Optimal Combination Of Variables Research Articles

Dominant Tree Species Mapping Using Machine Learning Based on Multi-Temporal and Multi-Source Data

Timely and accurate tree species mapping is crucial for forest resource inventory, supporting management, conservation biology, and ecological restoration. This study utilized Sentinel-1 and Sentinel-2 data to classify five dominant tree species in Chengde and Beijing. To effectively capture the influence of multi-temporal data, data were acquired in March, June, September, and December 2020, extracting various features, including bands, spectral indices, texture features, and topographic variables. The optimal input variable combination was explored using 1519 field survey samples for training and testing datasets. Classification employed Random Forest, XGBoost, and deep learning models, with performance evaluated through out-of-bag estimation and cross-validation. The XGBoost model achieved the highest accuracy of 81.25% (kappa = 0.74) when using Sentinel-1 and Sentinel-2 bands, indices, texture features, and DEM data. Results demonstrate the effectiveness of using Sentinel data for tree species classification and emphasize the value of machine learning algorithms. This study underscores the potential of combining synthetic aperture radar (SAR) and optical data for large-scale tree species classification, with significant implications for forest monitoring and management.

Model Updating in Dynamic Finite Element for Damage Detection on an Aircraft Wing

SHM is a fundamental area for aerospace engineering. Within this broad area, there are non-destructive ways to assess integrity. This paper presents an approach to damage detection through optimization of a finite element model, where the design variables are the characteristics of the sections forming the components of the structural system, and the objective function is the dynamic parameters: natural frequencies and modal shapes. This allows for the detection of damage that caused alterations in the modal parameters of the structure through an optimal combination of design variables that generate responses obtained in the modal analysis of the damaged structure once the model is calibrated. The practical application used is damage detection in a simplified model of an aircraft wing.

Risk of intraoperative hemorrhage during cesarean scar ectopic pregnancy surgery: development and validation of an interpretable machine learning prediction model

Current models for predicting intraoperative hemorrhage in cesarean scar ectopic pregnancy (CSEP) are constrained by known risk factors and conventional statistical methods. Our objective is to develop an interpretable prediction model using machine learning (ML) techniques to assess the risk of intraoperative hemorrhage during CSEP in women, followed by external validation and clinical application. This multicenter retrospective study utilized electronic medical record (EMR) data from four tertiary medical institutions. The model was developed using data from 1680 patients with CSEP diagnosed and treated at Qilu Hospital of Shandong University, Chongqing Health Center for Women and Children, and Dezhou Maternal and Child Health Care Hospital between January 1, 2008, and December 31, 2023. External validation data were obtained from Liao Cheng Dong Chang Fu District Maternal and Child Health Care Hospital between January 1, 2021, and December 31, 2023. Random forest (RF), Lasso, Boruta, and Extreme Gradient Boosting (XGBoost) were employed to identify the most influential variables in the model development data set; the best variables were selected based on reaching the λmin value. Model development involved eight machine learning methods with ten-fold cross-validation. Accuracy and decision curve analysis (DCA) were used to assess model performance for selection of the optimal model. Internal validation of the model utilized area under the receiver operating characteristic curve (AUC), sensitivity, specificity, Matthews correlation coefficient, and F1 score. These same indicators were also applied to evaluate external validation performance of the model. Finally, visualization techniques were used to present the optimal model which was then deployed for clinical application via network applications. Setting λmin at the value of 0.003, the optimal variable combination containing 9 variables was selected for model development. The optimal prediction model (Bayes) had an accuracy of 0.879 (95% CI: 0.857-0.901) an AUC of 0.882 (95% CI: 0.860-0.904), a DCA curve maximum threshold probability of 0.41, and a maximum return of 7.86%. The internal validation accuracy was 0.869 (95% CI: 0.847-0.891), an AUC of 0.822 (95% CI: 0.801-0.843), a sensitivity of 0.938, a specificity of 0.422, a Matthews correlation coefficient of 0.392, and an F1 score of 0.925. In the external validation, the accuracy was 0.936 (95% CI: 0.913-0.959), an AUC of 0.853 (95% CI: 0.832-0.874), a sensitivity of 0.954, a specificity of 0.5, a Matthews correlation coefficient of 0.365, and an F1 score of 0.966. This indicates that the prediction model performed well in both internal and external validation. The developed prediction model, deployed in the network application, is capable of forecasting the risk of intraoperative hemorrhage during CSEP. This tool can facilitate targeted preoperative assessment and clinical decision-making for clinicians. Prospective data should be utilized in future studies to further validate the extended applicability of the model. Natural Science Foundation of Shandong Province; Qilu Hospital of Shandong University.

