Results 71 to 80 of about 541,400 (289)

SemanticST: A Scalable Multi‐Contextual Graph Learning Framework for Uncovering Spatial Niches and Robust Multi‐Sample Integration in Spatial Transcriptomics

Advanced Science, EarlyView.
Technical limitations often let dominant signals overshadow rare cell types and fine‐grained heterogeneity in spatial transcriptomics. SemanticST, a graph neural network using multi‐semantic graph fusion and a novel min‐cut loss, recovers these subtle patterns.
Roxana Zahedi, Ahmadreza Argha, Nona Farbehi, Ivan Bakhshayeshi, Thantrira Porntaveetus, Youqiong Ye, Nigel H. Lovell, Hamid Alinejad‐Rokny   +7 more
wiley   +1 more source

Symmetry‐Imposed Selection Rules for Excitations of Nontrivial Plasmonic Topologies

Advanced Science, EarlyView.
A unified group‐theory selection rule governs the excitation of vectorial nearfield topologies across three plasmonic spin states. Derived from first principles, it predicts spin–orbit vortex splitting and multidimensional nested vortices, confirmed by phase‐resolved in situ measurements.
Jie Yang, Pengyi Feng, Fei Han, Weijin Chen, Zhongwei Jin, Jincheng Ni, Yuanjie Yang, Anxue Zhang, Guy A. E. Vandenbosch, Niels Verellen, Ewald Janssens, Jiafu Wang, Benfeng Bai, Cheng‐Wei Qiu, Xuezhi Zheng   +14 more
wiley   +1 more source

Multi-view clustering via simultaneously learning shared subspace and affinity matrix

International Journal of Advanced Robotic Systems, 2017
Due to the existence of multiple views in many real-world data sets, multi-view clustering is increasingly popular. Many approaches have been investigated, among which the subspace clustering methods finding the underlying subspaces of data have been ...
Nan Xu, Yanqing Guo, Jiujun Wang, Xiangyang Luo, Xiangwei Kong   +4 more
doaj   +1 more source

Ordered Subspace Clustering for Complex Non-Rigid Motion by 3D Reconstruction

Applied Sciences, 2019
As a fundamental and challenging problem, non-rigid structure-from-motion (NRSfM) has attracted a large amount of research interest. It is worth mentioning that NRSfM has been applied to dynamic scene understanding and motion segmentation.
Weinan Du, Jinghua Li, Fei Wu, Yanfeng Sun, Yongli Hu   +4 more
doaj   +1 more source

Deep Subspace Clustering with Block Diagonal Constraint

Applied Sciences, 2020
The deep subspace clustering method, which adopts deep neural networks to learn a representation matrix for subspace clustering, has shown good performance.
Jing Liu, Yanfeng Sun, Yongli Hu
doaj   +1 more source

Machine Learning‐Driven Design of Multicomponent Bone Inorganic Matrix Mimicking Scaffolds for Osteogenesis Enhanced by Neurogenesis

Advanced Science, EarlyView.
Schematic illustration of development of experimental datasets and algorithm models, screening and preparation of the scaffolds and their applications in vivo. ABSTRACT Bone defects require materials with osteogenic, neurogenic, and angiogenic activity, yet designing such materials within high‐dimensional compositional spaces remains challenging. Here,
Kunlu Lin, Ying Yang, Chuyao Zhou, Hanyue Mao, Zhiquan Zhang, Libangxi Liu, Xiaoying Yu, Haoming Liu, Long Liu, Xiaoyan Wang   +9 more
wiley   +1 more source

Subspace clustering via thresholding and spectral clustering [PDF]

2013 IEEE International Conference on Acoustics, Speech and Signal Processing, 2013
ICASSP ...
Reinhard Heckel, Helmut Bölcskei
openaire   +3 more sources

Optimized clustering method for spectral reflectance recovery

Frontiers in Psychology, 2022
An optimized method based on dynamic partitional clustering was proposed for the recovery of spectral reflectance from camera response values. The proposed method produced dynamic clustering subspaces using a combination of dynamic and static clustering,
Yifan Xiong, Guangyuan Wu, Xiaozhou Li, Xin Wang   +3 more
doaj   +1 more source

CS Decomposition Based Bayesian Subspace Estimation [PDF]

, 2012
In numerous applications, it is required to estimate the principal subspace of the data, possibly from a very limited number of samples. Additionally, it often occurs that some rough knowledge about this subspace is available and could be used to improve
Besson, Olivier, Dobigeon, Nicolas, Tourneret, Jean-Yves   +2 more
core   +1 more source

Computationally Evidence‐Grounded Sequence‐First Design of Peptide Binders

Advanced Science, EarlyView.
BOND‐PEP enables controllable, sequence‐first peptide binder design by grounding generation in binding evidence retrieved for each target. It uses topology‐conditioned message passing to integrate relevant peptide examples with the target protein sequence, forming a residue‐level representation that guides the generation of diverse, target‐specific ...
Wenze Ding
wiley   +1 more source