James Wolfer

A heterogeneous supercomputer model for high-performance parallel computing pedagogy

To visually illustrate the impact of architecture and communication on parallel computing we created a model supercomputer in the spirit of other engineering models. Combining Raspberry Pi computers with an Nvidia TK1 the resulting machine is distinguished by its instructional utility, asymmetric CPU and communication channel speed, and for incorporating current trends in heterogeneous supercomputing. Running Linux, the model supports major high-performance computing software environments, including OpenMP, MPI, and Nvidias CUDA. The model architecture includes aspects of heterogeneous, supercomputers such as shared- and distributed-memory MIMD, and 192 CUDA core SIMD-like processors.

The Micro-Cluster Showcase: 7 Inexpensive Beowulf Clusters for Teaching PDC

Just as a micro-computer is a personal, portable computer, a micro-cluster is a personal, portable, Beowulf cluster. In this special session, six cluster designers will bring and demonstrate micro-clusters they have built using inexpensive single-board computers (SBCs). The educators will describe how they have used their clusters to provide their students with hands-on experience using the shared-memory, distributed-memory, and heterogeneous computing paradigms, and thus achieve the parallel and distributed computing (PDC) objectives of CS 2013 [1].

Haptic representation of aortic pressure waveforms using synthetic ECG derived time intervals

While simple pulse-rate is perhaps the most common cardiovascular assessment, recent research suggests that there is valuable information contained in the actual pulse waveform. As the first step toward developing a feature-based haptic suite, this work investigates the ability of a consumer-grade haptic device to represent arterial touch as a function of the physiological waveform gated to synthetic ECGs instead of the more common square or triangle waveforms, which capture only heart rate. Included are preliminary observations indicating that there is a palpable difference between the representations, as well as an empirical description of the haptic sensation under both normal heart rhythm and synthesized arrhythmia.

Pulse Coupled Neural Networks and Image Morphology for Mammogram Preprocessing

Given that over 230,000 women in the United States alone will contract breast cancer, resulting in over 39,000 deaths and that there will be an estimated 458000 such deaths worldwide, the early detection and management of breast cancer is a significant problem. Currently, mammography provides the dominant front-line screening procedure. To assist in the interpretation of mammograms, a variety of computer aided diagnostic algorithms have been developed. A critical step in most of these algorithms is to remove image artifacts and isolate the breast from the mammogram background. This study explores the use of a biologically inspired model, the Pulse Coupled Neural Network, to form candidate image segments that, when combined with standard image morphology operators, can be used to remove image acquisition artifacts and isolate the breast profile in the mammogram.

Haptic palpation of aortic pressure waveforms

Cardiovascular disease is the leading cause of death worldwide. According to the World Health Organization, cardiovascular disease was responsible for 17.5 million deaths in 2012, or 30% of all deaths. Recent research suggests that, in addition to pulse rate, the pulse waveform itself contains useful diagnostic information. To explore tactile representation of these waveforms, this demonstration deploys a haptic representation of the aortic pressure profile synchronized to a synthetic electrocardiogram using a consumer grade haptic interface.

Topical tapestry: Weaving threads of parallel programming, computer graphics, and artificial intelligence into undergraduate CS courses

Traditionally, topics such as parallel computing, computer graphics, and artificial intelligence have been taught as stand-alone courses in the computing curriculum. Often these are elective courses, limiting the material to the subset of students choosing to take the course. Recently there has been movement to distribute topics across the curriculum in order to ensure that all graduates have been exposed to concepts such as parallel computing. This work describes one approach to threading topics from AI, graphics, and parallel processing into coursework starting early in a students program without substantially altering the basic course objectives. This, in turn, allows the student to sample topics early enough to make informed decisions when selecting electives.

Approaching Emerging Technologies: Exploring Significant Human-Computer Interaction in the Budget-Limited Classroom

There has been an explosion of sensor, presentation, and display technology available for exploration in Human-Computer Interaction. While much of this technology is readily available, approachable, and/or inexpensive, such as cell phone or Web display, other technology remains relatively expensive in the context of classroom instruction. This work presents an approach to exposing students to the principles encapsulated in expensive technologies using less expensive alternatives. Arranged in four broad categories, Brain-Computer Interfacing, Haptics, Augmented/Virtual Reality, and General interfaces, we survey a collection of devices and emerging technologies appropriate for student use in group and individual Human-Computer Interaction projects.

Enhancing a Shared-Access, Hardware-Based, Random Number Generation System

High quality random numbers form a critical foundation for computing in applications such as data encryption, simulation, and modeling. Recognizing the import of random numbers we have integrated hardware-based random bit generation into a major file system project for the Operating Systems class. Originally built around background radiation events detected by a Geiger counter, we are in the process of extending this to additional hardware-based random number generators configured for shared access by student teams. This work-in-progress documents the most recent deployment of this technology.

Projecting computing history: A hybrid live-virtual visit to the national museum of computing

History and travel are valuable components for building cultural awareness and preparing students to work in a global economy. In many STEM disciplines history is an intrinsic component of the pedagogy, serving to bind students to the professional community and culture. Computing, in contrast, has not systematically embedded historical awareness into the curriculum. As a step toward exposing students to computing history and enhancing cultural awareness, this work profiles a collaborative effort to take classes on a virtual field trip to The National Museum of Computing in the UK, with live faculty interaction across international borders.

Embedding a sense of history in the computing curriculum: Historic influences on a custom CPU instruction set

History can serve as a connecting thread bonding students to their professional community and intellectual heritage. Many STEM disciplines, such as physics and biology, consistently integrate historic figures into the curriculum. Computer Science, on the other hand, often omits history from the instructional landscape. As a step to mitigate the situation, this work explores some of the historic design influences behind a custom, robot enabled, CPU and corresponding instruction set. The CPU design has been the basis for student-implemented emulators to control robots in a Computer Organization course. By featuring a sampling of the men, women, machines, and instruction sets from history we provide a design context for the custom CPU. Knowing this history may help students develop a sense of why things work the way they do in modern computers, as well as instilling a sense of the enormous contribution pioneering men and women have made to their discipline.