Results 231 to 240 of about 169,651 (277)

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

open access: yesAdvanced 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   +2 more
wiley   +1 more source

Anonymous online student surveys anywhere

open access: yesJournal of Teaching and Learning with Technology, 2013
Vicky J. Meretsky
doaj  

Sub‐Micrometer‐Precision Path Following of Piezo‐Actuated Mobile Robot

open access: yesAdvanced Intelligent Systems, EarlyView.
This article reports on the Holonomic‐Beetle (HB), a palm‐sized robot that achieves sub‐micrometer (sub‐µm) precision path tracking across spatial ranges from 100 µm to 10 mm. Using proportional‐integral‐derivative (PID) control, the HB accurately tracks both complex and straight paths with sub‐µm path errors, surpassing existing robots.
Eiji Kusui   +9 more
wiley   +1 more source

Deep Reinforcement Learning Approaches for Sensor Data Collection by a Swarm of UAVs

open access: yesAdvanced Intelligent Systems, EarlyView.
This article presents four decentralized reinforcement learning algorithms for autonomous data harvesting and investigates how collaboration improves collection efficiency. It also presents strategies to minimize training times by improving model flexibility, enabling algorithms to operate with varying number of agents and sensors.
Thiago de Souza Lamenza   +2 more
wiley   +1 more source

ControlIt: A Universal Framework for Translational, Adaptive, and Online Brain–Computer Interfaces

open access: yesAdvanced Intelligent Systems, EarlyView.
Brain–computer interfaces (BCIs) lack a unified platform that works across signals and algorithms. ControlIt, an open‐source, modular ROS2‐based BCI framework supporting electroencephalography (EEG), electrocorticography (ECoG), and spike‐based decoding across both classification and regression tasks is presented.
Wanlin Yang   +12 more
wiley   +1 more source

Home - About - Disclaimer - Privacy