Traditional Multiple Regression Model Research Articles

Radial basis function neural network and overlay sampling uniform design toward polylactic acid molecular weight prediction

Polylactic acid (PLA) is a potential polymer material as a substitute for traditional plastics, and the accurate molecular weight distribution range of PLA is strictly required in practical applications. Therefore, exploring the relationship between synthetic conditions and PLA molecular weight is crucially important. In this work, direct polycondensation combined with overlay sampling uniform design (OSUD) was applied to synthesize the low molecular weight PLA. Then a multiple regression model and two artificial neural network models on PLA molecular weight versus reaction temperature, reaction time, and catalyst dosage were developed for PLA molecular weight prediction. The characterization results indicated that the low molecular weight PLA was efficiently synthesized under this method. Meanwhile, the experimental dataset acquired from OSUD successfully established three predictive models for PLA molecular weight. Among them, both artificial neural network models had significantly better predictive performance than the regression model. Notably, the radial basis function neural network model had the best predictive accuracy with only 11.9% of mean relative error on the validation dataset, which improved by 67.7% compared with the traditional multiple regression model. This work successfully predicted PLA molecular weight in a direct polycondensation process using artificial neural network models combined with OSUD, which provided guidance for the future implementation of molecular weight-controlled polymer’ synthesis.

Startup drift compensation of RLG based on monotone constrained RBF neural network

Serious startup drift of the Ring Laser Gyroscope (RLG) is observed during cold startup process, which will dramatically degrade the performances of the corresponding Inertial Navigation System (INS). In this paper, correlation analysis method, which analyzes the relationship between the startup drift of the RLG and the temperature change, is used to determine the significant temperature-related terms during gyroscope startup. Based on the significant temperature-related terms and the startup time length, a startup drift compensation model for RLG based on monotonicity-constrained Radial Basis Function (RBF) neural network is proposed and validated. Compared with the raw RLG data without compensation, the standard deviation of the RLG output with the proposed constrained RBF network model is decreased by more than 46%, and the peak-to-peak value is decreased by more than 35%. Compared with the traditional multiple regression model, the standard deviation and peak-to-peak value of the RLG output are decreased by more than 10% and 6%, respectively. Compared with the common RBF network model, the standard deviation and peak-to-peak value of the RLG output are decreased by more than 8% and 3%, respectively. Navigation experiments also validate the effectiveness of the compensation model.

A hybrid Budyko-type regression framework for estimating baseflow from climate and catchment attributes

Researchers seek improved models for estimating baseflow in ungauged catchments as the statistical and process-based methods traditionally used are not easily transferable and do not give robust predictions, respectively. In this study, a process-based statistical hybrid model for estimating baseflow, known here as the Budyko-type baseflow regression (BBR) model, was developed by combining the linear storage-discharge relationship with the Budyko function, and applying multiple regression. The performance of the hybrid model was then evaluated using data from 671 near-natural catchments acquired from four large-sample hydrometeorological datasets. The results showed that the BBR model performed well in estimating baseflow on both national and regional scales; the coefficient of determination between the observed and predicted mean annual baseflow varied from 0.85 to 0.94 for the calibration catchments and from 0.71 to 0.96 for the validation catchments. The BBR model has more of a physical basis, is more transferable, and is less likely to produce unrealistic (negative) mean annual baseflows than traditional multiple regression models. It is also less complex than process-based models. The calibrated BBR models were used to estimate the mean annual baseflow and the elasticity of the baseflow to climate and catchment attributes at the national scale for the United States, United Kingdom, Brazil, and Australia. The results showed that climate (precipitation and potential evapotranspiration) had the most control on the baseflow, and that the soil sand content and the Normalized Difference Vegetation Index were also important catchment attributes. The BBR model developed in this study offers scientists a new and improved method for estimating baseflow. The results generated by the model in this study will improve our understanding of how climate and landscape control the baseflow.

Machine learning classifiers do not improve prediction of hospitalization > 2 days after fast-track hip and knee arthroplasty compared with a classical statistical risk model.

