Comparison of debris flow susceptibility assessment methods:support vector machine,particle swarm optimization,and feature selection techniques

The selection of important factors in machine learning-based susceptibility assessments is crucial to obtain reliable susceptibility results.In this study,metaheuristic optimization and feature selection techniques were applied to identify the most important input parameters for mapping debris flow susceptibility in the southern mountain area of Chengde City in Hebei Province,China,by using machine learning algorithms.In total,133 historical debris flow records and 16 related factors were selected.The support vector machine(SVM)was first used as the base classifier,and then a hybrid model was introduced by a two-step process.First,the particle swarm optimization(PSO)algorithm was employed to select the SVM model hyperparameters.Second,two feature selection algorithms,namely principal component analysis(PCA)and PSO,were integrated into the PSO-based SVM model,which generated the PCA-PSO-SVM and FS-PSO-SVM models,respectively.Three statistical metrics(accuracy,recall,and specificity)and the area under the receiver operating characteristic curve(AUC)were employed to evaluate and validate the performance of the models.The results indicated that the feature selection-based models exhibited the best performance,followed by the PSO-based SVM and SVM models.Moreover,the performance of the FS-PSO-SVM model was better than that of the PCA-PSO-SVM model,showing the highest AUC,accuracy,recall,and specificity values in both the training and testing processes.It was found that the selection of optimal features is crucial to improving the reliability of debris flow susceptibility assessment results.Moreover,the PSO algorithm was found to be not only an effective tool for hyperparameter optimization,but also a useful feature selection algorithm to improve prediction accuracies of debris flow susceptibility by using machine learning algorithms.The high and very high debris flow susceptibility zone appropriately covers 38.01%of the study area,where debris flow may occur under intensive human activities and heavy rainfall events.

Efficacy of fexuprazan compared with rebamipide in Korean patients with gastritis:A matching-adjusted indirect comparison

BACKGROUND Gastritis is one of the most frequently diagnosed diseases requiring medical treatment in South Korea.Fexuprazan,a novel potassium-competitive acid blocker,has been approved for treating gastritis and erosive esophagitis.Meanwhile,rebamipide is the most commonly used mucoprotective agent for acute and chronic gastritis in real-world settings in South Korea.However,there have been no studies comparing the efficacy of these two drugs yet.AIM To compare the efficacy of fexuprazan with that of rebamipide for acute and chronic gastritis.METHODS This was a matching-adjusted indirect comparison.Individual patient data from a phase III study of fexuprazan(10 mg BID)were compared with cumulative data from two matching studies of rebamipide(100 mg TID).Erosion improvement and healing rates were compared between two weeks of fexurapan,two weeks of rebamipide,and four weeks of rebamipide.The two main outcome variables were presented as percentages,and the risk differences(RD)and 95%confidence intervals(CI)were calculated for the relative treatment effects.RESULTS In the primary analysis,the erosion improvement and healing rates after a twoweek treatment with fexuprazan were 64.5%and 53.2%,respectively,while a twoweek treatment with rebamipide resulted in erosion improvement and healing rates of 43.6%(RD:21.0%;95%CI:9.6-32.3;P<0.01)and 35.6%(RD:17.6%;95%CI:6.1-29.2;P=0.003),respectively.In the additional analysis,the erosion improvement and healing rates for the two-week fexuprazan treatment(64.2%and 51.2%,respectively)were similar to those obtained during a four-week treatment with rebamipide(60.6%;RD:3.6%;95%CI:-9.8,17.0;P=0.600 and 53.5%;RD:-2.3%;95%CI:-16.1,11.5;P=0.744,respectively).CONCLUSION The two-week fexuprazan treatment was superior to the two-week rebamipide treatment and similar to the fourweek rebamipide treatment for patients with gastritis.

Accuracy comparison and improvement for state of health estimation of lithium-ion battery based on random partial recharges and feature engineering

State of health(SOH)estimation of e-mobilities operated in real and dynamic conditions is essential and challenging.Most of existing estimations are based on a fixed constant current charging and discharging aging profiles,which overlooked the fact that the charging and discharging profiles are random and not complete in real application.This work investigates the influence of feature engineering on the accuracy of different machine learning(ML)-based SOH estimations acting on different recharging sub-profiles where a realistic battery mission profile is considered.Fifteen features were extracted from the battery partial recharging profiles,considering different factors such as starting voltage values,charge amount,and charging sliding windows.Then,features were selected based on a feature selection pipeline consisting of filtering and supervised ML-based subset selection.Multiple linear regression(MLR),Gaussian process regression(GPR),and support vector regression(SVR)were applied to estimate SOH,and root mean square error(RMSE)was used to evaluate and compare the estimation performance.The results showed that the feature selection pipeline can improve SOH estimation accuracy by 55.05%,2.57%,and 2.82%for MLR,GPR and SVR respectively.It was demonstrated that the estimation based on partial charging profiles with lower starting voltage,large charge,and large sliding window size is more likely to achieve higher accuracy.This work hopes to give some insights into the supervised ML-based feature engineering acting on random partial recharges on SOH estimation performance and tries to fill the gap of effective SOH estimation between theoretical study and real dynamic application.

