Multiple regression analysis of risk factors related to radiation pneumonitis

BACKGROUND Radiation pneumonitis(RP)is a severe complication of thoracic radiotherapy that may lead to dyspnea and lung fibrosis,and negatively affects patients’quality of life.AIM To carry out multiple regression analysis on the influencing factors of radiation pneumonitis.METHODS Records of 234 patients receiving chest radiotherapy in Huzhou Central Hospital(Huzhou,Zhejiang Province,China)from January 2018 to February 2021,and the patients were divided into either a study group or a control group based on the presence of radiation pneumonitis or not.Among them,93 patients with radiation pneumonitis were included in the study group and 141 without radiation pneumonitis were included in the control group.General characteristics,and radiation and imaging examination data of the two groups were collected and compared.Due to the statistical significance observed,multiple regression analysis was performed on age,tumor type,chemotherapy history,forced vital capacity(FVC),forced expiratory volume in the first second(FEV1),carbon monoxide diffusion volume(DLCO),FEV1/FVC ratio,planned target area(PTV),mean lung dose(MLD),total number of radiation fields,percentage of lung tissue in total lung volume(vdose),probability of normal tissue complications(NTCP),and other factors.RESULTS The proportions of patients aged≥60 years and those with the diagnosis of lung cancer and a history of chemotherapy in the study group were higher than those in the control group(P<0.05);FEV1,DLCO,and FEV1/FVC ratio in the study group were lower than those in the control group(P<0.05),while PTV,MLD,total field number,vdose,and NTCP were higher than in the control group(P<0.05).Logistic regression analysis showed that age,lung cancer diagnosis,chemotherapy history,FEV1,FEV1/FVC ratio,PTV,MLD,total number of radiation fields,vdose,and NTCP were risk factors for radiation pneumonitis.CONCLUSION We have identified patient age,type of lung cancer,history of chemotherapy,lung function,and radiotherapy parameters as risk factors for radiation pneumonitis.Comprehensive evaluation and examination should be carried out before radiotherapy to effectively prevent radiation pneumonitis.

Logistics Regression Analysis between TCM Constitution Types of Patients with Hypertension,Insomnia and ABPM,PSQI

[Objectives]The research aimed to explore the distribution characteristics of TCM constitution types of patients with hypertension and insomnia,and study the clinical characteristics of patients with different constitutions,in order to provide new ideas for the treatment of patients with hypertension and insomnia.[Methods]Cross sectional observation method was used,and 420 patients with hypertension and insomnia were selected.Required information was collected,and the constitution type of traditional Chinese medicine was determined,and relevant data were recorded.SPSS and Logistic regression analysis method were used to explore the correlation between the distribution of TCM constitution types and gender,age,24 h-SBP,24 h-DBP,24 h-BPV,PSQI score,etc.[Results]Among 420 patients,the proportion of gentleness constitution was the most,and others in turn were Qi deficiency constitution>Yang deficiency constitution>phlegm dampness constitution>Qi stagnation constitution>Yin deficiency constitution>blood stasis constitution>damp heat constitution>special constitution.Among male patients,the proportion of gentleness constitution was the most.Among female patients,the proportion of Qi deficiency constitution was the most.In each constitution,the proportion of men and women was different,and the difference in gentleness constitution,Qi deficiency constitution and Yin deficiency constitution had statistical significance(P<0.05).The proportion of gentleness constitution for young and middle-aged patients was the most,while elderly patients with Qi deficiency constitution was the most.There was difference in the distribution of TCM constitution in different age groups,and the difference had statistical significance(P<0.05).Compared with the patients with gentleness constitution,the patients with Qi deficiency constitution,Yang deficiency constitution,Yin deficiency constitution,damp heat constitution,blood stasis constitution and Qi stagnation constitution had different differences in terms of age,24 h-SBP,24 h-DBP,24 h-BPV and PSQI score,and there was statistical significance(P<0.05).Except damp heat constitution,blood stasis constitution and special constitution,other constitutions had certain correlation with age,24 h-SBP,24 h-DBP,24 h-BPV and PSQI score.[Conclusions]TCM constitution types of patients with hypertension and insomnia were dominant by gentleness constitution,Qi deficiency constitution and Yang deficiency constitution.The distribution of TCM constitution in different gender and age groups was different,and different TCM constitution was related to ABPM and PSQI.

