Results 41 to 50 of about 636 (118)

LaneDetectionAlgorithmBasedonBeamletTransformationandK-meansClustering

工程科学与技术, 2015
:Inordertosolvetheproblemsofthepoornoiseimmunityandlowrobustnessinthevideolanedetection,afastlanedetectionmethodbasedonnewfeatureextractionandclassificationwasproposed.Thesetofmidpointsofoptimalbeamletswasextracted ...
肖进胜, 程显, 李必军, 高威, 彭红   +4 more
doaj  

Recognition of Acupoints on Human Back Based on Machine Vision and Deep Learning

Big Data and Cognitive Computing
Traditional acupoint localization methods rely heavily on manual operation, resulting in high subjectivity and limited accuracy. To improve the precision and stability of acupoint detection, this study integrates machine vision technology with in situ ...
Zhike Zhao, Linman Song, Songying Li, Ruihao Xue, Peng Li   +4 more
doaj   +1 more source

Parameter‐Preserving Real‐time BIM Rendering via Direct GPU Ray Tracing

Computer Animation and Virtual Worlds, Volume 37, Issue 4, July/August 2026.
Parametric BIM geometry is preserved from Revit extraction to GPU ray tracing without mesh tessellation. A two‐tier cache reuses repeated geometry during export, and an instanced OptiX representation reduces memory at render time. The method lowers export time and GPU memory while preserving exact curved surfaces.
Jaehyuk Lim, Donggyu Lee, Junghyun Han, Seung‐wook Kim   +3 more
wiley   +1 more source

MGGAN: Learning a Multiscale Graph‐Based GAN for Non‐Parametric 3D Single‐Shape Deformation and Variation

Computer Animation and Virtual Worlds, Volume 37, Issue 4, July/August 2026.
MGGAN learns complex, high‐dimensional patterns and geometric statistics of a single 3D mesh using a multiscale graph‐based generative adversarial network. By combining spectral and spatial graph operators in a coarse‐to‐fine framework with noise injection at each scale, the method generates smooth, visually coherent, and topology‐preserving shape ...
Jorge Jabón, Sergio Corbera, Rafael Barea   +2 more
wiley   +1 more source

Integrate the Isogeometric Analysis Approach Based on the T-Splines Function for the Numerical Study of a Liquefied Petroleum Gas (LPG) Cylinder Subjected to a Static Load

Applied Sciences
LGP cylinders are necessary for fuel storage and home heating. To avoid material and human risk, it is essential to maintain their structural integrity. Extensive mechanical research studies and physical tests are necessary for its design.
Said ELFakkoussi, Mohammed Berrada Gouzi, Ahmed Elkhalfi, Sorin Vlase, Maria Luminita Scutaru   +4 more
doaj   +1 more source

Ultra‐Compact Low‐Loss 3D Glass Waveguide Chip Using Femtosecond Laser Writing Technique

Advanced Photonics Research, Volume 7, Issue 6, June 2026.
An ultra‐compact, low‐loss fan‐in/fan‐out device for 4‐core fiber is demonstrated using femtosecond laser direct writing. Multi‐scan and overwriting methods are employed to produce low‐loss waveguides. A trench‐assisted offset‐assisted cosine‐shaped model is proposed to reduce bending loss.
Fengrui Yu, Lin Ma, Mingjing Xu, Xiaoke Chen, Jinhua Wu, Zuyuan He   +5 more
wiley   +1 more source

Research on Autonomous Navigation System of Drilling Robots for Coal Mine Gas Outburst Prevention

Machines
Underground gas control is a critical link in coal mine safety production, and drilling robots serve as the core equipment for gas extraction drilling operations.
Shaoze You, Menggang Li, Chaoquan Tang, Jun Wang   +3 more
doaj   +1 more source

A Comprehensive Multistage Average Controller for Trajectory Tracking in Solar‐Powered Mobile Robots: Analysis of Actuator‐Driver and Power Stage Integration

International Journal of Mechanical System Dynamics, Volume 6, Issue 2, Page 224-246, June 2026.
ABSTRACT This work addresses the challenge of bidirectional trajectory tracking in solar‐powered wheeled mobile robots (WMRs), considering the mechanical structure, actuator‐driver, and power stage subsystems. Notably, this is the first study to explicitly model and control the actuator‐driver subsystem within this context. The proposed solution relies
Benjamin Natanael Santiago‐Nogales, Julio Cesar Ordaz‐Dehesa, Ramón Silva‐Ortigoza, Erik Reyes‐Reyes, J. Martín Alba‐Martínez, Juan Eduardo Velázquez‐Velázquez, José Rafael García‐Sánchez, Magdalena Marciano‐Melchor, Hind Taud   +8 more
wiley   +1 more source

Parameter identification of commercial proton exchange membrane fuel cells using phototropic growth algorithm

Franklin Open
Proton exchange membrane fuel cells (PEMFCs) are recognized as a cornerstone technology for sustainable energy systems thanks to their minimal environmental footprint and high energy conversion efficiency.
Hüseyin Bakır
doaj   +1 more source

From Single-Parameter Reinforcement Learning to Integrated Multi-Parameter Optimization: A Data-Driven Design Framework for Airship Aerodynamics

Aerospace
This study presents a reinforcement learning (RL)-based framework for the aerodynamic optimization of the Lotte airship, combining mid-fidelity dynamic simulations with adaptive learning strategies.
Qian Zhao, Yue Yu, Carlo E. D. Riboldi
doaj   +1 more source