Efficacy comparison of multipoint and single point scanning panretinal laser photocoagulation in non-proliferative diabetic retinopathy treatment

BACKGROUND Non-proliferative diabetic retinopathy(NPDR)poses a significant challenge in diabetes management due to its microvascular changes in the retina.Laser photocoagulation,a conventional therapy,aims to mitigate the risk of progressing to proliferative diabetic retinopathy(PDR).AIM To compare the efficacy and safety of multi-spot vs single-spot scanning panretinal laser photocoagulation in NPDR patients.METHODS Forty-nine NPDR patients(86 eyes)treated between September 2020 and July 2022 were included.They were randomly allocated into single-spot(n=23,40 eyes)and multi-spot(n=26,46 eyes)groups.Treatment outcomes,including bestcorrected visual acuity(BCVA),central macular thickness(CMT),and mean threshold sensitivity,were assessed at predetermined intervals over 12 months.Adverse reactions were also recorded.RESULTS Energy levels did not significantly differ between groups(P>0.05),but the multi-spot group exhibited lower energy density(P<0.05).BCVA and CMT improvements were noted in the multi-spot group at one-month posttreatment(P<0.05).Adverse reaction incidence was similar between groups(P>0.05).CONCLUSION While energy intensity and safety were comparable between modalities,multi-spot scanning demonstrated lower energy density and showed superior short-term improvements in BCVA and CMT for NPDR patients,with reduced laser-induced damage.

Global Research Progress on Municipal Waste and Future Prospect Based on the Cross-national Comparisons

Due to the acceleration of urbanization,the municipal waste(MW)problem has transformed into a global challenge for urb-an sustainability.To elucidate historical trends,current focal points,and future directions in MW research,we conducted a bibliometric analysis and employed knowledge graph visualization to scrutinize a total of 34212 articles,which were published between 1991 and 2021 in the Web of Science(WoS)core database.The results indicated that current major research themes encompass waste classifica-tion and recycling,waste management and public behavior,waste disposal methods and technologies,as well as environmental impact and evaluation.There has been a shift in the research focus from the environmental impacts of waste incineration to sustainable manage-ment related issues.A comparison of research from six typical countries revealed the differences in research priorities and techniques advantages.Scholars from the USA and Britain initiated MW research earlier than other countries and investigated management issues in depth,such as public behavior and willingness to pay.Meanwhile,Japanese,German,and Swedish scholars conducted extensive studies on advanced waste treatment technologies,such as disposal and recycling,risk assessment,and waste-to-energy techniques.Chinese scholars placed particular emphasis on end-of-pipe treatments and their associated environmental impacts.Hotspots and poten-tial future frontiers were identified by burst detection analysis.Keywords with high value of burst index(BI)worldwide are food waste and circular economy.Chinese scholars have put great efforts on waste environmental impact and its recycling technologies,while we’re expecting to further investigating vulnerable population.Furthermore,this study contributes to bridging the regional gap of scientific research among different countries and fostering international collaboration.

Comparison and Selection of Water Restoration Techniques for Artificial Landscape Lakes in Nantong City

As an important part of urban infrastructure,urban water system is of great and far-reaching significance for ensuring urban flood control and waterlogging safety,protecting ecological environment and building livable homes.Taking the urban water system of Nantong as an example,Nantong Water Resources Bureau issued R evision of Nantong Urban Water System Planning in 2017,and put forward the construction of the"two circles,eight lakes and nine veins"water system layout,giving new vitality to the urban water system.In view of problems existing in newly excavated artificial landscape lakes,such as fragile water ecosystem,strong eutrophication trend,poor environmental sensory effect and unsatisfactory water landscape effect,it is urgent to study the in-situ water ecological restoration technique of"algae-controlling zooplankton+submerged plant community"to build a"grass-type clear water"ecosystem for artificial landscape lakes,so as to improve the water sensory index and self-purification ability and finally realize the double improvement of"sensory effect and water quality"of artificial landscape lakes.

