Integrated, real-time, multi-scale system for monitoring avian interactions with offshore wind energy technologies
Explore the source record for details and available documents.
Cheung, Lawrence Chih-Hui↗
Engineering topics
Lewis, Jesse
Publications and source records attributed to Lewis, Jesse.
Improving the accessibility and transferability of machine learning algorithms for identification of animals in camera trap images: MLWIC2
Motion-activated wildlife cameras (or “camera traps”) are frequently used to remotely and noninvasively observe animals. The vast number of images collected from camera trap projects has prompted some biologists to employ machine learning algorithms to automatically recognize species in these images, or at least filter-out images that do not contain animals. These approaches are often limited by model transferability, as a model trained to recognize species from one location might not work as well for the same species in different locations. Furthermore, these methods often require advanced computational skills, making them inaccessible to many biologists. We used 3 million camera trap images from 18 studies in 10 states across the United States of America to train two deep neural networks, one that recognizes 58 species, the “species model,” and one that determines if an image is empty or if it contains an animal, the “empty-animal model.” Our species model and empty-animal model had accuracies of 96.8% and 97.3%, respectively. Furthermore, the models performed well on some out-of-sample datasets, as the species model had 91% accuracy on species from Canada (accuracy range 36%–91% across all out-of-sample datasets) and the empty-animal model achieved an accuracy of 91%–94% on out-of-sample datasets from different continents. Our software addresses some of the limitations of using machine learning to classify images from camera traps. By including many species from several locations, our species model is potentially applicable to many camera trap studies in North America. We also found that our empty-animal model can facilitate removal of images without animals globally. We provide the trained models in an R package (MLWIC2: Machine Learning for Wildlife Image Classification in R), which contains Shiny Applications that allow scientists with minimal programming experience to use trained models and train new models in six neural network architectures with varying depths.
59 BASIC BIOLOGICAL SCIENCES↗
Design Development of a Combined Deployment and Pointing System for the International Space Station Neutron Star Interior Composition Explorer Telescope
This paper describes the design of a unique suite of mechanisms that make up the Deployment and Pointing System (DAPS) for the Neutron Star Interior Composition Explorer (NICER/SEXTANT) instrument, an X-Ray telescope, which will be mounted on the International Space Station (ISS). The DAPS system uses four stepper motor actuators to deploy the telescope box, latch it in the deployed position, and allow it to track sky targets. The DAPS gimbal architecture provides full-hemisphere coverage, and is fully re-stowable. The compact design of the mechanism allowed the majority of total instrument volume to be used for science. Override features allow DAPS to be stowed by ISS robotics.
Budinoff, Jason↗
Design Development of a Combined Deployment and Pointing System for the International Space Station Neutron Star Interior Composition Explorer Telescope
This paper describes the design of a unique suite of mechanisms which make up the Deployment and Pointing System (DAPS) for the Neutron Star Interior Composition Explorer (NICER/SEXTANT) instrument, an X-Ray telescope, which will be mounted on the International Space Station (ISS). The DAPS system uses 4 stepper motor actuators to deploy the telescope box, latch it in the deployed position, and allow it to track sky targets. The DAPS gimbal architecture provides full-hemisphere coverage, and is fully re-stowable. The compact design of the mechanism allowed the majority of total instrument volume to be used for science. Override features allow DAPS to be stowed by ISS robotics.
NICER Pointing↗
GPM Solar Array Gravity Negated Deployment Testing
NASA Goddard Space Flight Center (GSFC) successfully developed a g-negation support system for use on the solar arrays of the Global Precipitation Measurement (GPM) Satellite. This system provides full deployment capability at the subsystem and observatory levels. In addition, the system provides capability for deployed configuration first mode frequency verification testing. The system consists of air pads, a support structure, an air supply, and support tables. The g-negation support system was used to support all deployment activities for flight solar array deployment testing.
Penn, Jonathan↗
The Sample Analysis at Mars Investigation and Instrument Suite
The Sample Analysis at Mars (SAM) investigation of the Mars Science Laboratory (MSL) addresses the chemical and isotopic composition of the atmosphere and volatiles extracted from solid samples. The SAM investigation is designed to contribute substantially to the mission goal of quantitatively assessing the habitability of Mars as an essential step in the search for past or present life on Mars. SAM is a 40 kg instrument suite located in the interior of MSL's Curiosity rover. The SAM instruments are a quadrupole mass spectrometer, a tunable laser spectrometer, and a 6-column gas chromatograph all coupled through solid and gas processing systems to provide complementary information on the same samples. The SAM suite is able to measure a suite of light isotopes and to analyze volatiles directly from the atmosphere or thermally released from solid samples. In addition to measurements of simple inorganic compounds and noble gases SAM will conduct a sensitive search for organic compounds with either thermal or chemical extraction from sieved samples delivered by the sample processing system on the Curiosity rover's robotic arm,
Mahaffy, Paul↗