Results 211 to 220 of about 82,326 (277)

Review of Memristors for In‐Memory Computing and Spiking Neural Networks

Advanced Intelligent Systems, EarlyView.
Memristors uniquely enable energy‐efficient, brain‐inspired computing by acting as both memory and synaptic elements. This review highlights their physical mechanisms, integration in crossbar arrays, and role in spiking neural networks. Key challenges, including variability, relaxation, and stochastic switching, are discussed, alongside emerging ...
Mostafa Shooshtari, Teresa Serrano‐Gotarredona, Bernabé Linares‐Barranco   +2 more
wiley   +1 more source

Multi-Feature Unsupervised Domain Adaptation (M-FUDA) Applied to Cross Unaligned Domain-Specific Distributions in Device-Free Human Activity Classification. [PDF]

Sensors (Basel)
Hassan M, Kelsey T.
europepmc   +1 more source

Robust Dysarthric Speech Recognition with GAN Enhancement and LLM Correction

Advanced Intelligent Systems, EarlyView.
This study tackles dysarthric speech recognition by combining generative adversarial network (GAN)‐generated synthetic data with large language model (LLM)‐based error correction. The approach integrates three key elements: an improved CycleGAN to generate synthetic dysarthric speech for data augmentation, a multimodal automatic speech recognition core
Yibo He, Kah Phooi Seng, Chee Shen Lim, Li Minn Ang   +3 more
wiley   +1 more source

Reducing Cross-Sensor Domain Gaps in Tactile Sensing via Few-Sample-Driven Style-to-Content Unsupervised Domain Adaptation. [PDF]

Sensors (Basel)
Jing X, Qian K.
europepmc   +1 more source

Upsampling DINOv2 Features for Unsupervised Vision Tasks and Weakly Supervised Materials Segmentation

Advanced Intelligent Systems, EarlyView.
Feature from recent image foundation models (DINOv2) are useful for vision tasks (segmentation, object localization) with little or no human input. Once upsampled, they can be used for weakly supervised micrograph segmentation, achieving strong results when compared to classical features (blurs, edge detection) across a range of material systems.
Ronan Docherty, Antonis Vamvakeros, Samuel J. Cooper   +2 more
wiley   +1 more source

Deep Learning-based Unsupervised Domain Adaptation via a Unified Model for Prostate Lesion Detection Using Multisite Biparametric MRI Datasets. [PDF]

Radiol Artif Intell
Li H, Liu H, von Busch H, Grimm R, Huisman H, Tong A, Winkel D, Penzkofer T, Shabunin I, Choi MH, Yang Q, Szolar D, Shea S, Coakley F, Harisinghani M, Oguz I, Comaniciu D, Kamen A, Lou B.   +18 more
europepmc   +1 more source

GraphNeuralCloth: A Graph‐Neural‐Network‐Based Framework for Non‐Skinning Cloth Simulation

Advanced Intelligent Systems, EarlyView.
This study presents a cloth motion capture system and a point‐cloud‐to‐mesh processing method to support the prediction of real‐world fabric deformation. GraphNeuralCloth, a graph neural‐network (GNN)‐based framework is also proposed to estimate the cloth morphology change in real time.
Yingqi Li, Xiaomei Wang, Xiaoqi Song, Chenchen Fan, Bohao Zhu, Jianan Peng, Qixin Liang, James Lam, Kam‐Yim Sze, Ka‐Wai Kwok   +9 more
wiley   +1 more source

Building an Intelligent Cardiovascular System Platform: Embedding Artificial Intelligence across All Facets of Cardiovascular Medicine

Advanced Intelligent Systems, EarlyView.
This paper presents an integrated AI‐driven cardiovascular platform unifying multimodal data, predictive analytics, and real‐time monitoring. It demonstrates how artificial intelligence—from deep learning to federated learning—enables early diagnosis, precision treatment, and personalized rehabilitation across the full disease lifecycle, promoting a ...
Mowei Kong, Xingwei Zhao, Qiuting Li, Yang Yu, Chunxiang Zhang   +4 more
wiley   +1 more source

EXPLORING BACKDOOR ATTACKS IN OFF-THE-SHELF UNSUPERVISED DOMAIN ADAPTATION FOR SECURING CARDIAC MRI-BASED DIAGNOSIS. [PDF]

Proc IEEE Int Symp Biomed Imaging
Liu X, Xing F, Gaggin H, Kuo CJ, El Fakhri G, Woo J.   +5 more
europepmc   +1 more source

Deep Learning Methods for Assessing Time‐Variant Nonlinear Signatures in Clutter Echoes

Advanced Intelligent Systems, EarlyView.
Motion classification from biosonar echoes in clutter presents a fundamental challenge: extracting structured information from stochastic interference. Deep learning successfully discriminates object speed and direction from bat‐inspired signals, achieving 97% accuracy with frequency‐modulated calls but only 48% with constant‐frequency tones. This work
Ibrahim Eshera, Gaurav Duggal, Rolf Müller   +2 more
wiley   +1 more source