anndataR improves interoperability between R and Python in single-cell transcriptomics. [PDF]
Deconinck L +10 more
europepmc +1 more source
This work proposes MDSC, an unsupervised low‐light enhancement framework integrating three core innovations: detail‐aware smoothing, multipath decomposition, and synergistic correction. It suppresses noise, handles rapid illumination variations, and prevents reflectance‐contrast amplification inherent to Retinex separation.
Yong Cheng +6 more
wiley +1 more source
Learning semantic similarity from sentence pairs using hybrid features centric approach and explainable siamese neural networks. [PDF]
Zhao W, Hu C.
europepmc +1 more source
An agentic AI‐driven decision‐support framework for prosumers is proposed, integrating PV generation, load profiling, and multihorizon optimization within a four‐agent architecture. The approach significantly reduces grid dependence, enhances self‐sufficiency and prevents system oversizing.
Adela BÂRA, Simona‐Vasilica OPREA
wiley +1 more source
A lightweight monocular perception framework generates high‐fidelity depth maps and integrates YOLOv8 detection to estimate object‐wise distances from a single RGB image. Evaluated on KITTI and the proposed D‐Far250 dataset, the system demonstrates accurate long‐range perception up to 250 m while maintaining real‐time performance, enabling scalable ...
Faseeh Muhammad +5 more
wiley +1 more source
A multi-context fusion-aware graph modelling for group activity recognition using pose-conditioned spatial encoding and actor relations. [PDF]
Tejonidhi MR +4 more
europepmc +1 more source
Robust Representation Learning for Clean Feature Discovery in Incomplete Multi‐View Clustering
Robust feature discovery in incomplete multi‐view clustering is achieved by coupling RPCA‐based clean representation recovery with neural‐network‐assisted graph learning. The resulting RIMVC framework constructs cleaner and more discriminative graph‐structured representations from incomplete and noisy multi‐view data, improving clustering robustness ...
Ping Hu +4 more
wiley +1 more source
Class-adaptive oracle-free metamorphic test case prioritization framework for vision-based deep neural networks. [PDF]
Li J, Mohamad R, Ahmad J.
europepmc +1 more source
A Language‐Guided Multimodal Foundation Model for Zero‐Shot and Multi‐Task Brain Signal Analysis
METIS aligns brain signals with natural‐language instructions to enable zero‐shot and multi‐task brain signal analysis. Pretrained on over 70 000 h of EEG and iEEG recordings, it generalizes across sleep stage classification, epilepsy detection, and neurological disorder diagnosis, providing a scalable foundation model for clinically meaningful brain ...
Mingzhi Chen +3 more
wiley +1 more source
Ten simple rules for making the supplement increase your paper's impact. [PDF]
Grimm V, Berger U, Mammola S.
europepmc +1 more source

