Results 71 to 80 of about 1,404 (207)

Hypergraph neural networks: from signal processing to convolution, u-nets and beyond

Arce, Gonzalo R.Qian, WeiNetwork data has gained significant attention in signal processing and machine learning communities. Existing research mainly centers on simple graphs, which depict only pairwise connections.
Wang, Fuli
core   +1 more source

Lightweight Hybrid Wafer Defect Pattern Network Based on Feedforward Efficient Attention

CAAI Transactions on Intelligence Technology, Volume 11, Issue 1, Page 149-166, February 2026.
ABSTRACT With the increase of semiconductor integration density, in order to cope with the increase of wafer defect complexity and types, especially the low recognition accuracy of overlapping mixed defects and unknown wafer defects, this study proposes a lightweight model for wafer defect detection called LightWMNet.
Zhiqiang Hu, Yiquan Wu
wiley   +1 more source

Stability Analysis of Different Quaternion‐Valued Impulsive BAM Neural Networks With Unknown Parameters and Time‐Varying Delays

Engineering Reports, Volume 8, Issue 1, January 2026.
This work tackles the unresolved stability problem of heterogeneous quaternion‐valued BAM neural networks plagued by unknown parameters, time‐varying delays, and impulses. By synergizing Lyapunov theory with inequality techniques, we establish rigorous, yet practical, global stability conditions.
Xi Long, Yaqin Li
wiley   +1 more source

Person Re-identification by Multi-hypergraph Fusion

, 2017
Matching people across nonoverlapping cameras, also known as person re-identification, is an important and challenging research topic. Despite its great demand in many crucial applications such as surveillance, person re-identification is still far ...
Chen, Xiaojing (xchen010@ucr.edu), Chen, Xiaojing, An, Le, Li, Xuelong, Yang, Songfan   +4 more
core   +1 more source

IntelliMetro‐Hybrid: A Machine Learning and Deep Learning Fusion Model for Economic Optimization in Smart Metro Systems

Transactions on Emerging Telecommunications Technologies, Volume 37, Issue 1, January 2026.
IntelliMetro‐Hybrid is an intelligent fusion framework that integrates machine learning (ML) and deep learning (DL) for real‐time anomaly detection and economic optimization in smart metro systems. The model combines tree‐based feature extraction (Random Forest, XG Boost) with a deep neural classifier to effectively handle imbalanced, heterogeneous ...
Sijin Peng, Yongchang Wei, Zhigang Sun, Yong Chen, Jiang Huang, Hao Chen, Liuyi Chen   +6 more
wiley   +1 more source

Hypergraph Learning: From Algorithms to Applications

Graphs are a general language for describing and modeling interconnected systems. To learn graph data, Graph Neural Networks (GNNs) have been introduced.
Saifuddin, Khaled Mohammed
core   +1 more source

Bi-View Contrastive Learning with Hypergraph for Enhanced Session-Based Recommendation

Information
Session-based recommendation (SBR) aims to predict a user’s next interests based on their actions in a single visit. Recent methods utilize graph neural networks to study the pairwise relationship of item transfers, yet these often overlook the complex ...
Zijun Wang, Lai Wei
doaj   +1 more source

Tensorized Hypergraph Neural Networks

Hypergraph neural networks (HGNN) have recently become attractive and received significant attention due to their excellent performance in various domains. However, most existing HGNNs rely on first-order approximations of hypergraph connectivity patterns, which ignores important high-order information.
Maolin Wang 0001, Yaoming Zhen, Yu Pan 0005, Yao Zhao 0001, Chenyi Zhuang, Zenglin Xu, Ruocheng Guo, Xiangyu Zhao 0001   +7 more
openaire   +2 more sources

Unsupervised Anomaly Detection Based on LLM for Heterogeneous Multivariate Time Series in the Intelligent Computing Center

IET Communications, Volume 20, Issue 1, January/December 2026.
This paper proposes a novel anomaly detection framework for non‐independent and identically distributed (non‐IID) data from heterogeneous devices. First, we introduce a chain of thought metric alignment and ranking mechanism based on a large language model to meet the data heterogeneity challenge.
Xingguo Jiang, Yue Wang, Chunpeng Wu, Xiaohui Wang, Hongyin Chen, Zhenying Tai, Hao Yue, Chang Liu   +7 more
wiley   +1 more source

Multiview Hypergraph Fusion Network for Change Detection in High-Resolution Remote Sensing Images

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Currently, convolutional neural networks and transformers have been the dominant paradigms for change detection (CD) thanks to their powerful local and global feature extraction capabilities. However, with the improvement of resolution, spatial, spectral,
Xue Zhao, Kai Zhang, Feng Zhang, Jiande Sun, Wenbo Wan, Huaxiang Zhang   +5 more
doaj   +1 more source