Nickel-Nitrogen-Carbon(Ni-N-C)Electrocatalysts Toward CO_(2)electroreduction to CO:Advances,Optimizations,Challenges,and Prosoects

Electrocatalytic reduction of CO_(2)into high energy-density fuels and value-added chemicals under mild conditions can promote the sustainable cycle of carbon and decrease current energy and environmental problems.Constructing electrocatalyst with high activity,selectivity,stability,and low cost is really matter to realize industrial application of electrocatalytic CO_(2)reduction(ECR).Metal-nitrogen-carbon(M-N-C),especially Ni-N-C,display excellent performance,such as nearly 100%CO selectivity,high current density,outstanding tolerance,etc.,which is considered to possess broad application prospects.Based on the current research status,starting from the mechanism of ECR and the existence form of Ni active species,the latest research progress of Ni-N-C electrocatalysts in CO_(2)electroreduction is systematically summarized.An overview is emphatically interpreted on the regulatory strategies for activity optimization over Ni-N-C,including N coordination modulation,vacancy defects construction,morphology design,surface modification,heteroatom activation,and bimetallic cooperation.Finally,some urgent problems and future prospects on designing Ni-N-C catalysts for ECR are discussed.This review aims to provide the guidance for the design and development of Ni-N-C catalysts with practical application.

Direct Pointwise Comparison of FE Predictions to StereoDIC Measurements:Developments and Validation Using Double Edge-Notched Tensile Specimen

To compare finite element analysis(FEA)predictions and stereovision digital image correlation(StereoDIC)strain measurements at the same spatial positions throughout a region of interest,a field comparison procedure is developed.The procedure includes(a)conversion of the finite element data into a triangular mesh,(b)selection of a common coordinate system,(c)determination of the rigid body transformation to place both measurements and FEA data in the same system and(d)interpolation of the FEA nodal information to the same spatial locations as the StereoDIC measurements using barycentric coordinates.For an aluminum Al-6061 double edge notched tensile specimen,FEA results are obtained using both the von Mises isotropic yield criterion and Hill’s quadratic anisotropic yield criterion,with the unknown Hill model parameters determined using full-field specimen strain measurements for the nominally plane stress specimen.Using Hill’s quadratic anisotropic yield criterion,the point-by-point comparison of experimentally based full-field strains and stresses to finite element predictions are shown to be in excellent agreement,confirming the effectiveness of the field comparison process.

Does US Dollar Supply Trigger House Price Fluctuations?An International Comparison

Cyclical fluctuations in asset prices are closely related to the overall stability of the macroeconomy and have thus become a significant topic in academic and professional exploration.Among these fluctuations,changes in the supply of the U.S.dollar,the global reserve,and primary settlement currency have a broad and far-reaching impact on international financial markets.Since COVID-19,asset prices across various countries have shown differing trends due to fluctuations in the U.S.dollar supply.Housing prices,a key focus in asset pricing research,have been affected to varying degrees.This thesis utilizes seven house price indices from representative cities worldwide from 2020 to 2023 to compare the differential impacts across various countries using an empirical approach.The results indicate that the impact of the U.S.dollar money supply(M2)diminishes in a gradient from the U.S.to East Asia,and then to Europe.

Comparison of Two Recurrent Neural Networks for Rainfall-Runoff Modeling in the Zou River Basin at Atchérigbé (Bénin)

Hydrological models are developed to simulate river flows over a watershed for many practical applications in the field of water resource management. The present paper compares the performance of two recurrent neural networks for rainfall-runoff modeling in the Zou River basin at Atchérigbé outlet. To this end, we used daily precipitation data over the period 1988-2010 as input of the models, such as the Long Short-Term Memory (LSTM) and Recurrent Gate Networks (GRU) to simulate river discharge in the study area. The investigated models give good results in calibration (R2 = 0.888, NSE = 0.886, and RMSE = 0.42 for LSTM;R2 = 0.9, NSE = 0.9 and RMSE = 0.397 for GRU) and in validation (R2 = 0.865, NSE = 0.851, and RMSE = 0.329 for LSTM;R2 = 0.9, NSE = 0.865 and RMSE = 0.301 for GRU). This good performance of LSTM and GRU models confirms the importance of models based on machine learning in modeling hydrological phenomena for better decision-making.

