Presentations

Permanent link for this collection

Browse

Recent Submissions

Now showing 1 - 20 of 62
  • Item
    Using Jetstream for OpenMP Offloading and OpenACC Testsuites
    (2021-08-06) Jarmusch, Aaron; Baker, Nolan; Chandrasekaran, Sunita
  • Item
    Finding Effector III Genes in phytophthora infestans and magnaporthe oryzae Using Machine Learning
    (2021-08-6) Campbell, Christine; Cooper, Lyric; Snapp-Childs, Winona; Sanders, Sheri
  • Item
    Visualizing metagenomic data in R using Jetstream
    (2020-08) Leffler, Haley; Sanders, Sheri; Papudeshi, Bhavya
  • Item
    Automatic Capture and Classification of Frog Calls
    (2020-08) Foran, Eliza; Underwood, Tenecious A.; Snapp-Childs, Winona; Sanders, Sheri A.
    Global frog populations are threatened by an increasing number of environmental threats such as habitat loss, disease, and pollution. Traditionally, in-person acoustic surveys of frogs have measured population loss and conservation outcomes among these visually cryptic species. However, these methods rely heavily on trained individuals and time-consuming field work. We propose an end-to-end workflow for the automatic recording, presence-absence identification, and web page visualization of frog calls by their species. The workflow encompasses recording of frog calls via custom Raspberry Pis, data-pushing to Jetstream cloud computer, and species classification by three different machine learning models: Random Forest, Convolutional Neural Network, and Recursive Neural Network.
  • Item
    HPC Rankings Based on Real Applications
    (2020-08) Baker, Nolan; Jarmusch, Aaron; Chadrasekaran, Sunita; Eigenmann, Rudolf
    Performance benchmarks are used to stress test hardware and software of large scale computing systems. A corporation known as SPEC has developed a benchmark suite, SPEC ACCEL, consisting of test codes representative of kernels in large applications. This project ranks the published results from ACCEL based on different criteria. The goal is to prepare a ranking website for the work-in-progress real-world SPEC HPG benchmark suite, HPC2021 that will soon be released (time frame 2020-2021).
  • Item
    Visualizing veterinary medical data sets with Jetstream
    (2019-07-28) Nguyen, Alan; Pierre, Yvan Jr.; Snapp-Childs, Winona; Birch, Scott
    Computed tomography (CT) is a diagnostic imaging test using x-rays to create multiple detailed diagnostic images of internal organs, bones, soft tissue and blood vessels. It produces a data set of thin, cross-sectional ``slices'' for viewing and is much more detailed than conventional radiography. Clinicians use CT examination to diagnose cancers, detect abnormal blood vessels, discover disorders of the abdomen, bones, and joints, and to plan surgical interventions such as heart defect or vascular repair. Dedicated visualization workstations allow radiologists to make high-resolution examinations of the data for diagnoses, but understanding the image stacks can be challenging for clinicians without specialized skills, training, and experience. To aid and enhance diagnostic evaluation, we explored a cloud-based workflow using Jetstream. CT data sets were segmented or translated into regions-of-interest (ROI) and/or volumetric 3D reconstructions which were then exported as polygonal 3D surface models. Using data sets obtained via CT from a variety of animal species, this project focused on the process of compiling a medical imaging/segmentation workstation instance with open source software on Jetstream, importing sample data sets into the imaging software, viewing 2D image sequences volumetrically, setting custom transfer functions based on tissue density, and segmenting the anatomy into multiple ROI for export as stereolithography files. Post-processing and polygon mesh editing techniques such as smoothing, transient reduction, and decimation were employed as the model was optimized for 3D printing or online distribution. Results were rendered into 2D graphical representations, and the 3D models were deployed into interactive or virtual reality environments, or were additively-manufactured (3D printed) into real-world objects for visual and tactile examination. After workflows were verified and vetted, the Jetstream medical segmentation VMs were made available for others to view and/or segment their own volumetric data sets.
  • Item
    Validating photogrammetric processes using Jetstream and synthetic images
    (2019-07-28) Zhao, Jenny; Mercer, Matthew; Gniady, Tassie; Wernert, Eric
    This project focuses on photogrammetry--the process of making 3D objects from 2D photographs--and the reverse engineering of this complex process. While a number of disciplines from cultural heritage to natural sciences use photogrammetry, the algorithms used by the most popular (and accurate) software packages are black box because of their proprietary nature. This project takes a synthetic 3D object which can be fully understood on the digital level and reverse engineers the photogrammetry process to determine the modeling process's accuracy. This is of key importance to anyone trying to make reliable models available to researchers unable to visit an object or collection in person. These researchers need to have full confidence in the final model in order to draw valid conclusions about it. A virtual machine was created on Jetstream to import synthetic models, capture them photogrammetrically with synthetic cameras, and export those captures for processing. Utilizing a parallel processing workflow on Jetstream, the speed-up in creating 3D models allowed for refinement and comparison of different variables and models with much shorter turn-around times.
  • Item
    Automatic recognition of frog calls
    (2019-07-28) Foran, Eliza G.; Suggs, Evan D.; Underwood, Tenecious A.; Snapp-Childs, Winona; Sanders, Sheri A.
    Recording animal calls and vocalizations is a time-honored data collection method in various fields of biological and environmental science. In the past, the only method available for analyzing such recordings involved extensive training of human experts. Now, however, machine learning techniques have made automatic recognition of such vocalizations possible. Automatic recognition of animal calls and vocalizations is desirable on two fronts: it reduces the burden of (at least initial) data analysis, and supports non-intrusive environmental monitoring. Here, we outline a proof-of-concept workflow that will make the quest from collecting data to understanding data more attainable for researchers. We simulate this data collection process by collecting animal (frog) calls using recording devices and Raspberry Pi's, then feed this data to a database and virtual machine hosted on XSEDE resources (i.e. Jetstream and Wrangler). We then show how database pulling, machine learning, and visualization works on Jetstream.
  • Item
    Impact of Virtualization and Containers on Application Performance and Energy Consumption
    (2018-07-24) Huber, Thomas; Junji, Li; Chandrasekaran, Sunita; Henschel, Robert
    This paper was presented at the PEARC18 conference in Pittsburgh, PA on July 24, 2018.
  • Item
    Harvesting Field Station Data; Raspberry Pi Sensors to Jetstream Databases
    (2018-07-24) Anderson, Jazzly; Slayton, Thomas; Guido, Emmanuel; Doak, Thomas; Sanders, Sheri; Walker, Tony
    This paper was given at the PEARC18 conference in Pittsburgh, PA on July 24, 2018.
  • Item
    Using Jetstream to Enable Large-Scale Text Analysis of Tweets
    (2018-07-24) Wittenbrook, Harrison; Humble, Lorissa; Gniady, Tassie; Kloster, David
    This paper was presented at the PEARC18 conference held in Pittsburgh, PA July 24, 2018.
  • Item
    Next Generation Cyberinfrastructure for Biological Research
    (2017-09-28) Stewart, Craig A.; Hancock, David Y.
  • Item
    Computing at scale: From laptop to cloud and HPC
    (2017-04-28) Merchant, Nirav
  • Item
    Jetstream overview -- what it is, how to apply for use
    (2017-03-08) Stewart, Craig A.; Hancock, David Y.; Fischer, Jeremy