Background and purposePrediction of postoperative outcomes and length of hospital stay (LOS) of patients is vital for allocation of healthcare resources. We investigated the performance of prediction models based on machinelearning algorithms compared with a previous risk stratification model using traditional multiple logistic regression, for predicting the risk of a LOS of > 2 days after fast-track total hip and knee replacement.Patients and methods3 different machine learning classifiers were trained on data from the Lundbeck Centre for Fast-track Hip and Knee Replacement Database (LCDB) collected from 9,512 patients between 2016 and 2017. The chosen classifiers were a random forest classifier (RF), a support vector machine classifier with a polynomial kernel (SVM), and a multinomial Naïve-Bayes classifier (NB).ResultsComparing performance measures of the classifiers with the traditional model revealed that all the models had a similar performance in terms of F1 score, accuracy, sensitivity, specificity, area under the receiver operating curve (AUC), and area under the precision-recall curve (AUPRC). A feature importance analysis of the RF classifier found hospital, age, use of walking aid, living alone, and joint operated on to be the most relevant input features. None of the classifiers reached a clinically relevant performance with the input data from the LCDB.InterpretationDespite the promising prospects of machine-learning practices for disease and risk prediction, none of the machine learning models tested outperformed the traditional multiple regression model in predicting which patients in this cohort had a LOS > 2 days.

Research on Batch Evaluation of Real Estate Price Based on XGBoost

Nowadays, there is an upsurge of research in the field of artificial intelligence around the world. As artificial intelligence slowly penetrates and is applied to all walks of life, the application of artificial intelligence to the field of real estate price batch evaluation has gradually become a reality. As the core area of artificial intelligence-machine learning, it has strong self-organization, self-adaptation and learning capabilities, and is very good at dealing with nonlinear mapping relations. It is a good choice to apply the ideas and methods of artificial intelligence to the field of real estate price batch evaluation.This paper uses Python web crawler technology to obtain Nanjing's second-hand housing transaction information data set from Shell.com, and cleans the second-hand housing transaction information data set to obtain a standardized data set. Then data processing is performed on the standardized data set, which mainly includes the quantitative processing of sub-type variables to obtain a standardized sample data set. Next, we build a real estate price batch evaluation model based on XGBoost, tune the main parameters of the regression model, and perform 5-fold cross-validation. Finally, we compare and analyze the XGboost regression model with the random forest regression model and the multiple regression model, and find that the XGBoost regression model has considerable advantages compared with the traditional multiple regression model, and is more suitable for building real estate price batch evaluation models; moreover, The real estate price batch evaluation model based on XGBoost is slightly better than the real estate price batch evaluation model based on random forest, and the regression prediction results are more robust.

A field study to predict Cd bioaccumulation in a soil-wheat system: Application of a geochemical model

An accurate model to predict Cd accumulation in crops based on soil properties would facilitate evaluations of soil quality and the potential risk posed by metals. However, given the heterogeneity of soil, such models are difficult to establish on large regional scales. This study for the first time examined the applicability of a multi-surface speciation model (MSM) in predicting Cd accumulation in wheat at a regional field scale, based on 140 soil-wheat paired samples collected from a 205-km2 field. The MSM resulted in a better correlation between Cd accumulation in wheat grain (R2 = 0.75) and roots (R2 = 0.74) than obtained with chemical extraction methods (total Cd in soil, 0.01 M CaCl2, and 0.43 M HNO3). In addition, while the performance of the MSM was comparable to that of a traditional multiple regression model, a parameter-fitting process was not required. The predictive ability of the MSM was further used to assess and predict the soil Cd risk and to develop a soil Cd sensitivity map to better localize areas of greatest sensitivity to Cd contamination. The results showed that the MSM can serve as a useful tool for regional soil risk assessments and thus in the development of soil protection measures.

Multi-Space Seasonal Precipitation Prediction Model Applied to the Source Region of the Yangtze River, China

This paper developed a multi-space prediction model for seasonal precipitation using a high-resolution grid dataset (0.5° × 0.5°) together with climate indices. The model is based on principal component analyses (PCA) and artificial neural networks (ANN). Trend analyses show that mean annual and seasonal precipitation in the area is increasing depending on spatial location. For this reason, a multi-space model is especially suited for prediction purposes. The PCA-ANN model was examined using a 64-grid mesh over the source region of the Yangtze River (SRYR) and was compared to a traditional multiple regression model with a three-fold cross-validation method. Seasonal precipitation anomalies (1961–2015) were converted using PCA into principal components. Hierarchical lag relationships between principal components and each potential predictor were identified by Spearman rank correlation analyses. The performance was compared to observed precipitation and evaluated using mean absolute error, root mean squared error, and correlation coefficient. The proposed PCA-ANN model provides accurate seasonal precipitation prediction that is better than traditional regression techniques. The prediction results displayed good agreement with observations for all seasons with correlation coefficients in excess of 0.6 for all spatial locations.

