Search Results - ran+jin

4 Results Sort By:
LORI: Local Low-Rank Imputation for Context-Aware AI
THE CHALLENGE Leveraging Artificial Intelligence (AI) for data-driven decision-making faces a major challenge in automatically configuring and optimizing complex AI pipelines across different use cases. As organizations deal with diverse datasets and fast-changing requirements, selecting the right combination of processing steps becomes increasingly...
Published: 4/16/2025   |   Inventor(s): Ran Jin, Chen Xiaoyu
Keywords(s):  
Category(s): Technology Classifications > Software
Attention-on-Attention for Human-Guided AI
THE CHALLENGE A major challenge facing industries like advanced manufacturing and quality inspection is the gap between human expertise in visual search and the limited capabilities of current AI systems. While skilled inspectors can dynamically scan, interpret, and integrate subtle visual cues over time, most existing automated solutions rely on static...
Published: 4/16/2025   |   Inventor(s): Ran Jin, Chen Xiaoyu
Keywords(s):  
Category(s): Technology Classifications > Communication, Technology Classifications > Software
Privacy-prEserving Data-sharing framework (PriED)
THE CHALLENGE Industrial Internet provides a communication and computation platform, allowing the collection of large-scale data for machine learning tasks. Despite the promise of training and deployment acceleration and potential optimization via sharing data sets, the adoption of such technologies is impacted by the increasing concerns of information...
Published: 4/9/2025   |   Inventor(s): Ismini Lourentzou, Ran Jin
Keywords(s):  
Category(s): Technology Classifications > Communication, Technology Classifications > Software
PRIME: A Personalized Recommendation for Information Visualization Methods via Extended matrix Completion
Information visualization is an important mode of human-computer interaction to acquire insights of complex datasets. However, a uniform visualization format may be inefficient to bring the insights to different users at different contexts due to the users' differences in knowledge, perception, and cognition capabilities. On the other hand, typical...
Published: 10/27/2023   |   Inventor(s): Ran Jin, Chen Xiaoyu, Nathan Lau
Keywords(s):  
Category(s): Technology Classifications > Software, Technology Classifications > Communication