Results 51 to 60 of about 13,553 (263)
Autoencoder–Based Image Representation Learning with Kolmogorov–Arnold Networks
International Journal of Applied Mathematics and Computer ScienceAutoencoders are widely used for learning compact latent representations of images. While convolutional architectures dominate this area due to their ability to exploit spatial locality, recent developments in neural network design have introduced ...
Urbaniak Ilona Anna +2 more
doaj +1 more source
Advanced Intelligent Discovery, EarlyView.Deep learning‐based denoising models are applied to DNA data storage systems to enhance error reduction and data fidelity. By integrating DnCNN with DNA sequence encoding methods, the study demonstrates significant improvements in image quality and correction of substitution errors, revealing a promising path toward robust and efficient DNA‐based ...
Seongjun Seo +5 more
wiley +1 more source
Advanced Intelligent Discovery, EarlyView.Sequential multicolor fluorescence imaging in dynamic microsystems is constrained by acquisition speed and excitation dose. This study introduces a real‐time framework to reconstruct spectrally separated channels from reduced cross‐channel acquisitions (frames containing mixed spectral contributions).
Juan J. Huaroto +3 more
wiley +1 more source
Clustering stability evaluation method based on SSIM
Journal of Algorithms & Computational Technology, 2019 In the clustering validity analysis, three main methods including intra-class cohesion, inter-class separation, and artificial judgment index can be used to evaluate the clustering results.
Yan Zhu Hu +4 more
doaj +1 more source
Advanced Intelligent Systems, Volume 7, Issue 3, March 2025.The use of image quality metrics in combination with machine learning enables automatic image quality assessment for fluorescence microscopy images. The method can be integrated into the experimental pipeline for optical microscopy and utilized to classify artifacts in experimental images and to build quality rankings with a reference‐free approach ...
Elena Corbetta, Thomas Bocklitz
wiley +1 more source
A Hybrid Transfer Learning Framework for Brain Tumor Diagnosis
Advanced 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
Scene‐Customized Learning for Multi‐Depth 3D Phase‐Only Hologram Generation
Advanced Intelligent Systems, EarlyView.Scene‐customized geometric modeling constructs GM‐4K, a controllable 4K RGB‐D dataset for learning‐based multi‐depth hologram generation. By tuning intensity spectra and depth‐region sampling, the dataset reveals how training‐data statistics affect phase‐only hologram encoding and supports a spectral test framework for evaluating model generalization ...
Yanan Zhang +5 more
wiley +1 more source
Improving Measurement Bias of Structural Similarity Index (SSIM) using Absolute Difference Equation
Applications of Modelling and Simulation, 2022 Structural similarity index (SSIM) is a framework for assessing the perceptual quality from an image using the degrading and structural information of an image.
Muhammad Irfan Jaafar +2 more
doaj
Advanced Intelligent Systems, EarlyView.An AI‐enabled micromixing framework is developed by integrating cGAN with Bayesian optimization for predictive control of microrobot‐driven flow manipulation. Through this framework, the spatiotemporal evolution of micromixing is learned directly from experimental images, while rapid identification of optimized microrobot actuation strategies is ...
Dineshkumar Loganathan, Chia‐Yuan Chen
wiley +1 more source
Reversible Data Hiding Based on Structural Similarity Block Selection
IEEE Access, 2020 Reversible data hiding (RDH) methods are widely used in many privacy-sensitive real-time applications for digital images. As an efficient RDH method, prediction-error histogram (PEH) shifting technique has found wide application for its high efficiency ...
Kehao Wang +5 more
doaj +1 more source