Results 121 to 130 of about 14,497 (259)

The Laplacian Spread of a Tree

Discrete Mathematics & Theoretical Computer Science, 2008
The Laplacian spread of a graph is defined to be the difference between the largest eigenvalue and the second smallest eigenvalue of the Laplacian matrix of the graph.
Yi-Zheng Fan, Jing Xu, Yi Wang, Dong Liang   +3 more
doaj  

Image and video analysis using graph neural network for Internet of Medical Things and computer vision applications

CAAI Transactions on Intelligence Technology, EarlyView.
Abstract Graph neural networks (GNNs) have revolutionised the processing of information by facilitating the transmission of messages between graph nodes. Graph neural networks operate on graph‐structured data, which makes them suitable for a wide variety of computer vision problems, such as link prediction, node classification, and graph classification.
Amit Sharma, Ashutosh Sharma, Alexey Tselykh, Alexander Bozhenyuk, Byung‐Gyu Kim   +4 more
wiley   +1 more source

Enhancing generalized spectral clustering with embedding Laplacian graph regularization

CAAI Transactions on Intelligence Technology, EarlyView.
Abstract An enhanced generalised spectral clustering framework that addresses the limitations of existing methods by incorporating the Laplacian graph and group effect into a regularisation term is presented. By doing so, the framework significantly enhances discrimination power and proves highly effective in handling noisy data.
Hengmin Zhang, Jian Yang, Bob Zhang, Yang Tang, Wenli Du, Bihan Wen   +5 more
wiley   +1 more source

Boosted unsupervised feature selection for tumor gene expression profiles

CAAI Transactions on Intelligence Technology, EarlyView.
Abstract In an unsupervised scenario, it is challenging but essential to eliminate noise and redundant features for tumour gene expression profiles. However, the current unsupervised feature selection methods treat all samples equally, which tend to learn discriminative features from simple samples.
Yifan Shi, Kaixiang Yang, Mengzhi Wang, Zhiwen Yu, Huanqiang Zeng, Yang Hu   +5 more
wiley   +1 more source

Short‐Term Multi‐Horizon Line Loss Rate Forecasting of a Distribution Network Using Attention‐GCN‐LSTM

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Accurately predicting line loss rates is crucial for effective management in distribution networks, particularly for short‐term multihorizon forecasts ranging from 1 hour to 1 week. In this study, we propose attention‐GCN–LSTM, a novel method that integrates graph convolutional networks (GCN), long short‐term memory (LSTM) and a three‐level ...
Jie Liu, Yijia Cao, Yong Li, Yixiu Guo, Wei Deng   +4 more
wiley   +1 more source

Robust Partial Multi‐Label Learning Under Dual Noise via Joint Subspace Learning

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Partial Multi‐label Learning (PML) deals with the ambiguity where each instance is annotated with a set of candidate labels, and only a subset of which is valid. While existing PML methods focus primarily on label disambiguation, they often rely on the assumption of a clean feature space.
Yuanjian Zhang, Zhanbo Fang, Tianna Zhao, Duoqian Miao, Witold Pedrycz   +4 more
wiley   +1 more source

ANPGT: Towards Adaptive Node Property Extraction and Integration

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Graph transformers (GTs) with elaborate positional/structural encodings (PEs/SEs) have excelled in graph representation learning, especially in graph‐level tasks. However, their potential in large‐scale node classification remains untapped for several reasons: (i) Current PEs/SEs are insufficient in modelling large‐scale real‐world graphs ...
Qin Chen, Yuanyi Ren, Guojie Song, Liang Wang, Bo Zheng   +4 more
wiley   +1 more source

MIDAS: a methodological framework for high‐speed high‐energy diffraction microscopy data reduction. Part I: methodology

Acta Crystallographica Section A, EarlyView.
This paper details the complete methodological framework implemented in the MIDAS software for processing high‐energy diffraction microscopy (HEDM) data. We describe the specific algorithms, coordinate systems and physical models used for both far‐field and near‐field HEDM analysis.
Hemant Sharma, Jun-Sang Park, Peter Kenesei   +2 more
wiley   +1 more source

The effect of nearby listings on house sale prices in Sydney: A spatio‐temporal regularization approach

Real Estate Economics, EarlyView.
Abstract We estimate the price impact of very nearby concurrently listed properties in the Sydney housing market and assess their competition effects. We apply a hedonic model with spatiotemporal effects regularized via a graph Laplacian prior at the month‐by‐SA2 regional level to seven SA4 subregions of metropolitan Sydney. The model structure enables
Willem P. Sijp, Mengheng Li
wiley   +1 more source

Complementarity in alliances: How strategic compatibility and hierarchy promote efficient cooperation in international security

American Journal of Political Science, EarlyView.
Abstract How can defense alliances reap the efficiency gains of working together when coordination and opportunism costs are high? Although specializing as part of a collective comes with economic and functional benefits, states must bargain over the distribution of those gains and ensure the costs of collective action are minimized.
J. Andrés Gannon
wiley   +1 more source