In the assessment of car insurance claims,the claim rate for car insurance presents a highly skewed probability distribution,which is typically modeled using Tweedie distribution.The traditional approach to obtaining ...In the assessment of car insurance claims,the claim rate for car insurance presents a highly skewed probability distribution,which is typically modeled using Tweedie distribution.The traditional approach to obtaining the Tweedie regression model involves training on a centralized dataset,when the data is provided by multiple parties,training a privacy-preserving Tweedie regression model without exchanging raw data becomes a challenge.To address this issue,this study introduces a novel vertical federated learning-based Tweedie regression algorithm for multi-party auto insurance rate setting in data silos.The algorithm can keep sensitive data locally and uses privacy-preserving techniques to achieve intersection operations between the two parties holding the data.After determining which entities are shared,the participants train the model locally using the shared entity data to obtain the local generalized linear model intermediate parameters.The homomorphic encryption algorithms are introduced to interact with and update the model intermediate parameters to collaboratively complete the joint training of the car insurance rate-setting model.Performance tests on two publicly available datasets show that the proposed federated Tweedie regression algorithm can effectively generate Tweedie regression models that leverage the value of data fromboth partieswithout exchanging data.The assessment results of the scheme approach those of the Tweedie regressionmodel learned fromcentralized data,and outperformthe Tweedie regressionmodel learned independently by a single party.展开更多
[Objectives] To study the effects of Xuebijing combined with ulinastatin on coagulation function of sepsis patients. [Methods]Fifty six patients conforming to the diagnosis criteria for sepsis and receiving the treatm...[Objectives] To study the effects of Xuebijing combined with ulinastatin on coagulation function of sepsis patients. [Methods]Fifty six patients conforming to the diagnosis criteria for sepsis and receiving the treatment from May 2015 to January 2019 were selected. They were randomly divided into treatment group and control group according to the order of treatment. The two groups were treated according to the International Guidelines for Management of Severe Sepsis and Septic Shock( 2012),in which ulinastatin and Xuebijing were added to the treatment group. Before the treatment and on the seventh day after the treatment,both groups of patients were measured for the activated partial thromboplastin time( APTT),fibrinogen( Fi B),platelet( PLT),and prothrombin time( PT) were measured;the treatment status of the both groups was continuously observed for 7 d,and the mechanical ventilation time,ICU hospitalization time,and 30-day survival rate were recorded. [Results] Both FIB and PLT of the treatment group were significantly increased,and both APTT and PT were significantly shortened.Compared with the control group,the difference was statistically significant( P < 0. 05). The mechanical ventilation time and ICU hospitalization time of the treatment group were significantly shorter than that of the control group,and the 30-day survival rate of the treatment group was significantly higher than that of the control group,and the difference was statistically significant( P < 0. 05). [Conclusions]Xuebijing combined with ulinastatin can improve coagulation disorders of sepsis patients.展开更多
For noncontact optical thermometry,in contrast with fluorescence intensity ratio(FIR)technology,excitation intensity ratio(EIR)technology has been seriously limited due to low sensitivity.Moreover,by exploring all pos...For noncontact optical thermometry,in contrast with fluorescence intensity ratio(FIR)technology,excitation intensity ratio(EIR)technology has been seriously limited due to low sensitivity.Moreover,by exploring all possible temperature-dependent response,developing multimode optical thermometry is of great importance.In this work,a new Na_(2)Y_(2)TeB_(2)O_(10):Tb^(3+)phosphor is obtained by a solid-state reaction.Based on FIR and EIR models of Tb',thermometric properties are studied thoroughly.Excellent relative and absolute sensitivity(S_(R)and S_(A))are acquired due to the significant difference in emission/excitation lines in response to temperature.Meanwhile,Tb^(3+)content-dependent luminescence quenching mechanism is discussed.This study shows a feasible route for exploiting well-performing FIR-/EIR-based thermometric materials.展开更多
基金This research was funded by the National Natural Science Foundation of China(No.62272124)the National Key Research and Development Program of China(No.2022YFB2701401)+3 种基金Guizhou Province Science and Technology Plan Project(Grant Nos.Qiankehe Paltform Talent[2020]5017)The Research Project of Guizhou University for Talent Introduction(No.[2020]61)the Cultivation Project of Guizhou University(No.[2019]56)the Open Fund of Key Laboratory of Advanced Manufacturing Technology,Ministry of Education(GZUAMT2021KF[01]).
