Results 131 to 140 of about 93,556 (252)

SAGE: Spatially Aware Gene Selection and Dual‐View Embedding Fusion for Domain Identification in Spatial Transcriptomics

Advanced Science, EarlyView.
SAGE is a unified framework for spatial domain identification in spatial transcriptomics that jointly models tissue architecture and gene programs. Topic‐driven gene selection (NMF plus classifier‐based scoring) highlights spatially informative genes, while dual‐view graph embedding fuses local expression and non‐local functional relations.
Yi He, Yunpei Xu, Liqing Ding, Hong‐Dong Li, Yaohang Li, Shaokai Wang   +5 more
wiley   +1 more source

Evaluating hyperparameter transferability in unsupervised anomaly detection for smart home environments

Cybersecurity
Deploying unsupervised anomaly detection systems in heterogeneous smart home environments is hindered by the need for costly, per-site hyperparameter tuning.
Juan-Ignacio Iturbe-Araya, Helena Rifà-Pous   +1 more
doaj   +1 more source

Unsupervised Hierarchical Symbolic Regression for Interpretable Property Modeling in Complex Multi‐Variable Systems

Advanced Science, EarlyView.
UHSR translates complex chemical behavior into clear and explainable equations. Applied to thin‐layer chromatography, it automatically uncovers the mathematical rules linking a molecule's structure to its polarity. This approach matches the accuracy of advanced AI while providing interpretable results, earning greater trust from chemists. The method is
Siyu Lou, Chengchun Liu, Dongxiao Zhang, Yuntian Chen, Fanyang Mo   +4 more
wiley   +1 more source

Analysis of Multiscale Condensation Phenomena Using a Zero‐Shot Computer Vision Framework

Advanced Science, EarlyView.
A zero‐shot computer vision framework quantifies multiscale condensation dynamics by automatically segmenting droplets and extracting physical parameters without labeled data. The workflow integrates data mining and statistical analysis to reveal droplet growth, coalescence statistics, and sweeping behaviors, enabling label‐free measurement of heat ...
Donghyeong Lee, Seokwan Roh, Jaewoo Jeong, Kuk‐Jin Yoon, Jungchul Lee, Youngsuk Nam   +5 more
wiley   +1 more source

High‐Conductivity Electrolytes Screened Using Fragment‐ and Composition‐Aware Deep Learning

Advanced Science, EarlyView.
We present a new deep learning framework that hierarchically links molecular and functional unit attributions to predict electrolyte conductivity. By integrating molecular composition, ratios, and physicochemical descriptors, it achieves accurate, interpretable predictions and large‐scale virtual screening, offering chemically meaningful insights for ...
Xiangwen Wang, Muyang Chen, Gengyi Bao, Yan Lai, Jinghe Cao, Xinhua Liu, Rui Tan   +6 more
wiley   +1 more source

Machine learning in medicine: a practical introduction to techniques for data pre-processing, hyperparameter tuning, and model comparison. [PDF]

BMC Med Res Methodol, 2022
Pfob A, Lu SC, Sidey-Gibbons C.
europepmc   +1 more source

In Situ Quantization with Memory‐Transistor Transfer Unit Based on Electrochemical Random‐Access Memory for Edge Applications

Advanced Science, EarlyView.
By combining ionic nonvolatile memories and transistors, this work proposes a compact synaptic unit to enable low‐precision neural network training. The design supports in situ weight quantization without extra programming and achieves accuracy comparable to ideal methods. This work obtains energy consumption advantage of 25.51× (ECRAM) and 4.84× (RRAM)
Zhen Yang, Yuxiang Yang, Baiqian Wang, Yaoyu Tao, Zelun Pan, Lei Cai, Teng Zhang, Longhao Yan, Xianbin Li, Yuchao Yang   +9 more
wiley   +1 more source

Hyperparameter Tuning and Automatic Image Augmentation for Deep Learning-Based Angle Classification on Intraoral Photographs-A Retrospective Study. [PDF]

Diagnostics (Basel), 2022
Cejudo Grano de Oro JE, Koch PJ, Krois J, Garcia Cantu Ros A, Patel J, Meyer-Lueckel H, Schwendicke F.   +6 more
europepmc   +1 more source

Neural Network‐Based Permittivity Engineering of Magnetic Absorbers for Customizable Microwave Absorption

Advanced Science, EarlyView.
A neural network‐enabled permittivity engineering paradigm is introduced, transcending traditional trial‐and‐error design. By decoupling electromagnetic parameters and screening a high‐throughput feature space, an ultrathin (1.0 mm) magnetic absorber is inversely designed, experimentally achieving a superior and customizable 5.1 GHz bandwidth and ...
Chenxi Liu, Jinzhe Li, Sen Li, Zhongqiu Guo, Yao Chen, Tian Li, Renchi Qin, Jiaxu Sun, Yongxi Lu, Fanbin Meng   +9 more
wiley   +1 more source

Machine Learning-Based Boosted Regression Ensemble Combined with Hyperparameter Tuning for Optimal Adaptive Learning. [PDF]

Sensors (Basel), 2022
Isabona J, Imoize AL, Kim Y.
europepmc   +1 more source