Results 181 to 190 of about 649,470 (297)

What to Make and How to Make It: Combining Machine Learning and Statistical Learning to Design New Materials

open access: yesAdvanced Intelligent Discovery, EarlyView.
Combining machine learning and probabilistic statistical learning is a powerful way to discover and design new materials. A variety of machine learning approaches can be used to identify promising candidates for target applications, and causal inference can help identify potential ways to make them a reality.
Jonathan Y. C. Ting, Amanda S. Barnard
wiley   +1 more source

Classification of Pulmonary Nodules Using Multimodal Feature‐Driven Graph Convolutional Networks with Specificity Proficiency

open access: yesAdvanced Intelligent Systems, EarlyView.
The radiomics feature could save the storage space of all medical samples; on the other hand, it avoids data leakage. Graph convolutional neural networks could summarize the similarity of benign and malignant pulmonary nodules to improve the performance in distinguishing them with radiomics and common clinical features.
Renjie Xu   +7 more
wiley   +1 more source

Prestressed Wood or Bamboo Structures: Historical Overview and State-of-the-Art

open access: yesBioResources
This review explores the evolution of prestressed timber/bamboo structures across component, connection, and structural levels, and it examines the corresponding performance of prestressed specimens.
Qingfang Lv, Juewen Wang, Yujie Lu
doaj  

Utilizing Data Imbalance to Enhance Compound–Protein Interaction Prediction Models

open access: yesAdvanced Intelligent Systems, EarlyView.
This research paper introduces FilmCPI, a sequence‐based model for predicting compound–protein interactions. It uniquely leverages data imbalance between proteins and compounds to improve performance. FilmCPI outperforms baseline models across multiple datasets and demonstrates strong transferability to unseen protein families without increasing ...
Wei Lin, Chi Chung Alan Fung
wiley   +1 more source

Lowering the Entrance Hurdle for Lab Automation: An Artificial Intelligence‐Supported, Interactive Robotic Arm for Automated, Repeated Testing Procedures

open access: yesAdvanced Intelligent Systems, EarlyView.
This study introduces a modular lab automation system with affordable robotics and artificial intelligence (AI), enabling flexible, human‐in‐the‐loop task orchestration. Key features include dynamic task recording, efficient data management, and AI‐assisted measurements.
Stefan Conrad   +3 more
wiley   +1 more source

Home - About - Disclaimer - Privacy