Emerging two-dimensional MXenes have been extensively studied in a wide range of fields thanks to their superior electrical and hydrophilic attributes as well as excellent chemical stability and mechanical flexibility...Emerging two-dimensional MXenes have been extensively studied in a wide range of fields thanks to their superior electrical and hydrophilic attributes as well as excellent chemical stability and mechanical flexibility.Among them,the ultrahigh electrical conductivity(σ)and tunable band structures of benchmark Ti_(3)C_(2)T_(x) MXene demonstrate its good potential as thermoelectric(TE)materials.However,both the large variation ofσreported in the literature and the intrinsically low Seebeck coefficient(S)hinder the practical applications.Herein,this study has for the first time systematically investigated the TE properties of neat Ti_(3)C_(2)T_(x) films,which are finely modulated by exploiting different dispersing solvents,controlling nanosheet sizes and constructing composites.First,deionized water is found to be superior for obtaining closely packed MXene sheets relative to other polar solvents.Second,a simultaneous increase in both S andσis realized via elevating centrifugal speed on MXene aqueous suspensions to obtain small-sized nanosheets,thus yielding an ultrahigh power factor up to~156μW m^(-1) K^(-2).Third,S is significantly enhanced yet accompanied by a reduction inσwhen constructing MXene-based nanocomposites,the latter of which is originated from the damage to the intimate stackings of MXene nanosheets.Together,a correlation between the TE properties of neat Ti_(3)C_(2)T_(x) films and the stacking of nanosheets is elucidated,which would stimulate further exploration of MXene TEs.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
Botryosphaeria laricina(larch shoot blight)was first identified in 1973 in Jilin Province,China.The disease spread rapidly and caused considerable damage because its pathogenesis was unknown at the time and there were...Botryosphaeria laricina(larch shoot blight)was first identified in 1973 in Jilin Province,China.The disease spread rapidly and caused considerable damage because its pathogenesis was unknown at the time and there were no effective controls or quarantine methods.At present,it shows a spreading trend,but most research can only conduct physiological analyses within a relatively short period,combining individual influencing factors.Nevertheless,methods such as neural network models,ensemble learning algorithms,and Markov models are used in pest and disease prediction and forecasting.However,there may be fitting issues or inherent limitations associated with these methods.This study obtained B.laricina data at the county level from 2003 to 2021.The dataset was augmented using the SMOTE algorithm,and then algorithms such as XGBoost were used to select the significant features from a combined set of 12 features.A new stacking fusion model has been proposed to predict the status of B.laricina.The model is based on random forest,gradient boosted decision tree,CatBoost and logistic regression algorithms.The accuracy,recall,specificity,precision,F_(1) value and AUC of the model reached 90.9%,91.6%,90.4%,88.8%,90.2%and 96.2%.The results provide evidence of the strong performance and stability of the model.B.laricina is mainly found in the northeast and this study indicates that it is spreading northwest.Reasonable means should be used promptly to prevent further damage and spread.展开更多
基金supported by the China Postdoctoral Science Foundation(grant No.2024M750511,J.T.)National Key R&D Program of China(grant No.2022YFB3603804,Y.Z.)National Natural Science Foundation of China(NSFC)under grant Nos.82172470(C.X.)and 22375050(Z.L.).
文摘Emerging two-dimensional MXenes have been extensively studied in a wide range of fields thanks to their superior electrical and hydrophilic attributes as well as excellent chemical stability and mechanical flexibility.Among them,the ultrahigh electrical conductivity(σ)and tunable band structures of benchmark Ti_(3)C_(2)T_(x) MXene demonstrate its good potential as thermoelectric(TE)materials.However,both the large variation ofσreported in the literature and the intrinsically low Seebeck coefficient(S)hinder the practical applications.Herein,this study has for the first time systematically investigated the TE properties of neat Ti_(3)C_(2)T_(x) films,which are finely modulated by exploiting different dispersing solvents,controlling nanosheet sizes and constructing composites.First,deionized water is found to be superior for obtaining closely packed MXene sheets relative to other polar solvents.Second,a simultaneous increase in both S andσis realized via elevating centrifugal speed on MXene aqueous suspensions to obtain small-sized nanosheets,thus yielding an ultrahigh power factor up to~156μW m^(-1) K^(-2).Third,S is significantly enhanced yet accompanied by a reduction inσwhen constructing MXene-based nanocomposites,the latter of which is originated from the damage to the intimate stackings of MXene nanosheets.Together,a correlation between the TE properties of neat Ti_(3)C_(2)T_(x) films and the stacking of nanosheets is elucidated,which would stimulate further exploration of MXene TEs.
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。
基金supported by the National Key R&D Program of China(Grant No.2021YFD1400300).
文摘Botryosphaeria laricina(larch shoot blight)was first identified in 1973 in Jilin Province,China.The disease spread rapidly and caused considerable damage because its pathogenesis was unknown at the time and there were no effective controls or quarantine methods.At present,it shows a spreading trend,but most research can only conduct physiological analyses within a relatively short period,combining individual influencing factors.Nevertheless,methods such as neural network models,ensemble learning algorithms,and Markov models are used in pest and disease prediction and forecasting.However,there may be fitting issues or inherent limitations associated with these methods.This study obtained B.laricina data at the county level from 2003 to 2021.The dataset was augmented using the SMOTE algorithm,and then algorithms such as XGBoost were used to select the significant features from a combined set of 12 features.A new stacking fusion model has been proposed to predict the status of B.laricina.The model is based on random forest,gradient boosted decision tree,CatBoost and logistic regression algorithms.The accuracy,recall,specificity,precision,F_(1) value and AUC of the model reached 90.9%,91.6%,90.4%,88.8%,90.2%and 96.2%.The results provide evidence of the strong performance and stability of the model.B.laricina is mainly found in the northeast and this study indicates that it is spreading northwest.Reasonable means should be used promptly to prevent further damage and spread.
