Search

• FFS maps were produced using CTREE, KNN, SVM, RF, GBM and XGBoost algorithms. • The performance of six machine learning techniques was evaluated. • This study will be the first to use the CTREE algorithm for FFS mapping. • XGBoost gave the best results compared to other models. • The most important factor for producing FFS maps in XGBoost models was annual temperature. Antalya is one of the provinces with the highest number of forest fires in Türkiye. In 2021, 278 forest fires occurred within the administrative boundaries of Antalya Regional Directorate of Forestry. The main objective of this study is to produce forest fire susceptibility (FFS) maps of Antalya province using machine learning (ML) models. In addition to forest fire inventory data, 16 factors, including topographic, environmental, meteorological, and human-driven, were used in the study. Inventory data included 2166 fire ignition points from the General Directorate of Forestry. 70 % of the inventory dataset was used to train the ML models and 30 % to validate the models. Overall accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC-ROC) approaches were considered as validation metrics. FFS maps of Antalya were produced using stand-alone ML algorithms, K-Nearest Neighbors, and Support Vector Machines, as well as tree-based Conditional Inference Trees (CTREE), Random Forest (RF), Gradient Boosting Machines (GBM), and Extreme Gradient Boosting (XGBoost) algorithms. To the best of our knowledge, this is the first study using the CTREE algorithm for forest fire susceptibility mapping. Therefore, this study is important for the related literature. The validation results revealed that the XGBoost model outperformed other models. It is thought that the FFS map produced using the XGBoost model will guide forest engineers, wildland firefighting teams, and firefighters to minimize damage and control forest fires. [ABSTRACT FROM AUTHOR]

Diabetic vascular complications (DVC) are the main cause of death in diabetic patients. However, there is a lack of effective biomarkers or convenient methods for early diagnosis of DVC. In this study, the salivary glycopatterns from 130 of healthy volunteers (HV), 139 patients with type 2 diabetes mellitus (T2DM) and 167 patients with DVC were case-by-case analyzed by using lectin microarrays. Subsequently, diagnostic models were developed using logistic regression and machine learning algorithms based on the data of lectin microarrays in training set. The performance of diagnostic models was evaluated in an independent blind cohort. The results of lectin microarrays indicated that the glycopatterns identified by 16 lectins (e.g. BS-I, PWM and EEL) were significantly altered in DVC patients compared with patients with T2DM, which suggested the alterations in salivary glycopatterns could reflect onset of DVC. Notably, K-Nearest Neighbor (KNN) model exhibited better performance for distinguishing DVC (accuracy: 0.939) than other models in blind cohort. The integrated classifier, which combined three machine learning models, exhibited a higher overall accuracy (≥ 0.933) than other models in blind cohort. Our study provided a cost-effective and non-invasive method for auxiliary diagnosis DVC based on the combination of salivary glycopatterns and machine learning algorithms. • There were no convenient methods for early diagnosis of diabetic vascular complications (DVC) • Salivary glycopatterns showed significantly altered in DVC patients compared to type 2 diabetes mellitus patients • The K-Nearest Neighbor (KNN) model exhibited better performance for distinguishing DVC (accuracy: 0.939) than other models in blind cohort • The integrated classifier exhibited a higher overall accuracy (≥ 0.933) than other models in blind cohort [ABSTRACT FROM AUTHOR]

Even though the World Health Organization declared the end of the pandemic, COVID-19 is still considered an endemic disease, affecting many people worldwide. As a result, hospitalization rates can continue to strain healthcare systems, particularly in low and middle-income countries. Thus, this article presents two predictive Machine Learning (ML) models to identify COVID-19 patients more likely to be hospitalized or face a higher mortality risk, aiming to assist physicians and healthcare administrators in making informed decisions. Previous research primarily focused on using expensive input data, such as clinical examinations and images, to implement ML models. In contrast, we implemented the models using information on patients' demographics, vaccination history, symptoms, and underlying health conditions. We trained the ML algorithms using data from the OpenDataSus database, focusing on patients undergoing hospital treatment in São Paulo, Brazil. Our study tested 14 different ML algorithms to determine their effectiveness: gradient boosting, light gradient boosting machine, logistic regression, linear discriminant analysis, ridge, AdaBoost, random forest, support vector machine, k-nearest neighbor, extra tree, decision tree, naive Bayes, quadratic discriminant analysis, and dummy. The results showed that the gradient-boosting model outperformed the others, achieving an accuracy rate of 83% and an Area Under the Curve (AUC) of 0.89 for predicting mortality risk. Moreover, the model achieved an accuracy rate of 71% and an AUC of 0.75 for predicting hospitalization risk. Our analysis evidence that including information on the number of vaccine doses can enhance the prediction results for hospitalization and mortality of patients. Based on these significant findings, we have developed a web application to assist healthcare professionals in identifying patients at a higher risk of severe outcomes from COVID-19. • Models for identifying COVID-19 patients at risk of mortality and hospitalization. • Gathered São Paulo hospital data for COVID-19 model training. • Evaluated 14 machine Learning algorithms; gradient boosting proved most effective. • Vaccine doses can improve the risk of mortality and hospitalization. • Web app aids healthcare professionals in identifying high-risk COVID-19 cases. [ABSTRACT FROM AUTHOR]

