Search NASA⌕ Search

SEARCH · Search NASA

Results for “CNN”

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 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

Objectively Identifying Transverse Cirrus Bands in Tropical Cyclones using a Convolutional Neural Network

Transverse cirrus bands (TCBs) are bands of upper-level clouds regularly seen in mesoscale and synoptic-scale weather systems. In tropical cyclones, their appearance has been subjectively linked to intensification and the diurnal cycle. However, these hypothesized relationships have not been rigorously tested due to the subjective nature of TCBs in satellite images. A machine learning technique that successfully identifies TCBs objectively in imagery from the GOES-16 Advanced Baseline Imager (ABI) has been developed to solve this problem. The technique uses a U-Net convolutional neural network (CNN) that assigns a probability to each pixel in an image based on the likelihood of the pixel being associated with a TCB. Using the U-Net CNN, a database of TCBs from 2019 to 2022 was developed for the Atlantic tropical cyclone basin by defining an appropriate probability threshold that defines the difference between TCB and non-TCB pixels. This threshold is where the Jaccard score, calculated using manually identified TCBs and model identified TCBs, is maximized. Statistics for TCB occurrence will also be presented, including the relationships between TCBs and storm relative motion, shear relative direction, cardinal direction, tropical cyclone intensity, tropical cyclone intensification rates, and time of day.

John Mark Mayhall↗
NASA NTRSDate not supplied

1D-Convolutional Neural Network Architecture for Generalized Time-Segmentation Tasks

Time segmentation of experimental data is a common and often difficult task. Consequently, it is of interest to automate this type of segmentation to reduce manual inputs, which are labor intensive and less consistent. However, simple thresholding algorithms are often insufficiently robust due either to noise or inconsistent data. This paper proposes a simple 1D CNN architecture as a generalized solution for typical time segmentation tasks. The layer architecture, training methods, and methods for simple customization are described as well as the results of application to three separate arc jet data streams: facility condition segmentation, video highlight segmentation, and calorimeter time-series segmentation.

Machine learning↗
NASA NTRSDate not supplied

1d-Convolutional Neural Network Architecture for Generalized Time-Segmentation Tasks

Time segmentation of experimental data is a common and often difficult task. Consequently, it is of interest to automate this type of segmentation to reduce manual inputs, which are labor intensive and less consistent. However, simple thresholding algorithms are often insufficiently robust due either to noise or inconsistent data. This paper proposes a simple 1D CNN architecture as a generalized solution for typical time segmentation tasks. The layer architecture, training methods, and methods for simple customization are described as well as the results of application to three separate arc jet data streams: facility condition segmentation, video highlight segmentation, and calorimeter time-series segmentation.

Machine learning↗
NASA NTRSDate not supplied

1D-Convolutional Neural Network Architecture for Generalized Time-Segmentation Tasks

Time segmentation of experimental data is a common and often difficult task. Consequently, it is of interest to automate this type of segmentation to reduce manual inputs, which are labor intensive and less consistent. However, simple thresholding algorithms are often insufficiently robust due either to noise or inconsistent data. This paper proposes a simple 1D convolutional neural net (CNN) architecture as a generalized solution for typical time segmentation tasks. The layer architecture, training methods, and methods for simple customization are described as well as the results of application to three separate arc jet data streams: facility condition segmentation, video highlight segmentation, and calorimeter time-series segmentation.

Machine learning↗
NASA NTRS1972

Nearest Neighbor Algorithms for Pattern Classification

A solution of the discrimination problem is considered by means of the minimum distance classifier, commonly referred to as the nearest neighbor (NN) rule. The NN rule is nonparametric, or distribution free, in the sense that it does not depend on any assumptions about the underlying statistics for its application. The k-NN rule is a procedure that assigns an observation vector z to a category F if most of the k nearby observations x sub i are elements of F. The condensed nearest neighbor (CNN) rule may be used to reduce the size of the training set required categorize The Bayes risk serves merely as a reference-the limit of excellence beyond which it is not possible to go. The NN rule is bounded below by the Bayes risk and above by twice the Bayes risk.

