Results 101 to 110 of about 95,777 (258)

Leveraging machine learning and citizen science data to describe flowering phenology across South Africa

PLANTS, PEOPLE, PLANET, EarlyView.
Recent shifts in flowering times are an index of, and a response to, human driven climate change. However, most information on these flowering changes is heavily skewed to the northern hemisphere. This imbalance limits our understanding of how climate change is affecting ecosystems, including the mismatches of flowering times between species, increased
Ross D. Stewart, Nicholas W. Bard, Michelle van der Bank, T. Jonathan Davies   +3 more
wiley   +1 more source

Distributed TensorFlow with MPI

, 2016
6 pages; fixed significant ...
Vishnu, Abhinav, Siegel, Charles, Daily, Jeffrey   +2 more
openaire   +2 more sources

HOWLish: a CNN for automated wolf howl detection

Remote Sensing in Ecology and Conservation, EarlyView.
Automated detection of wolf howls presents a great opportunity for large‐scale passive acoustic monitoring of wolf populations. Here we present HOWLish, a CNN trained for automated wolf howl detection, based on thousands of hours of soundscapes recorded in the wild.
Rafael Campos, Miha Krofel, Helena Rio‐Maior, Francesco Renna   +3 more
wiley   +1 more source

Assessing the Efficiency of Deep Learning Methods for Automated Vehicle Registration Recognition for University Entrance

Journal of Informatics and Web Engineering
With the ever-increasing number of vehicles on the road, a faster reliable security system for university entry is needed. This paper presents an approach for Automatic Number Plate Recognition (ANPR) using deep learning and PP-OCRv3.
Muhammad Syaqil Irsyad, Zarina Che Embi, Khairil Imran Bin Ghauth   +2 more
doaj   +1 more source

A UAV‐based deep learning pipeline for intertidal macrobenthos monitoring: Behavioral and age classification in Tachypleus tridentatus

Remote Sensing in Ecology and Conservation, EarlyView.
The endangered tri‐spine horseshoe crab (Tachypleus tridentatus), a “living fossil” crucial to coastal ecology and biomedical research, is experiencing severe population declines. Effective conservation requires efficient monitoring, which traditional methods cannot deliver at scale. We develop an integrated UAV deep learning framework tailored to this
Xiaohai Chen, Yuyuan Bao, Ziwei Ying, Mujiao Xie, Ting Li, Jixing Zou, Jun Shi, Xiaoyong Xie   +7 more
wiley   +1 more source

Wall‐to‐wall Amazon forest height mapping with Planet NICFI, Aerial LiDAR, and a U‐Net regression model

Remote Sensing in Ecology and Conservation, EarlyView.
Tree canopy height is a key indicator of forest biomass and structure, yet accurate mapping across the Amazon remains challenging. Here, we generated a canopy height map of the Amazon forest at ~4.8 m resolution using Planet NICFI imagery and a deep learning U‐Net model trained with airborne LiDAR data.
Fabien H. Wagner, Ricardo Dalagnol, Griffin Carter, Mayumi C. M. Hirye, Shivraj Gill, Le Bienfaiteur Sagang Takougoum, Samuel Favrichon, Michael Keller, Jean P. H. B. Ometto, Lorena Alves, Cynthia Creze, Stephanie P. George‐Chacon, Shuang Li, Zhihua Liu, Adugna Mullissa, Yan Yang, Erone G. Santos, Sarah R. Worden, Martin Brandt, Philippe Ciais, Stephen C. Hagen, Sassan Saatchi   +21 more
wiley   +1 more source

Enhancing Mobile Acute Lymphoblastic Cancer Detection: Transfer Learning from YOLOv9 to TensorFlow for Real-Time Applications

International Journal of Pioneering Technology and Engineering
The detection of acute lymphoblastic cancer (ALL) is critical for timely diagnosis and treatment. In this study, we propose a novel approach to enhance ALL detection using transfer learning techniques from YOLOv9 to TensorFlow, facilitating real-time ...
Osama Burak Elhalid, Ali Hakan Işık
doaj   +1 more source

Improving forest age estimation to understand subtropical forest regrowth dynamics using deep learning image segmentation of time‐series historical aerial photographs

Remote Sensing in Ecology and Conservation, EarlyView.
Accurately estimating forest age is key to understanding how forests recover and evaluating restoration success. We developed a two‐step deep learning approach using historical greyscale aerial photographs to map forest age at fine spatial scales. By combining a pre‐trained model with localized fine‐tuning, our U‐Net + ResNet50 architecture achieved ...
Ying Ki Law, Yi‐Fei Gu, Shuwen Liu, Guangqin Song, Aland H. Y. Chan, Cham Man Tse, Zhonghua Liu, Martha J. Ledger, Billy C. H. Hau, Sawaid Abbas, Jin Wu   +10 more
wiley   +1 more source

MNIST TensorFlow Tutorial

, 2020
This package replicates TensorFlow's MNIST tutorial, serving as a way to get hands-on experience with Chameleon and the basics of machine learning.
openaire   +1 more source

An autonomous network of acoustic detectors to map tiger risk by eavesdropping on prey alarm calls

Remote Sensing in Ecology and Conservation, EarlyView.
Tiger population recovery brings with it increased fatalities from human‐tiger conflict. We describe a network of autonomous intelligent passive acoustic sensors that monitor the forest for deer alarm calls as a proxy for tiger risk and provide a risk map to local communities in real‐time.
Arik Kershenbaum, Andrew Markham, Holly Root‐Gutteridge, Bethany Smith, Casey Anderson, Riley McClaughry, Ramjan Chaudhary, Amogh Vishwakarma, Stephen Cummins, Angela Dassow   +9 more
wiley   +1 more source