A Bayesian Network Approach to Lung Cancer Screening: Assessing the Impact of Data Quantity, Quality, and the Combination of Data from Danish Electronic Health Records.

Background/Objectives: Lung cancer (LC) is the leading cause of cancer mortality, making early diagnosis essential. While LC screening trials are underway globally, optimal prediction models and inclusion criteria are still lacking. This study aimed to develop and evaluate Bayesian Network (BN) models for LC risk prediction using a decade of data from Denmark. The primary goal was to assess BN performance on datasets varying in size and completeness, simulate real-world screening scenarios, and identify the most valuable data sources for LC screening. Methods: The study included 38,944 patients evaluated for LC, with 11,284 (29%) diagnosed. Data on comorbidities, medications, and general practice were available for the entire cohort, while laboratory results, smoking habits, and other variables were only available for subsets. The cohort was divided into four subsets based on data availability, and BNs were trained and validated across these subsets using cross-validation and external validation. To determine the optimal combination of variables, all possible data combinations were evaluated on the samples that contained all the variables (n = 5587). Results: A model trained on the small, complete dataset (AUC 0.78) performed similarly on a larger dataset with 21% missing data (AUC 0.78). Performance dropped when 39% of data were missing (AUC 0.67), resulting in informative variables missing completely in the dataset. Laboratory results and smoking data were the most informative, significantly outperforming models based only on age and smoking status (AUC 0.70). Conclusions: BN models demonstrated moderate to strong predictive performance, even with incomplete data, highlighting the potential value of incorporating laboratory results in LC screening programs.

Power performance optimization of twin vertical axis wind turbine for farm applications

Twin Vertical Axis Wind Turbines (VAWTs) appear to be the potential candidates for enhancing the power density of wind farms. Earlier twin-VAWT studies were mainly focused on carrying out the parametric study of one or two twin-VAWT variables together while treating the other variables as fixed. Since twin-VAWT variables strongly influence each other, therefore, this approach led to reporting conflicting optimal combinations of twin-VAWT variables for optimizing its power performance. Furthermore, previous studies considered higher rotor solidities, which is not desirable from a power generation perspective and it also reduces turbine lifespan. Using L16 (45) Taguchi orthogonal array along with a modified superposition model, this research optimized the power performance of twin-VAWT considering together, solidity ratio (σ), pitch angle (β), wind direction angle (δ), turbine spacing ratio (S/D) and rotational direction (φ) of the rotor as design variables. Unsteady CFD was employed to ascertain the power performance of orthogonal array designs followed by the orthogonal analysis for the optimum tip-speed ratios (TSRs) and power coefficients. Based upon the relative impact of the design variables on the mean optimum TSR, the variables were ranked as: (σ) > (δ) > (φ) > (β) and (S/D). On the other hand, a different trend for the relative impact of the design variables on the power performance was found: (β) > (δ) > (σ) > (φ) > (S/D). The orthogonal analysis optimum twin-VAWT configuration showed a positive synergistic interaction at TSRs > 2.5 and negative synergistic interaction at TSRs ≤ 2.5 in comparison to its standalone counterpart. Moreover, the orthogonal analysis’s optimum twin-VAWT underperformed by 4.7 % when compared with the best orthogonal array design at their respective optimum TSRs, indicating a sub-optimal design resulting from Taguchi orthogonal analysis. The incapability of orthogonal analysis to include the interaction effects among variables resulted in the sub-optimal twin-VAWT design. Linear graph method highlighted the presence of strong interaction effects among the design variables. For five design variables with four levels each (45), a full factorial Design of Experiments (DoE) of 1024 cases was constructed to include the interaction effects. Signal-to-noise ratios of full factorial DoE cases were predicted by the modified superposition model. The highest predicted signal-to-noise ratio among 1024 cases identified the best orthogonal array design as the actual optimum twin-VAWT configuration. The increase in power efficiency of twin-VAWT in comparison to its standalone counterpart was observed as the TSR was increased with the maximum power enhancement by 23 % at TSR 4.25. Furthermore, the optimal twin-VAWT configuration exhibited an optimal TSR of 3.5, contrasting with the standalone VAWT's optimal TSR of 3.0. This shift extended the power performance envelope of the optimum twin-VAWT, allowing for energy extraction across a broader range of TSR values. The undertaken study highlights the prospects of twin-VAWTs for increasing the farm power density.

