemed crucial for continuing medical education reforms, providing new challenges and opportunities for anatomical sciences educators. Anat Sci Educ 9: 583-602. © 2016 American Association of Anatomists.

Visual illusions on the Internet: 15 years of change in technology and user behavior.

Abstract. Looking back over 15 years of demonstrating visual phenomena and optical illusions on the Internet, I will discuss two major topics. The first concerns the methodology used to present interactive visual experiments on the web, with respect to (a) wide accessibility, ie independent of browser and platform, (b) capable and elegant graphic user interface, (c) sufficient computational power, (d) ease of development and, finally, (e) future-proofing in an ever-changing online environment. The second major topic addresses some aspects of user behaviour, mainly temporal patterns (eg changes over weeks. years, long-term), which reveal that there are more visitors during office hours.

Envisioning the future of home care: applications of immersive virtual reality.

Accelerating the design of technologies to support health in the home requires 1) better understanding of how the household context shapes consumer health behaviors and (2) the opportunity to afford engineers, designers, and health professionals the chance to systematically study the home environment. We developed the Living Environments Laboratory (LEL) with a fully immersive, six-sided virtual reality CAVE to enable recreation of a broad range of household environments. We have successfully developed a virtual apartment, including a kitchen, living space, and bathroom. Over 2000 people have visited the LEL CAVE. Participants use an electronic wand to activate common household affordances such as opening a refrigerator door or lifting a cup. Challenges currently being explored include creating natural gesture to interface with virtual objects, developing robust, simple procedures to capture actual living environments and rendering them in a 3D visualization, and devising systematic stable terminologies to characterize home environments.

Medical image processing on the GPU - past, present and future.

Graphics processing units (GPUs) are used today in a wide range of applications, mainly because they can dramatically accelerate parallel computing, are affordable and energy efficient. In the field of medical imaging, GPUs are in some cases crucial for enabling practical use of computationally demanding algorithms. This review presents the past and present work on GPU accelerated medical image processing, and is meant to serve as an overview and introduction to existing GPU implementations. The review covers GPU acceleration of basic image processing operations (filtering, interpolation, histogram estimation and distance transforms), the most commonly used algorithms in medical imaging (image registration, image segmentation and image denoising) and algorithms that are specific to individual modalities (CT, PET, SPECT, MRI, fMRI, DTI, ultrasound, optical imaging and microscopy). The review ends by highlighting some future possibilities and challenges.