ALBERT

All Library Books, journals and Electronic Records Telegrafenberg

feed icon rss

Ihre E-Mail wurde erfolgreich gesendet. Bitte prüfen Sie Ihren Maileingang.

Leider ist ein Fehler beim E-Mail-Versand aufgetreten. Bitte versuchen Sie es erneut.

Vorgang fortführen?

Exportieren
Filter
  • Artikel  (2)
  • Forschungsdaten
  • Karten
  • Norwegian Polar Institute  (1)
  • Public Library of Science  (1)
  • 2020-2023  (2)
  • 1940-1944
  • 1
    Publikationsdatum: 2022-05-26
    Beschreibung: © The Author(s), 2020. This article is distributed under the terms of the Creative Commons Attribution License. The definitive version was published in Hopkinson, B. M., King, A. C., Owen, D. P., Johnson-Roberson, M., Long, M. H., & Bhandarkar, S. M. Automated classification of three-dimensional reconstructions of coral reefs using convolutional neural networks. PLoS One, 15(3), (2020): e0230671, doi: 10.1371/journal.pone.0230671.
    Beschreibung: Coral reefs are biologically diverse and structurally complex ecosystems, which have been severally affected by human actions. Consequently, there is a need for rapid ecological assessment of coral reefs, but current approaches require time consuming manual analysis, either during a dive survey or on images collected during a survey. Reef structural complexity is essential for ecological function but is challenging to measure and often relegated to simple metrics such as rugosity. Recent advances in computer vision and machine learning offer the potential to alleviate some of these limitations. We developed an approach to automatically classify 3D reconstructions of reef sections and assessed the accuracy of this approach. 3D reconstructions of reef sections were generated using commercial Structure-from-Motion software with images extracted from video surveys. To generate a 3D classified map, locations on the 3D reconstruction were mapped back into the original images to extract multiple views of the location. Several approaches were tested to merge information from multiple views of a point into a single classification, all of which used convolutional neural networks to classify or extract features from the images, but differ in the strategy employed for merging information. Approaches to merging information entailed voting, probability averaging, and a learned neural-network layer. All approaches performed similarly achieving overall classification accuracies of ~96% and 〉90% accuracy on most classes. With this high classification accuracy, these approaches are suitable for many ecological applications.
    Beschreibung: This study was funded by grants from the Alfred P. Sloan Foundation (BMH, BR2014-049; https://sloan.org), and the National Science Foundation (MHL, OCE-1657727; https://www.nsf.gov). The funders had no role in the study design, data collection and analysis, decision to publish, or preparation of the manuscript.
    Repository-Name: Woods Hole Open Access Server
    Materialart: Article
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 2
    Publikationsdatum: 2022-05-27
    Beschreibung: © The Author(s), 2021. This article is distributed under the terms of the Creative Commons Attribution License. The definitive version was published in Goertz, C. E. C., Woodie, K., Long, B., Hartman, L., Gaglione, E., Christen, D., Clauss, T., Flower, J., Tuttle, A., Richard, C., Romano, T. A., Schmitt, T., Otjen, E., Osborn, S., Aibel, S., Binder, T., Van Bonn, W., Castellote, M., Mooney, T. A., Dennison-Gibby, S., Burek-Huntington, K., & Rowles, T. K. (2021). Stranded beluga (Delphinapterus leucas) calf response and care: reports of two cases with different outcomes. Polar Research, 40, 5514, https://doi.org/10.33265/polar.v40.5514.
    Beschreibung: Given the remote, rugged areas belugas typically inhabit and the low rehabilitation success rate with any cetacean, it is rare to have the opportunity to rescue a live-stranded beluga. The Alaska SeaLife Center cared for two stranded beluga calves with two different outcomes. In 2012, a neonatal male beluga calf (DL1202) stranded following intense storms in Bristol Bay. In 2017, a helicopter pilot discovered a stranded male beluga calf (DL1705) during a flight over Cook Inlet. The Alaska SeaLife Center transported both calves for rehabilitation and utilized supportive care plans based on those for other species of stranded cetaceans and care of neonatal belugas at zoological facilities. Diagnostics included complete blood counts, serum chemistries, microbial cultures, hearing tests, imaging and morphometric measurements to monitor systemic health. Treatments included in-pool flotation support; antimicrobials; gastrointestinal support; and close monitoring of respirations, urination, defecation and behaviour. After three weeks of supportive care, the Bristol Bay calf (DL1202) succumbed to sepsis secondary to a possible prematurity-related lack of passive transfer of antibodies. After seven weeks, the Cook Inlet calf (DL1705) recovered and all medications were discontinued. Unable to survive on his own, he was declared non-releasable and placed in long-term care at a zoological facility, to live with other belugas. Aspects and details from successful cases of cetacean critical care become important references especially vital for the survival of essential animals in small, endangered populations.
    Beschreibung: The ASLC, Georgia Aquarium, Mystic Aquarium, SeaWorld, John G. Shedd Aquarium, the Texas Marine Mammal Stranding Network and Vancouver Aquarium self-funded the cost of travel and salaries for their staff. Additional funding was provided by the Prescott Grant Program, Prescott Emergency Grant Program, SeaWorld Busch Gardens Conservation Fund and individual and corporate donations to the ASLC Center wildlife response programme.
    Schlagwort(e): Cetacean ; neonate ; nutrition ; hand-rearing ; critical care
    Repository-Name: Woods Hole Open Access Server
    Materialart: Article
    Standort Signatur Erwartet Verfügbarkeit
    BibTip Andere fanden auch interessant ...
Schließen ⊗
Diese Webseite nutzt Cookies und das Analyse-Tool Matomo. Weitere Informationen finden Sie hier...