Single Regression Research Articles

Using a convection-permitting climate model to assess wine grape productivity: two case studies in Italy

Abstract. The article explores the potential use of climate models to reproduce wine grape productivity at a local scale in Italy. To this end, both single and multiple regression approaches are used to link productivity data provided by two Italian wine consortia with bioclimatic indices. Temperature- and precipitation-based bioclimatic indices are computed using the observational dataset E-OBS, the high-resolution climate reanalysis product SPHERA, the regional climate model CNRM-ALADIN, and the kilometer-scale convection-permitting climate model CNRM-AROME. The multiple regression method outperforms the single regression systematically, enhancing the ability of bioclimatic indices to explain productivity variability. The results show that productivity is strongly tied to temperature-based bioclimatic indices in the area of the Consorzio per la tutela del Franciacorta in northern Italy, while for the Consorzio del Vino Nobile di Montepulciano area in central Italy both temperature- and precipitation-based indices are relevant. Climate models, providing similar results as E-OBS and SPHERA, appear to be a useful tool to explain productivity variance. In particular, the added value of convection-permitting resolution is evident when precipitation-based indices are considered. This assessment shows windows of opportunity for using climate models, especially at a convection-permitting scale, to investigate future climate change impact on wine production.

Object Detection in Real-time Video

Object detection in actual-time video is a important challenge in many programs, which includes autonomous driving, surveillance, and human-computer interplay. With the upward push of deep learning, models which include Convolutional Neural Networks (CNNs) have substantially stepped forward detection accuracy, however their excessive computational needs frequently restrict actual-time performance. This paper explores the evolution of item detection techniques, with a focus at the YOLO (You Only Look Once) framework, which addresses the want for both velocity and accuracy in real-time programs. YOLO transforms item detection right into a single regression problem, permitting high frame costs appropriate for actual-time video processing. We take a look at the performance of numerous YOLO variations (YOLOv3, YOLOv4, YOLOv5) in terms of detection accuracy, processing velocity, and computational performance, particularly in useful resource-restricted environments. Additionally, we examine the exchange-offs between speed and accuracy, especially in complicated environments regarding low lighting, occlusion, and ranging item sizes. Furthermore, we check out optimization techniques, such as model pruning, quantization, and hardware acceleration, to beautify YOLO’s actual- time performance. The effects demonstrate that YOLO, with proper optimization, can provide an effective answer for actual- time item detection, balancing pace and accuracy throughout various application situations. We finish by providing upgrades and destiny studies directions to conquer modern limitations and similarly increase the country of real-time item detection

Prevalence of valgus and varus foot deformities in 2784 children with cerebral palsy, a register-based cross-sectional study

BackgroundFoot deformities, such as valgus and varus in the coronal plane and equinus in the sagittal plane, are common in children with cerebral palsy (CP). The purpose of this study was to describe the prevalence of coronal plane foot deformities and their association with the Gross Motor Function Classification System (GMFCS) level, age, CP subtype, and equinus in children with CP.MethodsA cross-sectional study was performed of 2784 children (1644 boys, 1140 girls), mean age 10 years, 2 months (standard deviation, 4.83), from the Swedish CP Follow-up Program and registry for 2021–2023. Single and multiple binary regression analyses estimated the association between coronal plane foot deformities (valgus or varus) and sex, age, GMFCS level, CP subtype, and equinus.ResultsMore than half (58%) the children with CP had valgus feet and 6% had varus feet. Valgus feet were more common in young children with high GMFCS levels, whereas the number of varus feet remained consistently low across all GMFCS levels. The prevalence of valgus feet was lower in older children at GMFCS I and II, but remained high in older children at GMFCS III–V. Coronal plane foot deformities were associated with higher GMFCS levels (odds ratio [OR] 11, 95% confidence interval [CI] 8–15 for GMFCS V), lower age (OR 1.5, 95% CI 1.3–1.7), and equinus (OR 1.9, 95% CI 1.4–2.5).ConclusionsMost children with CP have a coronal plane foot deformity. Valgus is most commonly associated with higher GMFCS levels and lower age. These findings contribute to a mapping of the children with an increased risk of foot deformities and also highlight the need for continuous follow-up of foot deformities in children with CP.

