Handwritten tax receipt recognition method based on improved DBNet and CRNN. [PDF]
Wei L, Sun J.
europepmc +1 more source
Rab1A Promotes Hepatic Steatosis by Suppressing Mitophagy via the Raf‐1/ERK1/2/PINK1 Signaling Axis
Why does fat accumulate in the liver? Our study reveals Rab1A as the molecular switch that silences the cell's mitochondrial cleanup crew. Turning Rab1A off reactivates mitophagy, clears excess fat, and reverses fatty liver disease in mice—offering a promising new therapeutic target for MASLD, a growing global health challenge.
Li Zhang +9 more
wiley +1 more source
Unlocking the silent signals: Motor kinematics as a new frontier in early detection of mild cognitive impairment. [PDF]
Nagamine T.
europepmc +1 more source
An Integrated NLP‐ML Framework for Property Prediction and Design of Steels
This study presents a data‐driven framework that uses language‐processing techniques to interpret steel processing descriptions and machine‐learning models to predict mechanical properties. By organising complex process histories into meaningful groups and enabling rapid property forecasts, the work supports faster, more informed steel design through ...
Kiran Devraju +5 more
wiley +1 more source
Development and preliminary evaluation of a computer-assisted assessment tool for Chinese prewriting skills in preschoolers. [PDF]
Liu Z +9 more
europepmc +1 more source
ML Workflows for Screening Degradation‐Relevant Properties of Forever Chemicals
The environmental persistence of per‐ and polyfluoroalkyl substances (PFAS) necessitates efficient remediation strategies. This study presents physics‐informed machine learning workflows that accurately predict critical degradation properties, including bond dissociation energies and polarizability.
Pranoy Ray +3 more
wiley +1 more source
Exploring Handwriting-Based Biomarkers for Alzheimer's Disease: Identifying Discriminative Features and Tasks to Enhance Diagnostic Accuracy. [PDF]
Akyürek Anacur C +2 more
europepmc +1 more source
Efficient Screening of Organic Singlet Fission Molecules Using Graph Neural Networks
A high‐throughput screening framework based on graph neural networks (GNNs) and multi‐level validation facilitates the identification of singlet fission (SF) candidates. By efficiently predicting excitation energies across 20 million molecules, and integrating TDDFT calculations, synthetic accessibility assessments, and GW+BSE calculations, this ...
Li Fu +5 more
wiley +1 more source
A 48-class handwritten dataset for the endangered chakma language. [PDF]
Ferdeous J +5 more
europepmc +1 more source
Ferroelectric Devices for In‐Memory and In‐Sensor Computing
Inspired by biological systems, in‐memory and in‐sensor computing overcome von Neumann bottlenecks. Ferroelectric devices can mimic synaptic functions and sense stimuli like light or force, therefore are ideal for these paradigms. This review introduces the ferroelectric devices applied for in‐memory and in‐sensor computing, covering their structures ...
Hong Fang +5 more
wiley +1 more source