Large quarterly Bayesian vector autoregression model for the modern Russian economy

It is often difficult to choose the necessary variables when we are forecasting the economic dynamics. On the one hand, vector autoregression (VAR) models can solve this problem by taking into account a sufficiently large number of variables. However, on the other hand, excessive parametrization of such models is not always justified, because it is often possible to choose such a small combination of variables the predictive power of which will be no worse than unlimited VARs with a large number of variables and lags. Bayesian methods help to solve this problem by introducing a priori restrictions on the VAR coefficients. The main goal of this work is to build a Large quarterly Bayesian vector autoregression (QBVAR) for the modern Russian economy. The hypotheses of the study: 1) BVAR(p) models reveal their maximum potential with a small number of variables, but with a large number of lags, 2) The Minnesota prior distribution is not always the best option for the modern Russian economy in the BVAR(p) model. As a result of the analysis, it turned out that for a number of the most important macroeconomic variables (GDP, inflation, key rate, unemployment, wages), Normal-Flat / Wishart-type priors turned out to be the optimal. In case of 29 input variables and two lags, the predictive power of the QBVAR(2) model is worse than the equivalent frequency VAR(2) or VECM(2). However, when it was possible to find the optimal combinations of variables, QBVAR(p) turned to be several times more accurate than its analogous frequency VAR(p) for all important macro indicators. In addition, the stiffness parameters of the considered a priori distributions decreases with increasing lags entering the model, i. e. the higher the order of the model with the minimum optimal set of variables, the tighter the distribution is necessary to obtain more accurate predictions. For the Russian realities, it is necessary to use very tight priors, 6–8 variables and 9–12 lags in a quarterly representation.

Mathematical and Statistical Analysis of Fused Filament Fabrication Parameters for Thermoplastic Polyurethane Parts via Response Surface Methodology

This work aims to analyze the effects of the main process parameters of fused filament fabrication (FFF) on the mechanical properties and part weight of 3D-printed thermoplastic polyurethane (TPU). Raster angle (RA), infill percentage (IP), and extruder temperature (FFF) in the ranges of 0–90°, 15–55%, and 220–260 °C, respectively, were considered as the FFF input parameters, and output variables part weight (PW), elongation at break (E), maximum failure load (MFL), ratio of the maximum failure load to part weight (Ratio), and build time (BT) were considered as responses. The Response Surface Methodology (RSM) and Design of Experiments (DOE) were applied in the analysis. Subsequently, the RSM approach was performed through multi-response optimizations with the help of Design-Expert software. The experimental results indicated a higher maximum failure load is achieved with an increased raster angle and decreased extruder temperature. ANOVA results show that ET has the most significant effect on elongation at break, with elongation at break decreasing as ET increases. The raster angle does not significantly affect the part weight of the TPU samples. The ratio of the maximum failure load to part weight of samples decreases with an increase in IP and ET. The results also indicated that the part weight and build time of FFF-printed TPU samples increase with an increase in IP. An ET of 220 °C, RA of 0°, and IP of 15% are the optimal combination of input variables for achieving the minimal part weight; minimal build time; and maximum elongation at break, maximum failure load, and ratio of the maximum failure load to part weight.

Spatial non-stationarity effects of the driving factors on landscape ecological risk: A case of the Xiamen-Zhangzhou-Quanzhou Urban Agglomeration, China

Increasing construction land demands and population growth within urban agglomerations have led to increasingly prominent landscape ecological risk (LER) issues. However, the multi-scale nature and spatial non-stationarity characteristics of the driving patterns have not been fully investigated. In this study, taking the Xiamen-Zhangzhou-Quanzhou Urban Agglomeration (XZQUA) as a case, we analyzed the spatio-temporal evolution characteristics of LER utilizing the long time series land use data from 1980 to 2020; then, the Exploratory Regression Analysis (ERA) was employed to investigate the optimal combination of key influential elements affecting LER. Finally, the Multiscale Geographically Weighted regression (MGWR) model was applied to explore the spatial non-stationarity effects of the key driving elements. The results reveal that: (1) The LER of the XZQUA has shown a declining trend from 1980 to 2020, characterized with significantly and increasingly spatial autocorrelation as well. (2) The optimal variable combination is the temperature, distance from roads, elevation, and construction land area. (3) The MGWR model results reveal that the impact of various factors on LER demonstrates significant spatial non-stationarity. The mechanisms and intensity of these influences change depending on geographical location. The negative proportion of regression coefficients for construction land area (−0.203 to −0.002) and elevation (−0.046 to −0.001) all exceeded 80%, indicating a high negative effect on LER; The positive proportion of the regression coefficient for distance from roads (−0.026 to 0.042) exceeded 60%, indicating a predominantly positive effect on LER. Our findings provide guidance for regional policymakers to adopt targeted ecological risk intervention measures, thus reducing LER in the urban agglomeration.