The Relationship between Work Engagement and Workaholism and Nurses' Job well-being

Background: Nurses continuously face workaholism and work engagement that affect the professional performance of nurses. The aim of this study was to investigate the relationship between work engagement and workaholism with nurses' job well-being. Methods: This was a descriptive correlation study. Two hundred nurses from Lahijan Hospitals were selected by convenience sampling method in 1399. Data were collected using three standard questionnaires of work engagement, workaholism, and job well-being. Data analysis was used using SPSS21 software using descriptive statistics (mean, standard deviation, percentage) and inferential methods (Single regression test). Results: The results of the study showed that work engagement and workaholism can predict the job well-being of nurses in Lahijan hospitals (p<0.001). Among the dimensions of job well-being, the results showed that workaholism is negatively related to the job satisfaction of nurses(p=0.03), but has a positive relationship with the dimensions of perceived stress and nurses' sleep problems(p<0.001). Among the dimensions of job well-being, work engagement can predict positive the job satisfaction of nurses(p<0.001), but cannot predict the perceived stress and the nurses' sleep problems(p>0.05). Conclusion: According to the results of the study, work engagement and workaholism are good predictors for nurses' job well–being. Therefore, it is suggested that managers help to enhance nurses' job well-being by improving the motivated and vibrant work environment, creating work engagement, and reducing work addiction.

Analysis of clinical characteristics in patients with diabetic foot ulcers undergoing amputation and establishment of a nomogram prediction model

To assess the accuracy of a nomogram for predicting the risk of lower-extremity amputation (LEA) in individuals with diabetic foot ulcers (DFUs). We retrospectively analyzed data from 144 patients with DFUs at the Department of Orthopedics of the First Affiliated Hospital of Nanchang University, collected between January 2020 and December 2023. Univariate analysis determined primary predictive factors for amputation, followed by single and multifactor logistic regression analyses to indentify independent factors. These were utilized to develop a prediction model using R4.3.3, and a nomogram was created. Its performance was verified using receiver operating characteristic (ROC), corrected calibration, and clinical decision curves. Twelve primary predictive factors were identified from 20 variables, including age, Wagner grades, peripheral angiopathy of diabetes (PAD), chronic kidney disease(CKD), C-reactive protein(CRP) and the number of blood sugar abnormalities(BSA) etc. Multivariate logical regression analysis illustrated that Wagner grades, PAD, CRP, CKD, and the number of BSA were independent risk factors. The area under the curve (AUC) of the ROC curve was 0.967, and the revised calibration curve of the nomogram demonstrated strong fitting ability. This prediction model is a valuable tool for screening LEA risk and preventing DFU from progressing into amputation.

Assessment of physicochemical attributes and variation in mass-volume of Himalayan pears: Computer vision-based modeling

The current study attempts to examine the physicochemical properties of Himalayan pears and envision the relationship between mass and volume with various physical properties. These properties are measured using image processing techniques at different storage days (1st day, 4th day, 7th day, 10th day, and 13th day). The study employs both single and multivariable regression models, including linear, quadratic, rational, and exponential models to establish predictive relationships. Among the single variable models, the length-based linear and rational models demonstrated exceptional suitability for envisioning the mass and volume of pears, achieving higher R2 values of 0.92 and 0.90, respectively. For mass and volume prediction considering combined physical properties, the rational and exponential models exhibited the best fit with higher R2 values of 0.94 and 0.91, accompanied by low RMSE values of 0.217 and 0.141. Consequently, the established relationship between the mass and volume of Himalayan pears with its physical attributes contributes to the development of a faster, more authentic, and accurate grading system.

Development of a recommendation engine for university study programme selection: A regression-based approach

This paper is the third in a series focused on bridging the gap between secondary and higher education. Our primary objective is to develop a robust theoretical framework for an innovative e-business model called the Undergraduate Study Programme Search System (USPSS). This system considers multiple criteria to reduce the likelihood of exam failure or the need for multiple retakes, while maximizing the chances of successful program completion. Testing of the proposed algorithm demonstrated that the Stochastic Gradient Boosted Regression Trees method outperforms the current method used in Lithuania for admitting applicants to 47 educational programs. Specifically, it is more accurate than the Probabilistic Neural Network for 25 programs, the Ensemble of Regression Trees for 24 programs, the Single Regression Tree for 18 programs, the Random Forest Regression for 16 programs, the Bayesian Additive Regression Trees for 13 programs, and the Regression by Discretization for 10 programs.

