Class Of Regression Models Research Articles

An in-depth comparative analysis of data-driven and classic regression models for scour depth prediction around cylindrical bridge piers

The study focuses on the critical concern of designing secure and resilient bridge piers, especially regarding scour phenomena. Traditional equations for estimating scour depth are limited, often leading to inaccuracies. To address these shortcomings, modern data-driven models (DDMs) have emerged. This research conducts a comprehensive comparison involving DDMs, including support vector machine (SVM), gene expression programming (GEP), multilayer perceptron (MLP), gradient boosting trees (GBT) and multivariate adaptive regression spline (MARS) models, against two regression equations for predicting scour depth around cylindrical bridge piers. Evaluation employs statistical indices, such as root-mean-square error (RMSE), coefficient of determination (R2), mean average error (MAE) and normalized discrepancy ratio (S(DDRmax)), to assess their predictive performance. A total of 455 datasets from previous research papers are employed for assessment. Dimensionless parameters Froude number Fr=Ugy\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\left( {Fr = \\frac{U}{{\\sqrt {gy} }}} \\right)$$\\end{document}, Pier Froude number FrP=Ug′D\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$Fr_{P} = \\frac{U}{{\\sqrt {g^{\\prime } D} }}$$\\end{document}, and the ratio of scour depth to pier diameter (yD)\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$(\\frac{\ ext{y}}{{\ ext{D}}})$$\\end{document} are carefully selected as influential model inputs through dimensional analysis and the gamma test. The results highlight the superior performance of the SVM model. In the training phase, it exhibits an RMSE of 0.1009, MAE of 0.0726, R2 of 0.9401, and SDDR of 2.9237. During testing, the SVM model shows an RMSE of 0.023, MAE of 0.017, R2 of 0.984, and SDDR of 5.301. Additionally, it has an average error of − 0.065 and a total error of − 20.642 in the training set and an average error of − 0.005 and a total error of − 0.707 in the testing set. Conversely, the M5 model exhibits the lowest accuracy. The statistical metrics unequivocally establish the SVM model as significantly outperforming the experimental models, placing it in a higher echelon of predictive accuracy.

DFLOWFS: Deep Fast-Learning Optimal Weight Fuzzy System with bottom-up hierarchical structure for high-dimensional data regression

As a model for reasoning and decision-making based on fuzzy rules, fuzzy systems have high interpretability. However, when the data dimension increases, the fuzzy system will face the problem of “rule explosion”, making it difficult to learn and predict effectively. In this paper, the fuzzy system trained by the FLOWFS (Fast-Learning with Optimal Weights for Fuzzy Systems) algorithm is used as sub-module in the deep fuzzy system, and the deep fuzzy system DFLOWFS (Deep FLOWFS) is constructed from the bottom-up hierarchical structure as the following three steps. 1) The FLOWFS algorithm assigns weight attributions to each fuzzy rule, and the rule weights are trained by the least square method with regularization terms to shorten training time and improve accuracy. 2) Three strategies of dividing high-dimensional inputs into multiple low-dimensional inputs are proposed as sequential division, random division and correlation division. Then, it is verified by experiments that the correlation division has the best performance. 3) The sub-module discarding method is proposed to discard the sub-modules with poor performance to have a maximum improvement of 13.8% compared to the DFLOWFS without using the sub-module discarding method. Then, the optimized DFLOWFS is verified and compared with the other three classic regression models on the three UCI datasets. Experiments show that with the increase of the data dimension, DFLOWFS not only have good interpretability but also have good accuracy. Furthermore, DFLOWFS performs best among all models in comprehensive scores, with good learning ability and generalization ability. Therefore, the proposed strategies with hierarchical structure for optimal shallow fuzzy systems are effective, which give a new insight for fuzzy system research.