Relationship matters: Using machine learning methods to predict the mental health severity of Chinese college freshmen during the pandemic period

BackgroundPandemics act as stressors and may lead to frequent mental health disorders. College student, especially freshmen, are particularly susceptible to experiencing intense mental stress reactions during a pandemic. We aimed to identify stable and intervenable variables including academic, relationship and economic factors, and focused on their impact on mental health severity during the pandemic period. MethodsWe innovatively combined diverse machine learning methods, including XGBoost, SHAP, and K-means clustering, to predict the mental health severity of college freshmen. A total of 3281 college freshmen participated in the research. Discriminant analyses were performed on groups of participants with depression (PHQ-9), anxiety (GAD-7). All characteristic variables were selected based on their importance and interventionability. Further analyses were conducted with selected features to determine the optimal variable combination. ResultsXGBoost analysis revealed that relationship factors exhibited the highest predictive capacity for mental health severity among college freshmen (SHAPFamily Relationship = 0.373; SHAPPeer Support = 0.236). The impact of academic factors on college freshmen's mental health severity depended on their intricate interplay with relationship factors, resulting in complex interactive effects. These effects were heterogeneous among different subgroups. ConclusionsThe proposed machine learning approach utilizing XGBoost, SHAP and K-means clustering methods provides a valuable tool to gain insights into the relative contributions of academic, relationship and economic factors to Chinese college freshmen's mental health severity during the COVID-19 pandemic. The result guide the development of targeted intervention measures tailored to meet specific requirements within each subgroup.

Experimental Design for Optimization of Felbamate Nanosuspension Using Box-Behnken Design.

Felbamate, a valuable antiepileptic drug, suffers from low water solubility and potential side effects, limiting its therapeutic application. This study addresses this challenge by developing a felbamate nanosuspension for nose-to-brain delivery using a three-factor, three-level Box-Behnken design. The research focused on identifying the optimal combination of key formulation variables, chitosan concentration, chitosan/sodium tripolyphosphate ratio, and Tween 80 surfactant concentration to achieve a nanosuspension with desirable particle size, polydispersity index, and high entrapment efficiency (%EE), all critical parameters for efficient drug delivery via the nasal route. The study identified an optimized formulation consisting of 0.176% chitosan, a 3.3:1 chitosan/TPP ratio, and 1.55% Tween 80 through rigorous experimentation and response surface methodology analysis. The optimized formulation yielded a nanosuspension of 115.0 ± 4.37 nm mean particle size, 0.118 ± 0.021 polydispersity index, and +34.08 ± 2.4 mV zeta potential, indicating a stable system with a narrow size distribution suitable for enhanced drug delivery. The entrapment efficiency of 93.18 ± 1.69% confirmed effective encapsulation, while in-vitro dissolution studies demonstrated a significantly higher dissolution rate compared to pure felbamate, suggesting improved bioavailability. The results emphasize the capacity of this optimized nanosuspension to improve the therapeutic efficacy of felbamate and hence justify additional preclinical and clinical research.

Enhancing streamflow simulations with gated recurrent units deep learning models in the flood prone region with low-convergence streamflow data