Fish–Seascape Associations Within an Offshore Protected Area in the Arabian Gulf

ABSTRACTCoral reef ecosystems support high fish biodiversity through ecological interactions with structural complexity across multiple spatial scales including coral colony architecture and the surrounding seascape structure. In an era where the complexity of coral reef ecosystems is being diminished, understanding the importance of structural characteristics beyond single focal patches has the potential to better inform actions for protecting, restoring or creating habitat for reef‐associated species. A seascape ecology approach was applied to explore the associations between multiple scales of seascape structure and fish assemblage response variables within a small (49.6 km2) offshore no‐take MPA, Sir Bu Nair Island Protected Area, in Sharjah, United Arab Emirates. Fish–seascape associations were modelled with single regression trees. Both in situ and remote sensing–derived variables produced the best models with highest contributions from coral cover, amount of hard‐bottom habitat type and structural complexity of the seafloor terrain. Fish species richness was significantly higher where coral cover exceeded 35%. The hard‐bottom areas with coral supported diverse assemblages dominated by carnivorous and omnivorous fishes. The Sir Bu Nair Island Protected Area provides a critical refuge for threatened and regionally overexploited species including those with low resilience to fishing. The ecological success of this protected area is key to safeguarding regional marine biodiversity and recovering fish populations to enhance food security.

Investigating Clinical Factors Influencing Pulmonary Fibrosis in Acute Diquat Poisoning.

This study aimed to explore the factors influencing pulmonary fibrosis in patients with acute diquat poisoning through logistic regression analysis. A retrospective analysis was conducted on 68 cases of acute diquat poisoning due to suicidal intent admitted to our hospital from February 2020 to March 2023. Patients were divided into a combined group (28 cases with pulmonary fibrosis) and an acute diquat poisoning group (40 cases without). A healthy control group consisted of 40 individuals. General data were compared among the three groups, and laboratory indicators were analyzed. Single and multiple logistic regression analyses were performed to identify risk factors for pulmonary fibrosis. There were no significant differences in gender, age, BMI, poisoning status, or treatment timing among the groups (P > 0.05). The combined group had significantly higher diquat ingestion dose, SIRS score, SOFA score, and APACHE II score compared to the poisoning group (P < 0.05). In the acute poisoning group, these scores were also higher than in the healthy controls (P < 0.05). Laboratory indicators, including Hb, PLT, ALP, DBil, ALB, BUN, Glu, BNP, and pH, showed no significant differences (P > 0.05). However, WBC, ALT, TBil, DBil, Cr, K+, Tn I, and Lac levels were significantly higher in the combined group compared to the acute poisoning group (P < 0.05). Logistic regression analysis identified factors influencing pulmonary fibrosis as diquat ingestion dose, K+, ALT, PaO2, Lac, and HCO3-. The factors influencing pulmonary fibrosis in acute diquat poisoning include diquat ingestion dose, K+, ALT, PaO2, Lac, and HCO3-. These findings enhance understanding of pulmonary fibrosis pathogenesis and may inform clinical management for affected patients.

The relationship between mixed venous blood oxygen saturation and pulmonary arterial and venous pressures in patients with heart failure.

Recent discoveries have identified intrapulmonary bronchopulmonary anastomoses (IBAs) as a relatively common phenomenon forming intrapulmonary right-to-left shunts. This study hypothesizes that IBAs play a significant role in the pathophysiology of heart failure. We aim to investigate the impact of these intrapulmonary right-to-left shunts on pulmonary arterial and venous pressures in heart failure patients, utilizing mixed venous oxygen saturation (SvO₂) as a key measurement. This study included 237 patients with heart failure who underwent cardiac catheterization. The relationships between SvO₂ and pulmonary artery systolic pressure (sPAP), pulmonary artery wedge pressure (PAWP), and left ventricular end-diastolic pressure (LVEDP) were examined using various statistical methods (single regression analysis, partial correlation analysis, structural equation modeling, and Bayesian estimation). All statistical methods that we performed showed that SvO₂ was significantly and negatively correlated with both sPAP and PAWP (p < 0.01, respectively). However, SvO₂ did not significantly correlate with LVEDP. These results suggest that a decrease in SvO₂ leads to an increase in PAWP and sPAP, while LVEDP is only passively influenced by PAWP. This phenomenon likely reflects the impact of an intrapulmonary right-to-left shunt caused by IBAs. The decrease in SvO₂ causes an increase in sPAP and may also cause an increase in PAWP via IBAs.