Research on the Effect of Artificial Intelligence Real Estate Forecasting Using Multiple Regression Analysis and Artificial Neural Network: A Case Study of Ghana

To transition from conventional to intelligent real estate, the real estate industry must enhance its embrace of disruptive technology. Even though the real estate auction market has grown in importance in the financial, economic, and investment sectors, few artificial intelligence-based research has tried to predict the auction values of real estate in the past. According to the objectives of this research, artificial intelligence and statistical methods will be used to create forecasting models for real estate auction prices. A multiple regression model and an artificial neural network are used in conjunction with one another to build the forecasting models. For the empirical study, the study utilizes data from Ghana apartment auctions from 2016 to 2020 to anticipate auction prices and evaluate the forecasting accuracy of the various models available at the time. Compared to the conventional Multiple Regression Analysis, using artificial intelligence systems for real estate appraisal is becoming a more viable option (MRA). The Artificial Neural network model exhibits the most outstanding performance, and efficient zonal segmentation based on the auction evaluation price enhances the model’s prediction accuracy even more. There is a statistically significant difference between the two models when it comes to forecasting the values of real estate auctions.

Factor Decomposition and Regression Analysis of the Energy Related Carbon Emissions in Shandong, China: A Perspective of Industrial Structure

An in-depth study of the energy related carbon emissions has important practical significance for carbon emissions reduction and structural adjustment in Shandong Province and throughout China.Based on the perspective of industrial structure,the expanded KAYA equation to measure the energy related carbon emissions of the primary industries(Resources and Agriculture)and secondary industries(Manufacturing and Construction)and tertiary industries(Retail and Service)was utilized in Shandong Province from 2011 to 2017.The carbon emissions among industries in Shandong Province were empirically analyzed using the Logarithmic Mean Divisia Index decomposition approach.The results were follows:(1)Under the three industrial dimensions,the energy structure effect and the energy intensity effect have a restraining influence on the carbon emissions of the three industries.(2)The development level effect and the employment scale effect play a pulling role in carbon emissions.(3)From the perspective of the employment structure effect of the primary industry,there is a restraining effect on carbon emissions,while the employment structure effects of the secondary and tertiary industries play a pulling role in carbon emissions,and the employment structure effect of the tertiary industry has a greater pulling effect on carbon emissions than the secondary industry.

Multiple Regression Analysis of Influencing Factors on Yield of New Sugarcane Variety Yuetang 03-373

[Objectives]The purpose of this study was to provide reference for cultivation and promotion of a new sugarcane variety Yuetang 03-373,on the basis of analyzing and summarizing the characters of the variety.[Methods]Correlation,multiple regression and path analyses were performed for the yield and yield components of Yuetang 03-373.[Results]Correlation analysis shows that cane yield was significantly correlated with millable stalk number,stalk length and stalk diameter,and among them,the correlation with millable stalk number was the strongest.Multiple regression and path analyses show that millable stalk number contributed the most to cane yield,followed by stalk length,and stalk diameter contributed the least.The regression equation of cane yield against the three yield components was y=-2.8713+1.5497x1+5.8990x2-395.4294x3(R=0.9672**).[Conclusions]Millable stalk number and stalk length were the important and major factors for high yield of Yuetang 03-373,indicating that Yuetang 03-373 is a sugarcane variety of millable stalk type.In cultivation,full play should be given to the advantage of Yuetang 03-373 in millable stalk number,as well as stalk length(plant height),in order to achieve the purpose of increasing yield.

Using Linear Regression Analysis and Defense in Depth to Protect Networks during the Global Corona Pandemic

The purpose of this research was to determine whether the Linear Regression Analysis can be effectively applied to the prioritization of defense-in-depth security tools and procedures to reduce cyber threats during the Global Corona Virus Pandemic. The way this was determined or methods used in this study consisted of scanning 20 peer reviewed Cybersecurity Articles from prominent Cybersecurity Journals for a list of defense in depth measures (tools and procedures) and the threats that those measures were designed to reduce. The methods further involved using the Likert Scale Model to create an ordinal ranking of the measures and threats. The defense in depth tools and procedures were then compared to see whether the Likert scale and Linear Regression Analysis could be effectively applied to prioritize and combine the measures to reduce pandemic related cyber threats. The results of this research reject the H0 null hypothesis that Linear Regression Analysis does not affect the relationship between the prioritization and combining of defense in depth tools and procedures (independent variables) and pandemic related cyber threats (dependent variables).