Metabolomic profiling of preterm birth in pregnant women living with HIV

BackgroundPreterm birth is a leading cause of death in children under the age of five. The risk of preterm birth is increased by maternal HIV infection as well as by certain antiretroviral regimens, leading to a disproportionate burden on low- and medium-income settings where HIV is most prevalent. Despite decades of research, the mechanisms underlying spontaneous preterm birth, particularly in resource limited areas with high HIV infection rates, are still poorly understood and accurate prediction and therapeutic intervention remain elusive.ObjectivesMetabolomics was utilized to identify profiles of preterm birth among pregnant women living with HIV on two different antiretroviral therapy (ART) regimens.MethodsThis pilot study comprised 100 mother-infant dyads prior to antiretroviral initiation, on zidovudine monotherapy or on protease inhibitor-based antiretroviral therapy. Pregnancies that resulted in preterm births were matched 1:1 with controls by gestational age at time of sample collection. Maternal plasma and blood spots at 23–35 weeks gestation and infant dried blood spots at birth, were assayed using an untargeted metabolomics method. Linear regression and random forests classification models were used to identify shared and treatment-specific markers of preterm birth.ResultsClassification models for preterm birth achieved accuracies of 95.5%, 95.7%, and 80.7% in the untreated, zidovudine monotherapy, and protease inhibitor-based treatment groups, respectively. Urate, methionine sulfone, cortisone, and 17α-hydroxypregnanolone glucuronide were identified as shared markers of preterm birth. Other compounds including hippurate and N-acetyl-1-methylhistidine were found to be significantly altered in a treatment-specific context.ConclusionThis study identified previously known as well as novel metabolomic features of preterm birth in pregnant women living with HIV. Validation of these models in a larger, independent cohort is necessary to ascertain whether they can be utilized to predict preterm birth during a stage of gestation that allows for therapeutic intervention or more effective resource allocation.

A new ordinal mixed-data sampling model with an application to corporate credit rating levels

In this paper we propose a new ordinal logistic regression model (OLMIDAS) that allows the inclusion of independent variables at higher frequencies than that of the dependent variable. A simulation study shows that our proposed model can find the true patterns in the data. In an empirical study we apply OLMIDAS to the prediction of corporate credit rating levels and compare its performance to classical logistic regression models with an annual aggregation of the higher-frequency variable, such as ordinal logistic regression and multinomial logistic regression. We find that OLMIDAS outperforms the classical logistic regression models while providing additional knowledge of the structure of the higher-frequency explanatory variable.

Machine learning based churn prediction in telecom

In the new era of continuous social development, the level of information technology service construction is also increasing, among which the telecommunications service industry has also developed into a relatively large business cluster under this trend. Due to fierce commercial competition, telecommunication companies also face the problem of losing customers. Asking telecom companies to determine the trend of customer churn from the huge amount of customer information data has become a challenge for all telecom companies to solve. This paper takes a telecom company as a reference, using a large amount of subscriber data from it as a research sample, and uses data mining machine learning and other techniques to make churn predictions on customer data, using three classification methods to evaluate the prediction results and help telecom service providers analyze the causes of customer churn. Firstly, the situation faced by the telecom service company is discussed in terms of the relevant background, then by presenting and analyzing the customer data, and finally by using Logical Regression, Mission Tree, and SVM classification models for classification and evaluation, the causes associated with customer churn are summarized, then the methods of customer churn retention are outlined, and the factors associated with customer churn are listed. The factors associated with churn are listed. This provides a reference for an in-depth study of the theoretical approach and application of customer churn.

Generative learning‐based model for the prediction of 2D stress distribution

AbstractIn this study, we introduce a Generative learning‐based approach to accelerate Finite Element simulations. The aim is to explore the ability of a Generative learning‐based approach to predict the output of Finite Element simulations. Often, the drawback of classical regression models is that they are bound to the distribution of training data and cannot extrapolate outside of the training domain. In the current study, to overcome this, we propose a Generative Adversarial Network (GAN) based approach for learning to infer structural mechanics simulations. GANs have the ability to learn the underlying distribution of data and can efficiently extrapolate outside the training range. We train the proposed network on data obtained from classical Finite Element simulations based on linear elastic and Johnson‐Cook plasticity models. The goal here is to understand the ability of a GAN to replace FEM by incorporating the underlying mechanics knowledge into the network to enhance the generalizing ability of the network for various materials on various loading and boundary conditions. We propose an encoder‐decoder‐like U‐Net generator architecture with activated skip connections and a PatchGAN‐based discriminator that discriminates based on local patches of data leading to a more robust critique for the generator. The advantage of the proposed framework is that it takes inputs such as the nodal information, their corresponding edges, nodal coordinates and the boundary conditions for each particular node from a Finite Element pre‐processor and computes the von Mises stress at each node as output that can be read by a Finite Element post‐processor. Also, the novelty of the proposed GAN is that, unlike the existing literature, it takes nodal values such as applied Boundary conditions and coordinates as inputs instead of images and performs nonlinear regression with Finite Element data and gives von‐Mises stresses at each node as output.