Cyber entrepreneurship and employment generation of small and medium enterprises in south-east Nigeria

The study evaluated influence of cyber entrepreneurship on employment generation of Small and Medium Enterprises in South-East Nigeria. Specifically, the study sought to: ascertain the effect of selling of digital information product on job creation of Small and Medium Enterprises and examine the effect of selling of physical product on employment generation of Small and Medium Enterprises. The study adopted descriptive research design. The study area was South-east Nigeria. Research design of the study was questionnaire survey research. The sample size of 387 respondents was taken from population of 13,455 staff among 204 small and medium enterprises (SMEs) operated in South-east Nigeria. The selected SMEs under study were as follows: Rokana Industries Ltd. Umualum- Nekede; Cutix Plc Umuanuka, Otolo, Nnewi; Juhel Nigeria Ltd Nkwubor Rd. Emene; Mikko Plastics Ind. Ltd Umuocham, Aba and Eze-Rome Oil Palm Abakaliki Ebonyi State. The research question were answered with simple percentage, mean and deviation while hypotheses were tested with single regression. The empirical results show that selling of digital information product has significant effect on job creation of Small and Medium Enterprises in South-East Nigeria (t-statistic; 6.484; P-value; 0.000 &lt; Sig-value; 0.05) and selling of physical products have significant effect employment generation of Small and Medium Enterprises in South-East Nigeria (t-statistic; 11. 826; P-value; 0.000 &lt; Sig-value; 0.05). The study recommended that government and organizations should as a way of empowerment, train and equip youths with the necessary skills and facilities that will aid their involvement in online application services.

Effects of different hinge positions on tibial rotation in uniplanar medial opening wedge high tibial osteotomy with three-dimensional tibial models.

To investigate the effects of different hinge positions in the sagittal and axial planes on distal tibial rotation (DTR) during medial opening wedge high tibial osteotomy (MOWHTO) with three-dimensional tibial models. Preoperative CT data from 30 knee joints in 30 patients who underwent surgery for varus malalignment of knee were included. 1 standard hinge position (0°), 6 axial planes (±5°, ±10°, ±15°), and 6 sagittal planes (±5°, ±10°, ±15°) hinge positions were defined and virtual uniplanar osteotomy was performed. The correction angle of each model was generated using Fujisawa's point. Participants' baseline characteristics, radiologic parameters and DTR were measured. One-Way Repeated Measures ANOVA and single factor linear regression analysis were used to analyze the association between tibial rotation and hinge position in the sagittal and axial planes. We found a clear linear correlation between changes in hinge position in the sagittal plane and DTR. The changes in DTR were the smallest when the hinge position was at 5°, where internal or external rotation of the DTR may occur. When the front aspect of hinge axis rotated distally, DTR tended towards internal. Meanwhile, when the front aspect of hinge axis rotated proximally, DTR tended towards external. There were no correlations with every hinge axis position in the axial plane. It is sagittal but not axial hinge axis affects DTR in uniplanar MOWHTO with three-dimensional tibial models. In the sagittal plane, every change in hinge position was significantly linearly correlated with DTR. However, no linear correlations were observed between every hinge position change in the axial plane.

Implementation of the YOLO Method for Detection of Human Emotions Based on Facial Mimics

Emotion detection through facial expression recognition plays an important role in everyday life, such as how to respond correctly to emotional expressions in social interactions, so that you can establish and build verbal or nonverbal communication with other people and so on. Facial expressions are facial changes in response to a person's emotional state, intentions, or social communication. Face detection is the first step that must be taken in facial analysis, including facial expression recognition. There are many methods that can be used to carry out the face detection process, such as the YOLO method. This YOLO method reframes object detection as a single regression problem, directly from image pixels to bounding box coordinates and class probabilities. By using the YOLO method, the process only needs to look once at the input image, to predict what objects are in the image and where those objects are. Based on the results of the tests carried out, the YOLO method can be used to detect human facial expressions with a success rate of 80%, with neutral, surprise and disgust facial expressions having a good level of accuracy and fear facial expressions having a poor accuracy level. The YOLO method is able to detect facial expressions of humans who wear accessories such as glasses.