Logistic Regression Analysis of Influencing Factors on Serum ALT and HCV RNA Changes in Patients with Chronic Hepatitis C

Objective This study was undertaken to investigate the influencing factors on serum ALT level and hepatitis C virus(HCV)RNA titer in chronic hepatitis C(CHC)patients.Methods All patients enrolled into this study were anti-HCV positive.Retrospective tracing method was applied to detect serum ALT level and HCV RNA titer and to collect general information of the patients such as genders,age groups,interferon medication history,infection pathways,height and weight.Then the multi-factor analysis was adopted with the application of binominal logistic regression mode.Results The abnormal rate of ALT level was positively correlated to HCV RNA and gender while negatively correlated to interferon medication history and age group,with Wald value of the 4 factors as 39.604,11.823,18.991 and 7.389,respectively.The positive rate of HCV RNA was negatively correlated to interferon medication history and gender while positively correlated to ALT level,with corresponding Wald value of the 3 factors as81.394,7.618 and 27.562,respectively.Conclusions The normal ALT level in HCV infected patients was associated with viral load,age,gender and interferon medication history,while the normal rate of HCV RNA titer was closely associated with gender,interferon medication history and ALT level.

A beta regression analysis of COVID-19 mortality in Brazil

Brazil was one of the countries most impacted by the COVID-19 pandemic,with a cumulative total of nearly 700,000 deaths by early 2023.The country's federative units were unevenly affected by the pandemic and adopted mitigation measures of different scopes and intensity.There was intense conflict between the federal government and state governments over the relevance and extent of such measures.We build a simple regression model with good predictive power on state COVID-19 mortality rates in Brazil.Our results reveal that the federative units'urbanization rate and per capita income are important for determining their mean mortality rate and that the number of physicians per 100,000 inhabitants is important for modeling the mortality rate precision.Based on the fitted model,we obtain approximations for the levels of administrative efficiency of local governments in dealing with the pandemic.

Effects of nitrogen fertilizer application on saline-alkali land cotton in China quantified using meta-analysis and regression analysis

Nitrogen fertilizer application is an important means to promote cotton production in saline-alkali land.A metaanalysis and regression analysis of 49 peer-reviewed studies were conducted using yield data(373 data points),dry matter accumulation(114 data points),and water use efficiency(157 data points)to quantify the effect of nitrogen fertilizer on the yield,dry matter accumulation,and water use efficiency of cotton in saline-alkali land in China for different planting management practices and different growing environments.The results showed that the nitrogen application significantly improved the yield,dry matter accumulation,and water use efficiency by 34.11%,36.27%,and 33.87%,respectively,compared with no nitrogen application.The largest improvements in the yield,dry matter accumulation,and water use efficiency occurred in areas where saline-alkali land had been improved for many years,in Eastern China,South Central China,and Northwest China(areas with annual average precipitation≤200 mm or>800 mm,and annual average evaporation≤800 mm or>2400 mm),in areas with trickle irrigation,and fields with a planting density of 100000 to 250000 plants/hm2.Cotton exhibited the optimal response to nitrogen application at a rate of 300-375 kg/hm2,a basal application ratio of 20%-40%,and top-dressing in the cotton bud,flowering boll,and full boll stages.The effect of nitrogen application increased as the salinity increased.A suitable nitrogen application rate,top-dressing ratio,and top-dressing period are crucial for increasing cotton production in saline-alkali land,although environmental differences and planting measures have to be considered.This study provided information on the correct application of nitrogen fertilizer to maximize its benefits and suggests controlling nitrogen fertilizer inputs in agriculture to protect the soil environment and ensure sustainable agricultural development.