ST-GWLR: combining geographically weighted logistic regression and spatiotemporal hotspot trend analysis to explore the effect of built environment on traffic crash

ABSTRACT Road traffic crashes are becoming thorny issues being faced worldwide. Traffic crashes are spatiotemporal events and the research on the spatiotemporal patterns and variation trends of traffic crashes has been carried out. However, the impact of built environment on traffic crash spatiotemporal trends has not received much attention. Moreover, the spatial non-stationarity between the variation trends of traffic crashes and their influencing factors is usually neglected. To make up for the lack of analysis of built environment factors influencing spatiotemporal hotspot trends in traffic crashes, this paper proposed a method of “ST-GWLR” for analyzing the influence of built environment factors on spatiotemporal hotspot trends of traffic crashes by combining the spatiotemporal hotspot trend analysis and Geographically Weighted Logistic Regression (GWLR) modeling methods. Firstly, the traffic crash spatiotemporal hotspot trends were explored using the space-time cube model, hotspot analysis, and Mann-Kendall trend test. Then, the GWLR was introduced to capture the spatial non-stationarity neglected by the classic Global Logistic Regression (GLR) model, to improve the accuracy of the model estimation. GWLR model is used for the first time to analyze the significant local correlation between the traffic crash spatiotemporal hotspot trends and the built environment factors, to accurately and effectively identify the built environment factors that have significant influences on the hotspot trends of traffic crashes. The performance of the GWLR models and GLR models was examined and compared sufficiently. The results showed that the proposed ST-GWLR, which captured spatial non-stationarity, performed better than the classic GLR combined with spatiotemporal analysis, and improved the prediction accuracy of the models by 14.9%, 13.9%, and 15.1%, respectively. There were significant local correlations between intensifying hotspots and persistent hotspots of traffic crashes and the built environment factors. The findings of this paper have positive implications for traffic safety management and urban built environment planning.

Prediction of lung papillary adenocarcinoma-specific survival using ensemble machine learning models

Accurate prognostic prediction is crucial for treatment decision-making in lung papillary adenocarcinoma (LPADC). The aim of this study was to predict cancer-specific survival in LPADC using ensemble machine learning and classical Cox regression models. Moreover, models were evaluated to provide recommendations based on quantitative data for personalized treatment of LPADC. Data of patients diagnosed with LPADC (2004–2018) were extracted from the Surveillance, Epidemiology, and End Results database. The set of samples was randomly divided into the training and validation sets at a ratio of 7:3. Three ensemble models were selected, namely gradient boosting survival (GBS), random survival forest (RSF), and extra survival trees (EST). In addition, Cox proportional hazards (CoxPH) regression was used to construct the prognostic models. The Harrell’s concordance index (C-index), integrated Brier score (IBS), and area under the time-dependent receiver operating characteristic curve (time-dependent AUC) were used to evaluate the performance of the predictive models. A user-friendly web access panel was provided to easily evaluate the model for the prediction of survival and treatment recommendations. A total of 3615 patients were randomly divided into the training and validation cohorts (n = 2530 and 1085, respectively). The extra survival trees, RSF, GBS, and CoxPH models showed good discriminative ability and calibration in both the training and validation cohorts (mean of time-dependent AUC: > 0.84 and > 0.82; C-index: > 0.79 and > 0.77; IBS: < 0.16 and < 0.17, respectively). The RSF and GBS models were more consistent than the CoxPH model in predicting long-term survival. We implemented the developed models as web applications for deployment into clinical practice (accessible through https://shinyshine-820-lpaprediction-model-z3ubbu.streamlit.app/). All four prognostic models showed good discriminative ability and calibration. The RSF and GBS models exhibited the highest effectiveness among all models in predicting the long-term cancer-specific survival of patients with LPADC. This approach may facilitate the development of personalized treatment plans and prediction of prognosis for LPADC.

