Results 121 to 130 of about 34,039 (292)

A Review and Prospect of Appearance Defect Detection Methods for High Voltage Equipment Based on Vision Large Models

High Voltage, EarlyView.
ABSTRACT High voltage equipment, as a core component of power systems, plays an indispensable role in ensuring the reliability of power supply through its safe and stable operation. Traditional visual defect detection for high voltage equipment, however, often relies on manual inspection and experience‐based judgement, which struggles to meet the ...
Zhenbing Zhao, Shuo Feng, Teng Ma, Chenkang Tang, Wenlong Liao, Yixuan Huang, Yongjie Zhai, Wenqing Zhao   +7 more
wiley   +1 more source

Small Object Detection Method for Bioimages Based on Improved YOLOv8n Model

Integrative 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, Chengrui Shang, Xian Hou, Qi Wang, Jiao Wang, Taxing Zhang, Xiangjiang Zhan, Shengkai Pan   +7 more
wiley   +1 more source

Efficient Masked Autoencoder for Birdsong Representation with Applications on Wild Bird Species Classification

Integrative Zoology, EarlyView.
Research on mosquito feeding preferences and the malaria parasites they transmit is essential for understanding the interactions between hosts, vectors, and parasites. In this study, vertebrate hosts were identified in 72 mosquitoes. Most blood meals (58.7%) came from birds, representing 25 species, while 40.0% came from mammals (13 species), and 1.3 ...
Qin Zhang, Shipeng Hu, Hengrui Wang, Jizheng Yi, Guoxiong Zhou, Xiangyu Shen, Weixiong Peng, Zhishu Xiao, Aibin Chen   +8 more
wiley   +1 more source

A Wildlife Multi‐Modal Recognition Method Based on Infrared Camera Images Using MWAC

Integrative Zoology, EarlyView.
A multimodal wild wildlife classification model MWAC consists of two parts:(1) Wavelet KAN module (WDS‐KAN) for image feature extraction, and (2) Label Correlated Text Extraction module (LC‐BERT) for text feature extraction. ABSTRACT Nowadays, infrared camera technology has become an important tool for large‐scale monitoring and assessment of wildlife ...
Siming Deng, Guoxiong Zhou, Genhua Liu, Zhishu Xiao, Xiaoqun Huang, Yang Hu, Ling Gui   +6 more
wiley   +1 more source

Identification of cannabis use disorder using the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (DSM‐5) versus DSM‐5‐proxy measures: Differences by socio‐demographic characteristics

Addiction, EarlyView.
Abstract Background and Aims Cannabis use disorder (CUD) is a pressing public health concern in the United States, and understanding trends in prevalence requires considerations of how changes in measurement influence identification of CUD. Starting in 2021, the National Survey on Drug Use and Health (NSDUH) assessed CUD using all 11 Diagnostic and ...
Evan L. Eschliman, Erin M. Annunziato, Nicole D. Fitzgerald, Pia M. Mauro   +3 more
wiley   +1 more source

Cross‐sectional and longitudinal associations of cannabis use with cognitive functioning in individuals with a cannabis use disorder: The moderating role of nicotine

Addiction, EarlyView.
Abstract Background and Aims Cannabis is among the most widely used psychoactive substances globally and is often consumed alongside tobacco. Cannabis use has been associated with impairments in attention, learning, and memory, whereas nicotine can acutely enhance, but chronically impair, certain cognitive functions.
Emese Kroon, Nora de Bode, Karis Colyer‐Patel, Jia Hua Hsieh, Francesca Filbey, Janna Cousijn   +5 more
wiley   +1 more source

Splatshop: Efficiently Editing Large Gaussian Splat Models

Computer Graphics Forum, EarlyView.
Abstract We present Splatshop, a highly optimized toolbox for interactive editing (selection, deletion, painting, transformation, …) of 3D Gaussian Splatting models. Utilizing a comprehensive collection of heuristic approaches, we carefully balance between exact and fast rendering to enable precise editing without sacrificing real‐time performance. Our
Markus Schütz, Christoph Peters, Florian Hahlbohm, Elmar Eisemann, Marcus Magnor, Michael Wimmer   +5 more
wiley   +1 more source

Investigation of the Effectiveness of Programs Optimization Methods for Parallel Computing Systems with GPU

Вестник Дагестанского государственного технического университета: Технические науки
Objective. The paper defines the relevance of the task of increasing the efficiency of software, which in this case is understood as reducing the operating time of the designed software in the process of solving computationally complex problems.
A. Yu. Bezruchenko, V. A. Egunov
doaj   +1 more source

Optimized M-SHAKE Constraint Implementations for GPU-Accelerated Molecular Dynamics: Balancing Precision and Performance Across Architectures. [PDF]

J Comput Chem
Mixed‐precision (MP) and pairwise single‐precision (PW‐SP) implementations of the M‐SHAKE constraint solver reduce numerical errors and energy drift relative to pure single precision. On GPUs with limited FP64 throughput, both PW‐SP and MP outperform full double precision, with PW‐SP providing the largest speedup.
Jung J, La Torre DU, Kobayashi C, Ozaki K, Sugita Y.   +4 more
europepmc   +2 more sources

Image‐Based Spatio‐Temporal Interpolation for Split Rendering

Computer Graphics Forum, EarlyView.
Abstract Low‐powered devices – such as small form factor head‐mounted displays (HMDs) – struggle to deliver a smooth and high‐quality viewing experience, due to their limited power and rendering capabilities. Cloud rendering attempts to solve the quality issue, but leads to prohibitive latency and bandwidth requirements, hindering use with HMDs over ...
M. Steiner, T. Köhler, L. Radl, B. Budge, M. Steinberger   +4 more
wiley   +1 more source