This research introduces a novel approach to improve and optimize the predictive capacity of consumer purchase behaviors on e-commerce platforms. This study presented an introduction to the fundamental concepts of the...This research introduces a novel approach to improve and optimize the predictive capacity of consumer purchase behaviors on e-commerce platforms. This study presented an introduction to the fundamental concepts of the logistic regression algorithm. In addition, it analyzed user data obtained from an e-commerce platform. The original data were preprocessed, and a consumer purchase prediction model was developed for the e-commerce platform using the logistic regression method. The comparison study used the classic random forest approach, further enhanced by including the K-fold cross-validation method. Evaluation of the accuracy of the model’s classification was conducted using performance indicators that included the accuracy rate, the precision rate, the recall rate, and the F1 score. A visual examination determined the significance of the findings. The findings suggest that employing the logistic regression algorithm to forecast customer purchase behaviors on e-commerce platforms can improve the efficacy of the approach and yield more accurate predictions. This study serves as a valuable resource for improving the precision of forecasting customers’ purchase behaviors on e-commerce platforms. It has significant practical implications for optimizing the operational efficiency of e-commerce platforms.展开更多
An E//B neutral particle analyzer(NPA)has been designed and is under development at Sichuan University and Southwestern Institute of Physics.The main purpose of the E//B NPA is to measure the distribution function of ...An E//B neutral particle analyzer(NPA)has been designed and is under development at Sichuan University and Southwestern Institute of Physics.The main purpose of the E//B NPA is to measure the distribution function of fast ions in the HL-2A/3 tokamak.The E//B NPA contains three main units,i.e.the stripping unit,the analyzing unit and the detection unit.A gas stripping chamber was adopted as the stripping unit.The results of the simulations and beam tests for the stripping chamber are presented.Parallel electric and magnetic fields provided by a NdFeB permanent magnet and two parallel electric plates were designed and constructed for the analyzing unit.The calibration of the magnetic and electric fields was performed using a 50 kV electron cyclotron resonance ion source(ECRIS)platform.The detection unit consists of 32lutetium-yttrium oxyorthosilicate(LYSO)detector modules arranged in two rows.The response functions ofα,hydrogen ions(H^(+),H_(2)^(+)and H_(3)^(+))andγfor a detector module were measured with^(241)Am,^(137)Cs and^(152)Eu sources together with the 50 kV ECRIS platform.The overall results indicate that the designed E//B NPA device is capable of measuring the intensity of neutral hydrogen and deuteron atoms with energy higher than 20 keV.展开更多
Forward osmosis(FO), as an emerging technology, is influenced by different factors such as operating conditions,module characteristics, and membrane properties. The general aim of this study was to develop a suitable(...Forward osmosis(FO), as an emerging technology, is influenced by different factors such as operating conditions,module characteristics, and membrane properties. The general aim of this study was to develop a suitable(flexible,comprehensive, and convenient to use) computational tool which is able to simulate osmosis through an asymmetric membrane oriented in pressure retarded osmosis(PRO) mode in a wide variety of scenarios. For this purpose, an agent-based model was created in NetLogo platform, which is an easy-to-use application environment with graphical visualization abilities and well suited for modeling a complex system evolving over time. The simulation results were validated with empirical data obtained from literature and a great agreement was observed. The effect of various parameters on process performance was investigated in terms of temperature,cross-flow velocity, length of the module, pure water permeability coefficient, and structural parameter of the membrane. Results demonstrated that the increase in all parameters, except structural parameter of the membrane and the length of module led to the increase of average water flux. Moreover, nine different draw solutes were selected in order to assess the influence of net bulk osmotic pressure difference between the draw solution(DS) and feed solution(FS)(known as the driving force of FO process) on water flux. Based on the findings of this paper, the performance of FO process(PRO mode) can be efficiently evaluated using the NetL ogo platform.展开更多
目的:建立天南星中化学成分快速表征的分析方法,并用于该药材的质量控制。方法:采用超高效液相色谱联用四级杆串联飞行时间质谱(UPLC-Q-TOF/MS)结合UNIFI质谱数据分析平台,选择Waters Acquity UPLC HSS T 3 C 18色谱柱,以0.1%甲酸水和0...目的:建立天南星中化学成分快速表征的分析方法,并用于该药材的质量控制。方法:采用超高效液相色谱联用四级杆串联飞行时间质谱(UPLC-Q-TOF/MS)结合UNIFI质谱数据分析平台,选择Waters Acquity UPLC HSS T 3 C 18色谱柱,以0.1%甲酸水和0.1%甲酸乙腈为流动相进行梯度洗脱,流速为0.35 mL/min,进样量5μL;选择电喷雾离子源,以MS^(E)模式采集正、负离子下天南星化学成分的质谱数据;通过UNIFI平台自带数据库结合文献检索建立天南星化学成分数据库,并根据化合物的精准分子质量、二级碎片离子信息及与对照品和文献数据等比对进化学成分的鉴定。结果:在正离子模式下鉴定出49个化合物,负离子模式下鉴定16个化合物,主要以有机酸、氨基酸及黄酮苷类化合物为主。其中,35个化合物可能首次从天南星中发现。结论:采用UPLC-Q-TOF/MS结合UNIFI平台的分析方法可快速鉴定天南星的化学成分,该研究结果可为天南星药效物质基础的研究以及质量控制体系建立和产品开发等提供科学依据。展开更多
文摘This research introduces a novel approach to improve and optimize the predictive capacity of consumer purchase behaviors on e-commerce platforms. This study presented an introduction to the fundamental concepts of the logistic regression algorithm. In addition, it analyzed user data obtained from an e-commerce platform. The original data were preprocessed, and a consumer purchase prediction model was developed for the e-commerce platform using the logistic regression method. The comparison study used the classic random forest approach, further enhanced by including the K-fold cross-validation method. Evaluation of the accuracy of the model’s classification was conducted using performance indicators that included the accuracy rate, the precision rate, the recall rate, and the F1 score. A visual examination determined the significance of the findings. The findings suggest that employing the logistic regression algorithm to forecast customer purchase behaviors on e-commerce platforms can improve the efficacy of the approach and yield more accurate predictions. This study serves as a valuable resource for improving the precision of forecasting customers’ purchase behaviors on e-commerce platforms. It has significant practical implications for optimizing the operational efficiency of e-commerce platforms.
