Results 121 to 130 of about 86,509 (306)

All‐in‐One Analog AI Hardware: On‐Chip Training and Inference with Conductive‐Metal‐Oxide/HfOx ReRAM Devices

Advanced Functional Materials, EarlyView.
An all‐in‐one analog AI accelerator is presented, enabling on‐chip training, weight retention, and long‐term inference acceleration. It leverages a BEOL‐integrated CMO/HfOx ReRAM array with low‐voltage operation (<1.5 V), multi‐bit capability over 32 states, low programming noise (10 nS), and near‐ideal weight transfer.
Donato Francesco Falcone, Victoria Clerico, Wooseok Choi, Tommaso Stecconi, Folkert Horst, Laura Bégon‐Lours, Matteo Galetta, Antonio La Porta, Nikhil Garg, Fabien Alibart, Bert Jan Offrein, Valeria Bragaglia   +11 more
wiley   +1 more source

Mechanical Behavior and Fracture Mechanisms of MXene/PVDF Nanocomponsites: In Situ Characterization and Multiscale Analysis

Advanced Functional Materials, EarlyView.
Multiscale experiments and modeling reveal how Ti3C2Tx MXene nanosheets reinforce PVDF nanocomposites. An optimal MXene loading (∼1 wt.%) nearly doubles tensile strength through efficient stress transfer, flake alignment, and crack‐deflection mechanisms, transforming ductile polymer behavior into a controlled multi‐stage fracture pathway which aligns ...
Bita Soltan Mohammadlou, James FitzPatrick, Li Meng, Kateryna Shevchuk, Ahmad Najafi, Yury Gogotsi   +5 more
wiley   +1 more source

A Dual-Path Multi-Scale Feature Fusion Decoder for SegFormer

Procedia Computer Science, 2023
Hongyu Zhang, Suyu Wang, Yingying Zhang
openaire   +1 more source

An adaptive fusion of composite attention convolutional neural network for polyp image segmentation

Frontiers in Physiology
BackgroundAccurate localization and segmentation of polyp lesions in colonoscopic images are crucial for the early diagnosis of colorectal cancer and treatment planning. However, endoscopic imaging is often affected by noise interference.
Bojiao Jin, Yi Zhang, Qianqing Nie, Lin Qi, Wei Qian   +4 more
doaj   +1 more source

Multimodal Soft Surgical Robots Enabled by Eco‐Degradable, Sterilizable Polymers and Transient Electronics

Advanced Functional Materials, EarlyView.
A compostable PGS soft surgical robot with interchangeable modules integrates transient Mo tactile and Si thermal sensors for dual feedback. The device preserves its function after clinical‐grade sterilization, demonstrates stable actuation and cardiac tissue grasping with real‐time in vivo pulsatile monitoring, and biodegrades post‐use with soil‐safe, 
Minseong Chae, Kyung‐Sub Kim, Gyeong‐Seok Hwang, Jun‐Seok Shim, Sung‐Woo Kim, Yong‐Wu Kim, Jieun Han, Jae‐Young Bae, Jae‐Hwan Lee, Minjung Chae, Jooik Jeon, Joo‐Hyeon Park, You‐Jung Park, Ju‐Yong Lee, Sung‐Geun Choi, Min‐Ha Oh, Yong‐Joong Shin, Young‐In Ryu, Ji‐Woo Gu, Seong‐Yu Choi, Jeong‐Yun Sun, Jung Keun Hyun, Myoung‐Ryul Ok, Sang Yup Kim, Edyta Wyszkowska, Ju‐Young Kim, Kang‐Sik Lee, Seung‐Kyun Kang   +27 more
wiley   +1 more source

Dynamic gated fusion network with hierarchical multi-scale attention for hyperspectral image classification

Scientific Reports
Hyperspectral image classification is a critical task in remote sensing, but existing methods often employ fixed feature fusion strategies, making it difficult to adapt to the data characteristics of different scenarios.
Xianjian Shi, Lilong Liu, Xin Bao, Bin Pan, Sajid Hussain   +4 more
doaj   +1 more source

Tissue‐Stimulator Platform for Electrically Stimulating Pancreatic β‐Cells for Long‐Term Functional Regulation

Advanced Functional Materials, EarlyView.
We present a tissue‐stimulator platform for seamless electrode integration with pancreatic tissue, applying uniform electrical stimulation through optimized design with biohybrid 3D printing. Advantageous effects of electrical stimulation on β‐cell function were observed, including enhanced calcium signaling, islet morphology, and maturation.
Jihwan Kim, Uijung Yong, Myungji Kim, Jaewook Kim, Yeonggwon Jo, In Kyong Shim, Song Cheol Kim, Jinah Jang   +7 more
wiley   +1 more source

Human Action Recognition Based on 3D Convolution and Multi-Attention Transformer

Applied Sciences
To address the limitations of traditional two-stream networks, such as inadequate spatiotemporal information fusion, limited feature diversity, and insufficient accuracy, we propose an improved two-stream network for human action recognition based on ...
Minghua Liu, Wenjing Li, Bo He, Chuanxu Wang, Lianen Qu   +4 more
doaj   +1 more source

Mean-Shift Tracking Algorithm Based on Adaptive Fusion of Multi-feature

, 2015
The classic mean-shift tracking algorithm has achieved success in the field of computer vision because of its speediness and efficiency. However, classic mean-shift tracking algorithm would fail to track in some complicated conditions such as some parts ...
Xiao YH(肖阳辉), Yang K(杨凯), Wang ED(王恩德), Feng JH(冯俊惠)   +3 more
core  

Standalone and embedded stereo visual odometry based navigation solution [PDF]

, 2015
© Cranfield University, 2014This thesis investigates techniques and designs an autonomous visual stereo based navigation sensor to improve stereo visual odometry for purpose of navigation in unknown environments. In particular, autonomous navigation in a
Chermak, Lounis
core