Cataracts Associated With Fibroblast Growth Factor Receptor Inhibitors for Cholangiocarcinoma

Since fibroblast growth factor receptor inhibitors (FGFRi) are used for treatment of intrahepatic cholangiocarcinoma (iCCA), understanding potential complications following longer-term use in clinical practice settings is warranted. This study describes cataract formation or progression as a complication of FGFRi use for the treatment of iCCA, even after treatment discontinuation. To describe cases of cataract formation or worsening in patients with iCCA treated with FGFRi and to characterize the ophthalmologic features, risk factors, and outcomes for FGFRi-associated cataracts. This retrospective case series study used data from patients with iCCA harboring FGFR2 aberrations who received FGFRi in clinical trials or as standard therapy from the University of California, San Francisco, Hepatobiliary Tissue Bank and Registry. Data were collected from patient visits between February 2015 and October 2021, and this retrospective investigation was conducted from September 6, 2022, to May 4, 2023. Data analysis was conducted from May 5, 2023, to September 6, 2023. Use of an FGFRi for the treatment of iCCA. The primary outcome was designated as development of a new or worsening cataract after FGFRi initiation. Statistical analysis for the association between cataract formation and clinical covariates was performed using unpaired t tests and Fisher exact tests. A single bivariate logistic regression model was used to examine total duration of FGFRi therapy and age at the conclusion of FGFRi therapy as predictors of cataract development. A total of 18 patients were included in the study; median (range) patient age was 54 (27-81) years, and 13 patients (72%) were female. Nine patients (50%) developed a cataract or had cataract progression in at least 1 eye after initiation of FGFRi. Of 17 eyes with cataract, 8 eyes (47%) required cataract surgery. One patient rapidly developed a cataract associated with phacomorphic glaucoma, which required urgent surgery. The median (range) time to cataract onset or worsening from initiation of FGFRi was approximately 18 (1-23) months. Five of 9 patients (56%) who developed cataracts or had cataract progression were diagnosed with new or worsening cataracts after discontinuation of FGFRi. Patients who developed cataracts had longer median (range) duration of FGFRi treatment compared with patients who did not develop cataracts (13 months [2-26] vs 5 months [1-11]; odds ratio, 1.01; 95% CI, 1.00-1.02; P = .02). While this retrospective case series study cannot prove cause and effect conclusively due to the study design, study results highlight cataract formation or progression as a potential adverse effect of FGFRi therapy, supporting consideration of periodic eye examinations in patients who have received this treatment.

Research on multi-source information fusion tool wear monitoring based on MKW-GPR model

To enhance intelligent manufacturing capabilities and achieve the goal of online real-time high-precision monitoring of tool wear with small sample data, this paper proposes a multi-source information fusion method for turning tool wear monitoring based on the multi-kernel weighted Gaussian process regression (MKW-GPR) model. Firstly, the framework and process of multi-source information fusion for turning tool wear monitoring are established, and the experimental platform is constructed. Secondly, a full-life cutting experiment of the turning tool is conducted. During the experiment, tool wear image data and multi-sensor signal data, including cutting force and vibration signals, are collected. Then, the experimental data were processed to construct a dataset with multi-source information fusion, leading to the establishment of the MKW-GPR model. Subsequently, the experimental dataset was employed to validate the effectiveness of the turning tool wear monitoring model. The results demonstrate that, in recognizing the wear state, the MKW-GPR model exhibited superior recognition performance compared to the single kernel function Gaussian process regression model. Furthermore, in predicting the wear value, the MKW-GPR model is better than the long short-term memory (LSTM), random forest (RF), and scalable end-to-end tree boosting (XGBoost) models. During the small sample size a priori point data prediction performance test, the MKW-GPR model achieved the highest accuracy, with a maximum relative error of only 1.92% in predicting tool life during the severe wear stage. These findings substantiate the feasibility and effectiveness of the proposed turning tool wear monitoring method.