Comparison of the Development of CDMO at Home and Abroad and Its Enlightment to China

Objective To analyze the development status of contract development manufacturing organization(CDMO)at home and abroad,and to make some suggestions for the development of CDMO in China.Methods The relevant literature was searched and reviewed,and the development status of CDMOs in the United States,France,Japan and China was compared from the aspects of market scale,development process,development focus,advantages and disadvantages,and policy support.Then,some suggestions for the development of CDMO enterprises in China were summarized.Results and Conclusion Through the comparison of CDMO development at home and abroad,it can be seen that China started CDMO late,there were many technical barriers and its globalization layout were not sufficient.However,the development trend was good and it focused on the field of chemical drugs and biological drugs to constantly develop innovative drugs.China needs to continuously improve its own technical capabilities to carry out innovative research.Therefore,cost reduction and efficiency increase will be the key elements for the development of CDMOs,and they are expected to have a rapid and comprehensive development in the future.

“大、小、重、慢”疾病定义与全科医生“4善”定位的探讨

随着我国医药卫生体制的深度改革,特别是分级诊疗制度的推进,全科医生在基层医疗保健体系中的角色日益重要。全科医生不仅是居民健康的第一道防线,更是常见疾病预防、诊断、治疗及健康教育的关键执行者。国家对全科医生提出了“小病善治、大病善识、重病善转、慢病善管”的临床定位。本文通过问答形式,分析“小、大、重、慢”疾病的分类与全科医生的“4善”定位,探讨全科医生在新医改时代下的重要职能及挑战。访谈者认为虽然分级诊疗制度旨在优化医疗资源配置,但在实践中仍面临“大、小、重、慢”疾病分类的模糊性和基层医疗资源的不均衡分配等问题。全科医生在这个体系中扮演着至关重要的角色,其需要具备综合的临床诊疗能力,并与专科医生共同制定临床判断标准和诊疗标准。为了应对这些挑战并充分发挥全科医生在现代医疗体系中的作用,迫切需要对全科医学教育和实践进行进一步改革与优化,同时强化全科医生的角色定位,以确保在提升医疗服务质量和效率的同时,实现公平和可持续的健康保障体系。

基于FS-SIA的毁伤预测神经网络超参数优化方法

针对毁伤预测中神经网络超参数设置及调试过程较为复杂的问题,提出一种基于特征选择结合群体智能(feature selection and swarm intelligence algorithm,FS-SIA)的超参数优化方法,用于在毁伤预测中对神经网络进行超参数的搜索和优化。首先,通过多种特征排序方法确定毁伤特征的重要性,选取公共的特征偏序子集用于模型训练。其次,针对具体的神经网络模型,分别采用多种群体智能算法进行超参数的搜索和优化。最后,得出特征集性能最优的超参数训练模型。实验结果表明,相较于未经特征排序而单纯采用群体智能算法的其他超参数优化模型,所提方法在毁伤预测中具有更快的收敛速度和更高的准确率。

Comparison of stand structure and growth between artificial and natural forests of Pinus sylvestiris var. mongolica on sandy land

Mongolian pine (Pinus sylvestiris Linnaeus var. mongolica Litvinov) as a valuable conifer tree species has been broadly introduced to the sandy land areas in 揟hree North?regions (North, northwest and northeast of China), but many problems occurred in the earliest Mongolian pine plantations in Zhanggutai, Zhangwu County, Liaoning Province (ZZL). In order to clarify the reason, comprehensive investigations were carried out on differences in structure characteristics, growth processes and ecological factors between artificial stands (the first plantation established in ZZL in 1950s) and natural stands (the origin forests of the tree species in Honghuaerji, Inner Mongolia) on sandy land. The results showed that variation of diameter-class distributions in artificial stands and natural stands could be described by Weibull and Normal distribution models, respectively. Chapman-Richards growth model was employed to reconstruct the growth process of Mongolian pine based on the data from field investigation and stem analysis. The ages of maximum of relative growth rate and average growth rate of DBH, height, and volume of planted trees were 11, 22 years, 8, 15 years and 35, 59 years earlier than those of natural stand trees, respectively. In respect of the incremental acceleration of volume, the artificial and natural stands reached their maximum values at 14 years and 33 years respectively. The quantitative maturity ages of artificial stands and natural stands were 43 years and 102 years respectively. It was concluded that the life span of the Mongolian pine trees in natural stands was about 60 years longer than those in artificial stands. The differences mentioned above between artificial and natural Mongolian pine forests on sandy land were partially attributed to the drastic variations of ecological conditions such as latitude, temperature, precipitation, evaporation and height above sea level. Human beings' disturbances and higher density in plantation forest may be ascribed as additional reasons. Those results may be potentially useful for the management and afforestation of Mongolian pine plantations on sandy land in arid and semi-arid areas.

