In this study,using 3,5‑di(3′,5′‑dicarboxylphenyl)‑1H‑1,2,4‑triazole(H4L)as ligands,a gadolinia‑based organic framework complex{[GdNa(L)(H_(2)O)3]·2H_(2)O}_(n)(Gd‑Na‑MOF)was successfully designed and synthesize...In this study,using 3,5‑di(3′,5′‑dicarboxylphenyl)‑1H‑1,2,4‑triazole(H4L)as ligands,a gadolinia‑based organic framework complex{[GdNa(L)(H_(2)O)3]·2H_(2)O}_(n)(Gd‑Na‑MOF)was successfully designed and synthesized by hydrothermal method.The structure and properties were systematically characterized and tested by techniques such as single‑crystal X‑ray diffraction,powder X‑ray diffraction,thermogravimetric analysis,infrared spectroscopy,and fluorescence spectroscopy.The results indicate that this complex has a unique 3D structure,excellent thermal stability,and outstanding luminescent performance.Based on its luminescent properties,a polymer‑embedding method was employed to fabricate the Gd‑Na‑MOF into a flexible,washable composite fluorescent film,Gd‑Na‑MOF@PMMA/BMA(PMMA=polymethyl methacrylate,BMA=butyl methacrylate).This fluorescent film exhibited highly sensitive recognition capability for tyramine,with a low detection limit of 1.66μmol·L^(-1).It was used for the detection of tyramine in bananas,with a recovery rate of 96.92%‑100.26%.CCDC:2466949.展开更多
随着互联网和电子商务的蓬勃发展,网络购物成为人们生活的常态。精准预测用户的网络购物行为,能为相关行业提供有价值的决策参考。基于此,文章基于集成学习法进行预测,为改进传统Stacking模型中只能结合基分类器预测结果的情况,在构建St...随着互联网和电子商务的蓬勃发展,网络购物成为人们生活的常态。精准预测用户的网络购物行为,能为相关行业提供有价值的决策参考。基于此,文章基于集成学习法进行预测,为改进传统Stacking模型中只能结合基分类器预测结果的情况,在构建Stacking模型时融入贝叶斯模型平均(bayesian model averaging,BMA),体现各基分类器对预测结果的贡献程度,有效结合多个模型优势。利用累积重要性筛选出有代表性的特征变量,评估模型性能以确定合适的基分类器组合,并结合逻辑回归元学习器构建最终的Stacking模型,基于构建好的模型融合BMA进行预测。实验结果表明,融入BMA后的Stacking模型预测用户网络购物行为效果较好。展开更多
文摘In this study,using 3,5‑di(3′,5′‑dicarboxylphenyl)‑1H‑1,2,4‑triazole(H4L)as ligands,a gadolinia‑based organic framework complex{[GdNa(L)(H_(2)O)3]·2H_(2)O}_(n)(Gd‑Na‑MOF)was successfully designed and synthesized by hydrothermal method.The structure and properties were systematically characterized and tested by techniques such as single‑crystal X‑ray diffraction,powder X‑ray diffraction,thermogravimetric analysis,infrared spectroscopy,and fluorescence spectroscopy.The results indicate that this complex has a unique 3D structure,excellent thermal stability,and outstanding luminescent performance.Based on its luminescent properties,a polymer‑embedding method was employed to fabricate the Gd‑Na‑MOF into a flexible,washable composite fluorescent film,Gd‑Na‑MOF@PMMA/BMA(PMMA=polymethyl methacrylate,BMA=butyl methacrylate).This fluorescent film exhibited highly sensitive recognition capability for tyramine,with a low detection limit of 1.66μmol·L^(-1).It was used for the detection of tyramine in bananas,with a recovery rate of 96.92%‑100.26%.CCDC:2466949.
文摘随着互联网和电子商务的蓬勃发展,网络购物成为人们生活的常态。精准预测用户的网络购物行为,能为相关行业提供有价值的决策参考。基于此,文章基于集成学习法进行预测,为改进传统Stacking模型中只能结合基分类器预测结果的情况,在构建Stacking模型时融入贝叶斯模型平均(bayesian model averaging,BMA),体现各基分类器对预测结果的贡献程度,有效结合多个模型优势。利用累积重要性筛选出有代表性的特征变量,评估模型性能以确定合适的基分类器组合,并结合逻辑回归元学习器构建最终的Stacking模型,基于构建好的模型融合BMA进行预测。实验结果表明,融入BMA后的Stacking模型预测用户网络购物行为效果较好。
