Search NASA⌕ Search

SEARCH · Search NASA

Results for “task analysis”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 235 records · Page 13

Toward Large-Scale Image Segmentation on Summit

Semantic segmentation of images is an important computer vision task that emerges in a variety of application domains such as medical imaging, robotic vision and autonomous vehicles to name a few. While these domain-specific image analysis tasks involve relatively small image sizes (~ 10 2 × 10 2 ), there are many applications that need to train machine learning models on image data with extents that are orders of magnitude larger (~10 4 × 10 4 ). Training deep neural network (DNN) models on large extent images is extremely memory-intensive and often exceeds the memory limitations of a single graphical processing unit, a hardware accelerator of choice for computer vision workloads. Here, an efficient, sample parallel approach to train U-Net models on large extent image data sets is presented. Its advantages and limitations are analyzed and near-linear strong-scaling speedup demonstrated on 256 nodes (1536 GPUs) of the Summit supercomputer. Using a single node of the Summit supercomputer, an early evaluation of a recently released model parallel framework called GPipe is demonstrated to deliver ~ 2X speedup in executing a U-Net model with an order of magnitude larger number of trainable parameters than reported before. Performance bottlenecks for pipelined training of U-Net models are identified and mitigation strategies to improve the speedups are discussed. Together, these results open up the possibility of combining both approaches into a unified scalable pipelined and data parallel algorithm to efficiently train U-Net models with very large receptive fields on data sets of ultra-large extent images.

Seal, Sudip↗

Processing CCD Images to Detect Transits of Earth-Sized Planets: Maximizing Sensitivity While Achieving Reasonable Downlink Requirements

We have performed end-to-end laboratory and numerical simulations to demonstrate the capability of differential photometry under realistic operating conditions to detect transits of Earth-sized planets orbiting solar-like stars. Data acquisition and processing were conducted using the same methods planned for the proposed Kepler Mission. These included performing aperture photometry on large-format CCD images of an artificial star fields obtained without a shutter at a readout rate of 1 megapixel/sec, detecting and removing cosmic rays from individual exposures and making the necessary corrections for nonlinearity and shutterless operation in the absence of darks. We will discuss the image processing tasks performed `on-board' the simulated spacecraft, which yielded raw photometry and ancillary data used to monitor and correct for systematic effects, and the data processing and analysis tasks conducted to obtain lightcurves from the raw data and characterize the detectability of transits. The laboratory results are discussed along with the results of a numerical simulation carried out in parallel with the laboratory simulation. These two simulations demonstrate that a system-level differential photometric precision of 10-5 on five- hour intervals can be achieved under realistic conditions.

Earth-size planets↗

Transparent runtime parallelization of the R scripting language

Scripting languages such as R and Matlab are widely used in scientific data processing. As the data volume and the complexity of analysis tasks both grow, sequential data processing using these tools often becomes the bottleneck in scientific workflows. We describe pR, a runtime framework for automatic and transparent parallelization of the popular R language used in statistical computing. Recognizing scripting languages interpreted nature and data analysis codes use pattern, we propose several novel techniques: (1) applying parallelizing compiler technology to runtime, whole-program dependence analysis of scripting languages, (2) incremental code analysis assisted with evaluation results, and (3) runtime parallelization of file accesses. Our framework does not require any modification to either the source code or the underlying R implementation. Experimental results demonstrate that pR can exploit both task and data parallelism transparently and overall has better performance as well as scalability compared to an existing parallel R package that requires code modification.

