Results 171 to 180 of about 24,126 (306)
Contributions to Plasma Physics, EarlyView.ABSTRACT The properties of plasmas in the low‐density limit are described by virial expansions. Analytical expressions are known for the lowest virial coefficients from Green's function approaches. Recently, accurate path‐integral Monte Carlo (PIMC) simulations were performed for the hydrogen plasma at low densities by Filinov and Bonitz (Phys. Rev.
Gerd Röpke +3 more
wiley +1 more source
Rockburst prediction based on data preprocessing and hyperband‐RNN‐DNN
Deep Underground Science and Engineering, EarlyView.A data preprocessing workflow is proposed to address challenges in rockburst data analysis. Coupled algorithms preprocess the data set, and hyperband optimization is used to enhance RNN performance. Results show that preprocessing improves accuracy, while dense layers enhance model stability and prediction performance.
Yong Fan +4 more
wiley +1 more source
Deep Underground Science and Engineering, EarlyView.The flowchart illustrates rock specimen testing, vibration signal acquisition, and feature extraction with Gaborlet and sparse filtering for classification. Abstract Traditional lithology identification methods mainly rely on core sampling and well‐logging data.
Jian Hao +5 more
wiley +1 more source
Deep Underground Science and Engineering, EarlyView.The fused data extracted from the distributed monitoring system as the data basis, combined with dynamic geological data, are imported into a deep learning model. As the geological conditions of mining and excavation change, the risk of water inrush at the working face is retrieved in real time.
Yongjie Li +4 more
wiley +1 more source
Efficient Graph Similarity Computation with Alignment Regularization
We consider the graph similarity computation (GSC) task based on graph edit distance (GED) estimation. State-of-the-art methods treat GSC as a learning-based prediction task using Graph Neural Networks (GNNs). To capture fine-grained interactions between
Tan, Guang, Zhuo, Wei
core
Deep Underground Science and Engineering, EarlyView.This study demonstrates the feasibility of an underground closed‐loop thermal storage facility at a post‐mining site, intended for seasonal heat energy storage. Its principal design shows water flow directions in winter and summer (1, 2), heat pumps (3), an upper water reservoir (4), and connecting pipes (5).
Dmytro Rudakov, Oleksandr Inkin
wiley +1 more source
The effect of regularization in graph learning for the kere two-sample problem.
The effect of regularization in graph learning for the kere two-sample problem.
Ragnar L. Gudmundarson (18388657) +1 more
core +1 more source
Deep Underground Science and Engineering, EarlyView.This research proposes an interpretable hybrid stacking ensemble framework, optimized by the Sparrow Search Algorithm, to enhance hard rock pillar stability prediction. By integrating six machine learning models—k‐nearest neighbors, support vector machines, random forests, Gradient Boosting Decision Tree, eXtreme Gradient Boosting, and Light Gradient ...
Ning Wang +3 more
wiley +1 more source
Linear prediction models with graph regularization for Web-page categorization
, 2006 We present a risk minimization formulation for learning from both text and graph structures which is motivated by the problem of collective inference for hypertext document categorization.
Dom, Byron +2 more
core
An n‐of‐1 gene‐directed drug repurposing trial for an ultrarare genetic condition
Epilepsia, EarlyView.Abstract Objective Gain‐of‐function (GoF) variants in the KCNC1 potassium channel subunit gene (Kv3.1) cause motor/cognitive delays and hypotonia and have been associated with seizures. Fluoxetine has inhibitory effects on Kv3.1. However, open‐label nonrandomized administration is insufficient to guide clinical decision‐making in ultrarare conditions ...
Vedika Jha +13 more
wiley +1 more source