Barrios, J. O.↗
NASA NTRS1995

STS-70 Flight: Day 5

The fifth day of the STS-70 Space Shuttle Discovery mission is contained on this video. The crew continues working on experiments, such as the Space Tissue Loss Analysis and the Bioreactor Development System. CNN reporter, John Holliman, interviewed the flight crew and the crew also answered questions posed by Internet users while on NASA's Shuttle Web. There are brief views of Earth's surface included.

Source record↗
NASA NTRS1996

STS-78 Flight Day 4

On this fourth day of the STS-78 mission, the flight crew, Cmdr. Terence T. Henricks, Pilot Kevin R. Kregel, Payload Cmdr. Susan J. Helms, Mission Specialists Richard M. Linnehan, Charles E. Brady, Jr., and Payload Specialists Jean-Jacques Favier, Ph.D. and Robert B. Thirsk, M.D., discuss the flight during an interview with the Cable News Network (CNN). The crew then continues research concentrated on the Torque Velocity Dynamometer measurements of leg and arm muscle power, the Astronaut Lung Function Experiment, and effects of microgravity exercise with the bicycle ergometer and its associated instruments.

Source record↗
NASA NTRS1996

STS-79 Flight Day 7

On this seventh day of the STS-79 mission, the flight crew, Cmdr. William F. Readdy, Pilot Terrence W. Wilcutt, Mission Specialists, Thomas D. Akers, Shannon Lucid, Jay Apt, and Carl E. Walz, share a brief video tour of the Mir Space Station with flight controllers, taking a break from the transfer activities that has occupied the astronauts' time during three days of docked operations. Readdy and Apt floated through several of Mir's modules and back into Atlantis' double Spacehab module during the tour pointing out the numerous transfer items stowed on both spacecraft. Readdy, Wilcutt, Lucid and Blaha are seen discussing their mission in an interview with CNN's John Holliman.

Source record↗
NASA NTRS1997

STS-86 Day 06 Highlights

On this sixth day of the STS-86 mission, the flight crew, Cmdr. James D. Wetherbee, Jr., Pilot Michael J. Bloomfield, Mission Specialists Scott E. Parazynski, Jean-Loup Chretien, Vladimir G. Titov, Wendy B. Lawrence and Mike Foale are seen discussing their mission objectives in an interview with CNN, PBS and the Russian media.

Source record↗
NASA NTRS1997

STS-87 Day 08 Highlights

On this eighth day of the STS-87 mission, the flight crew, Cmdr. Kevin R. Kregel, Pilot Steven W. Lindsey, Mission Specialists Winston E. Scott, Kalpana Chawla, and Takao Doi, and Payload Specialist Leonid K. Kadenyuk take time out from their duties to be interviewed by CNN. As they reach the one week mark in their 16-day flight, the STS-87 crew shift the focus of their efforts towards the variety of science experiments flying on this mission.

Source record↗
NASA NTRS1998

STS-89 Day 06 Highlights

On this sixth day of the STS-89 mission, the flight crew, Cmdr. Terrence W. Wilcutt, Pilot Frank Edwards, and Mission Specialists Michael P. Anderson, James F. Reilly, Bonnie J. Dunbar, Salizhan Shakirovich Sharipov, David A. Wolf and Andrew S.W. Thomas, are interviewed by John Holliman of Cable News Network (CNN) and Russian news media. The crew discuss the progress of the mission and activities that lie ahead for Mir crew member Andy Thomas.

Source record↗
NASA NTRS1999

STS-96 FD Highlights and Crew Activities Report: Flight Day 05

On this fifth day of the STS-96 Discovery mission, the flight crew, Commander Kent V. Rominger, Pilot Rick D. Husband, and Mission Specialists Ellen Ochoa, Tamara E. Jernigan, Daniel T. Barry, Julie Payette, and Valery Ivanovich Tokarev are seen performing logistics transfer activities within the Discovery/International Space Station orbiting complex. The crew transfers supplies, equipment, and water. Payette and Tokarev perform maintenance activities on the storage batteries in the Zarya module. Barry and Tokarev install acoustic insulation around some of the fans inside Zarya. Jernigan and Husband install shelving in 2 soft stowage racks. Husband and Barry troubleshoot and perform maintenance activities on the Early Communications System. At the end of the workday, Rominger, Jernigan, and Barry discussed the progress of the mission with NBC's "Today," CBS "This Morning," and CNN.