99 GENERAL AND MISCELLANEOUS↗

AnalyzeThat: A Programmable Shared-Memory System for an Array of Processing-In-Memory Devices

Processing In Memory (PIM), the concept of integrating processing directly with memory, has been attracting a lot of attention since PIM can assist in overcoming the throughput limitation caused by data movement between CPU and memory. The challenge, however, is that it requires the programmers to have a deep understanding of the PIM architecture to maximize the benefits such as data locality and parallel thread execution on multiple PIM devices. In this study, we present AnalyzeThat, a programmable shared-memory system for parallel data processing with PIM devices. Thematic to AnalyzeThat is a rich PIM-Aware Data Structure (PADS), which is an encapsulation that integrally ties together the data, the analysis tasks and the runtime needed to interface with the PIM device array. The PADS abstraction provides (i) a key-value data container that allows programmers to easily store data on multiple PIMs, (ii) a suite of parallel operations with which users can easily implement data analysis applications, and (iii) a runtime, hidden to programmers, which provides the mechanisms needed to overlay both the data and the tasks on the PIM device array in an intelligent fashion, based on PIM-specific information collected from the hardware. We have developed a PIM emulation framework called AnalyzeThat. Our experimental evaluation with representative data analytics applications suggests that the proposed system can significantly reduce the PIM programming effort without losing its technology benefits.

97 MATHEMATICS AND COMPUTING↗

Human Performance Modeling and Simulation for Launch Team Applications

This paper describes ongoing research into modeling and simulation of humans for launch team analysis, training, and evaluation. The initial research is sponsored by the National Aeronautics and Space Administration's (NASA)'s Office of Safety and Mission Assurance (OSMA) and NASA's Exploration Program and is focused on current and future launch team operations at Kennedy Space Center (KSC). The paper begins with a description of existing KSC launch team environments and procedures. It then describes the goals of new Simulation and Analysis of Launch Teams (SALT) research. The majority of this paper describes products from the SALT team's initial proof-of-concept effort. These products include a nominal case task analysis and a discrete event model and simulation of launch team performance during the final phase of a shuttle countdown; and a first proof-of-concept training demonstration of launch team communications in which the computer plays most roles, and the trainee plays a role of the trainee's choice. This paper then describes possible next steps for the research team and provides conclusions. This research is expected to have significant value to NASA's Exploration Program.

Peaden, Cary J.↗

A programmable shared-memory system for an array of processing-in-memory devices

Processing in memory (PIM), the concept of integrating processing directly with memory has been attracting a lot of attention, since PIM can assist in overcoming the throughput limitation caused by data movement between CPU and memory. The challenge, however, is that it requires the programmers to have a deep understanding of the PIM architecture to maximize the benefits such as data locality and parallel thread execution on multiple PIM devices. In this study, we present AnalyzeThat, a programmable shared-memory system for parallel data processing with PIM devices. Thematic to AnalyzeThat is a rich PIM-aware data structure (PADS), which is an encapsulation that integrally ties together the data, the analysis tasks and the runtime needed to interface with the PIM device array. The PADS abstraction provides (i) a sophisticated key-value data container that allows programmers to easily store data on multiple PIMs, (ii) a suite of parallel operations with which users can easily implement data analysis applications, and (iii) a runtime, hidden to programmers, which provides the mechanisms needed to overlay both the data and the tasks on the PIM device array in an intelligent fashion, based on PIM-specific information collected from the hardware. We have developed a PIM emulation framework called AnalyzeThat. In conclusion, our experimental evaluation with representative data analytics applications suggests that the proposed system can significantly reduce the PIM programming effort without losing its technology benefits.

97 MATHEMATICS AND COMPUTING↗

ATDRS payload technology research and development

Four technology development tasks were chosen to reduce (or at least better understand) the technology risks associated with proposed approaches to Advanced Tracking and Data Relay Satellite (ATDRS). The four tasks relate to a Tri-Band Antenna feed system, a Digital Beamforming System for the S Band Multiple Access System (SMA), an SMA Phased Array Antenna, and a Configuration Thermal/Mechanical Analysis task. The objective, approach, and status of each are discussed.

Anzic, G.↗

Program For Systematic Documentation Of Tasks

Task Analysis Report Generation Tool (TARGET) computer program is graphical-interface software tool used to capture procedural knowledge and translate knowledge into hierarchical report. Designed to help programmer document expert's task, enabling programmer to build expert-system computer program that helps others perform task. Flexibility key element of design and of knowledge-acquisition session. Easy to use and tailored to accommodate users ranging from novice to experienced builder of expert systems. Written in C language.

