Explaining the Origin of Negative Poisson's Ratio in Amorphous Networks With Machine Learning
Advanced Intelligent Discovery, EarlyView.This review summarizes how machine learning (ML) breaks the “vicious cycle” in designing auxetic amorphous networks. By transitioning from traditional “black‐box” optimization to an interpretable “AI‐Physics” closed‐loop paradigm, ML is shown to not only discover highly optimized structures—such as all‐convex polygon networks—but also unveil hidden ...
Shengyu Lu, Xiangying Shen
wiley +1 more source
Functional near-infrared spectroscopy identifies neural biomarkers of burnout in active-duty Police officers. [PDF]
Sci RepChen WY +6 more
europepmc +1 more source
Advanced Intelligent Discovery, EarlyView.The authors develop a deep learning model for real‐time tracking of wound progression. The deep learning framework maps the nonlinear evolution of a time series of images to a latent space, where they learn a linear representation of the dynamics. The linear model is interpretable and suitable for applications in feedback control.
Fan Lu +11 more
wiley +1 more source
Discriminating models of trait evolution. [PDF]
EvolutionRoa Lozano J +4 more
europepmc +1 more source
Overcoming the Nyquist Limit in Molecular Hyperspectral Imaging by Reinforcement Learning
Advanced Intelligent Discovery, EarlyView.Explorative spectral acquisition guide automatically selects informative spectral bands to optimize downstream tasks, outperforming full‐spectrum acquisition. The selected hyperspectral data are used for tasks such as unmixing and segmentation. BandOptiNet encodes selection states and outputs optimal bands to guide spectral acquisition. Recent advances
Xiaobin Tang +4 more
wiley +1 more source
Deep learning-based approach for differential diagnosis of odontogenic cysts from histopathological images. [PDF]
Med Oral Patol Oral Cir BucalTorul D +6 more
europepmc +1 more source
Advanced Intelligent Systems, Volume 7, Issue 3, March 2025.OxSpred, an eXtreme‐Gradient‐Boosting‐‐based supervised learning model, accurately annotates oxidative stress in innate immune cells at the single‐cell level, providing interpretable embeddings with significant biological relevance. This innovative tool revolutionizes the understanding of innate immune cell functions during inflammation and enhances ...
Po‐Yuan Chen, Tai‐Ming Ko
wiley +1 more source
Simulation-Guided Interpretable Fault Diagnosis of Hydraulic Directional Control Valves Under Limited Fault Data Conditions. [PDF]
Sensors (Basel)Xia Y, Xiao A, Xiao H, Zhao X, Liu H.
europepmc +1 more source
Advanced Intelligent Systems, Volume 7, Issue 3, March 2025.Quantitative phase maps of single cells recorded in flow cytometry modality feed a hierarchical architecture of machine learning models for the label‐free identification of subtypes of ovarian cancer. The employment of a priori clinical information improves the classification performance, thus emulating the clinical application of liquid biopsy during ...
Daniele Pirone +11 more
wiley +1 more source
Clinical validation of lightweight CNN architectures for reliable multi-class classification of lung cancer using histopathological imaging techniques. [PDF]
Sci RepRaza A, Hanif F, Mohammed HA.
europepmc +1 more source