Results 81 to 90 of about 3,626 (230)

Time Series Embedding Methods for Classification Tasks: A Review

open access: yesExpert Systems, Volume 42, Issue 11, November 2025.
ABSTRACT Time series analysis has become crucial in various fields, from engineering and finance to healthcare and social sciences. Due to their multidimensional nature, time series often need to be embedded into a fixed‐dimensional feature space to enable processing with various machine learning algorithms.
Habib Irani   +3 more
wiley   +1 more source

RESP2: An Uncertainty Aware Multi‐Target Multi‐Property Optimization AI Pipeline for Antibody Discovery

open access: yesAdvanced Science, Volume 12, Issue 38, October 13, 2025.
RESP2, an enhanced antibody discovery pipeline for multi‐target and multi‐property optimization, identifies antibodies with optimized developability and broad affinity to multiple antigen variants. In silico evaluation shows RESP2 outperforms leading AI methods, achieving ≥85% success rates.
Jonathan Parkinson   +3 more
wiley   +1 more source

diPaRIS: Dynamic and Interpretable Protein‐RNA Interactions Prediction With U‐Shaped Network and Novel Structure Encoding

open access: yesAdvanced Science, Volume 12, Issue 38, October 13, 2025.
This study presents diPaRIS, a deep learning method designed to predict dynamic protein‐ RNA interactions with enhanced accuracy. By integrating RNA structures in vivo through a novel encoding scheme for nucleotide correlations, diPaRIS improves the interpretability of binding motifs and outperforms current state‐of‐the‐art methods across multiple ...
Lishen Zhang   +5 more
wiley   +1 more source

Identifying Small‐Displacement Stereotypical Behavior of Captive Slow Lorises Based on AnimalYOLO‐Bytetrack Network

open access: yesEcology and Evolution, Volume 15, Issue 10, October 2025.
This study analyzes small‐displacement stereotypical behaviors of multiple captive slow lorises and proposes a new method that utilizes automatic tracking and the analysis of the cyclical changes in movement amplitude. By employing the AnimalYOLO‐Bytetrack multi‐target tracking network to monitor and quantify the movements of slow lorises, a detection ...
Ziqi Yang   +12 more
wiley   +1 more source

Optimal view detection for ultrasound-guided supraclavicular block using deep learning approaches. [PDF]

open access: yesSci Rep, 2023
Jo Y   +7 more
europepmc   +1 more source

Enhancing Diabetes Management With CRIBC: A Novel NER Model for Constructing A Comprehensive Chinese Medical Knowledge Graph

open access: yesEngineering Reports, Volume 7, Issue 10, October 2025.
This study proposes CRIBC, an advanced Named Entity Recognition (NER) model tailored for Chinese medical text processing. By integrating Chinese‐RoBERTa‐WWM‐EXT with BiLSTM‐CRF and IDCNN, CRIBC enables more accurate entity extraction and knowledge representation.
Yiqing Xu   +2 more
wiley   +1 more source

Anatomy‐Guided, Modality‐Agnostic Segmentation of Neuroimaging Abnormalities

open access: yesHuman Brain Mapping, Volume 46, Issue 14, 01 October 2025.
Region ModalMix is a data augmentation strategy that leverages brain parcellations to improve MRI‐based tumor segmentation under missing modality conditions. By mixing anatomical regions across available modalities during training, our framework enhances model robustness, supporting more reliable decision making with incomplete multimodal neuroimaging ...
Diala Lteif   +4 more
wiley   +1 more source

Deep Learning for fODF Estimation in Infant Brains: Model Comparison, Ground‐Truth Impact, and Domain Shift Mitigation

open access: yesHuman Brain Mapping, Volume 46, Issue 14, 01 October 2025.
We quantify domain‐shift impacts of three state‐of‐the‐art deep learning models for fiber orientation estimation in dMRI of neonatal and baby brains, across age, scanner, input variations, target output ground truths, and demonstrate how fine‐tuning and data harmonization strategies improve model robustness for clinical and research applications ...
Rizhong Lin   +6 more
wiley   +1 more source

Home - About - Disclaimer - Privacy