Depression is one of the most severe mental health illnesses among senior citizens.Aiming at the low accuracy and poor interpretability of traditional prediction models,a novel interpretable depression predictive mode...Depression is one of the most severe mental health illnesses among senior citizens.Aiming at the low accuracy and poor interpretability of traditional prediction models,a novel interpretable depression predictive model for the elderly based on the improved sparrow search algorithm(ISSA)optimized light gradient boosting machine(LightGBM)and Shapley Additive exPlainations(SHAP)is proposed.First of all,to achieve better optimization ability and convergence speed,various strategies are used to improve SSA,including initialization population by Halton sequence,generating elite population by reverse learning and multi-sample learning strategy with linear control of step size.Then,the ISSA is applied to optimize the hyper-parameters of light gradient boosting machine(LightGBM)to improve the prediction accuracy when facing massive high-dimensional data.Finally,SHAP is used to provide global and local interpretation of the prediction model.The effectiveness of the proposed method is validated by a series of comparative experiments based on a real-world dataset.展开更多
目的研究慢性胃炎腻苔患者的口腔微生物菌群组成特征,探索腻苔的形成机制。方法收集40例慢性胃炎患者舌苔样本(腻苔组20例,非腻苔组20例)和20名正常人舌苔样本(健康对照组)。利用16SrRNA基因变性梯度凝胶电泳(denatured gradient gel el...目的研究慢性胃炎腻苔患者的口腔微生物菌群组成特征,探索腻苔的形成机制。方法收集40例慢性胃炎患者舌苔样本(腻苔组20例,非腻苔组20例)和20名正常人舌苔样本(健康对照组)。利用16SrRNA基因变性梯度凝胶电泳(denatured gradient gel electrophoresis,DGGE)技术检测各组舌苔微生物菌群,得到舌苔样本细菌DGGE图谱,将其数字化后进行主成分分析(PCA)和偏最小二乘判别法分析(PLS-DA)。结果慢性胃炎腻苔组、非腻苔组与健康对照组舌苔的微生物组成存在差异。(1)腻苔组与非腻苔组之间有5条具有显著差异的条带,PLS判别模型的预报准确率达到97.5%;腻苔组和健康对照组之间有8条具有显著差异的条带,PLS判别模型的预报准确率达到95.0%;非腻苔组和健康对照组之间的条带差异不明显。(2)腻苔组的8号条带亮度高于非腻苔组和健康对照组,测序结果显示其最近邻居为Moraxella ca-tarrhalis(黏膜炎莫拉氏菌/卡他莫拉菌),但两者相似度仅为96.2%,可能是目前尚未报道的一个新菌种;10号条带亮度为健康对照组>非腻苔组>腻苔组,测序结果显示其与Rothia mucilaginosa(黏滑罗斯菌)相似度达到100.0%。结论 8号条带的菌种可能与慢性胃炎腻苔的形成有密切关系,10号条带的菌种可能与慢性胃炎非腻苔形成有一定的关系,提示口腔微生物菌群的变化可能是腻苔的形成机制之一。展开更多
We investigate sharp conditions for boundary and interior gradient estimates of continuous viscosity solutions to fully nonlinear, uniformly elliptic equations under Dirichlet boundary conditions. When these condition...We investigate sharp conditions for boundary and interior gradient estimates of continuous viscosity solutions to fully nonlinear, uniformly elliptic equations under Dirichlet boundary conditions. When these conditions are violated, there can be blow up of the gradient in the interior or on the boundary of the domain. In particular we de- rive sharp results on local and global Lipschitz continuity of continuous viscosity solutions under more general growth conditions than before. Lipschitz regularity near the boundary allows us to predict when the Dirichlet condition is satisfied in a classical and not just in a viscosity sense, where detachment can occur. Another consequence is this： if interior gra- dient blow up occurs, Perron-type solutions can in general become discontinuous, so that the Dirichlet problem can become unsolvable in the class of continuous viscosity solutions.展开更多
基金supported by the National Natural Science Foundation of China(Nos.62172287,62102273)。
文摘Depression is one of the most severe mental health illnesses among senior citizens.Aiming at the low accuracy and poor interpretability of traditional prediction models,a novel interpretable depression predictive model for the elderly based on the improved sparrow search algorithm(ISSA)optimized light gradient boosting machine(LightGBM)and Shapley Additive exPlainations(SHAP)is proposed.First of all,to achieve better optimization ability and convergence speed,various strategies are used to improve SSA,including initialization population by Halton sequence,generating elite population by reverse learning and multi-sample learning strategy with linear control of step size.Then,the ISSA is applied to optimize the hyper-parameters of light gradient boosting machine(LightGBM)to improve the prediction accuracy when facing massive high-dimensional data.Finally,SHAP is used to provide global and local interpretation of the prediction model.The effectiveness of the proposed method is validated by a series of comparative experiments based on a real-world dataset.
基金financed by the Alexander von Humboldt Foundationcontinued in March 2009 at the Mathematisches Forschungsinstitut Oberwolfach in the "Research in Pairs"program
文摘We investigate sharp conditions for boundary and interior gradient estimates of continuous viscosity solutions to fully nonlinear, uniformly elliptic equations under Dirichlet boundary conditions. When these conditions are violated, there can be blow up of the gradient in the interior or on the boundary of the domain. In particular we de- rive sharp results on local and global Lipschitz continuity of continuous viscosity solutions under more general growth conditions than before. Lipschitz regularity near the boundary allows us to predict when the Dirichlet condition is satisfied in a classical and not just in a viscosity sense, where detachment can occur. Another consequence is this： if interior gra- dient blow up occurs, Perron-type solutions can in general become discontinuous, so that the Dirichlet problem can become unsolvable in the class of continuous viscosity solutions.