Regression analysis and features of negative activation energy for MHD nanofluid flow model:A comparative study

This article elucidates the impact of activation energy on magnetohydrodynamic(MHD)stagnation point nanofluid flow over a slippery surface in a porous regime with thermophoretic and Brownian diffusions.Negative activation energy is scarce in practice,but the impact of negative activation energy could not be neglected as it is noticed in chemical processes.The rate of some Arrhenius-compliant reactions is retarded by increasing the temperature and is therefore associated with negative activation energies,such as exothermic binding of urea or water.In some processes,the temperature dependence of the pressure-induced unfolding and the urea-induced unfolding of proteins at ambient pressure give negative activation energies.The present mathematical model is solved with successive linearization method(a spectral technique).A comparison of results is made for negative and positive values of activation energy.Apart from it,the quadratic multiple regression model is discussed briefly and explained with bar diagrams.It is observed that with rise in unsteadiness parameter from 0 to 1(taking positive activation energy),skin friction and Sherwood number are increased by 9.36%and 19%respectively,and Nusselt number is decreased by 26%.However,for negative activation energy,9.36%and 112%enhancement is observed in skin friction and Sherwood number,respectively.

Unveiling the Predictive Capabilities of Machine Learning in Air Quality Data Analysis: A Comparative Evaluation of Different Regression Models

Air quality is a critical concern for public health and environmental regulation. The Air Quality Index (AQI), a widely adopted index by the US Environmental Protection Agency (EPA), serves as a crucial metric for reporting site-specific air pollution levels. Accurately predicting air quality, as measured by the AQI, is essential for effective air pollution management. In this study, we aim to identify the most reliable regression model among linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), logistic regression, and K-nearest neighbors (KNN). We conducted four different regression analyses using a machine learning approach to determine the model with the best performance. By employing the confusion matrix and error percentages, we selected the best-performing model, which yielded prediction error rates of 22%, 23%, 20%, and 27%, respectively, for LDA, QDA, logistic regression, and KNN models. The logistic regression model outperformed the other three statistical models in predicting AQI. Understanding these models' performance can help address an existing gap in air quality research and contribute to the integration of regression techniques in AQI studies, ultimately benefiting stakeholders like environmental regulators, healthcare professionals, urban planners, and researchers.

Change Point Analysis to Detect the Effect of Pruning Severity on Tree Growth

The effect of pruning severity on tree growth was analyzed by change point detection using segmented regression. The present study applied this analysis to a well-known published data set including diameter growth response, tree age, pruning severity and pretreatment crown size. First, multiple regression analysis was performed to assess the effect of tree age, pruning severity and pretreatment crown size on diameter growth response. Next, segmented regression analysis was performed to assess the effect of pruning severity on diameter growth response. The results of the multiple regression showed that diameter growth response was significantly influenced by pruning severity and pretreatment crown size. The results of the segmented regression showed that in the whole data set, an abrupt change toward a decrease in diameter growth response was detected at 25% of the live crown removed. However, in the group of fully crowned and open-grown, diameter growth response continuously decreased with increasing pruning severity with no significant abrupt change, whereas in the group of 70% - 90% live crown, diameter growth response did not significantly decrease up to the break point (53% crown removed) and then abruptly decreased. This may be the first study to show the numerical evaluation of the effect of pruning severity on tree growth by change point analysis.

Cancer mortality in Serbia, 1991-2015: an age-period-cohort and joinpoint regression analysis

Background:As the result of dramatic political changes,civil wars,and a long-term refugee crisis from the end of the last to beginning of this century,the population of Serbia has experienced significant health problems.The aim of this study was to assess cancer mortality trends in Serbia.Methods:This nationwide study was carried out to analyze cancer mortality in Serbia during 1991-2015 using offi-cial data.The age-standardized mortality rates(per 100,000)were calculated by direct standardization,using the world standard population by Segi.The average annual percent change(AAPC)and corresponding 95%confidence interval(CI)were computed using joinpoint regression analysis.Age-period-cohort analysis was performed to address the possible underlying reasons for the observed temporal trends.Results:Over the 25-year study period,there were 466,075 cancer deaths(266,043 males and 200,032 females)in Serbia.Overall cancer mortality increased between 1991 and 2009 in both males(by+0.9%per year)and females(by+0.8%per year)and has been decreasing since then,by−0.9%annually in both sexes.For almost all major cancers except stomach cancer,cancer mortality in Serbia demonstrated upward trends during the study period.The largest increases were noted in lung cancer among females(AAPC=+3.7,95%CI 3.5-3.9)and prostate cancer in males(AAPC=+1.9,95%CI 1.4-2.3).Conclusions:After two decades of increase,cancer mortality rates are finally declining in Serbia.Despite this,these rates place Serbia among the countries with the highest cancer mortality in the world.

