Results 221 to 230 of about 4,772,239 (326)

High‐Fidelity Synthetic Raman Spectra Generation for Sinter Basicity Prediction Using β$$ \beta $$‐Variational Autoencoders

Journal of Raman Spectroscopy, EarlyView.
A β$$ \beta $$‐variational autoencoder with β$$ \beta $$ = 0.1 generates high‐fidelity synthetic Raman spectra of industrial sinter with a 16‐fold improvement in spectral fidelity over SMOTE‐based augmentation (KL divergence: 0.0075 vs. 0.121), enabling reliable basicity prediction (R2 = 0.83) from limited labeled datasets.
Marjorie Ariele Pereira, Daniel Cruz Cavalieri, Adilson Ribeiro Prado, Cassius Zanetti Resende, Erica Simões Rodrigues   +4 more
wiley   +1 more source

HiSTaR: identifying spatial domains with hierarchical spatial transcriptomics variational autoencoder. [PDF]

J Transl Med
Yu J, Yuan J, Yi Q, Ye Z, Xu P, Liu W.
europepmc   +1 more source

Raman Spectroscopy and Generative Variational Autoencoders for Metallurgical Coke Quality Prediction

Journal of Raman Spectroscopy, EarlyView.
An integrated soft sensor framework combining standardized Raman spectroscopy, synergy‐vector feature selection, variational autoencoder‐based data augmentation, and regression models (kNN, PLS, and SVR) predicts metallurgical coke quality (CSR and DI).
Pedro Henrique Agrimpio Coutinho, Daniel Cruz Cavalieri, Adilson Ribeiro Prado   +2 more
wiley   +1 more source

Promises and limitations of deep learning for predicting knee osteoarthritis progression from medical imaging: A systematic review

Knee Surgery, Sports Traumatology, Arthroscopy, EarlyView.
Abstract Purpose To systematically evaluate the performance, methodological quality, and translational barriers of deep learning (DL) models for predicting knee osteoarthritis (KOA) progression from medical imaging. Methods Following PRISMA guidelines, we searched PubMed, Scopus, and Web of Science (inception to June 2026) for peer‐reviewed studies ...
Amna Gillani, Rüdiger von Eisenhart‐Rothe, Klaus Woertler, Michael T. Hirschmann, Daniel Rueckert, Florian Hinterwimmer   +5 more
wiley   +1 more source

A Transformer-Based Variational Autoencoder for Training Data Generation in Spindle Motor Vibration-Based Anomaly Detection. [PDF]

Sensors (Basel)
Kim J, Hwang Y.
europepmc   +1 more source

From Planar to 3D Nanophotonic Lenses: Advancing Design, Fabrication, and Applications

Laser &Photonics Reviews, EarlyView.
Three‐dimensional nanophotonic lenses are enabled by an integrated workflow that links design parameterization, full‐wave electromagnetic simulation, computational optimization, and freeform fabrication. This Review summarizes how these tools expand optical design freedom beyond a single patterned plane by enriching the local meta‐atom response and ...
Wei Zhu, Lyudmila V. Goncharova, Eric Johlin   +2 more
wiley   +1 more source

MLN2SVG: domain-aware spatially variable gene detection using contrastive variational autoencoder and multi-level neighbor search. [PDF]

Brief Bioinform
Hussain S, Ayoub M, Ye F, Liu X.
europepmc   +1 more source

Artificial Intelligence for Identifying Tumor‐Reactive CD8+ T Cells: Biological Principles, Computational Advances, and Future Directions

Med Research, EarlyView.
This review details a three‐stage paradigm shift for tumor‐reactive CD8+ T‐cell identification: decoding transcriptomic states, deciphering clonal functional efficacy, and molecular‐level therapeutic TCR design. Addressing translational hurdles and generative AI “scientific blind spots”—such as missing catch bonds—we present a visionary roadmap.
Chao Yang, Yingying Sun, Yan Zhang, Yifen Shi, Zhiwen Shi   +4 more
wiley   +1 more source

Early damage detection in bridges using a variational autoencoder-based hybrid unsupervised learning framework. [PDF]

Sci Rep
Pakzad SS, Masoodi AR.
europepmc   +1 more source

Artificial Intelligence‐Driven Natural Product Drug Discovery: From Computational Genome Mining to Clinical Translation

Medicinal Research Reviews, EarlyView.
ABSTRACT Natural products (NPs) have historically yielded numerous therapeutic agents, yet their integration into modern drug discovery has been constrained by chemical complexity, low abundance, laborious dereplication, and limited target annotation.
Antonio Lavecchia
wiley   +1 more source