Source record↗
NASA NTRS2000

STS-99 Flight Day Highlights and Crew Activities Report

Live footage shows the Blue Team (second of the dual shift crew), Dominic L. Pudwill Gorie, Janice E. Voss and Mamoru Mohri, beginning the first mapping swath covering a 140-mile-wide path. While Mohri conducts mapping operations, Voss and Gorie are seen participating in a news conference with correspondents from NBC and CNN. The Red Team (first of the dual shift crew), Kevin R. Kregel, Janet L. Kavandi and Gerhard P.J. Thiele, relieves the Blue Team and are seen continuing the mapping operations for this around the clock Shuttle Radar Topography Mission (SRTM). Commander Kregel is shown performing boom (mass) durability tests, calibrating the EarthCam Payload, and speaking with the Launch Control Center (LCC) about trouble shooting a bracket for better camera angle.

Source record↗
NASA NTRS2002

Bioinspired engineering of exploration systems for NASA and DoD

A new approach called bioinspired engineering of exploration systems (BEES) and its value for solving pressing NASA and DoD needs are described. Insects (for example honeybees and dragonflies) cope remarkably well with their world, despite possessing a brain containing less than 0.01% as many neurons as the human brain. Although most insects have immobile eyes with fixed focus optics and lack stereo vision, they use a number of ingenious, computationally simple strategies for perceiving their world in three dimensions and navigating successfully within it. We are distilling selected insect-inspired strategies to obtain novel solutions for navigation, hazard avoidance, altitude hold, stable flight, terrain following, and gentle deployment of payload. Such functionality provides potential solutions for future autonomous robotic space and planetary explorers. A BEES approach to developing lightweight low-power autonomous flight systems should be useful for flight control of such biomorphic flyers for both NASA and DoD needs. Recent biological studies of mammalian retinas confirm that representations of multiple features of the visual world are systematically parsed and processed in parallel. Features are mapped to a stack of cellular strata within the retina. Each of these representations can be efficiently modeled in semiconductor cellular nonlinear network (CNN) chips. We describe recent breakthroughs in exploring the feasibility of the unique blending of insect strategies of navigation with mammalian visual search, pattern recognition, and image understanding into hybrid biomorphic flyers for future planetary and terrestrial applications. We describe a few future mission scenarios for Mars exploration, uniquely enabled by these newly developed biomorphic flyers.

Space Flight↗
NASA NTRS2005

Risk and Exploration: Earth, Sea and Stars

The NASA History Division is pleased to present the record of a unique meeting on risk and exploration held under the auspices of the NASA Administrator, Sean O Keefe, at the Naval Postgraduate School in Monterey, California, from September 26-29, 2004. The meeting was the brainchild of Keith Cowing and astronaut John Grunsfeld, NASA's chief scientist at the time. Its goals, stated in the letter of invitation published herein, were precipitated by the ongoing dialogue on risk and exploration in the wake of the Columbia Shuttle accident, the Hubble Space Telescope servicing question, and, in a broader sense, by the many NASA programs that inevitably involve a balance between risk and forward-looking exploration. The meeting, extraordinarily broad in scope and participant experience, offers insights on why we explore, how to balance risk and exploration, how different groups defi ne and perceive risk differently, and the importance of exploration to a creative society. At NASA Headquarters, Bob Jacobs, Trish Pengra, and Joanna Adamus of NASA Public Affairs led the meeting's implementation. The Naval Postgraduate School, commanded by Rear Admiral Patrick W. Dunne, provided a congenial venue. The meeting was broadcast on NASA TV, and thanks are due in this regard to Al Feinberg, Tony Stewart, Jim Taylor, and the planners collaborative: Mark Shaddock and Spotlight Productions, Donovan Gates of Donovan Gates Production, and Michael Ditertay and his staff on this 30-person television crew. Thanks to their efforts, a DVD record of the meeting has also been produced. Thanks are also due to the moderators: Miles O Brien of CNN, Chris McKay of NASA Ames, David Halpern of the White House Office of Science and Technology Policy, and John Grunsfeld, NASA Headquarters. In order to maintain the informal flavor of the meetings, these proceedings are based on transcripts that have been lightly edited for grammar and punctuation. Most references to slides shown during the presentations have been deleted.