Ortiz, Christopher John↗

Preliminary Results Obtained in Integrated Safety Analysis of NASA Aviation Safety Program Technologies

This is a listing of recent unclassified RTO technical publications processed by the NASA Center for AeroSpace Information from January 1, 2001 through March 31, 2001 available on the NASA Aeronautics and Space Database. Contents include 1) Cognitive Task Analysis; 2) RTO Educational Notes; 3) The Capability of Virtual Reality to Meet Military Requirements; 4) Aging Engines, Avionics, Subsystems and Helicopters; 5) RTO Meeting Proceedings; 6) RTO Technical Reports; 7) Low Grazing Angle Clutter...; 8) Verification and Validation Data for Computational Unsteady Aerodynamics; 9) Space Observation Technology; 10) The Human Factor in System Reliability...; 11) Flight Control Design...; 12) Commercial Off-the-Shelf Products in Defense Applications.

Source record↗

ATDRS payload technology R & D

Four technology development tasks were chosen to reduce (or at least better understand) the technology risks associated with proposed approaches to Advanced Tracking and Data Relay Satellite (ATDRS). The four tasks relate to a Tri-Band Antenna feed system, a Digital Beamforming System for the S Band Multiple-Access System (SMA), an SMA Phased Array Antenna, and a Configuration Thermal/Mechanical Analysis task. The objective, approach, and status of each are discussed.

Anzic, G.↗

BactoGeNIE: A large-scale comparative genome visualization for big displays

The volume of complete bacterial genome sequence data available to comparative genomics researchers is rapidly increasing. However, visualizations in comparative genomics--which aim to enable analysis tasks across collections of genomes--suffer from visual scalability issues. While large, multi-tiled and high-resolution displays have the potential to address scalability issues, new approaches are needed to take advantage of such environments, in order to enable the effective visual analysis of large genomics datasets. In this paper, we present Bacterial Gene Neighborhood Investigation Environment, or BactoGeNIE, a novel and visually scalable design for comparative gene neighborhood analysis on large display environments. We evaluate BactoGeNIE through a case study on close to 700 draft Escherichia coli genomes, and present lessons learned from our design process. In conclusion, BactoGeNIE accommodates comparative tasks over substantially larger collections of neighborhoods than existing tools and explicitly addresses visual scalability. Given current trends in data generation, scalable designs of this type may inform visualization design for large-scale comparative research problems in genomics.

59 BASIC BIOLOGICAL SCIENCES↗

Design and Analysis of Components of a Pressure/Vacuum Vessel System [Slides]

Performed design and analysis tasks to support design and testing of a prototype Experimental Physics Package for Shock Physics Experiments at Proton Radiography. Testing of low-fidelity vessel system prototype is in progress. General finite element analysis (FEA) process: identify critical components, simplify model geometry, take advantage of symmetry, apply proper boundary conditions, create a mesh that will solve quickly but accurately, check for solution convergence.

42 ENGINEERING↗

Parallel streaming between heterogeneous HPC resources for real-time analysis

Performing analysis or generating visualizations concurrently with high performance simulations can yield great benefits compared to post-processing data. Writing and reading large volumes of data can be reduced or eliminated, thereby producing an I/O cost savings. One such method for concurrent simulation and analysis is in transit - streaming data from the resource running the simulation to a separate resource running the analysis. In transit analysis can be beneficial since computational resources may not have certain resources needed for visualization and analysis (e.g. GPUs) and to reduce the impact of performing analysis tasks to the run time of the simulation. When sending and receiving data in transit, data redistribution mechanisms are needed in order to support heterogeneous data layouts that may be required by the simulation and analysis applications. The work described in this paper compares two mechanisms for on-the-fly data redistribution when streaming data in parallel between two distributed memory applications. Finally, our results show that it is often more advantageous to stream data in the same layout as the sender and redistribute data amongst processes on the receiving end than to stream data in the final layout needed by the receiver.