[Display omitted] • Micro-NIR spectrometer was proposed to identify the paper types. • Four machine learning algorithms were discussed in both Micro-NIR and ATR-FTIR. • The performance of Micro-NIR model was better than ATR-FTIR. Quick identification of paper types for customs is extremely crucial. Although there are a variety of researches focus on the discrimination of paper, these techniques either require complex preprocessing or large-scale instruments, which are not suitable for customs environments. In this study, we predicted the type of customs paper by using a Micro-NIR spectrometer, and compared the results with Attenuated Total Reflection-Fourier Transform Infrared Spectroscopy (ATR-FTIR). Four different classification algorithms, including linear and non-linear classifiers: K-nearest neighbor (KNN), soft independent modeling of class analogy (SIMCA), partial least squares discriminant analysis (PLS-DA), and least squares-support vector machine (LS-SVM) were employed to classify the type of paper. 20 groups of datasets were selected by Monte Carlo sampling. For Micro-NIR data, the performances of KNN and LS-SVM were outstanding than SIMCA and PLS-DA, with the average accuracies 96.06% and 98.91%, respectively. The outcome of SIMCA and PLS-DA were similar, with the average accuracies 93.00% and 93.97%. Based on the standard derivation, the best stability of models was LS-SVM (1.06%), followed by PLS-DA (1.12%), KNN (1.22%) and SIMCA (3.07%). Compared with ATR-FTIR, the effects of Micro-NIR were better, which were embodies in the better KNN and SIMCA models, and the comparable LS-SVM model. The result demonstrated that the Micro-NIR combined with machine learning algorithms was an effective method to classify the type of customs paper efficiently and quickly, even better than ATR-FTIR. [ABSTRACT FROM AUTHOR]

The elemental analysis of cherts is very important for understanding their geological history, formation and origin. In this work, chert samples collected from a mining complex located in the Gargano promontory (Apulia, Italy) have been investigated by laser-induced breakdown spectroscopy (LIBS) using a commercial handheld (h) LIBS instrument. In order to discriminate chert samples according to their mining site, the broadband LIBS spectra acquired on the specimens were subjected to multivariate data analysis. In particular, machine learning (ML) algorithms, including discriminant analysis (DA), support vector machine (SVM), and k-nearest neighbors (KNN), were applied to the data set from the averaged LIBS spectra of each sample dimensionally reduced by principal components analysis (PCA). Among the classifiers tested, the highest accuracy (72.34%) in identifying the chemical features of five different chert suites and discriminating their sources was achieved by Leave-One-Out Cross-Validation (LOO-CV) using the cosine KNN ML algorithm. The exclusion of PC1, which appeared to be mainly influenced by elements featuring large intra-class variation and engraved the clusterization, allowed to improve the accuracy of the classification reaching the value of 80.85% using the linear DA algorithm. The classification and discrimination between 2 classes (1 × 1) reached a high rate of correct predictions, which implied that this discrimination could be used as a subsequent mean to confirm if the class predicted in the previously performed multiclass classification was correct. In conclusion, the results of this study demonstrated that even chemically similar geological materials could be discriminated using LIBS analysis combined with appropriate multivariate chemometric data processing, in particular with the aim of recognizing and differentiating specific geological chert sources and identifying the origin of chert archaeological artifacts. [Display omitted] • Handheld LIBS analysis was used for the geochemical classification and provenance identification of cherts. • PCA of the whole experimental hLIBS spectra was used to find the class clusterization in the scores plot. • Three types of supervised machine learning (ML) algorithms were tested to classify the samples. [ABSTRACT FROM AUTHOR]