基金supported by the National Magnetic Confinement Fusion Energy R&D Program of China(No.2018YFE0310200)National Natural Science Foundation of China(Nos.11705242,11805138 and 12175156)the Fundamental Research Funds for the Central Universities in China(Nos.YJ201820 and YJ201954)。
文摘An E//B neutral particle analyzer(NPA)has been designed and is under development at Sichuan University and Southwestern Institute of Physics.The main purpose of the E//B NPA is to measure the distribution function of fast ions in the HL-2A/3 tokamak.The E//B NPA contains three main units,i.e.the stripping unit,the analyzing unit and the detection unit.A gas stripping chamber was adopted as the stripping unit.The results of the simulations and beam tests for the stripping chamber are presented.Parallel electric and magnetic fields provided by a NdFeB permanent magnet and two parallel electric plates were designed and constructed for the analyzing unit.The calibration of the magnetic and electric fields was performed using a 50 kV electron cyclotron resonance ion source(ECRIS)platform.The detection unit consists of 32lutetium-yttrium oxyorthosilicate(LYSO)detector modules arranged in two rows.The response functions ofα,hydrogen ions(H^(+),H_(2)^(+)and H_(3)^(+))andγfor a detector module were measured with^(241)Am,^(137)Cs and^(152)Eu sources together with the 50 kV ECRIS platform.The overall results indicate that the designed E//B NPA device is capable of measuring the intensity of neutral hydrogen and deuteron atoms with energy higher than 20 keV.
文摘Forward osmosis(FO), as an emerging technology, is influenced by different factors such as operating conditions,module characteristics, and membrane properties. The general aim of this study was to develop a suitable(flexible,comprehensive, and convenient to use) computational tool which is able to simulate osmosis through an asymmetric membrane oriented in pressure retarded osmosis(PRO) mode in a wide variety of scenarios. For this purpose, an agent-based model was created in NetLogo platform, which is an easy-to-use application environment with graphical visualization abilities and well suited for modeling a complex system evolving over time. The simulation results were validated with empirical data obtained from literature and a great agreement was observed. The effect of various parameters on process performance was investigated in terms of temperature,cross-flow velocity, length of the module, pure water permeability coefficient, and structural parameter of the membrane. Results demonstrated that the increase in all parameters, except structural parameter of the membrane and the length of module led to the increase of average water flux. Moreover, nine different draw solutes were selected in order to assess the influence of net bulk osmotic pressure difference between the draw solution(DS) and feed solution(FS)(known as the driving force of FO process) on water flux. Based on the findings of this paper, the performance of FO process(PRO mode) can be efficiently evaluated using the NetL ogo platform.
文摘目的:建立天南星中化学成分快速表征的分析方法,并用于该药材的质量控制。方法:采用超高效液相色谱联用四级杆串联飞行时间质谱(UPLC-Q-TOF/MS)结合UNIFI质谱数据分析平台,选择Waters Acquity UPLC HSS T 3 C 18色谱柱,以0.1%甲酸水和0.1%甲酸乙腈为流动相进行梯度洗脱,流速为0.35 mL/min,进样量5μL;选择电喷雾离子源,以MS^(E)模式采集正、负离子下天南星化学成分的质谱数据;通过UNIFI平台自带数据库结合文献检索建立天南星化学成分数据库,并根据化合物的精准分子质量、二级碎片离子信息及与对照品和文献数据等比对进化学成分的鉴定。结果:在正离子模式下鉴定出49个化合物,负离子模式下鉴定16个化合物,主要以有机酸、氨基酸及黄酮苷类化合物为主。其中,35个化合物可能首次从天南星中发现。结论:采用UPLC-Q-TOF/MS结合UNIFI平台的分析方法可快速鉴定天南星的化学成分,该研究结果可为天南星药效物质基础的研究以及质量控制体系建立和产品开发等提供科学依据。
