Results 91 to 100 of about 44,463 (307)
, 2023 Each point represents each observation. X-axis is the covariate of interest, Fasting Blood Sugar. Non-elevated = 1, Elevated = 2. The SHAP value represents the log-odds for heart disease. (TIF)
Samuel Y. Huang (14670660) +1 more
core +1 more source
Full‐Stack Architectures for Intelligent Brain‐Computer Interfaces
Advanced Science, EarlyView.System‐level overview of brain–computer interfaces (BCIs), illustrating the integration of neural signal acquisition, wireless transmission, and adaptive decoding. Advanced electrode, tissue interfaces, energy‐efficient communication, and robust algorithms collectively enable stable signal quality, real‐time processing, and closed‐loop operation ...
Hee Kyu Lee +9 more
wiley +1 more source
Mean absolute SHAP values for features grouped by input type.
, 2023 SHAP values for groups of features were calculated by summing the SHAP values of all of the individual features, and then the mean absolute SHAP value across all samples was calculated for the grouped features.
Miguel Rocha (1426192) +2 more
core +1 more source
Advanced Science, EarlyView.Rare‐earth catalysts regulate lithium–sulfur battery chemistry through f‐orbital–mediated interactions, enabling simultaneous polysulfide adsorption and catalytic conversion on conductive carbon hosts. This synergistic control suppresses the shuttle effect, accelerates redox kinetics, and guides stable Li2S nucleation, providing a mechanistic framework
Fan Wang +5 more
wiley +1 more source
Advanced Science, EarlyView.This perspective proposes a cohesive machine learning strategy to decode microplastic aging. It advocates for Federated Learning to dismantle global data silos and introduces the TRACE framework (TRansport, Aging, Corona, Ecotoxicity). By integrating physics‐informed modeling with causal discovery, this approach bridges the laboratory‐field gap to ...
Yaping Lyu +6 more
wiley +1 more source
Dianxin kexue在电信行业中，客户流失的准确预测对于相关企业维持市场竞争力和增加收益至关重要。为此提出一个结合CatBoost算法和SHAP（shapley additive explanations）模型的客户流失预测框架，旨在提高预测的准确性，同时增强模型的可解释性。利用新疆某通信公司的实际营业数据，通过数据预处理及特征工程，构建预测模型，选取5种主要关键性能指标评估模型性能。实验结果显示，所提出模型在选取的评价指标上均优于当前主流机器学习预测模型。最后引入SHAP框架增强模型可解释性，揭示影响客户流失的关键因素 ...
王圣节, 张庆红
doaj +1 more source
Scalable SHAP-Informed Neural Network
In the pursuit of scalable optimization strategies for neural networks, this study addresses the computational challenges posed by SHAP-informed learning methods introduced in prior work.
Jarrod Graham, Victor S. Sheng
core +1 more source
CauFinder: Steering Cell‐State and Phenotype Transitions by Causal Disentanglement Learning
Advanced Science, EarlyView.CauFinder combines causal disentanglement modeling and network control to prioritize causal drivers of cell‐state transitions from observational transcriptomic data. The framework separates transition‐relevant signals from spurious associations, nominates intervention targets across biological and disease contexts, and identifies DAAM1 as an actionable
Chengming Zhang +11 more
wiley +1 more source
Soil temperature prediction based on explainable artificial intelligence and LSTM
Frontiers in Environmental ScienceSoil temperature is a key parameter in many disciplines, and its research has important practical significance. In recent years, the prediction of soil temperature by deep learning has achieved good results.
Qingtian Geng, Leilei Wang, Qingliang Li
doaj +1 more source
Advanced Science, EarlyView.Based on the largest printable mesoscopic perovskite solar cells database we established, stacking model achieved precise PCE prediction (R2 = 0.73, MAE = 2.18%). Multiple experiments verified the accuracy of the model, which guided the fabrication of high‐PCE devices with an efficiency of 19.36%.
Hao Meng +9 more
wiley +1 more source