Assessment of aerosol types on improving the estimation of surface PM2.5 concentrations by using ground-based aerosol optical depth dataset

In this study, the influence of aerosol type classification on estimating surface PM2.5 concentrations was assessed by using ground-based aerosol optical depth (AOD) at 22 ground-based observation points in the United States. To clarify the influence, a two-stage model consisting of a multiple regression model (MRM) and an aerosol classification model (ACM) was proposed to estimate surface PM2.5 concentrations, and results from a traditional MRM and the new ACM-MRM were compared. Results show that the average determination coefficient (R2) of the ACM-MRM (0.52) was greater than that of the MRM (0.44), while the root mean square error (RMSE) and mean absolute percent error (MAPE) of the ACM-MRM (3.74 μg/m3 and 34.91%, respectively) were lower than the values obtained with the MRM (4.09 μg/m3 and 37.64%, respectively). The use of ACM improved the estimation of daily PM2.5 concentrations in different regions and different seasons by reducing the deviations caused by aerosol type changes. Further analysis demonstrated that aerosol type changes had adverse influences on the estimation of short-term PM2.5 concentrations and the introduction of ACM can effectively restrain the adverse influences when aerosols change frequently.

Unequal residential exposure to air pollution and noise: A geospatial environmental justice analysis for Ghent, Belgium.

Following the growing empirical evidence on the health effects of air pollution and noise, the fair distribution of these impacts receives increasing attention. The existing environmental inequality studies often focus on a single environmental impact, apply a limited range of covariates or do not correct for spatial autocorrelation. This article presents a geospatial data analysis on Ghent (Belgium), combining residential exposure to air pollution and noise with socioeconomic variables and housing variables. The global results show that neighborhoods with lower household incomes, more unemployment, more people of foreign origin, more rental houses, and higher residential mobility, are more exposed to air pollution, but not to noise. Multiple regression models to explain exposure to air pollution show that residential mobility and percentage of rental houses are the strongest predictors, stressing the role of the housing market in explaining which people are most at risk. Applying spatial regression models leads to better models but reduces the importance of all covariates, leaving income and residential mobility as the only significant predictors for air pollution exposure. While traditional multiple regression models were not significant for explaining noise exposure, spatial regression models were, and also indicate the significant contribution of income to the model. This means income is a robust predictor for both air pollution and noise exposure across the whole urban territory. The results provide a good starting point for discussions about environmental justice and the need for policy action. The study also underlines the importance of taking spatial autocorrelation into account when analyzing environmental inequality.

Gene-environment interaction between adiponectin gene polymorphisms and environmental factors on the risk of diabetic retinopathy.

Aims/IntroductionTo evaluate whether the adiponectin gene is associated with diabetic retinopathy (DR) risk and interaction with environmental factors modifies the DR risk, and to investigate the relationship between serum adiponectin levels and DR.Materials and MethodsFour adiponectin polymorphisms were evaluated in 372 DR cases and 145 controls. Differences in environmental factors between cases and controls were evaluated by unconditional logistic regression analysis. The model-free multifactor dimensionality reduction method and traditional multiple regression models were applied to explore interactions between the polymorphisms and environmental factors.ResultsUsing the Bonferroni method, we found no significant associations between four adiponectin polymorphisms and DR susceptibility. Multivariate logistic regression found that physical activity played a protective role in the progress of DR, whereas family history of diabetes (odds ratio 1.75) and insulin therapy (odds ratio 1.78) were associated with an increased risk for DR. The interaction between the C-11377 G (rs266729) polymorphism and insulin therapy might be associated with DR risk. Family history of diabetes combined with insulin therapy also increased the risk of DR. No adiponectin gene polymorphisms influenced the serum adiponectin levels. Serum adiponectin levels did not differ between the DR group and non-DR group.ConclusionsNo significant association was identified between four adiponectin polymorphisms and DR susceptibility after stringent Bonferroni correction. The interaction between C-11377G (rs266729) polymorphism and insulin therapy, as well as the interaction between family history of diabetes and insulin therapy, might be associated with DR susceptibility.

