Results 51 to 60 of about 350 (134)

Deep Quake Dynamics: A Multimodal Fault‐Aware Approach to Earthquake Magnitude and Occurrence Time Forecasting

Geoscience Data Journal, Volume 13, Issue 2, April 2026.
EQMT integrates earthquake catalog data, fault‐network geometry, engineered features, and graph embeddings in a unified framework for forecasting earthquake magnitude and occurrence time. The framework is designed to reflect inter‐fault spatial dependencies together with temporal seismic patterns, addressing limitations of approaches based only on ...
Kiymet Kaya, Murat Sahin, Furkan Mangir, Alp Baris Beydemir, Cenk Yaltirak, Sule Gunduz Oguducu   +5 more
wiley   +1 more source

Coil Sketching for Fast and Efficient 4D Lung MRI Reconstruction

Magnetic Resonance in Medicine, Volume 95, Issue 4, Page 2241-2253, April 2026.
ABSTRACT Purpose To develop and evaluate a memory‐efficient and accelerated reconstruction framework for respiratory‐resolved 4D lung MRI using coil sketching and Toeplitz approximation, enabling high‐quality motion‐compensated low‐rank (MoCo‐LR) reconstructions on clinically accessible GPU hardware.
Joseph W. Plummer, Pierre Daudé, Anastasia Tsakirellis, Jordan Taylor, Joel Moss, Rajiv Ramasawmy, Ahsan Javed, Adrienne E. Campbell‐Washburn   +7 more
wiley   +1 more source

Application of Variational Autoencoder‐Based Clustering for Geophysical Fluid Circulations With Small Sample Size

Journal of Geophysical Research: Machine Learning and Computation, Volume 3, Issue 2, April 2026.
Abstract The variational autoencoder (VAE), a deep generative model, can extract a good feature representation for clustering from complex data; however, the use of this algorithm in the geophysical fluid circulation has been limited. The sample size for a geophysical phenomenon is generally small because of a large dimensional size, especially for ...
Kunihiro Aoki, Hideyuki Nakano, Nariaki Hirose, Norihisa Usui, Kei Sakamoto, Takahiro Toyoda, Shogo Urakawa, Yuma Kawakami   +7 more
wiley   +1 more source

Spectral Decomposition of Chemical Semantics for Activity Cliffs‐Aware Molecular Property Prediction

Advanced Science, Volume 13, Issue 13, 3 March 2026.
PrismNet mimics chemical intuition by functioning as a computational prism, refracting molecular graphs into complementary semantic views and spectral frequencies. This dual‐decomposition strategy effectively captures both global topologies and subtle “activity cliff” perturbations.
Chaoyang Xie, Junhu Xu, Guangyi Huang, Shihang Wang, Mutian He, Xinyu Dong, Huiyang Hong, Xiaojun Yao, Qi Wang, Yuquan Li   +9 more
wiley   +1 more source

Multi‐View Biomedical Foundation Models for Molecule‐Target and Property Prediction

Advanced Science, Volume 13, Issue 14, 9 March 2026.
Molecular foundation models can provide accurate predictions for a large set of downstream tasks. We develop MMELON, an approach that integrates pre‐trained graph, image, and text foundation models and validate our multi‐view model on over 120 tasks, including GPCR binding.
Parthasarathy Suryanarayanan, Yunguang Qiu, Shreyans Sethi, Diwakar Mahajan, Hongyang Li, Yuxin Yang, Elif Eyigoz, Aldo Guzmán‐Sáenz, Daniel E. Platt, Timothy H. Rumbell, Kenney Ng, Sanjoy Dey, Myson Burch, Bum Chul Kwon, Pablo Meyer, Feixiong Cheng, Jianying Hu, Joseph A. Morrone   +17 more
wiley   +1 more source

Multivariate Contrastive Predictive Coding with Sliding Windows for Disease Prediction from Electronic Health Records

Advanced Intelligent Systems, Volume 8, Issue 3, March 2026.
Adaptive multi‐indicator contrastive predictive coding is introduced as a self‐supervised pretraining framework for multivariate EHR time series. An adaptive sliding‐window algorithm and 2D convolutional neural network encoder capture localized temporal patterns and global indicator dependencies, enabling label‐efficient disease prediction that ...
Hongxu Yuan, Xiaozhu Jing, Yuzheng Yan, Wuman Luo   +3 more
wiley   +1 more source

Optimizing the Evaluation Matrix for Cloud‐Edge Clock Synchronization Strategies: A Multi‐Modal Fuzzy‐PSO Enhanced AHP Method

Engineering Reports, Volume 8, Issue 3, March 2026.
This work introduces FuzzyMPsoAhp, a novel method that overcomes AHP limitations in cloud‐edge clock synchronization. It achieves an 43.3% lower consistency ratio than GaAhp, providing a practical and efficient tool for evaluating synchronization strategies ABSTRACT The traditional analytic hierarchy process (AHP) has significant limitations in ...
Zhang Weiran, Hou Yanhong
wiley   +1 more source

HADA: A Hybrid Anomaly Detection Approach Using Unsupervised Machine Learning

Engineering Reports, Volume 8, Issue 3, March 2026.
Overview of HADA, an unsupervised fraud detection pipeline that preprocesses and scales transaction data, applies PCA for dimensionality reduction, scores anomalies using Isolation Forest, selects anomalous transactions via thresholding, and clusters the selected anomalies using Agglomerative Hierarchical Clustering (AHC) to produce interpretable ...
Francis Thiong'o, Lawrence Nderu, Ronald Waweru Mwangi, Isaac Nyabisa Oteyo   +3 more
wiley   +1 more source

Untamed: Unconstrained Tensor Decomposition and Graph Node Embedding for Cortical Parcellation

Human Brain Mapping, Volume 47, Issue 4, March 2026.
Using the proposed automated Untamed atlas generation pipeline, the resulting atlas achieves higher or comparable task contrast alignment relative to 14 baseline atlases. Ablation studies further show that incorporating spatial maps from NASCAR tensor decomposition yields higher resting‐state functional connectivity homogeneity compared to atlases ...
Yijun Liu, Jian Li, Jessica L. Wisnowski, Richard M. Leahy   +3 more
wiley   +1 more source

Micapipe: A pipeline for multimodal neuroimaging and connectome analysis. [PDF]

Neuroimage, 2022
Cruces RR, Royer J, Herholz P, Larivière S, Vos de Wael R, Paquola C, Benkarim O, Park BY, Degré-Pelletier J, Nelson MC, DeKraker J, Leppert IR, Tardif C, Poline JB, Concha L, Bernhardt BC.   +15 more
europepmc   +1 more source