基于近端策略优化的两栖无人平台路径规划算法研究

为解决水陆两栖无人平台在复杂环境中的路径规划问题,针对传统方法难以应对动态障碍物和多变环境的局限性,提出了一种基于近端策略优化(PPO)的路径规划算法,包含四种感知信息输入方案以及速度强化奖励函数,适应动态和静态环境.该算法通过批次函数正则化、策略熵引入和自适应裁剪因子,显著提升了算法的收敛速度和稳定性.研究中采用了ROS仿真平台,结合Flatland物理引擎和PedSim插件,模拟了包含动态障碍物的多种复杂场景.实验结果表明,采用BEV+V状态空间输入结构和离散动作空间的两栖无人平台,在路径规划中展现出高成功率和低超时率,优于传统方法和其他方案.仿真和对比实验显示采用鸟瞰图与速度组合的状态空间数据结构配合速度强化奖励函数算法提高了性能,收敛速度提高25.58%,路径规划成功率提升25.54%,超时率下降13.73%.

考虑运营风险的医疗废物回收选址多目标鲁棒优化研究

为规避突发公共卫生事件下的不确定风险,研究医疗废物回收网络中的回收中心、处理中心、处置中心等节点选址问题,以总成本最小以及总风险最小为目标,构建考虑运营风险的医疗废物回收选址多目标鲁棒优化模型,设计非支配排序遗传算法,提出p鲁棒迭代算子求解p值下界,采用轮盘赌选择,结合精英策略、均匀交叉和反向变异等遗传操作。基于仿真案例,求解确定性模型与鲁棒优化模型得到帕累托解。模型对比结果表明鲁棒优化模型适用所有情景,且成本相对遗憾值均小于2%,能够有效应对参数不确定引起的设施选址变化。对p值进行灵敏度分析,结果表明当0.004≤p≤0.08时,解的质量随p值增大而上升;p值越接近下界0.004,目标值下降越迅速,越适于应对紧急情况;同时决策者的风险偏好程度和总成本对设施布局有重要影响,需对二者进行综合权衡。

Comparison of the City Water Consumption Short-Term Forecasting Methods

There are a lot of methods in city water consumption short-term forecasting both inside and outside the country. But among these methods there exist many advantages and shortcomings in model establishing, solving and predicting accuracy, speed, applicability. This article draws lessons from other realm mature methods after many years′ study. It′s systematically studied and compared to predict the water consumption in accuracy, speed, effect and applicability among the time series triangle function method, artificial neural network method, gray system theories method, wavelet analytical method.

基于响应面分析下中草药移栽机的优化设计

通过响应面分析法对中草药移栽机进行优化设计,以提高中草药种植效率和质量。首先,选取移栽速度、移栽深度和移栽器械倾角3个因素作为设计变量,选取移栽成功率和移栽损伤率作为评价指标;在此基础上,设计了一个采用多种传感器组合的控制系统,采用模糊控制算法进行控制,并通过试验得到的数据进行响应面分析,得出了最优设计方案。研究结果表明:最优移栽速度为0.2 m/s,最优移栽深度为15 cm,最优移栽器械倾角为25°;通过优化设计,中草药移栽机的移栽成功率提高了11.8%,移栽损伤率降低了9.6%,取得了较好的效果。

基于粒子群优化算法的农业机器人控制策略研究

介绍了粒子群优化算法的概念,并由数学模型、边界约束和环境约束对农业机器人优化约束模型进行了分析,实现了对农业机器人的动态避障和路径规划。仿真实验表明:针对复杂的作业环境,农业机器人可以进行最优避障路径规划,且算法收敛速度较快,能够满足设计要求,证明系统具有一定的可行性。

水力循环高架设施栽培装置优化设计及试验分析

高架设施栽培模式提升了温室作物的产量和质量。为此,针对固定式高架设施遮荫问题,通过测定30°、40°、50°、60°等不同角度栽培装置的光照遮阴变化情况,确定了基于光照因素的最优高架栽培架式角度为50°。为了解决固定式高架设施角度过大、底层作物光照不足等问题,利用温室控温管路系统中水的压力,创新设计了一种以水轮机为动力的自动循环高架装置,分析了结构组成及工作原理,采用SolidWorks软件设计了三维模型。同时,通过Fluent模拟分析不同型号叶轮作用下的水力压力和速度变化,确定了双列直线型六叶轮为最优叶轮选型。装置是以水力产生动力使栽培槽围绕支架匀速转动,为高架设施架式设计提供一种新思路,在创造良好光照条件的同时减少能源的消耗,具有较高的经济效益,在实际生产中具有一定的推广应用价值。