Dick, Steven J.↗
NASA NTRS2017

NeMO-Net: The Neural Multi-Modal Observation and Training Network for Global Coral Reef Assessment

In the past decade, coral reefs worldwide have experienced unprecedented stresses due to climate change, ocean acidification, and anthropomorphic pressures, instigating massive bleaching and die-off of these fragile and diverse ecosystems. Furthermore, remote sensing of these shallow marine habitats is hindered by ocean wave distortion, refraction and optical attenuation, leading invariably to data products that are often of low resolution and signal-to-noise (SNR) ratio. However, recent advances in UAV and Fluid Lensing technology have allowed us to capture multispectral 3D imagery of these systems at sub-cm scales from above the water surface, giving us an unprecedented view of their growth and decay. Exploiting the fine-scaled features of these datasets, machine learning methods such as MAP, PCA, and SVM can not only accurately classify the living cover and morphology of these reef systems (below 8 percent error), but are also able to map the spectral space between airborne and satellite imagery, augmenting and improving the classification accuracy of previously low-resolution datasets. We are currently implementing NeMO-Net, the first open-source deep convolutional neural network (CNN) and interactive active learning and training software to accurately assess the present and past dynamics of coral reef ecosystems through determination of percent living cover and morphology. NeMO-Net will be built upon the QGIS platform to ingest UAV, airborne and satellite datasets from various sources and sensor capabilities, and through data-fusion determine the coral reef ecosystem makeup globally at unprecedented spatial and temporal scales. To achieve this, we will exploit virtual data augmentation, the use of semi-supervised learning, and active learning through a tablet platform allowing for users to manually train uncertain or difficult to classify datasets. The project will make use of Pythons extensive libraries for machine learning, as well as extending integration to GPU and High-End Computing Capability (HECC) on the Pleiades supercomputing cluster, located at NASA Ames. The project is being supported by NASAs Earth Science Technology Office (ESTO) Advanced Information Systems Technology (AIST-16) Program.

NeMO-Net↗
NASA NTRS2017

NeMO-Net The Neural Multi-Modal Observation Training Network for Global Coral Reef Assessment

In the past decade, coral reefs worldwide have experienced unprecedented stresses due to climate change, ocean acidification, and anthropomorphic pressures, instigating massive bleaching and die-off of these fragile and diverse ecosystems. Furthermore, remote sensing of these shallow marine habitats is hindered by ocean wave distortion, refraction and optical attenuation, leading invariably to data products that are often of low resolution and signal-to-noise (SNR) ratio. However, recent advances in UAV and Fluid Lensing technology have allowed us to capture multispectral 3D imagery of these systems at sub-cm scales from above the water surface, giving us an unprecedented view of their growth and decay. Exploiting the fine-scaled features of these datasets, machine learning methods such as MAP, PCA, and SVM can not only accurately classify the living cover and morphology of these reef systems (below 8 error), but are also able to map the spectral space between airborne and satellite imagery, augmenting and improving the classification accuracy of previously low-resolution datasets.We are currently implementing NeMO-Net, the first open-source deep convolutional neural network (CNN) and interactive active learning and training software to accurately assess the present and past dynamics of coral reef ecosystems through determination of percent living cover and morphology. NeMO-Net will be built upon the QGIS platform to ingest UAV, airborne and satellite datasets from various sources and sensor capabilities, and through data-fusion determine the coral reef ecosystem makeup globally at unprecedented spatial and temporal scales. To achieve this, we will exploit virtual data augmentation, the use of semi-supervised learning, and active learning through a tablet platform allowing for users to manually train uncertain or difficult to classify datasets. The project will make use of Pythons extensive libraries for machine learning, as well as extending integration to GPU and High-End Computing Capability (HECC) on the Pleiades supercomputing cluster, located at NASA Ames. The project is being supported by NASAs Earth Science Technology Office (ESTO) Advanced Information Systems Technology (AIST-16) Program.

Remote Sensin↗