Prediction Models of Blood Glucose Change During Aerobic Exercise Using Machine Learning Techniques

PURPOSE: This study aimed to explore the relationship between blood glucose level changes and body characteristics during exercise and to present six models for predicting changes in blood glucose levels during exercise.METHODS: 148 healthy men and women (age: 31.9±9.7 year, fasting blood glucose: 102.1±14.1 mg/dL, &lt;i&gt;p&lt;/i&gt;=.032) participated in the study, and 30 of them participated in the study. Eight variables were selected to build two prediction models: 24-hour ingested carbohydrates, age, blood glucose, heart rate changes, sex, skeletal muscle mass, heart rate recovery after exercise, and resting heart rate. Logistic regression and random forest classifier models were used to predict the changes in blood glucose levels during exercise.RESULTS: A total of six models were created for all participants, male and female. Random forest classification (training set: AUC=0.837, Youden index=0.66; validation set: AUC=0.730, Youden index=0.53) and logistic regression classification models (training set: AUC=0.807, Youden index=0.55; validation set: AUC=0.735, Youden index=0.57) were built.CONCLUSION: The random forest model showed good performance in classifying internal data, whereas the logistic regression classification model demonstrated relatively good performance in classifying validation data.

A Model-Free Feature Selection Technique of Feature Screening and Random Forest-Based Recursive Feature Elimination

This paper studies data with mass features, commonly observed in applications such as text classification and medical diagnosis. We allow data to have several structures without requiring a specific model and propose an efficient model-free feature selection procedure. The proposed method can work with various types of datasets. We demonstrate that this method has several desirable properties, including high accuracy, model-free, and computational efficiency and can be applied to practical problems with different modelings. We prove that the proposed method achieves selection consistency and L 2 consistency under mild regularity conditions. We conduct simulations on various datasets, including data generated from the generalized linear model, additive model, Poisson regression, and binary classification model. These simulations illustrate the superior performance of the proposed method compared to other existing methods across different model settings. In addition, we apply our method to two real examples, the Tecator dataset and the Daily Demand Orders dataset, both of which are continuous and high dimensional. In both cases, our method consistently achieves high accuracy in prediction and model selection.

Performance of Radiomics Based Multi-Parameter Models Derived from Lung CT in Differentiating Benign Non-Inflammatory, Inflammatory and Malignant Pulmonary Nodule

Pulmonary nodules are a significant clinical issue that require accurate and efficient diagnosis. This study constructed a machine learning model, combining radiomics features of chest CT sequences with three types of microvascular density (MVD) values, to differentiate benign, inflammatory and malignant pulmonary nodules. A total of 100 patients with lung nodules on CT images and corresponding pathological results were retrospectively included in the study. The MVD values and radiomics features were calculated and extracted based on the segmented nodules. Univariate correlation analysis and principal component analysis were performed to select radiomics features. Combined MVD values and selected radiomics features, we conducted a logistic regression classification model. The area under the curve (AUC) was applied to show model performance. Our model reached an AUC value of 0.867 when tested on independent datasets. The performance of the model to differentiate benign, malignant and inflammatory nodules reached AUC values of only 0.908, 0.833, and 0.730, respectively. We conducted a prediction model that shows promising results in distinguishing three different types of lung nodules.