Highly accurate streamflow simulations are essential for water resources and river management. However, there are longstanding challenges for streamflow modeling in the hydrology field. As a result, deep learning methods have been introduced as novel tools and are being used in simulation. This paper proposes a novel approach that utilizes unconventional data preprocessing techniques to improve the accuracy of daily streamflow predictions in flood-prone regions. We applied this approach to a flood-prone area in western Iran and simulated daily streamflow using a deep learning Gated Recurrent Unit (GRU) method under various data selection scenarios. These scenarios focused on identifying the optimal combination of input variables, time steps, and outlier removal techniques. The outlier removal methods investigated in this study include Mahalanobis distance, critical section removal, Z-score, and no removal. The average rainfall of the area, data driven precipitation, Normalized Difference Vegetation Index (NDVI), surface soil moisture, groundwater baseflows, and streamflow in the hydrometric station were evaluated using correlation control method, and inputs with the lowest correlation were removed. Based on the results obtained from the deep learning models produced in the research, it was found that the GRU model, with various modified inputs using Z-score removal, had the best performance. The model had an average of Root Mean Squared Error (RMSE) at 5.24 mm and R2 (Coefficient of Determination) at 0.91 during training, while during validation, it had an RMSE of 7.74 mm and R2 of 0.83. Considering using relatively low convergence data in streamflow simulation in this study, it can be said that the listed scenarios showed an appropriate result in dealing with the data and recognizing the complex pattern of the daily streamflow, and the future studies will show the improvement of the GRU models if higher convergence data will be used.

Experimental Investigations on the Fabrication of Low Alloy Steels Using Wire Arc Additive Method

Wire arc additive manufacturing (WAAM) has emerged as a transformational technology with the capacity to redefine the landscape of alloy steel component production. This method utilizes an electric arc to selectively fuse a continuous wire feed, progressively constructing intricate metal structures layer by layer. GMAW-based WAAM adaptability enables the creation of complex geometries and customized part designs, making it applicable across diverse industrial sectors. This paper investigates WAAM-specific applications in alloy steel fabrication, focusing on key process variables such as voltage, travel speed, and Gas mixture ratio. The experimental parameters for a single layer are examined with voltage ranging from 20 to 22, travel speed from 23, 25, and 27 mm/min, and Gas mixture ratio 1,5,9 mm/min. It utilizes materials like TM B9, a 1.2- diameter flux-cored wire. Additionally, the study considers the nominal composition (wt-%) of 9 Chromium, and 1 Molybdenum, with small additions of nitrogen and niobium to improve the creep resistance. Furthermore, the final findings of the study suggest that the optimal combination of process variables for achieving highquality weld beads in WAAM of alloy steel components can be determined through Response Surface Methodology (RSM). RSM is a statistical method for analysing and modeling the relationship between the response of interest and some independent variables. In this case, the response variable would be the quality of the weld bead, which encompasses factors such as bead geometry, integrity, and absence of defects.

Development of an equation to predict delta bilirubin levels using machine learning

ObjectiveDelta bilirubin (albumin-covalently bound bilirubin) may provide important clinical utility in identifying impaired hepatic excretion of conjugated bilirubin, but it cannot be measured in real-time for diagnostic purposes in clinical laboratories. MethodsA total of 210 samples were collected, and their delta bilirubin levels were measured four times using high-performance liquid chromatography. Data collected included age, sex, diagnosis code, delta bilirubin, total bilirubin, direct bilirubin, total protein, albumin, globulin, aspartate aminotransferase, alanine transaminase, alkaline phosphatase, gamma-glutamyl transferase, lactate dehydrogenase, hemoglobin, serum hemolysis value, hemolysis index, icterus value (Iv), icterus index (Ii), lipemia value (Lv), and lipemia index. To conduct feature selection and identify the optimal combination of variables, linear regression machine learning was performed 1,000 times. ResultsThe selected variables were total bilirubin, direct bilirubin, total protein, albumin, hemoglobin, Iv, Ii, and Lv. The best predictive performance for high delta bilirubin concentrations was achieved with the combination of albumin-direct bilirubin-hemoglobin-Iv-Lv. The final equation composed of these variables was as follows: delta bilirubin = 0.35 × Iv + 0.05 × Lv − 0.23 × direct bilirubin − 0.05 × hemoglobin − 0.04 × albumin + 0.10. ConclusionThe equation established in this study is practical and can be easily applied in real-time in clinical laboratories.