Recurrence Multilinear Regression Technique for Improving Accuracy of Energy Prediction in Power Systems

This paper demonstrates how artificial intelligence can be implemented in order to predict the energy needs of daily households using both multilinear regression (MLR) and single linear regression (SLR) methods. As a basic implementation, the SLR makes use of one input variable, which is the total amount of energy generated as an input. The MLR implementation involves multiple input variables being taken from various energy sources, including gas, coal, geothermal, wind, water, biomass, oil, etc. All of these variables are derived from detailed energy production data from the various energy sources. The purpose of this paper is to demonstrate that it is possible to analyze energy demand and supply directly together as a way to produce a more in-depth analysis. By analyzing energy production data from previous periods of time, a prediction of energy demand can be made. Compared to the SLR implementation, the MLR implementation is found to perform better because it is able to achieve a smaller error value. Furthermore, the forecasting pattern is carried out sequentially based on a periodic pattern, so this paper calls this method the recurrence multilinear regression (RMLR) method. This paper also creates a pre-clustering using the K-Means algorithm before the energy prediction to improve accuracy. Other models such as exponential GPR, sequential XGBoost, and seq2seq LSTM are used for comparison. The prediction results are evaluated by calculating the MAE, RMSE, MAPE, MAPA, and time execution for all models. The simulation results show that the fastest and best model that obtains the smallest error (3.4%) is the RMLR clustered using a weekly pattern period.

Development of a Nomogram for Predicting ICU Readmission.

Background This study aims to develop and validate a comprehensive prediction model for ICU readmissions. Readmission following ICU discharge is associated with adverse outcomes such as increased mortality, prolonged hospital stays, and elevated healthcare costs. Consequently, predicting and preventing readmissions is crucial. Previous models for predicting ICU readmissions were primarily based on physiological indices; however, these indices fail to capture the complete nature of treatment or patient conditions beyond physiological measures, thereby limiting the accuracy of these predictions. Methodology A total of 1,400 patients who had an unplanned ICU admission at Sapporo Medical University Hospital from January 2015 to October 2022 were included; a single regression analysis was performed using unplanned ICU readmission as the dependent variable. After performing a single regression analysis, logistic regression analysis using the stepwise method was performed using variables with significant differences, and a predictive nomogram was created using the variables that remained in the final model. To internally validate the predictive nomogram model, nonparametric bootstrapping (1,000 replications) was performed on the original model. Results Of the 1,400 patients who had an unplanned admission to the ICU, 114 (8.1%) were readmitted to the ICU unplanned. Seven main variables (Sequential Organ Failure Assessment score, respiratory rate, Glasgow Coma Scale, sleep disturbance, Continuous Kidney Replacement Therapy, presence of tracheal suctioning, and Oxygen Saturation) were selected to be associated with ICU readmission. The evaluation of the models showed excellent discrimination with an area under the receiver operating characteristic of 0.805 (original model) and 0.796 (bootstrap model). Calibration plots also confirmed good agreement between observed and predicted reentry. Conclusions This new predictive model is more accurate than previous models because it includes physiological indicators as well as other patient conditions and procedures needed and is expected to be used in clinical practice. In particular, the inclusion of new factors, such as sleep disturbance and the need for tracheal suctioning, enabled a more comprehensive patient assessment. The use of this predictive nomogram as a criterion for discharging ICU patients may prevent unplanned ICU readmission.

Soil Salinity Inversion Based on a Stacking Integrated Learning Algorithm

Soil salinization is an essential risk factor for agricultural development and food security, and obtaining regional soil salinity information more reliably remains a priority problem to be solved. To improve the accuracy of soil salinity inversion, this study focuses on the Manas River Basin oasis area, the largest oasis farming area in Xinjiang, as the study area and proposes a new soil salinity inversion model based on stacked integrated learning algorithms. Firstly, we selected four machine learning regression models, namely, random forest (RF), back propagation neural network, support vector regression, and convolutional neural network, for performance evaluation. Based on the model performance, we selected the more effective RF and BPNN as the basic regression models and further constructed a stacking integrated learning model. This stacking integration learning model improved the prediction accuracy by training a secondary model to fuse the prediction results of these two basic models as new features. We compared and analyzed the stacking integrated learning model with four single machine learning regression models. Findings indicated that the stacking integrated learning regression model fitted better and had good stability; on the test set, the stacking integrated learning regression model showed a relative increase of 8.2% in R2, a relative decrease of 14.0% in RMSE, and a relative increase of 6.5% in RPD when compared to the RF model, which was the single most effective machine learning regression model, and the stacking model was able to achieve soil salinity inversion more accurately. The soil salinity in the oasis areas of the Manas River Basin tended to decrease from north to south from 2016 to 2020 from a spatial point of view, and it was reduced in April from a temporal point of view. The percentage of pixels with a high soil salinity content of 2.75–2.80 g kg−1 in the study area had decreased by 19.6% in April 2020 compared to April 2016. The innovatively constructed stacking integrated learning regression model improved the accuracy of soil salinity estimation on the basis of the superior results obtained in the training of the single optimal machine learning regression model. As a consequence, this model can provide technological backup for fast monitoring and inversion of soil salinity as well as prevention and containment of salinization.