Anomaly prediction of CT equipment based on IoMT data

BackgroundLarge-scale medical equipment, which is extensively implemented in medical services, is of vital importance for diagnosis but vulnerable to various anomalies and failures. Most hospitals that conduct regular maintenance have been suffering from medical equipment-related incidents for years. Currently, the Internet of Medical Things (IoMT) has emerged as a crucial tool in monitoring the real-time status of the medical equipment. In this paper, we develop an IoMT system of Computed Tomography (CT) equipment in the West China Hospital, Sichuan University and collected the system status time-series data. Novel multivariate time-series classification models and frameworks are proposed to predict the anomalies of CT equipment. The important features that are closely related to the equipment anomalies are identified with the model.MethodsWe extracted the real-time CT equipment status time-series data of 11 equipment between May 19, 2020 and May 19, 2021 from the IoMT, which includes the equipment oil temperature, anode voltage, etc. The arcs are identified as labels of anomalies due to their relationship with decreased imaging quality and CT equipment failures. To improve prediction accuracy, the statistics and transformations of the raw historical time-series data segment in the sliding time window are used to construct new features. Due to the particularity of time-series data, two frameworks are proposed for splitting the training and test sets. Then the Decision Tree, Support Vector Machine, Logistic Regression, Naive Bayesian, and K-Nearest Neighbor classification models are used to classify the system status. We also compare our model to state-of-the-art models.ResultsThe results show that the anomaly prediction accuracy and recall of our method are 79% and 77%, respectively. The oil temperature and anode voltage are identified as the decisive features that may lead to anomalies. The proposed model outperforms the others when predicting the anomalies of the CT equipment based on our dataset.ConclusionsThe proposed method could predict the state of CT equipment and be used as a reference for practical maintenance, where unexpected anomalies of medical equipment could be reduced. It also brings new insights into how to handle non-uniform and imbalanced time series data in practical cases.

Statistical test for detrending-moving-average-based multivariate regression model

The detrending-moving-average-based multivariate linear regression has been recently introduced as a new tool to probe into multiscale dependent behavior between multivariate data. It well solves the dependence among the nonstationary variates while classic multivariate linear regression dose not. The real-world applications demonstrate its versatility and robustness. However, the statistical significance of this new model needs to be further improved mathematically not just empirically. Hence, the main motivation of this paper is to provide a solid theoretical basis for the latest regression framework. Specifically, four propositions and three theorems are deduced theoretically to support the statistical significance test of detrending-moving-average-based multivariate linear regression model. These propositions and theorems revolve around hypothesis testing of each partial regression coefficients and regression model. They can examine the statistical significance at every given scales. Moreover, we also resort to synthetic time series to verify the performances of the proposed statistical test procedure. By using those statistical tests, we investigate the multiscale interdependence between the crude oil price and the exchange rates among oil-importing and oil-exporting countries. Some interesting findings show that the dependent behavior between the oil price and exchange rates varies at various scales, which cannot be achieved from classical multivariate regression model.

Regularized Machine Learning Models for Prediction of Metabolic Syndrome Using GCKR, APOA5, and BUD13 Gene Variants: Tehran Cardiometabolic Genetic Study.

Metabolic syndrome (MetS) is a complex multifactorial disorder that considerably burdens healthcare systems. We aim to classify MetS using regularized machine learning models in the presence of the risk variants of GCKR, BUD13 and APOA5, and environmental risk factors. A cohort study was conducted on 2,346 cases and 2,203 controls from eligible Tehran Cardiometabolic Genetic Study (TCGS) participants whose data were collected from 1999 to 2017. We used different regularization approaches [least absolute shrinkage and selection operator (LASSO), ridge regression (RR), elasticnet (ENET), adaptive LASSO (aLASSO), and adaptive ENET (aENET)] and a classical logistic regression (LR) model to classify MetS and select influential variables that predict MetS. Demographics, clinical features, and common polymorphisms in the GCKR, BUD13 and APOA5 genes of eligible participants were assessed to classify TCGS participant status in MetS development. The models' performance was evaluated by 10-repeated 10-fold crossvalidation. Various assessment measures of sensitivity, specificity, classification accuracy, and area under the receiver operating characteristic curve (AUC-ROC) and AUC-precision-recall (AUC-PR) curves were used to compare the models. During the follow-up period, 50.38% of participants developed MetS. The groups were not similar in terms of baseline characteristics and risk variants. MetS was significantly associated with age, gender, schooling years, body mass index (BMI), and alternate alleles in all the risk variants, as indicated by LR. A comparison of accuracy, AUCROC, and AUC-PR metrics indicated that the regularization models outperformed LR. Regularized machine learning models provided comparable classification performances, whereas the aLASSO model was more parsimonious and selected fewer predictors. Regularized machine learning models provided more accurate and parsimonious MetS classifying models. These high-performing diagnostic models can lay the foundation for clinical decision support tools that use genetic and demographical variables to locate individuals at high risk for MetS.