Factors associated with needle sharing among people who inject drugs in Yunnan, China: a combined network and regression analysis

Background:Network analyses have been widely utilized to evaluate large datasets,but have not yet been used to explore factors associated with risk behaviours.In combination with traditional regression analysis,network analyses may provide useful information and highlight key factors for reducing needle sharing behaviours among people who inject drugs(PWID).Methods:Sociodemographic data,and information on injection behaviour and sexual practices were collected from a cross-sectional survey that was conducted with PWID in five prefectures of Yunnan province,China.A combination of logistic regression and correlation network analyses were used to explore key factors for reducing needle-sharing behaviours among PWID.Results:In a total of 1049 PWID,37.5%had a history of needle or syringe sharing.The logistic analysis showed that Zhaotong,Qujing,Dehong,or Lincang residents,diazepam use,longer injection duration,needle reuse,and infection with HIV,viral hepatitis,tuberculosis and/or malaria were independently associated with needle sharing.The correlation network analyses showed that,compared to PWID who had never shared needles,PWID who did share needles would achieve harm reduction goals faster and more permanently.HIV serostatus and marital status were found to be closely associated with other risk factors.By combining regression analyses with network analyses,it was shown that PWID who are HIV seropositive will be an ideal target group for harm reduction programs.Conclusion:Needle-sharing behaviours are common among PWID in Yunnan,and harm reduction programs may help PWID who are HIV seropositive reduce risk behaviours and prevent blood borne diseases.

Heteroscedastic regression analysis method for mixed data

The heteroscedastic regression model was established and the heteroscedastic regression analysis method was presented for mixed data composed of complete data,type-Ⅰ censored data and type-Ⅱ censored data from the location-scale distribution.The best unbiased estimations of regression coefficients,as well as the confidence limits of the location parameter and scale parameter were given.Furthermore,the point estimations and confidence limits of percentiles were obtained.Thus,the traditional multiple regression analysis method which is only suitable to the complete data from normal distribution can be extended to the cases of heteroscedastic mixed data and the location-scale distribution.So the presented method has a broad range of promising applications.

Theoretical modeling of vectoring dual synthetic jet based on regression analysis

The excellent vectoring characteristic of Dual Synthetic Jet(DSJ)provides a new control strategy for the active flow control,such as thrust vectoring control,large area cooling,separated flow control and so on.For incompressible flow,the influence relation of source variables,such as structure parameters of actuators,driving parameters and material attributes of piezoelectric vibrating diaphragm,on the vectoring DSJ and a theoretical model are established based on theoretical and regression analysis,which are all verified by numerical simulations.The two synthetic jets can be deemed as a main flow with a higher jet velocity and a disturbing flow with a lower jet velocity.The results indicate that the influence factors contain the low-pressure area formed at the exit of the disturbing flow,which could promote the vectoring deflection,and the impact effect of the disturbing flow and the suppressive effect of the main flow with the effect of restraining the vectoring deflection.The vectoring angle is a complex parameter coupled by all source variables.The detailed theoretical model,whose error is controlled within 3.6 degrees,can be used to quantitatively assess the vectoring feature of DSJ and thus to provide a guidance for designing the control law applied in the active flow control.

Operational method for determining bottom hole pressure in mechanized oil producing wells,based on the application of multivariate regression analysis

One of the major tasks of monitoring production well operations is to determine bottom-hole flowing pressure.The overwhelming majority of wells in the Perm Krai are serviced using borehole pumps,which makes it difficult to take direct bottom-hole flowing pressure measurements.The bottomhole filtration pressure(BHFP)in these wells is very often determined by recalculating the parameters measured at the well mouth(annulus pressure,dynamic fluid level depth).The recalculation is done by procedures based on analytically determining the characteristics of the gas-liquid mixture in the wellbore,which is very inconsistent to perform due to the mixture's complex behavior.This article proposes an essentially different approach to BHFP measurements that relies on the mathematical processing of the findings of more than 4000 parallel mouth and deep investigations of the oil production wells of a large oil-production region.As a result,multivariate mathematical models are elaborated that allow reliably determining the BHFP of oil-production wells in operation.

