Results 141 to 150 of about 5,438,478 (196)

Fault Diagnosis Method for DC Current Transformers Based on Deep Learning Hybrid Model

Vector: The Journal of Engineering, Volume 2027, Issue 1, January/December 2027.
Aiming at the problems of scarce fault samples, strong noise interference and complex feature coupling in the current DCCT fault diagnosis process, a DCCT fault diagnosis method based on a hybrid deep learning model is proposed. The performance of the proposed method is verified through experiments.
Cai Xu, Geng Chen, Site Li, Xinwei Zhang, Rigong Te   +4 more
wiley   +1 more source

Hyperspectral Multilevel GCN and CNN Feature Fusion for Change Detection

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Hyperspectral image (HSI) change detection focuses on identifying differences in multitemporal HSIs. Graph convolutional networks (GCNs) have demonstrated greater promise than convolutional neural networks (CNNs) in remote sensing, particularly for ...
Chhaya Katiyar, Vidya Manian
doaj   +1 more source

CASARS Recommender Systems: A Systematic Review on Methods, Datasets, Limitations, and Future Directions

WIREs Data Mining and Knowledge Discovery, Volume 16, Issue 4, December 2026.
This paper presents the results of a systematic literature review on recommender systems that simultaneously incorporate the context‐aware and session‐aware recommendation paradigms (CASARS). To provide an overview of this specific research area, our review investigated: (1) which techniques have been employed to model contextual preference from the ...
Matheus Henrique Cecilio Leme, Vinicius Sylvestre Simm, Douglas Rorie Tanno, Marcos Aurelio Domingues   +3 more
wiley   +1 more source

Artificial Intelligence‐Supported Adaptive Flipped Learning and Changes in Autonomy, Competence, Relatedness and Novelty in Higher Education: A Quasi‐Experimental Study

European Journal of Education, Volume 61, Issue 4, December 2026.
ABSTRACT This quasi‐experimental study examined whether AI‐supported Adaptive Flipped Learning (AFL) was associated with psychological need and novelty‐related experiences in 311 university students (AFL: 164; comparison: 147) across 16 classes.
Alberto Ferriz‐Valero, Ricardo Sánchez‐Gil‐Machín, Salvador García‐Martínez, Nuria Molina‐García, Alberto Real‐Fernández, Salvador Baena‐Morales   +5 more
wiley   +1 more source

graph convolutional network(GCN)

Farumashia, 2021
openaire   +1 more source

A Network‐Enhanced Supervised Learning Framework for Early Prediction of Corruption Risk Indicators in Public Procurement Data

Expert Systems, Volume 43, Issue 12, December 2026.
ABSTRACT A tender receiving only one offer (single bidding) is generally recognized as a sign of restricted competition and a potential corruption risk indicator. Existing corruption risk models rely predominantly on ex post information, limiting their usefulness for early stage prediction.
Kostas Loumponias, Andreas Kosmatopoulos, Foivos Katsetsiadis, Theodora Tsikrika, Stefanos Vrochidis, Ioannis Kompatsiaris   +5 more
wiley   +1 more source

Multimodal Machine Learning and AI‐Accelerated Electrocatalytic CO2 Reduction Towards Self‐Interpretable Discovery Loops

ChemSusChem, Volume 19, Issue 21, 12 November 2026.
Artificial intelligence and machine learning (AI/ML) are reshaping electrochemical CO2 reduction (CO2RR) by linking active site, dynamic interfaces, operating conditions, and performance across scales. This review highlights how interpretable models for understanding operando data, establishing knowledge frameworks, and self‐driving laboratories enable
Shuhao Wang, Dazhi Yao, Aoni Xu, Qian Sun, Chuan Zhao   +4 more
wiley   +1 more source

Contextual Semantic Pattern Recognition for Mental Health Monitoring Using ClinicalBERT Transformers

Brain and Behavior, Volume 16, Issue 11, November 2026.
ABSTRACT Purpose This study aimed to develop an interpretable ClinicalBERT‐based framework for mental health monitoring using structured clinical data. Method Because the Mental Health Diagnosis and Treatment Monitoring dataset contains structured patient attributes rather than free‐text clinical narratives, a structured‐to‐text transformation module ...
Junjun Sun
wiley   +1 more source

Advanced Demand Prediction for Demand‐Responsive Transit (DRT) Systems: Integrating Graph Convolutional Networks and Deep Learning Techniques

Engineering Reports, Volume 8, Issue 11, November 2026.
This study develops a graph‐based deep learning framework to predict short‐term demand in demand‐responsive transit systems. Using real‐world data from Kalamazoo's Metro Connect, the model supports service zone optimization and infrastructure planning by accurately forecasting spatial–temporal passenger demand with high resolution.
Diana Al‐Nabulsi, Jun‐Seok Oh, Valerian Kwigizile   +2 more
wiley   +1 more source

Multimodal Deep Learning Approach Using Laser Doppler Flowmetry, Fluorescence Spectroscopy, and Clinical Data for Multi‐Class Mental Health and Severity Classification

Engineering Reports, Volume 8, Issue 11, November 2026.
X‐DyFGate introduces adaptive cross‐modal fusion of physiological and clinical information for personalized mental health assessment. The framework combines cross‐attention, dynamic feature gating, and interpretable multimodal learning to achieve highly accurate and clinically meaningful predictions.
Kavitha Suresh Jayasree, Nagarajan Bharanidharan   +1 more
wiley   +1 more source