Results 111 to 120 of about 601,753 (327)

Active semi-supervised learning for biological data classification.

PLoS ONE, 2020
Due to datasets have continuously grown, efforts have been performed in the attempt to solve the problem related to the large amount of unlabeled data in disproportion to the scarcity of labeled data.
Guilherme Camargo, Pedro H Bugatti, Priscila T M Saito   +2 more
doaj   +1 more source

Reinforcement Learning Approach to Advance Non‐Fullerene Acceptor‐Based Semi‐Transparent Organic Solar Cell

Advanced Theory and Simulations, EarlyView.
This study introduces a deep Q‐learning framework for semi‐transparent organic solar cells, combining AI and the Transfer Matrix Method to balance transparency/efficiency. Targeting PBDB‐T:ITIC‐based layers with asymmetric DMD contacts, the algorithm optimizes thickness/material properties, achieving 48.97% AVT and sustained photocurrent.
Erman Cokduygulular, Muhammed Yusuf Aykut, Caglar Cetinkaya   +2 more
wiley   +1 more source

A 3D Printing Strategy for Hard Curved Surfaced Circuits: From Materials to Applications

Advanced Science, EarlyView.
Conventional PCB etching (multi‐step) and indirect transfer techniques fail to meet structural electronics’ demands for lightweight, miniaturized, and customized manufacturing. 3D‐printed conformal circuits enable direct integration of conductive traces into substrates or onto surfaces, achieving integrated structural‐functional fabrication.
Wang Qin, Shujuan Li, Wei Wei, Haiqing Bai, Shikui Jia, Robert G Landers, Yunlong Ma, Sha Wei, Tuo Kang, Miao Zhang, Weipei Zhang, Mingkun Wang, Tongxin Guan   +12 more
wiley   +1 more source

Adaptive Machine Learning for Electronic Nose‐Based Forensic VOC Classification

Advanced Science, EarlyView.
A 32‐element electronic nose enhanced with machine learning demonstrates exceptional accuracy in differentiating between living and deceased individuals (98.1%), discriminating human and animal specimens (97.2%), and estimating postmortem intervals.
Ivan Shtepliuk, Kerstin Montelius, Jens Eriksson, Donatella Puglisi   +3 more
wiley   +1 more source

Harnessing Machine Learning to Enhance Transition State Search with Interatomic Potentials and Generative Models

Advanced Science, EarlyView.
Comprehensive evaluation of MLIPs and generative models for TS search using an end‐to‐end benchmark platform. Success rates, TS quality, and barrier prediction errors are systematically compared across models. The results reveal key performance trade‐offs and provide actionable insights for improving ML‐based transition state search and reaction ...
Qiyuan Zhao, Yunhong Han, Duo Zhang, Jiaxu Wang, Peichen Zhong, Taoyong Cui, Bangchen Yin, Yirui Cao, Haojun Jia, Chenru Duan   +9 more
wiley   +1 more source

Comprehensive Genetic Map of Muscle Lipidome Reveals Novel Insights Into Flavor Variation in Ruminant Meat

Advanced Science, EarlyView.
Ruminant meat is widely appreciated for its distinctive flavor. Lipids play a central role in influencing meat flavor, yet their genetic and biochemical basis remains largely unexplored. Here, a comprehensive lipid genetic map of sheep muscle is constructed and 20 candidate genes potentially modulating lipid levels are identified to provide a roadmap ...
Xueying Zhang, Yuanyuan Kong, Jialei Chen, Ran Li, Zhongyu Wang, Yali Song, Tianshu Dai, Yuxin Fu, Beixiang Jiang, Jize Zeng, Shengwei Pei, Yangkai Liu, Qianjie Feng, Weiwei Fu, Zehu Yuan, Joram Mwashigadi Mwacharo, Fadi Li, Xiangpeng Yue   +17 more
wiley   +1 more source

The Effectiveness of Semi-Supervised Learning Techniques in Identifying Calcifications in X-ray Mammography and the Impact of Different Classification Probabilities

Applied Sciences
Identifying calcifications in mammograms is crucial for early breast cancer detection, and semi-supervised learning, which utilizes a small dataset for supervised learning combined with deep learning, is anticipated to be an effective approach for ...
Miu Sakaida, Takaaki Yoshimura, Minghui Tang, Shota Ichikawa, Hiroyuki Sugimori, Kenji Hirata, Kohsuke Kudo   +6 more
doaj   +1 more source

Application of Massive Parallel Deep Learning Algorithm in the Prediction of Colorectal Carcinogenesis of Familial Polyposis

IEEE Access, 2020
Based on the massively parallel deep learning algorithm, this paper studies familial polyposis colorectal carcinogenesis, and proposes a semi-supervised multi-task survival analysis method based on deep learning, which transforms the survival analysis ...
Fuqiang Zhang, Sichao Jiang, Yanke Li
doaj   +1 more source

Magnetically Controllable and Degradable Milliscale Swimmers as Intraocular Drug Implants

Advanced Science, EarlyView.
Magnetically controllable degradable milliscale swimmers (MDMS) offer a promising alternative to commercial intraocular drug implants, reducing complications like implant dislocation and uncontrolled drug release. MDMS achieve high velocities in ocular environments, enable real‐time imaging, and deliver drugs effectively without disrupting retinal ...
Erdost Yildiz, Ugur Bozuyuk, Eray Yildiz, Fan Wang, Mertcan Han, Alp Can Karacakol, Devin Sheehan, Yan Yu, Metin Sitti   +8 more
wiley   +1 more source

SemiLT: A Multianchor Transfer Learning Method for Cross‐Modality Cell Label Annotation from scRNA‐seq to scATAC‐seq

Advanced Science, EarlyView.
A multianchor transfer learning method, SemiLT, enables accurate cell label annotation in sparse scATAC‐seq data by leveraging well‐annotated scRNA‐seq references. By addressing temporal discrepancies between modalities, SemiLT improves rare cell type identification and batch correction.
Zhitong Chen, Maoteng Duan, Xiaoying Wang, Bingqiang Liu   +3 more
wiley   +1 more source