Search

In recent years, machine learning (ML) algorithms have gained substantial recognition for ecological modeling across various temporal and spatial scales. However, little evaluation has been conducted for the prediction of soil organic carbon (SOC) on small data sets commonly inherent to long-term soil ecological research. In this context, the performance of ML algorithms for SOC prediction has never been tested against traditional process-based modeling approaches. Here, we compare ML algorithms, calibrated and uncalibrated process-based models as well as multiple ensembles on their performance in predicting SOC using data from five long-term experimental sites (comprising 256 independent data points) in Austria. Using all available data, the ML-based approaches using Random forest and Support vector machines with a polynomial kernel were superior to all process-based models. However, the ML algorithms performed similar or worse when the number of training samples was reduced or when a leave-one-site-out cross validation was applied. This emphasizes that the performance of ML algorithms is strongly dependent on the data-size related quality of learning information following the well-known curse of dimensionality phenomenon, while the accuracy of process-based models significantly relies on proper calibration and combination of different modeling approaches. Our study thus suggests a superiority of ML-based SOC prediction at scales where larger datasets are available, while process-based models are superior tools when targeting the exploration of underlying biophysical and biochemical mechanisms of SOC dynamics in soils. Therefore, we recommend applying ensembles of ML algorithms with process-based models to combine advantages inherent to both approaches. • We evaluated process-based (PB) and machine-learning (ML) models for SOC prediction. • Random forest & support vector machine predicted SOC superior to PB models. • Reduced data availability and quality significantly weakened ML model performance. • ML-assisted PB model ensembles strongly improved model performance. [ABSTRACT FROM AUTHOR]

• 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]

Conventional brute-force attacks can now be detected and identified based on statistical analysis of logs and traffic data. However, they fail to detect low-frequency and distributed brute-force attack behaviors. To address different attack methods, new detection techniques have emerged. This study compares various machine learning algorithms and selects two methods, namely the clustering algorithm k-means and bdscan, as well as the decision tree algorithm for data learning. In one approach, normal user login data is integrated with enterprise email log data. The data is first statistically analyzed and filtered, followed by quantifying data characteristics using information entropy. Subsequently, machine learning algorithms are employed for classification, and the results are visualized for display. In another approach, labeled raw data is used to train a model using the decision tree algorithm. By comparing the two analysis results, a more accurate model can be obtained. These analytical methods can help enterprises strengthen email security and defend against low-frequency and distributed brute-force attacks. [ABSTRACT FROM AUTHOR]

The growth of the world population is leading to an increased demand for food production. Consequently, there is a need to update agricultural processes to enhance production. Smart farming has evolved as a farm management concept that leverages real-time, dependable, and site-specific agricultural information to ensure consistent and sustainable yields. This study focuses on soil nutrient analysis, specifically nitrogen (N), phosphorus (P), and potassium (K) for enhancing crop production. Maintaining an appropriate balance of NPK is crucial for the well-rounded nutrition of crops. Various environmental factors such as temperature, rainfall, humidity, and soil pH affect the NPK composition of agricultural land. The optimal usage of NPK levels can help to improve plant growth, increase crop yields, and enhance overall farm productivity. Hence, we have proposed a stack regressor learning algorithm comprising of two layers for accurate, reliable, and context-sensitive predictions of NPK levels. The proposed approach considers the combined impact of these environmental factors and predicts the optimal NPK requirements tailored to specific crops and agricultural land. The analysis of graphs demonstrates that the predictive accuracy of the proposed stacked regressor model far surpasses that of preexisting built-in machine learning models. This study helps farmers make informed decisions, leading to productivity and sustainability. [ABSTRACT FROM AUTHOR]

Summary: Immune thrombocytopenia (ITP) is an autoimmune disease characterized by antibody‐mediated platelet destruction and impaired platelet production. The mechanisms underlying ITP and biomarkers predicting the response of drug treatments are elusive. We performed a metabolomic profiling of bone marrow biopsy samples collected from ITP patients admission in a prospective study of the National Longitudinal Cohort of Hematological Diseases. Machine learning algorithms were conducted to discover novel biomarkers to predict ITP patient treatment responses. From the bone marrow biopsies of 91 ITP patients, we quantified a total of 4494 metabolites, including 1456 metabolites in the positive mode and 3038 metabolites in the negative mode. Metabolic patterns varied significantly between groups of newly diagnosed and chronic ITP, with a total of 876 differential metabolites involved in 181 unique metabolic pathways. Enrichment factors and p‐values revealed the top metabolically enriched pathways to be sphingolipid metabolism, the sphingolipid signalling pathway, ubiquinone and other terpenoid–quinone biosynthesis, thiamine metabolism, tryptophan metabolism and cofactors biosynthesis, the phospholipase D signalling pathway and the phosphatidylinositol signalling system. Based on patient responses to five treatment options, we screened several metabolites using the Boruta algorithm and ranked their importance using the random forest algorithm. Lipids and their metabolism, including long‐chain fatty acids, oxidized lipids, glycerophospholipids, phosphatidylcholine and phosphatidylethanolamine biosynthesis, helped differentiate drug treatment responses. In conclusion, this study revealed metabolic alterations associated with ITP in bone marrow supernatants and a potential biomarker predicting the response to ITP. [ABSTRACT FROM AUTHOR]

