构建使用了PD-1抑制剂的肿瘤患者出现甲状腺功能障碍的风险预测模型,分析使用PD-1肿瘤抑制剂导致的甲状腺功能障碍的相关风险因素,设计监测预警系统。选取2020年—2023年广西医科大学附属肿瘤医院1225例使用PD-1抑制剂肿瘤患者的临床资...构建使用了PD-1抑制剂的肿瘤患者出现甲状腺功能障碍的风险预测模型,分析使用PD-1肿瘤抑制剂导致的甲状腺功能障碍的相关风险因素,设计监测预警系统。选取2020年—2023年广西医科大学附属肿瘤医院1225例使用PD-1抑制剂肿瘤患者的临床资料,包括人口学特征、既往史、实验室检测等63个变量。本文选取相关性前10/20/30/40/50/60个变量的4种传统机器学习模型进行性能比较。通过F1分数、灵敏度、准确率、精确率、特异性曲线下面积(Area Under the Curve,AUC)评估以上预测模型的性能,并利用Shapley加性解释(Shapley Additive Explanation,SHAP)可视化解释本文的机器学习模型。与促甲状腺激素相关性排名前10的变量依次为:羟丁酸脱氢酶、乳酸脱氢酶、淋巴细胞绝对值、天门冬氨酸转移酶、钙离子、碱性磷酸酶、谷氨酰转肽酶、单核细胞绝对值、红细胞分布宽度SD、胆碱酯酶。建立了使用PD-1抑制剂的肿瘤患者出现甲状腺功能障碍的风险预测模型,并在全局解释和局部解释的层面上分别作出模型预测结果影响的解释。展开更多
Virtual power plant(VPP)integrates a variety of distributed renewable energy and energy storage to participate in electricity market transactions,promote the consumption of renewable energy,and improve economic effici...Virtual power plant(VPP)integrates a variety of distributed renewable energy and energy storage to participate in electricity market transactions,promote the consumption of renewable energy,and improve economic efficiency.In this paper,aiming at the uncertainty of distributed wind power and photovoltaic output,considering the coupling relationship between power,carbon trading,and green cardmarket,the optimal operationmodel and bidding scheme of VPP in spot market,carbon trading market,and green card market are established.On this basis,through the Shapley value and independent risk contribution theory in cooperative game theory,the quantitative analysis of the total income and risk contribution of various distributed resources in the virtual power plant is realized.Moreover,the scheduling strategies of virtual power plants under different risk preferences are systematically compared,and the feasibility and accuracy of the combination of Shapley value and independent risk contribution theory in ensuring fair income distribution and reasonable risk assessment are emphasized.A comprehensive solution for virtual power plants in the multi-market environment is constructed,which integrates operation strategy,income distribution mechanism,and risk control system into a unified analysis framework.Through the simulation of multi-scenario examples,the CPLEXsolver inMATLAB software is used to optimize themodel.The proposed joint optimization scheme can increase the profit of VPP participating in carbon trading and green certificate market by 29%.The total revenue of distributed resources managed by VPP is 9%higher than that of individual participation.展开更多
Inverse design of advanced materials represents a pivotal challenge in materials science.Leveraging the latent space of Variational Autoencoders(VAEs)for material optimization has emerged as a significant advancement ...Inverse design of advanced materials represents a pivotal challenge in materials science.Leveraging the latent space of Variational Autoencoders(VAEs)for material optimization has emerged as a significant advancement in the field of material inverse design.However,VAEs are inherently prone to generating blurred images,posing challenges for precise inverse design and microstructure manufacturing.While increasing the dimensionality of the VAE latent space can mitigate reconstruction blurriness to some extent,it simultaneously imposes a substantial burden on target optimization due to an excessively high search space.To address these limitations,this study adopts a Variational Autoencoder guided Conditional Diffusion Generative Model(VAE-CDGM)framework integrated with Bayesian optimization to achieve the inverse design of composite materials with targeted mechanical properties.The VAE-CDGM model synergizes the strengths of VAEs and Denoising Diffusion Probabilistic Models(DDPM),enabling the generation of high-quality,sharp images while preserving a manipulable latent space.To accommodate varying dimensional requirements of the latent space,two optimization strategies are proposed.When the latent space dimensionality is excessively high,SHapley Additive exPlanations(SHAP)sensitivity analysis is employed to identify critical latent features for optimization within a reduced subspace.Conversely,direct optimization is performed in the low-dimensional latent space of VAE-CDGM when dimensionality is modest.The results demonstrate that both strategies accurately achieve the targeted design of composite materials while circumventing the blurred reconstruction flaws of VAEs,which offers a novel pathway for the precise design of advanced materials.展开更多