UPLC-QDA and machine learning for distinguishing different commodity specifications of Fritillariae Cirrhosae Bulbus and application of data augmentation technology

This study aimed to establish a method based on machine learning technology for accurately predicting the commodity specifications of Fritillariae Cirrhosae Bulbus and explore the application of data augmentation technology in the field of drug analysis. The correlation optimized warping(COW) algorithm was used to perform peak calibration on the UPLC-QDA multi-channel superimposed data of 30 batches of samples, and the data were normalized. Through unsupervised learning methods such as clustering analysis, principal component analysis(PCA), and correlation analysis, the general characteristics of the data were understood. Then, the logistic regression algorithm was used for supervised learning on the data, and the condition tabular generative adversarial networks(CTGAN) was used to generate a large amount of data. Logistic regression classification models were trained separately using the real data and the data generated by CTGAN, and these models were evaluated. The logistic regression model trained with real data achieved cross-validation and test set accuracies of 0.95 and 1.00, respectively, while the logistic regression model trained with both real and CTGAN-generated data achieved cross-validation and test set accuracies of 0.99 and 1.00, respectively. The results indicate that machine learning can accurately predict the classification of Songbei, Qingbei, and Lubeibased on UPLC-QDA detection data. CTGAN-generated data can partially compensate for the lack of data in drug analysis, improving the accuracy and predictive ability of machine learning models.

Establishment risk of invasive golden mussel in a water diversion project: An assessment framework

Inter-basin water diversion projects have led to accelerated colonization of aquatic organisms, including the freshwater golden mussel (Limnoperna fortunei), exacerbating global biofouling concerns. While the influence of environmental factors on the mussel's invasion and biofouling impact has been studied, quantitative correlations and underlying mechanisms remain unclear, particularly in large-scale inter-basin water diversion projects with diverse hydrodynamic and environmental conditions. Here, we examine the comprehensive impact of environmental variables on the establishment risk of the golden mussel in China's 1432-km-long Middle Route of the South-to-North Water Diversion Project. Logistic regression and multiclass classification models were used to investigate the environmental influence on the occurrence probability and reproductive density of the golden mussel. Total nitrogen, ammonia nitrogen, water temperature, pH, and velocity were identified as crucial environmental variables affecting the biofouling risk in the project. Logistic regression analysis revealed a negative correlation between the occurrence probability of all larval stages and levels of total nitrogen and ammonia nitrogen. The multiclass classification model showed that elevated levels of total nitrogen hindered mussel reproduction, while optimal water temperature enhanced their reproductive capacity. Appropriate velocity and pH levels were crucial in maintaining moderate larval density. This research presents a quantitative analytical framework for assessing establishment risks associated with invasive mussels, and the framework is expected to enhance invasion management and mitigate biofouling issues in water diversion projects worldwide.

Power Modified Lindley Distribution: Properties, Classical and Bayesian Estimation and Regression Model with Applications

In this article, we explore a new probability density function, called the power modified Lindley distribution. Its main feature is to operate a simple trade-off among the generalized exponential, Weibull and gamma distributions, offering an alternative to these three well-established distributions. The proposed model turns out to be quite flexible: its probability density function can be right skewed and its associated hazard rate function may be increasing, decreasing, unimodal and constant. First the model parameters of the proposed distribution are obtained by the maximum likelihood method. Next, Bayes estimators of the unknown parameters are obtained under different loss functions. In addition, bootstrap confidence intervals are provided to compare with Bayes credible intervals. Besides, log power modified Lindley regression model for censored data is proposed. Two real data sets are analyzed to illustrate the flexibility and importance of the proposed model.

Comparison of data-driven methods for linking extreme precipitation events to local and large-scale meteorological variables

Extreme precipitation events can lead to severe negative consequences for society, the economy, and the environment. It is therefore crucial to understand when such events occur. In the literature, there are a vast number of methods for analyzing their connection to meteorological drivers. However, there has been recent interest in using machine learning methods instead of classic statistical models. While a few studies in climate research have compared the performance of these two approaches, their conclusions are inconsistent. To determine whether an extreme event occurred locally, we trained models using logistic regression and three commonly used supervised machine learning algorithms tailored for discrete outcomes: random forests, neural networks, and support vector machines. We used five explanatory variables (geopotential height at 500 hPa, convective available potential energy, total column water, sea surface temperature, and air surface temperature) from ERA5, and local data from the Danish Meteorological Institute. During the variable selection process, we found that convective available potential energy has the strongest relationship with extreme events. Our results showed that logistic regression performs similarly to more complex machine learning algorithms regarding discrimination as measured by the area under the receiver operating characteristic curve (ROC AUC) and other performance metrics specialized for unbalanced datasets. Specifically, the ROC AUC for logistic regression was 0.86, while the best-performing machine learning algorithm achieved a ROC AUC of 0.87. This study emphasizes the value of comparing machine learning and classical regression modeling, especially when employing a limited set of well-established explanatory variables.

