Results 191 to 200 of about 6,849,681 (296)

Segmentation of uterus and placenta in MR images using a fully convolutional neural network. [PDF]

open access: yesProc SPIE Int Soc Opt Eng, 2020
Shahedi M   +8 more
europepmc   +1 more source

A Convolutional Neural Network Using Anterior Segment Photos for Infectious Keratitis Identification [PDF]

open access: yes
Vannarut Satitpitakul,1,2 Apiwit Puangsricharern,3 Surachet Yuktiratna,3 Yossapon Jaisarn,4 Keeratika Sangsao,4 Vilavun Puangsricharern,1,2 Ngamjit Kasetsuwan,1,2 Usanee Reinprayoon,1,2 Thanachaporn Kittipibul1,2 1Center of Excellence for Cornea and Stem
Satitpitakul V   +8 more
core  

Retinomorphic Visual Processing Enabled by Contact‐Engineered IGZO Optoelectronic Synaptic Memtransistors

open access: yesAdvanced Science, EarlyView.
Here, we present an optoelectronic synaptic memtransistor (OSMT) integrating photoresponsive IGZO with contact‐engineered HfO2, enabling electrically and optically tunable synaptic weights. The device demonstrates broad range of tunable conductance states and array‐level image processing, highlighting its potential for intelligent machine vision ...
Donghyun Kang   +6 more
wiley   +1 more source

A Versatile‐Designable Framework for Active and Programmable Shape‐Morphing Soft Matter Systems: From Inverse Design to Closed‐Loop Control

open access: yesAdvanced Science, EarlyView.
A versatile framework integrates addressable electrothermal actuation and strain‐constraint mechanisms to construct programmable shape‐morphing soft matter systems. By combining an analytical inverse design strategy for high‐fidelity 3D surface reconstruction with deep learning‐based closed‐loop control, this approach enables zero‐energy shape locking,
Kai Liu   +5 more
wiley   +1 more source

Molecularly Engineered Wing‐Shaped Azobenzene Memristors for Logic‐in‐Memory and Edge Visual Intelligence

open access: yesAdvanced Science, EarlyView.
Rational engineering of terminal substituents in symmetric azobenzene‐based molecules enables precise control over conformationally coupled charge‐transfer processes. This design yields tunable nonvolatile resistive memory behaviors, ranging from write‐once‐read‐many‐times (WORM) to rewritable switching.
Yanze Liu   +11 more
wiley   +1 more source

Home - About - Disclaimer - Privacy