• The direction of the financial dollarization rate is predicted one week ahead. • Four machine learning algorithms are utilized. • Parameters of the machine learning algorithms are optimized with genetic algorithm. Financial dollarization has many implications on the economy and the banking sector of developing countries. High level of financial dollarization causes fragilities on the balance sheet of the banks. Due to the negative effects of dollarization on the banks, predicting the financial dollarization rate for the following periods becomes very crucial for the soundness of the banking sector. This study aims to predict the weekly movement of the financial dollarization rate in the Turkish banking sector. The dataset includes asset dollarization rate series for 848 weeks between 30/12/2005 and 25/03/2022. Four different machine learning algorithms (K-Nearest Neighbor, Decision Tree, Naïve Bayes, and Support Vector Machine) are utilized to predict the next week's financial dollarization rate movement. The parameters of the machine learning algorithms are optimized with a genetic algorithm. The parameters are divided into two groups as common parameters and model-specific parameters. Common parameters are the parameters utilized in all machine learning models and include the score transform method, standardization choice, the values on the cost matrix (used to reduce the misclassification rate), and autoregressive degree. The overall dataset is divided into four sub-periods and three different predicting schemes are utilized in each sub-period and overall period. According to the results of the analysis, the prediction performance in the overall dataset, which covers a wider period, was up to 73 % and the prediction performance was up to 90 % in sub-period datasets where the economy was relatively stable. [ABSTRACT FROM AUTHOR]

• Different soil to water ratios can affect prediction performance using Vis-NIR and pXRF spectra. • Prediction performance of EC and pH were affected by soil sampling strategies. • Vis-NIR spectra had higher prediction performance compared to pXRF. • Combined Vis-NIR and pXRF spectra had no improvement on prediction accuracy. Soil electrical conductivity (EC) and pH play a critical role in managing agricultural productivity. We investigated the effect of soil to water ratios (1:1, 1:2.5, 1:5) and sampling strategies (surface, profile wall, and surface + profile wall) on prediction accuracy using individual and combined visible near infrared (Vis-NIR) and portable X-ray fluorescence (pXRF) spectra with machine learning algorithms for EC and pH. In total, 200 soil samples were collected from the soil surface (100 soil samples) and profile wall (100 soil samples) in pasture lands in Eskisehir, Türkiye. The soil samples were analyzed by considering soil to water ratios (1:1, 1:2.5, 1:5) for EC and pH and scanned by Vis-NIR (350–2500 nm) and pXRF (0–45 keV). In total 54 different predictor models were tested to achieve the highest prediction accuracy for both EC and pH. The seven machine learning regressions (elastic net, k-nearest neighbors, lasso, partial least squares, random forest, ridge, and support vector machine-linear) were applied in modeling with calibration (70 % soil samples) and validation (30 % soil samples) datasets for each model. The results suggested that the EC 1:2.5 and EC 1:5 ratios had relatively higher prediction accuracy (r = 0.95, R2 = 0.93, RMSE = 0.58, MAE = 0.46, RPD = 3.57, and RPIQ = 5.33) using Vis-NIR spectra with partial least squares and support vector machine-linear models in profile wall compared to other sampling strategies and EC 1:1 ratio. The pH 1:2.5 ratio had relatively higher prediction accuracy (r = 0.90, R2 = 0.81, RMSE = 0.07, MAE = 0.06, RPD = 2.49, and RPIQ = 3.71) using Vis-NIR spectra with random forest model in profile wall compared to other sampling strategies and pH 1:1 and pH 1:5 ratios. In addition, combined Vis-NIR and pXRF spectra had no improvement in prediction accuracy. Finally, it can be concluded that the prediction accuracy is affected by soil to water ratios and sampling strategies. Individual Vis-NIR spectra can reach the highest prediction accuracy for EC and pH compared to combined pXRF and Vis-NIR spectra. [ABSTRACT FROM AUTHOR]

• In this study, a new data augmantetion model was proposed. • The presented model was tested by statistical methods. • This model can be used in any work where data augmantetion will be done. Cancer disease is among the leading causes of death in the world today. It has been scientifically proven that if the disease is detected in the first stages, the success rate in treatment can be close to 100%. Accordingly, it can be said that the problems caused by breast cancer can be solved to a great extent thanks to early diagnosis. Data sets that can be processed in early diagnosis are required. Researchers use artificial intelligence techniques to develop systems to assist specialist doctors. It is of great importance to have a data set on which researchers can work. The more parameters of these data sets and the number of these parameters, the more artificial learning process takes place. In this study, both a new data augmentation method for two different classes in the database of breast cancer was presented and breast cancer was diagnosed with this method. First, the database was analyzed statistically with the proposed data augmentation method. Then, the new values obtained from the data augmentation process were added to the database with a 5-times and 10-times augmentation. Experimental studies were conducted between raw database and databases with augmentatied data. The proposed model with 5 different Machine Learning Algorithms (MLA) (k Nearest Neighbors (k-NN), Decision Tree (DT), Naive Bayes (NB), Random Forest (RF)) and Support Vector Machine (SVM)) were tested. The accuracy rates in train and test operations were increased in the following order; for k-NN, same − 15%, for DT, 0.1–13.01%, for RF, same − 14.03%, for NB, 14.7%−19.7%, for SVM, 15.9%−14.06%. The rates obtained from the experimental results proved to be very promising. The proposed method can be used as an alternative data augmentation method for researchers to get more accurate results in their studies. [ABSTRACT FROM AUTHOR]