97 MATHEMATICS AND COMPUTING↗

Technology assessment of future intercity passenger transportation systems. Volume 7: Study recommendations

Research and analysis tasks to alleviate negative impacts, to augment positive impacts, or to better understand the impacts produced by the potential introduction of the alternate transportation technologies are identified. The project team's recommendations on research and analysis efforts which have resulted from the technology assessment are provided. Many of the recommendations apply to the future supply of intercity passenger transportation services, categorized by mode. Other recommendations pertain to broad issues in intercity transportation--e.g., finance, regulation, traveler values--that will affect all modes.

Source record↗

Enhancements to the Design Manager's Aide for Intelligent Decomposition (DeMAID)

This paper discusses the addition of two new enhancements to the program Design Manager's Aide for Intelligent Decomposition (DeMAID). DeMAID is a knowledge-based tool used to aid a design manager in understanding the interactions among the tasks of a complex design problem. This is done by ordering the tasks to minimize feedback, determining the participating subsystems, and displaying them in an easily understood format. The two new enhancements include (1) rules for ordering a complex assembly process and (2) rules for determining which analysis tasks must be re-executed to compute the output of one task based on a change in input to that or another task.

Rogers, James L.↗

Enhancements to the Design Manager's Aide for Intelligent Decomposition (DeMaid)

This paper discusses the addition of two new enhancements to the program Design Manager's Aide for Intelligent Decomposition (DeMAID). DeMAID is a knowledge-based tool used to aid a design manager in understanding the interactions among the tasks of a complex design problem. This is done by ordering the tasks to minimize feedback, determining the participating subsystems, and displaying them in an easily understood format. The two new enhancements include (1) rules for ordering a complex assembly process and (2) rules for determining which analysis tasks must be re-executed to compute the output of one task based on a change in input to that or another task.

Rogers, James L.↗

A procedure for the frequency analysis of telerobotic tasks data

In the last few years, teleoperated tasks have been the subject of extensive research to determine the best combination of control modalities according to specific criteria. The operator's performance were compared on the basis of task completion time and of force and torque measurements during the tasks. This paper proposes a procedure for the spectral analysis of force and torque signals generated during teleoperation experiments. There are two main reasons for examining teleoperation data in the frequency domain: a spectral analysis of different tasks can validate the assumptions made in the design of the teleoperator, and a task's frequency signature can be a valuable measure of the operator's performance.

Fiorini, Paolo↗

Air Traffic Complexity Measurement Environment (ACME): Software User's Guide

A user's guide for the Air Traffic Complexity Measurement Environment (ACME) software is presented. The ACME consists of two major components, a complexity analysis tool and user interface. The Complexity Analysis Tool (CAT) analyzes complexity off-line, producing data files which may be examined interactively via the Complexity Data Analysis Tool (CDAT). The Complexity Analysis Tool is composed of three independently executing processes that communicate via PVM (Parallel Virtual Machine) and Unix sockets. The Runtime Data Management and Control process (RUNDMC) extracts flight plan and track information from a SAR input file, and sends the information to GARP (Generate Aircraft Routes Process) and CAT (Complexity Analysis Task). GARP in turn generates aircraft trajectories, which are utilized by CAT to calculate sector complexity. CAT writes flight plan, track and complexity data to an output file, which can be examined interactively. The Complexity Data Analysis Tool (CDAT) provides an interactive graphic environment for examining the complexity data produced by the Complexity Analysis Tool (CAT). CDAT can also play back track data extracted from System Analysis Recording (SAR) tapes. The CDAT user interface consists of a primary window, a controls window, and miscellaneous pop-ups. Aircraft track and position data is displayed in the main viewing area of the primary window. The controls window contains miscellaneous control and display items. Complexity data is displayed in pop-up windows. CDAT plays back sector complexity and aircraft track and position data as a function of time. Controls are provided to start and stop playback, adjust the playback rate, and reposition the display to a specified time.

Source record↗