Refrigeration capacity modeling of europium titanate based magnetocaloric compounds using computational single hidden layer intelligent and random forest regression methods

Europium titanate (EuTiO3) is a quantum para-electric magnetocaloric compound with potential application in green magnetic cooling technology. Super-exchange and indirect interactions existing between the magnetic moments of this compound are responsible for the observed magnetic properties such as the refrigeration capacity which falls among the key factors that characterize the usefulness of magnetic system of cooling in addressing energy crisis. Crystallographic substitutions and ionic replacement potentially shift magnetic ordering between anti-ferromagnetism to ferromagnetism and ultimately alters the refrigeration (magnetic) capacity of EuTiO3 compound. This work proposes extreme learning machine (ELM) and random forest regression (RFR) computational approaches to model refrigeration capacity of europium titanate magnetic refrigerant with the aid of applied magnetic field, ionic concentrations and ionic radii predictors. Sigmoid activation based extreme learning machine algorithm(SGA-ELM) demonstrates superior performance over sine function activation based extreme learning machine algorithm(SIA-ELM) with improvement of 0.03 %, 16.04 % and 35.03 % on the basis of Pearson correlation coefficient (CC), root mean square error (RMSE) and mean absolute error (MAE) performance yardsticks, respectively on testing set of EuTiO3 based magnetocaloric compounds. SGA-ELM performs better than SIA-ELM and RFR model with improvement of 35.03 % and 66.84 %, respectively while SIA-ELM model performs better than RFR model with improvement of 59.97 %. SGA-ELM model developed in this work outperforms the existing swarm based support vector regression (SW-SVR) models with performance improvement of 15.38 % (for SW-SVR-Gas with Gaussian function) and 42. 71 % % (for SW-SVR-Pol with polynomial function) using mean absolute deviation (MAD) performance yardstick. Significance of magnetic field and dopants concentrations on refrigeration capacity of different EuTiO3 perovskite was investigated with SGA-ELM model. The accuracy of developed models in determining refrigeration capacity of EuTiO3 compounds would ultimately circumvents experimental challenges and explores future potentials of these classes of compound for addressing present and future energy crisis in cooling industries.

Definition of a framework for volumetric modulated arc therapy plan quality assessment with integration of dose-, complexity-, and robustness metrics

Background and purposeConventionally, the quality of radiotherapy treatment plans is assessed through visual inspection of dose distributions and dose-volume histograms. This study developed a framework to evaluate plan quality using dose, complexity, and robustness metrics. Additionally, a method for predicting plan robustness metrics using dose and complexity metrics was introduced for cases where plan robustness evaluation is unavailable or impractical. Materials and methodsThe framework and prediction models were developed and validated using 103-bronchial Volumetric Modulated Arc Therapy (VMAT)-plans. The application of the framework was demonstrated using 25-VMAT-plans. To identify significant metrics for plan evaluation, 122-metrics were analysed and narrowed down using multivariate Spearman correlation. Metric limits were set with Statistical process control (SPC). Robustness metrics were predicted using multivariable or single linear regression models based on dose-and complexity-metrics. ResultsTwenty-five-metrics were selected based on the amount and strength of correlations. R95(dose coverage) and HI95/5(homogeneity index) stood out among the dose-metrics, while the complexity-metrics showed similar correlations. Average scenarios dose at 95 % Clinical Target Volume D95mean(CTV) and Errorbar-based Volume-Histograms (EVH) were notable for robustness metrics. Approximately 99 % of evaluated metrics fell within established SPC limits. The prediction model for D95mean(CTV) showed good performance (adjusted R2 = 0.88, mean squared error (MSE) = 3.84 × 10−6), while the model for EVH demonstrated moderate reliability (adjusted R2 = 0.52, MSE = 0.2). No statistically significant differences were found between the predicted (using dose-and complexity-metrics) and calculated robustness metrics (EVH (p-value = 0.9) and D95mean(CTV) (p-value = 1)). ConclusionsThe developed framework enables early detection of sub-optimal, complex and non-robust treatment plans. The predictive model can be used when robustness evaluations are impractical.