DOU-Pose: Robust Camera-Based Visual Localization for Autonomous Vehicles in Repetitive and Low-Texture Intelligent Transportation Environments. [PDF]
Qiu X +7 more
europepmc +1 more source
KFO‐Atlas reveals how real‐world aromas are organized as structured mixtures rather than individual molecules. Building on these principles, KFO‐Gen, a generative AI framework, designs perceptually valid aroma formulations and reconstructs meat‐like aromas exclusively from plant‐derived odorants, providing a foundation for mixture‐level studies and AI ...
Jingzhi Zhang +5 more
wiley +1 more source
Distributed Kalman Filter with Maximum Correlation Entropy Criterion and Consensus Weighted Term Fusion. [PDF]
Feng X, Gao Z, Liu T.
europepmc +1 more source
High‐throughput Differential Dynamic Microscopy measures frequency‐resolved mechanical fingerprints from 3 to 10 μL$\umu{\rm L}$ mucus samples using only a few minutes of operator attention per sample. This automated analysis enables scalable mucus phenotyping for translational research by distinguishing mechanical heterogeneity among donors, disease ...
Feng Ling +18 more
wiley +1 more source
Determination of Larval Instars of <i>Ips hauseri</i> (Coleoptera: Curculionidae: Scolytinae), Using Kernel Density Estimation and Mixture Modeling of Head Capsule Widths. [PDF]
Jiao J +6 more
europepmc +1 more source
Grounded in real biological RNA‐seq data, the framework benchmarks ten differential transcript usage (DTU) methods across short‐read bulk, long‐read bulk, long‐read single‐cell, and long‐read spatial transcriptomics. By integrating reference transcript sets with ranked DTU results, the Transcript Set Enrichment Score (TSES) identifies data‐type ...
Chenxing Zhang +6 more
wiley +1 more source
Comparative Analysis of Algorithms for Extracting Frames from Unexplored Regions in Molecular Dynamics Simulations. [PDF]
Nagare A +7 more
europepmc +1 more source
Predicting Enzyme Turnover Numbers and Enabling Rational Enzyme Evolution
MCKcat, a deep learning framework combining multi‐scale convolution and cross‐attention, accurately predicts enzyme turnover number (kcat) by fusing sequence and reaction representations. It couples with rational design in a two‐step strategy for Bacillus aryabhattai laccase engineering, achieving a 75% positive rate with synergistically enhanced ...
Fengya Ge +6 more
wiley +1 more source
Faster Hamiltonian Monte Carlo by learning leapfrog scale: an offline randomized solution. [PDF]
Wu C, Pudlo P, Robert CP, Stoehr J.
europepmc +1 more source
Simultaneous Tumor Segmentation, Image Restoration, and Blur Kernel Estimation in PET Using Multiple Regularizations. [PDF]
Li L, Wang J, Lu W, Tan S.
europepmc +1 more source