文摘In the assessment of car insurance claims,the claim rate for car insurance presents a highly skewed probability distribution,which is typically modeled using Tweedie distribution.The traditional approach to obtaining the Tweedie regression model involves training on a centralized dataset,when the data is provided by multiple parties,training a privacy-preserving Tweedie regression model without exchanging raw data becomes a challenge.To address this issue,this study introduces a novel vertical federated learning-based Tweedie regression algorithm for multi-party auto insurance rate setting in data silos.The algorithm can keep sensitive data locally and uses privacy-preserving techniques to achieve intersection operations between the two parties holding the data.After determining which entities are shared,the participants train the model locally using the shared entity data to obtain the local generalized linear model intermediate parameters.The homomorphic encryption algorithms are introduced to interact with and update the model intermediate parameters to collaboratively complete the joint training of the car insurance rate-setting model.Performance tests on two publicly available datasets show that the proposed federated Tweedie regression algorithm can effectively generate Tweedie regression models that leverage the value of data fromboth partieswithout exchanging data.The assessment results of the scheme approach those of the Tweedie regressionmodel learned fromcentralized data,and outperformthe Tweedie regressionmodel learned independently by a single party.
文摘[Objectives] To study the effects of Xuebijing combined with ulinastatin on coagulation function of sepsis patients. [Methods]Fifty six patients conforming to the diagnosis criteria for sepsis and receiving the treatment from May 2015 to January 2019 were selected. They were randomly divided into treatment group and control group according to the order of treatment. The two groups were treated according to the International Guidelines for Management of Severe Sepsis and Septic Shock( 2012),in which ulinastatin and Xuebijing were added to the treatment group. Before the treatment and on the seventh day after the treatment,both groups of patients were measured for the activated partial thromboplastin time( APTT),fibrinogen( Fi B),platelet( PLT),and prothrombin time( PT) were measured;the treatment status of the both groups was continuously observed for 7 d,and the mechanical ventilation time,ICU hospitalization time,and 30-day survival rate were recorded. [Results] Both FIB and PLT of the treatment group were significantly increased,and both APTT and PT were significantly shortened.Compared with the control group,the difference was statistically significant( P < 0. 05). The mechanical ventilation time and ICU hospitalization time of the treatment group were significantly shorter than that of the control group,and the 30-day survival rate of the treatment group was significantly higher than that of the control group,and the difference was statistically significant( P < 0. 05). [Conclusions]Xuebijing combined with ulinastatin can improve coagulation disorders of sepsis patients.
基金supported by the National Natural Science Foundation of China(No.22165031)National Undergraduate Innovation and Entrepreneurship Foundation(Nos.202210673034 and 202210673052)Program for Excellent Young Talents,Yunnan University.
文摘For noncontact optical thermometry,in contrast with fluorescence intensity ratio(FIR)technology,excitation intensity ratio(EIR)technology has been seriously limited due to low sensitivity.Moreover,by exploring all possible temperature-dependent response,developing multimode optical thermometry is of great importance.In this work,a new Na_(2)Y_(2)TeB_(2)O_(10):Tb^(3+)phosphor is obtained by a solid-state reaction.Based on FIR and EIR models of Tb',thermometric properties are studied thoroughly.Excellent relative and absolute sensitivity(S_(R)and S_(A))are acquired due to the significant difference in emission/excitation lines in response to temperature.Meanwhile,Tb^(3+)content-dependent luminescence quenching mechanism is discussed.This study shows a feasible route for exploiting well-performing FIR-/EIR-based thermometric materials.
