Results 101 to 110 of about 36,198 (253)

Fine‐scale spatio‐temporal niche partitioning enables coexistence of wild ungulates and livestock in a resource‐limited Himalayan landscape, India

open access: yesWildlife Biology, EarlyView.
Understanding how wild ungulates share space with domestic livestock is central to conservation planning in Himalayan multi‐use landscapes. This study focuses on multi‐axis niche relationships among six wild ungulates: hangul Cervus hanglu hanglu, Kashmir musk deer Moschus cupreus, Himalayan goral Naemorhedus goral, kashmir markhor Capra falconeri ...
Mohsin Javid   +2 more
wiley   +1 more source

Efficient and Interpretable Pavement Crack Classification via SylphNet: Systematic Hyperparameter Analysis on a Primary Road Image Dataset

open access: yesArtificial Intelligence for Engineering, EarlyView.
SylphNet is a lightweight CNN for interpretable three‐class pavement crack classification, achieving 97.50% accuracy with only 1.036M parameters and approximately 2.1 ms inference latency. Systematic component and hyperparameter analysis, repeated‐seed validation, computational profiling, and complementary XAI methods support its efficiency, robustness,
Tamanna Yasmin   +4 more
wiley   +1 more source

Refined Safety Distance Measurement of Heavy Construction Machinery Near Electricity Operation Based on Feature‐Homogenised Spatial Target Analysis

open access: yesHigh Voltage, EarlyView.
ABSTRACT Heavy construction machinery is essential for power infrastructure construction and maintenance, making safety distance measurement crucial for ensuring operational safety. Existing methods, which rely on target space mapping, face challenges such as error accumulation and limited accuracy.
Fuqi Ma   +4 more
wiley   +1 more source

PowerGPT‐R1: Vision‐Language Reinforcement Fine‐Tuning With Verifiable Reward for Power Inspection

open access: yesHigh Voltage, EarlyView.
ABSTRACT Vision‐driven intelligent power inspection systems have long faced the challenge of scarce high‐quality datasets in specialised domains, leading to limited performance of traditional deep learning methods (e.g., Faster‐RCNN) in few‐shot learning scenarios. Recent breakthroughs in language models, particularly the open‐source DeepSeek‐R1 model,
Yangyang Zhong   +12 more
wiley   +1 more source

PJ-YOLO: Prior-Knowledge and Joint-Feature-Extraction Based YOLO for Infrared Ship Detection

open access: yes
Infrared ship images have low resolution and limited recognizable features, especially for small targets, leading to low accuracy and poor generalization of traditional detection methods.
Chaofeng Li, Guanghua Fu, Yongjie Liu
core   +1 more source

Research on Embodied Intelligence Technology for Electric Power Equipment Based on Large‐Scale Pre‐Trained Models

open access: yesHigh Voltage, EarlyView.
ABSTRACT With the development of electric power artificial intelligence (AI) technology, many complicated challenges emerged during application. Traditional AI algorithms work well in specialised tasks such as detection and classification. However, they are unlikely to solve general problems.
Yuanpeng Tan   +4 more
wiley   +1 more source

YOLO systematic

open access: yes
This project hosts the protocol, search strategies, and data extraction templates for a systematic review of YOLO applications in ...
Henri Hartman
core   +1 more source

Fear generalization, cross‐sensitization and behavioural responses to multiple dangers in a freshwater snail

open access: yesJournal of Animal Ecology, EarlyView.
We show that juvenile exposure to a danger can not only prime individuals to be more responsive to that same danger later in life but also to an ostensibly unrelated danger. These patterns of behavioural cross‐sensitization can have important ecological implications for how animals respond to multiple and novel stressors. Abstract Behavioural responses
Janice L. Yan   +3 more
wiley   +1 more source

Small Object Detection Method for Bioimages Based on Improved YOLOv8n Model

open access: yesIntegrative Zoology, EarlyView.
This study proposes a small object detection method for bioimages based on an improved YOLOv8n model. Experimental results demonstrate that the proposed approach effectively enhances detection precision, recall, and mAP50, offering a novel solution for the technical challenges in biological microscopy research.
Xiaoyu Li   +7 more
wiley   +1 more source

Reusing Geospatial Data of Invasive Alien Insect Species From the Literature: Significance, Challenges, and Potential

open access: yesIntegrative Zoology, EarlyView.
We use bibliometric analysis to evaluate geospatial data reuse for invasive alien insect species (IAIS). Of 1032 relevant publications, 51.0% lacked downloadable raw data. Integrating cross‐regional, temporal, and multi‐species data could address single‐study limitations, but data scarcity remains a barrier.
Shuhao Tan   +5 more
wiley   +1 more source

Home - About - Disclaimer - Privacy