A query-driven digital twin architecture actively requests environment data based on simulation outcomes, reducing redundant data transmission.
Explore technology by industry and role
Newest additions first. Explore past and current notes by industry and role.
All notes
Newest additions first. Explore past and current notes by industry and role.
Introduces asymmetric style transfer that leverages labeled synthetic data and unlabeled real-world references without symmetric annotations
The risk field connects physical states and virtual reconstruction, enabling clear identification of high-risk scenarios.
Proposes DFQI, which directly integrates source information into target Q-function learning via L1 penalty linking coefficients
Classifies DMP leakage types and proposes SecDMP, a provably secure hardware defense that prevents secret exposure.
An i-AlexNet architecture is proposed to classify ECG signals into normal and abnormal categories in real time
An AI-based image enhancement workflow improves detectability of interconnect defects in SAM images
A new placement framework jointly optimizes device locations and access point selections for routing-aware performance.
AI can distinguish Marfan from non-Marfan facial images from ordinary online photos
An independent evaluation framework for assessing the reliability of AI-generated testbenches is proposed
Introduces private filtering based on record fit to scale noise according to typical data sensitivity
A real-time edge AI model for classifying all stages of gastric neoplasms during endoscopy is developed
Successfully identifies and delineates small, flat high-grade squamous intraepithelial neoplasia lesions
Diverse goals and resets with adaptive friction curriculum enable precise in-hand manipulation policy training
Achieves 93% lesion detection accuracy, outperforming visual estimation and manual QCA