Construction of quantile regression using natural gradient descent

Building mathematical models is an important part of developing digital products in various industries, medicine, geology, construction, finance and other areas. Modeling allows optimizing production processes, identifying patterns, predicting time series, classifying objects, and constructing regressions. Quantile regression models are a generalization of median regression and can be used to examine data in depth. Quantile analysis involves estimating model parameters and determining quantile values of the dependent variable for given values of the independent variable. This is done by minimizing the loss function based on quantile values. In contrast to the method of least squares, quantile regression allows to predict the values of the dependent variable more accurately when the values of the independent variable change. That is, quantile regression is more robust. It can be used to solve many problems in various fields of science and business, where it is necessary to more accurately predict the values of the dependent variable under changing conditions. The natural gradient descent is an effective method for constructing regression and has a higher rate of convergence than the classical algorithm. However, in practice this method is quite complicated from a computational point of view, since it requires the calculation of the second derivative. This problem is especially acute when training neural networks, where the number of parameters is much higher than when building classical regression models. The study of methods of regression construction and application of numerical methods are of practical and scientific interest. This paper will look at quantile regression, natural gradient descent and their combination to build mathematical models. Gradient descent is one of the most popular optimization methods and is widely used in machine learning. The natural gradient descent is the preferred method because it is more efficient and has a high rate of convergence. In addition, this method is less vulnerable to hitting local minima and provides more accurate estimates of model parameters. In practice, however, this method is computationally difficult, as it requires the calculation of the second derivative. The article presents an algorithm for model building using natural gradient descent. The essence of using quantile regression in a natural gradient descent is to use a quantile estimate of the loss function instead of the usual estimate used in the least squares method. This allows not only the mean value of the dependent variable, but also more extreme values (e.g., median, 25th percentile, 95th percentile, etc.) to be considered when constructing the model. The resulting method has also been compared with other popular quantile regression-supported gradient descent methods on open data sets of different dimensionality, both in terms of the number of factors and the number of observations. In addition, the possibilities of further development and optimization of this method will be discussed.

Neuronally enriched microvesicle RNAs are differentially expressed in the serums of Parkinson's patients.

Circulating small RNAs (smRNAs) originate from diverse tissues and organs. Previous studies investigating smRNAs as potential biomarkers for Parkinson's disease (PD) have yielded inconsistent results. We investigated whether smRNA profiles from neuronally-enriched serum exosomes and microvesicles are altered in PD patients and discriminate PD subjects from controls. Demographic, clinical, and serum samples were obtained from 60 PD subjects and 40 age- and sex-matched controls. Exosomes and microvesicles were extracted and isolated using a validated neuronal membrane marker (CD171). Sequencing and bioinformatics analyses were used to identify differentially expressed smRNAs in PD and control samples. SmRNAs also were tested for association with clinical metrics. Logistic regression and random forest classification models evaluated the discriminative value of the smRNAs. In serum CD171 enriched exosomes and microvesicles, a panel of 29 smRNAs was expressed differentially between PD and controls (false discovery rate (FDR) < 0.05). Among the smRNAs, 23 were upregulated and 6 were downregulated in PD patients. Pathway analysis revealed links to cellular proliferation regulation and signaling. Least absolute shrinkage and selection operator adjusted for the multicollinearity of these smRNAs and association tests to clinical parameters via linear regression did not yield significant results. Univariate logistic regression models showed that four smRNAs achieved an AUC ≥ 0.74 to discriminate PD subjects from controls. The random forest model had an AUC of 0.942 for the 29 smRNA panel. CD171-enriched exosomes and microvesicles contain the differential expression of smRNAs between PD and controls. Future studies are warranted to follow up on the findings and understand the scientific and clinical relevance.