Evolutionary computation for feature selection in classification: A comprehensive survey of solutions, applications and challenges

X Song, Y Zhang, W Zhang, C He, Y Hu, J Wang… - Swarm and Evolutionary …, 2024 - Elsevier
Feature selection (FS), as one of the most significant preprocessing techniques in the fields
of machine learning and pattern recognition, has received great attention. In recent years …

Image segmentation evaluation: a survey of methods

Z Wang, E Wang, Y Zhu - Artificial Intelligence Review, 2020 - Springer
Image segmentation is a prerequisite for image processing. There are many methods for
image segmentation, and as a result, a great number of methods for evaluating …

A novel framework combining band selection algorithm and improved 3D prototypical network for tree species classification using airborne hyperspectral images

J Wu, L Chen, J Wang, Y Li, E Chen, X Zhang - Computers and Electronics …, 2024 - Elsevier
Fine-grained identification of forest types and tree species represents a critical aspect of
forest resource inventory and monitoring. The use of airborne hyperspectral remote sensing …

Tackling Optimization and System-Driven Engineering in Coupling Physical Constraints with MBSE: The Case of a Mobile Autonomous Line of Products

L Brisacier-Porchon, O Hammami - Conference on Systems Engineering …, 2023 - Springer
The main goal of product line engineering is to build complex system architecture at the best
quality, cost, and resource< Q, R, T> ratio. The return on investment (ROI) in terms of< Q, R …

[HTML][HTML] 基于SOP-SRL 波段选择和3D-Gabor 滤波的高光谱图像分类

陈立伟, 张雅涵, 王立国 - 哈尔滨工程大学学报, 2021 - html.rhhz.net
为了解决高光谱图像分类精度低, 计算复杂度高的问题, 本文提出一种基于可扩展的自表示学习
波段选择方法(SOP-SRL) 和3D-Gabor 滤波的高光谱图像分类方法, 以表示高光谱图像的空间 …

Hyperspectral band selection based on adaptive neighborhood grouping and local structure correlation

X Wang, G Wang - Journal of Sensors, 2021 - Wiley Online Library
Band selection is a direct and effective dimension reduction method and is one of the
hotspots in hyperspectral remote sensing research. However, most of the methods ignore …