Results 61 to 70 of about 5,679 (259)

Explainability Feature Bands Adaptive Selection for Hyperspectral Image Classification

Remote Sensing
Hyperspectral remote sensing images are widely used in resource exploration, urban planning, natural disaster assessment, and feature classification. Aiming at the problems of poor interpretability of feature classification algorithms for hyperspectral ...
Jirui Liu, Jinhui Lan, Yiliang Zeng, Wei Luo, Zhixuan Zhuang, Jinlin Zou   +5 more
doaj   +1 more source

Micromachined Double‐Membrane Mechanically Tunable Metamaterial for Thermal Infrared Filtering

Advanced Photonics Research, Volume 6, Issue 5, May 2025.
Herein, a mechanically tunable double‐layer plasmonic metamaterial leveraging the extraordinary optical transmission effect observed in subwavelength arrays of openings within thin metal layers is presented. The concept is experimentally validated by integrating the proposed metamaterial structure into an electrostatic parallel‐plate actuator to create
Oleg Bannik, Fedor Kovalev, Mingkai Liu, Michal Zawierta, Dilusha Silva, Lorenzo Faraone, Mariusz Martyniuk, Ilya Shadrivov   +7 more
wiley   +1 more source

Identification of an Osteochondral Erosion Process in Gout Driven by Fibrinogen‐Integrin Activation and Local MSU Crystallization

Advanced Science, EarlyView.
Cartilage injury promotes local fibrinogen deposition, which accelerates monosodium urate crystallization and activates integrin‐mediated matrix‐degradation. This self‐amplifying cycle drives gout‐related cartilage erosion. Disrupting fibrinogen deposition or restoring the cartilage barrier could interrupt this vicious cycle.
Hanlin Xu, Simin Bi, Zhechen Liu, Xiaofeng Zhou, Hengwei Qin, Nicola Dalbeth, Minbiao Ji, Yinghui Hua   +7 more
wiley   +1 more source

Deep Reinforcement Learning for Band Selection in Hyperspectral Image Classification [PDF]

, 2022
Band selection refers to the process of choosing the most relevant bands in a hyperspectral image. By selecting a limited number of optimal bands, we aim at speeding up model training, improving accuracy, or both.
Hua, Yuansheng, Saha, Sudipan, Bruzzone, Lorenzo, Bovolo, Francesca, Zhu, Xiao Xiang, Mou, LiChao   +5 more
core   +1 more source

Nanoscale Optical Inhomogeneities From Compositional Segregation Within Individual GaN‐on‐Si Quantum Wells

Advanced Science, EarlyView.
This work visualizes local variations in luminescence and relates them to nanoscale chemical inhomogeneities in single InxGa1−xN quantum wells. We demonstrate that the elemental segregation is only inherent to quantum wells with high indium content. Density functional theory shows this to be the result of strain‐induced phase stabilization, explaining ...
Jing‐Yang Chung, Tara P. Mishra, Zackaria Mahfoud, Thomas E. Gage, Jianguo Wen, Katherine P. Rice, Isabelle Martin, Li Zhang, Govindo J. Syaranamual, Stephen J. Pennycook, Silvija Gradečak, Pieremanuele Canepa, Michel Bosman   +12 more
wiley   +1 more source

Semi-supervised hyperspectral band selection via spectral-spatial hypergraph model [PDF]

, 2015
Band selection is an essential step toward effective and efficient hyperspectral image classification. Traditional supervised band selection methods are often hindered by the problem of lacking enough training samples. To address this problem, we propose
Zhou, Jun, Zhang, Zhihong, Wang, Yanyang, Guo, Zhouxiao, Bai, Xiao   +4 more
core   +1 more source

Deep Learning Enables Identification of Antimicrobial Peptides Through Mechanochromic Fingerprints

Angewandte Chemie, EarlyView.
We demonstrate a new platform for antimicrobial peptide identification by combining polydiacetylene, hyperspectral imaging, and deep learning. The trained model classifies distinct spectral fingerprints into 14 peptide classes with 96.79% accuracy, revealing previously hidden molecular information beyond conventional colorimetric sensing.
Jiali Chen, Che‐Lun Chin, Qingzhen Zhu, Ling Chao, Kaori Sugihara   +4 more
wiley   +2 more sources

Label‐Free Myelin Fingerprinting: An Adult Human Post‐Mortem Brain Slice Platform via Coherent Anti‐Stokes Raman Spectroscopy

Advanced Science, EarlyView.
A serum‐free, air–liquid interface organotypic slice culture model preserves human post‐mortem corpus callosum tissue, successfully recovering from slicing trauma to reflect the donor's underlying disease state. Pairing label‐free Coherent anti‐Stokes Raman scattering (CARS) microscopy with k‐means clustering enables objective, high‐resolution ...
Kasra Roya‐Kouchaki, Jeroen P. Korterik, Femke Tjebbes, Geert J. Schenk, Herman L. Offerhaus, Antonio Luchicchi   +5 more
wiley   +1 more source

Incorporating band selection in the spatial selection of spectral endmembers

International Journal of Applied Earth Observations and Geoinformation, 2020
The impact of band selection on endmember selection is seldom explored in the analysis of hyperspectral imagery. This study incorporates the N-dimensional Spectral Solid Angle (NSSA) band selection tool into the Spectral-Spatial Endmember Extraction ...
Yaqian Long, Benoit Rivard, Derek Rogge
doaj   +1 more source

Super‐Multiplexed Label‐Free Raman Imaging Uncovers Novel Testicular Metabolic Couplings for Residual Body and Spermatogonial Differentiation

Advanced Science, EarlyView.
Super‐multiplexed Label‐free Raman Imaging (SLRI) enables 2D/3D metabolic mapping of intact Drosophila testes. Moving beyond descriptive morphology, it establishes a multidimensional tool for tissue metabolic remodeling, and offers a generalizable platform for complex tissue analysis, with implications extending to development and disease. ABSTRACT The
Jiaxin Li, Xia Chen, Yujuan Qi, Chen Qiao, Qiuru Huang, Dan Zhao, Weiyi Qian, Li Di, Yi Shi, Xiangqi Hu, Yueyue Shao, Kehan Wang, Zhiyu Tang‐Yang, Hanzhi Zang, Yuwen Du, Anran Dong, Jinxiong Feng, Jiayun Chen, Ying Zheng, Xiaofang Tan, Xiaoyu Zhao, Zhonghua Shi, Bo Zheng, Jun Yu   +23 more
wiley   +1 more source