文摘构建使用了PD-1抑制剂的肿瘤患者出现甲状腺功能障碍的风险预测模型,分析使用PD-1肿瘤抑制剂导致的甲状腺功能障碍的相关风险因素,设计监测预警系统。选取2020年—2023年广西医科大学附属肿瘤医院1225例使用PD-1抑制剂肿瘤患者的临床资料,包括人口学特征、既往史、实验室检测等63个变量。本文选取相关性前10/20/30/40/50/60个变量的4种传统机器学习模型进行性能比较。通过F1分数、灵敏度、准确率、精确率、特异性曲线下面积(Area Under the Curve,AUC)评估以上预测模型的性能,并利用Shapley加性解释(Shapley Additive Explanation,SHAP)可视化解释本文的机器学习模型。与促甲状腺激素相关性排名前10的变量依次为:羟丁酸脱氢酶、乳酸脱氢酶、淋巴细胞绝对值、天门冬氨酸转移酶、钙离子、碱性磷酸酶、谷氨酰转肽酶、单核细胞绝对值、红细胞分布宽度SD、胆碱酯酶。建立了使用PD-1抑制剂的肿瘤患者出现甲状腺功能障碍的风险预测模型,并在全局解释和局部解释的层面上分别作出模型预测结果影响的解释。
基金funded by the Department of Education of Liaoning Province and was supported by the Basic Scientific Research Project of the Department of Education of Liaoning Province(Grant No.LJ222411632051)and(Grant No.LJKQZ2021085)Natural Science Foundation Project of Liaoning Province(Grant No.2022-BS-222).
文摘Virtual power plant(VPP)integrates a variety of distributed renewable energy and energy storage to participate in electricity market transactions,promote the consumption of renewable energy,and improve economic efficiency.In this paper,aiming at the uncertainty of distributed wind power and photovoltaic output,considering the coupling relationship between power,carbon trading,and green cardmarket,the optimal operationmodel and bidding scheme of VPP in spot market,carbon trading market,and green card market are established.On this basis,through the Shapley value and independent risk contribution theory in cooperative game theory,the quantitative analysis of the total income and risk contribution of various distributed resources in the virtual power plant is realized.Moreover,the scheduling strategies of virtual power plants under different risk preferences are systematically compared,and the feasibility and accuracy of the combination of Shapley value and independent risk contribution theory in ensuring fair income distribution and reasonable risk assessment are emphasized.A comprehensive solution for virtual power plants in the multi-market environment is constructed,which integrates operation strategy,income distribution mechanism,and risk control system into a unified analysis framework.Through the simulation of multi-scenario examples,the CPLEXsolver inMATLAB software is used to optimize themodel.The proposed joint optimization scheme can increase the profit of VPP participating in carbon trading and green certificate market by 29%.The total revenue of distributed resources managed by VPP is 9%higher than that of individual participation.
文摘Inverse design of advanced materials represents a pivotal challenge in materials science.Leveraging the latent space of Variational Autoencoders(VAEs)for material optimization has emerged as a significant advancement in the field of material inverse design.However,VAEs are inherently prone to generating blurred images,posing challenges for precise inverse design and microstructure manufacturing.While increasing the dimensionality of the VAE latent space can mitigate reconstruction blurriness to some extent,it simultaneously imposes a substantial burden on target optimization due to an excessively high search space.To address these limitations,this study adopts a Variational Autoencoder guided Conditional Diffusion Generative Model(VAE-CDGM)framework integrated with Bayesian optimization to achieve the inverse design of composite materials with targeted mechanical properties.The VAE-CDGM model synergizes the strengths of VAEs and Denoising Diffusion Probabilistic Models(DDPM),enabling the generation of high-quality,sharp images while preserving a manipulable latent space.To accommodate varying dimensional requirements of the latent space,two optimization strategies are proposed.When the latent space dimensionality is excessively high,SHapley Additive exPlanations(SHAP)sensitivity analysis is employed to identify critical latent features for optimization within a reduced subspace.Conversely,direct optimization is performed in the low-dimensional latent space of VAE-CDGM when dimensionality is modest.The results demonstrate that both strategies accurately achieve the targeted design of composite materials while circumventing the blurred reconstruction flaws of VAEs,which offers a novel pathway for the precise design of advanced materials.