Studies on parametric optimization of PLA/graphene composites synthesized by fused filament fabrication for thermal applications

The objective of this study is to examine the impact of various material and processing factors on the hardness (Shore D) and tensile strength of PLA/graphene composites. The study employed the Taguchi method to systematically optimize and statistically analyze various process variables, including the content of graphene (0 %, 0.5 %, and 1.0 % by weight), infill density (80 %, 90 %, and 100 %), and print speed (160 mm/s, 170 mm/s, and 180 mm/s). The composite material was fabricated utilizing the fused filament fabrication (FFF) technique, employing polylactic acid (PLA) and graphene as the primary feedstock materials. A standardized experiment was conducted in accordance with ASTM standards to assess the hardness and strength of samples that were prepared based on the experimental design. Based on the S/N ratio response table, it can be concluded that the reinforcement content is the most significant factor affecting both hardness and tensile strength. The optimal combination of process variables for achieving high hardness and tensile strength was found to be a graphene content of 1 %, an infill density of 100 %, and a print speed of 180 mm/s. The analysis of variance (ANOVA) indicated that the variable with the greatest statistical significance and substantial impact on the properties is the content of reinforcement. The analysis of fractures indicated a transition from ductile to brittle behavior with an increase in infill density. Furthermore, both composites demonstrated a brittle mode of failure irrespective of the infill density. Thus this composite material synergistically combines the inherent biodegradability of PLA with the improved thermal conductivity of graphene.

Optimization Design of a Polyimide High-Pressure Mixer Based on SSA-CNN-LSTM-WOA

Foam mixers are classified as low-pressure and high-pressure types. Low-pressure mixers rely on agitator rotation, facing cleaning challenges and complex designs. High-pressure mixers are simple and require no cleaning but struggle with uneven mixing for high-viscosity substances. Traditionally, increasing the working pressure resolved this, but material quality limits it at higher pressures. To address the issues faced by high-pressure mixers when handling high-viscosity materials and to further improve the mixing performance of the mixer, this study focuses on a polyimide high-pressure mixer, identifying four design variables: impingement angle, inlet and outlet diameters, and impingement pressure. Using a Full Factorial Design of Experiments (DOE), the study investigates the impacts of these variables on mixing unevenness. Sample points were generated using Optimal Latin Hypercube Sampling—OLH. Combining the Sparrow Search Algorithm (SSA), Convolutional Neural Network (CNN), and Long Short-Term Memory Network (LSTM), the SSA-CNN-LSTM model was constructed for predictive analysis. The Whale Optimization Algorithm (WOA) optimized the model, to find an optimal design variable combination. The Computational Fluid Dynamics (CFD) simulation results indicate a 70% reduction in mixing unevenness through algorithmic optimization, significantly improving the mixer’s performance.

Optimization Design of Injection Mold Conformal Cooling Channel for Improving Cooling Rate

Optimizing the design of the conformal cooling channel can increase the cooling rate of injection mold. The aim of this study was the problem of low cooling efficiency of injection mold for deep-cavity plastic parts under the conventional cooling channel. Based on the analysis of the heat transfer principle of the injection mold, a mathematical description of the cooling time of the conformal cooling channel was made. By designing orthogonal experiments and using simulation methods in the Autodesk Moldflow 2019 software, with the minimum cooling time of the mold as the optimization goal, experimental optimization was carried out for the three design variables of the channel, thereby obtaining the optimal combination of design variables for the conformal cooling channel. The conformal cooling channel layout was innovatively designed, and through computer simulation experiments, it was concluded that the conformal cooling channel adopted a series flat-head layout, which has the shortest cooling time and the fastest cooling rate. Metal additive manufacturing technology was used to complete the manufacturing of the mold insert with the conformal cooling channel. After the trial production of the conformal cooling injection mold, the molding cycle was obviously shortened, and the injection molding production efficiency was significantly improved.

Multi-Model Comprehensive Inversion of Surface Soil Moisture from Landsat Images Based on Machine Learning Algorithms

Soil moisture plays an important role in maintaining ecosystem stability and sustainable development, especially for the upper reaches of the Yellow River region. Therefore, accurately and conveniently monitoring soil moisture has become the focus of scholars. This study combines three machine learning algorithms: random forest (RF), support vector machine (SVM), and back propagation neural network (BPNN)—with the traditional monitoring of soil moisture using remote sensing indices to construct a more accurate soil moisture inversion model. To enhance the accuracy of the soil moisture inversion model, 27 environmental variables were screened and grouped, including vegetation index, salinity index, and surface temperature, to determine the optimal combination of variables. The results show that screening the optimal independent variables in the Xijitan landslide distribution area lowered the root mean square error (RMSE) of the RF model by 16.95%. Of the constructed models, the combined model shows the best applicability, with the highest R2 of 0.916 and the lowest RMSE of 0.877% with the test dataset; the further research shows that the BPNN model achieved higher overall accuracy than the other two individual models, with the test set R2 being 0.809 and the RMSE 0.875%. The results of this study can provide a theoretical reference for the effective use of Landsat satellite data to monitor the spatial and temporal distribution of and change in soil water content on the two sides of the upper Yellow River basin under vegetation cover.