Methods for developing and analyzing clinically rich data for patient‐centered outcomes research: an overview

Methods for developing and analyzing clinically rich data for patient‐centered outcomes research: an overview

Regression-fuzzy approach to land valuation

In this paper, we demonstrate that the fuzzy pricing model can improve regression analysis in applications where non-smoothness appears. Combining the fuzzy and regression approaches it is capable of modelling complex non-linearities. The application of this approach describes an effort to design a regression-fuzzy system to estimate real estate market values, especially for vacant urban plots. The results are compared with those obtained using a traditional multiple regression model only. The changes of parameters in the domain of independent variables of the regression function are determined by the analysis of membership functions defining the terms of the fuzzy model. The paper also describes possible future research. The suggested method is interesting for real estate appraisers, real estate companies, and bureaus because it provides a better overview of location prices. The suggested approach could be also used in various other economic and business analyses.

Prediction of the performance of impact hammer by adaptive neuro-fuzzy inference system modelling

Impact type excavators are widely used for excavations, performed in weak-laminated-foliated-anisotropic rocks. Therefore the prediction of the performance of impact hammer is very important in many mining and civil engineering projects. This paper describes the construction of adaptive neuro-fuzzy inference system model for predicting the performance of impact hammer type excavator by considering rock and excavating machine properties such as block punch strength index, geological strength index system and impact hammer power. Extensive field and laboratory studies were conducted in the tunnel construction route of the second stage of Izmir Metro Project, which excavated in laminated-foliated flysch rocks. The results of the constructed adaptive neuro-fuzzy inference system and traditional multiple regression models were compared. Although the prediction performance of traditional multiple regression model is high, it is seen that adaptive neuro-fuzzy inference model exhibits better prediction performance according to statistical performance indicators. By means of the developed model, the performance of impact type excavators can be predicted in terms of net excavation based on the selected rock and machine properties.

Integration of IKONOS imagery for geostatistical mapping of sediment grain size at Baramarae beach, Korea

We describe the potential of high-resolution remote sensing imagery in the geostatistical mapping of sediment grain size distribution in order to supplement sparsely sampled ground observations. Within a multi-Gaussian framework, the IKONOS imagery is used as local means both to estimate the grain size values and to model local uncertainty at unsampled locations. Multiple regression and generalized additive models are applied to compute local mean values. From a case study of Baramarae beach, Korea, all imagery bands showed a reasonable linear relationship with grain size values in phi units, having a correlation coefficient of more than –0.80. Accounting for the IKONOS imagery via simple kriging with local means could reflect detailed surface characteristics with less smoothing effects. Cross validation results showed that the mean square errors from simple kriging with local means via the generalized additive model provided a relative improvement of about 60% over univariate multi-Gaussian kriging and a superior predictive capability when compared with simple kriging with local means via the traditional multiple regression model.

An Adaptive Neuro-Fuzzy Inference System Based Approach to Real Estate Property Assessment

This paper describes a first effort to design and implement an adaptive neuro-fuzzy inference system-based approach to estimate prices for residential properties. The data set consists of historic sales of houses in a market in the Midwest region of the United States and it contains parameters describing typical residential property features and the actual sale price. The study explores the use of fuzzy inference systems to assess real estate property values and the use of neural networks in creating and fine-tuning the fuzzy rules used in the fuzzy inference system. The results are compared with those obtained using a traditional multiple regression model. The paper also describes possible future research in this area.

Combining Geographic Information Systems and Regression Models to Generate Locational Value Residual Surfaces in the Assessment of Residential Property Values

Locational Value Residual Surface (LVRS) has been suggested as an alternative to resolving the difficulty in the traditional modelling of locational influence on property values in a particular area. The objective of this paper was to compare the relative performance of models that apply locational value residual surface (LVRS) and the traditional multiple regression models in the prediction of residential property values. A controlled sample of 125 single- and double-storey residential properties was used to construct regression models. It was found that models applying LVRS were marginally better than the traditional models in predicting property values.

Kalman Filter Analysis in Dendroclimatology

SUMMARY The use of the Kalman filter in the analysis of tree-ring data is summarized. By use of this filter technique, the traditional multiple regression models can be modified to cover linear models with time-dependent coefficients. In that way changes in tree response to weather variations could be detected, possibly indicating anthropogenic influences. The filtering and smoothing operations of the filter are illustrated using simulated tree-ring series. A method for the selection of predictor variables is proposed, which takes into account the special features of time-dependent regression models. Furthermore, the consequences of highly correlated predictors are discussed. An application is given to a ring-width series of a European silver fir from Bad Herrenalb (F.R.G.). The method appears suitable for dealing with both gradual changes and sudden shocks in tree response.