Virtual Determination of Sex:Estimating Cut off Value of Digital Metric Traits of Foramen Magnum on Three-dimensional Computed Tomography with Receiver Operating Characteristic and Logistic Regression Analysis

Background:Radiological imaging plays a pivotal role in forensic anthropology.As have the imaging techniques advances,so have the digital skeletal measurements inched towards precision.Secular trends of the population keep on changing in modem times.Hence,finding the precise technique of bone measurement,with greater reproducibility,in modem population is always needed in making population specific biological profile.Aim and Objective:The aim of this study was to estimate the accuracy of the foramen magnum measurement,obtained by three dimensional multi-detector computed tomography using volume rendering technique with the cut off value of each variable,in sex determination of an individual.Materials and Methods:Two metric traits,an antero-posterior diameter(APD)and transverse diameter(TD),were measured digitally in an analysis of 130 radiological images having equal proportion of male and female samples.Foramen magnum index and area of foramen magnum(Area by Radinsky's[AR],Area by Teixeira5s[AT])were derived from APD and TD.Results:Descriptive statistical analysis,using unpaired t-test,showed significant higher value in males in all the variables.Using Pearson correlation analysis,maximum correlation was observed between area(AT and AR r=0.999)and between area and TD(AR r=0.955 and AT r=0.945 respectively).When used individually,TD had the highest predictive value(67.7%)for sex detennination among all the parameters followed by AT(65.4%)and AR(64.6%).Cutoff value of variables TD,AR and AT were 29.9 mm,841.80 mm2 and 849.70 mm2 respectively.Receiver operating characteristic curve predicted male and female sex with 96.2%and 89.2%accuracy respectively.The overall accuracy of the model was 92.7%.Conclusion:Measurements from 3D CT using volume rendering technique were precise,and the application of logistic regression analysis predicted the sex with more accuracy.

Effect of Complex Parameters of Porous Media on Desalination Performance in Air-Gap Diffusion Distillation Based on Multiple Regression Analysis

Air-Gap Diffusion Distillation(AGDD) is a new technology aiming at solving the problem of the safety of drinking water for residents in remote areas that uses a super hydrophilic porous medium as the hot channel and evaporation surface. In the experiment, it was found that the parameters of porous media have a significant influence on the desalination(evaporation) efficiency of AGDD. Although porous media are widely used as evaporation components, the factors affecting their evaporation efficiency are not fully understood. The evaporation process in super hydrophilic porous media is rarely discussed. A large number of experiments have been carried out based on AGDD. The introduction of statistical methods solves the problem that experiments cannot distinguish the contribution of complex parameters of porous media to evaporation efficiency. Stepwise regression analysis is used to reduce the dimensionality of the independent variables and construct regression equations(coefficient of determination R~2 reached 81.3%-96.8%). Evaporation flux correlations and dimensionless mass transfer correlations are established based on porous media parameters. We found that the surface evaporation of super hydrophilic porous media can be divided into three stages: diffusion evaporation, capillary evaporation, and thermal evaporation. The evaporation efficiency of these three stages is controlled by the vapor diffusion process resistance, capillary force, and energy supply. At low saturation, evaporation efficiency is limited by the resistance of the vapor diffusion process. The evaporation efficiency of the porous media is affected predominantly by the pore size, the specific surface area, porosity and the characteristic length. At high saturation, the evaporation efficiency becomes influenced primarily by the permeability. A small thickness and a high hydrophilicity also improve the evaporation efficiency.

Presentation of regression analysis,GP and GMDH models to predict the pedestrian density in various urban facilities

In this study,the relationship between space mean speed(SMS),flow rate and density of pedestrians was investigated in different pedestrian facilities,including 1 walkway,2 sidewalks,2 signalized crosswalks and 2 mid-block crosswalks.First,statistical analysis was performed to investigate the normality of data and correlation of variables.Regression analysis was then applied to determine the relationship between SMS,flow rate,and density of pedestrians.Finally,two prediction models of density were obtained using genetic programming(GP)and group method of data handling(GMDH)models,and k-fold and holdout cross-validation methods were used to evaluate the models.By the use of regression analysis,the mathematical relationships between variables in all facilities were calculated and plotted,and the best relationships were observed in flow rate-density diagrams.Results also indicated that GP had a higher R2 than GMDH in the prediction of pedestrian density in terms of flow rate and SMS,suggesting that GP was better able to model SMS and pedestrian density.Moreover,the application of k-fold cross-validation method in the models led to better performances compared to the holdout cross-validation method,which shows that the prediction models using k-fold were more reliable.Finally,density relationships in all facilities were obtained in terms of SMS and flow rate.