Development and web deployment of prediction model for pulmonary arterial pressure in chronic thromboembolic pulmonary hypertension using machine learning.

Mean pulmonary artery pressure (mPAP) is a key index for chronic thromboembolic pulmonary hypertension (CTEPH). Using machine learning, we attempted to construct an accurate prediction model for mPAP in patients with CTEPH. A total of 136 patients diagnosed with CTEPH were included, for whom mPAP was measured. The following patient data were used as explanatory variables in the model: basic patient information (age and sex), blood tests (brain natriuretic peptide (BNP)), echocardiography (tricuspid valve pressure gradient (TRPG)), and chest radiography (cardiothoracic ratio (CTR), right second arc ratio, and presence of avascular area). Seven machine learning methods including linear regression were used for the multivariable prediction models. Additionally, prediction models were constructed using the AutoML software. Among the 136 patients, 2/3 and 1/3 were used as training and validation sets, respectively. The average of R squared was obtained from 10 different data splittings of the training and validation sets. The optimal machine learning model was linear regression (averaged R squared, 0.360). The optimal combination of explanatory variables with linear regression was age, BNP level, TRPG level, and CTR (averaged R squared, 0.388). The R squared of the optimal multivariable linear regression model was higher than that of the univariable linear regression model with only TRPG. We constructed a more accurate prediction model for mPAP in patients with CTEPH than a model of TRPG only. The prediction performance of our model was improved by selecting the optimal machine learning method and combination of explanatory variables.

Experimental analysis and optimization of machining parameters for Nitinol alloy: A Taguchi and multi-attribute decision-making approach

Abstract The automotive and aerospace sectors have a strong demand for Nitinol alloy machined parts; therefore, optimizing machining parameters is essential to achieving better process performance results in terms of cost and product quality. In general, the process variables that influence machining include feed (f), depth of cut (t), and spindle speed (S). Material removal rate (MRR), tool wear (TW), and surface roughness (Ra) are pertinent output performance indicators. Analysis of variance has been performed to assess the effect of process variables on the aforesaid output performance. It has been found that feed has a significant effect on MRR and surface roughness with a contribution of 50.65 and 33.62%, respectively, whereas spindle speed has a major contribution on TW with a contribution of 51.9%. This study assesses how well the Nitinol 56 machining process works overall. In this work, the Taguchi method has been used to determine the effect of aforesaid process variables on the output performance indices. To satisfy previously stated conflicting performance indices, a variety of multi-attribute decision-making approaches were used, such as utility, TOPSIS, and grey, to determine the optimal process variables. The optimal process variable combination has been achieved as f = 0.133 mm·rev−1, d = 0.06, and S = 835 RPM. This combination has been achieved using all methods.

Optimal design and modelling of sustainable bio-catalytic enzyme for wastewater treatment using response surface methodology and artificial neural network

ABSTRACT The accessibility of various wastewater treatment systems has become increasingly prominent in current times, coinciding with a rising concern regarding the substantial content of food waste that poses a significant challenge in waste management. In this context, ecoenzymes have emerged as a promising technique for water treatment due to their remarkable efficiency in pollutant removal and cost-effectiveness. Nevertheless, many experts encounter difficulties in determining the optimal combination of ecoenzyme variables to maximize pollutant removal. The objective of this study is to apply a comprehensive approach utilizing Response Surface Methodology (RSM), Artificial Neural Networks (ANN), and Multi-objective Genetic Algorithm (MOGA) methods for the modeling and optimization of ecoenzyme-based water treatment processes. The research outcomes demonstrate a noteworthy alignment between the actual removal rates of Total Suspended Solids (TSS), Volatile Suspended Solids (VSS), and Total Ammonia Nitrogen (TAN) with the values predicted by both RSM and ANN models, validating the robustness of the regression analysis (R2 >0.95). From the optimization results, it is elucidated that to attain the maximum removal of TSS, VSS, and TAN, the treatment process should be conducted over a period of 3.5 days, employing specific enzyme concentrations of 0.07 units/ml for protease, 0.027 units/ml for amylase, and 0.36 units/ml for lipase. This study employed machine learning approaches and MOGA optimization to predict the optimum ecoenzyme properties for maximum wastewater removal utilizing the concept of a low-cost, sustainable purification technology.