Results 251 to 260 of about 63,696 (324)

A Hybrid Transfer Learning Framework for Brain Tumor Diagnosis

open access: yesAdvanced Intelligent Systems, Volume 7, Issue 3, March 2025.
A novel hybrid transfer learning approach for brain tumor classification achieves 99.47% accuracy using magnetic resonance imaging (MRI) images. By combining image preprocessing, ensemble deep learning, and explainable artificial intelligence (XAI) techniques like gradient‐weighted class activation mapping and SHapley Additive exPlanations (SHAP), the ...
Sadia Islam Tonni   +11 more
wiley   +1 more source

Unlocking Gait Analysis Beyond the Gait Lab: High-Fidelity Replication of Knee Kinematics Using Inertial Motion Units and a Convolutional Neural Network. [PDF]

open access: yesArthroplast Today
Bini SA   +8 more
europepmc   +1 more source

Penalized Likelihood Regression in Reproducing Kernel Hilbert Spaces with Randomized Covariate Data

open access: green, 2010
Xiwen Ma   +5 more
openalex   +2 more sources

Recent Advancements in Topic Modeling Techniques for Healthcare, Bioinformatics, and Other Potential Applications

open access: yesAdvanced Intelligent Systems, EarlyView.
This article offers a comprehensive review of topic modeling techniques, tracing their evolution from inception to recent developments. It explores methods such as latent Dirichlet allocation, latent semantic analysis, non‐negative matrix factorization, probabilistic latent semantic analysis, Top2Vec, and BERTopic, highlighting their strengths ...
Pratima Kumari   +6 more
wiley   +1 more source

RefineCatDiff: Toward High‐Quality Medical Image Segmentation via a Categorical Diffusion Refinement Framework

open access: yesAdvanced Intelligent Systems, EarlyView.
This study proposes RefineCatDiff, a refinement framework for high‐quality medical image segmentation. By developing a categorical distribution‐based discrete diffusion process for refinement, the framework aligns well with the characteristics of image segmentation tasks. Experimental results on multiple datasets across different modalities demonstrate
Feng Liu   +8 more
wiley   +1 more source

Highly Efficient Classification of Time‐Series Based on Resistive Switching Cluster‐Assembled Materials

open access: yesAdvanced Intelligent Systems, EarlyView.
Cluster‐assembled nanocomposite devices are employed for the classification of neuronal traces, without any preprocessing of the input time‐series or prior training of the nonlinear devices. The classification method relies on the statistical analysis of the device's output time‐series, achieving higher classification accuracy compared to more energy ...
Filippo Profumo   +5 more
wiley   +1 more source

Home - About - Disclaimer - Privacy