Parkinson's disease (PD) is the second most common neurological disorder caused by damage to dopaminergic neurons. Therefore, it is important to develop systems for early and automatic diagnosis of PD. For this purpose, a study that will contribute to the development of systems for the automatic diagnosis of PD is presented. The Electroencephalography (EEG) signals were decomposed into sub-bands using adaptive decomposition methods, such as empirical mode decomposition, variational mode decomposition, and Vold-Kalman order filtering (VKF). Various features were extracted from the sub-band decomposed signals, and the significant ones were determined by Chi-squared test. These important features were applied as input to support vector machine (SVM), fitch neural network (FNN), k-nearest neighbours (KNN), and decision trees (DT), machine learning (ML) models and classification was performed. We analysed the performance of ML models by obtaining accuracy, sensitivity, specificity, positive predictive value, negative predictive values, F1-score, false-positive rate, kappa statistics, and area under the curve. The classification process was performed for two cases: PD ON-HC and PD OFF-HC groups. The most successful method in this study was the VKF method, which was applied for the first time in this field with the approach specified for both cases. In both instances, the SVM algorithm was employed as the ML model, with classifier performance criterion values close to 100%. The results obtained in this study seem to be successful compared to the results of recent research on the diagnosis of PD. [ABSTRACT FROM AUTHOR]

The leaf area index (LAI), a crucial biophysical indicator, is used to assess and monitor crop growth for effective agricultural management. This study assessed the LAI at the seedling stage after conducting a field experiment with rainfed groundnut. The study tests the performance of multiple machine learning regression algorithms (MLRAs) and empirical vegetation indices (VIs) in retrieving groundnut's LAI using freely available Sentinel-2 data. The bands at 665 nm, 705 nm, 842 nm, and 2190 nm are the most sensitive for retrieving groundnut's LAI, according to an analysis of its band spectrum. Results suggest that VIs computed with wavebands centered at red (665 nm), red edge (705 nm), and near-infrared (842 nm) exhibited optimal R2 with Sentinel-2 data. Normalized difference vegetation index (NDVI), red edge normalized difference vegetation index (NDVIre), simple ratio (SR), red edge simple ratio (SRre), and green normalized difference vegetation index (gNDVI) were utilized as predictors for LAI. Regarding the results of the validation between estimated and measured LAI, SR demonstrated the highest accuracy for groundnut LAI prediction (r2 = 0.67, RMSE = 0.89). Ten MLRAs were tested, and results indicate from the perspective of the accuracy of models, the Gaussian processes regression, GPR (r2 = 0.73 and RMSE = 0.81), Kernel ridge regression, KRR (r2 = 0.72 and RMSE = 0.82) and Support vector regression, SVR (r2 = 0.70 and RMSE = 0.85) demonstrated to be the most suitable for LAI estimation for rainfed groundnut at the seedling stage. The systematic analysis based on the regression approaches tested here revealed that the GPR outperformed other models combined, therefore, most suitable for estimating rainfed groundnut LAI at the seedling stage. These findings serve as a benchmark for obtaining crop biophysical parameters in the framework of groundnut traits monitoring in a tropical West Africa. [ABSTRACT FROM AUTHOR]

In recent years, machine learning algorithms have been used in the mass appraisal of real estate. In this study, 5 machine learning algorithms are used for residential type real estate. Machine learning algorithms used for mass appraisal in this study are Artificial Neural Networks (ANN), Random Forest (RO), Multiple Regression Analysis (MRA), K-Nearest Neighborhood (k-nn), Support Vector Regression (SVR). To test the study, real estate data collected from the central districts of Ankara, were used. The main purpose of this study is to find out which machine learning algorithm gives the best results for the mass appraisal of real estates and to reveal the most important variables that affect the prices of real estate. According to the results obtained for the city of Ankara, it was observed that the best algorithm for mass appraisal is RF in residential-type real estates, followed by the ANN, k-nn, and linear regression algorithms, respectively. According to the results obtained from the residential real estate, it was concluded that heating and distances to places of importance had the greatest effect on the value. [ABSTRACT FROM AUTHOR]

The damage assessment of numerous buildings after the earthquake is still a challenge by traditional methods as it requires a significant amount of time and resources for carrying out building-by-building seismic damage assessment. This study presents the machine learning (ML)-based damage assessment of buildings after an earthquake. The applicability of the machine learning model will be limited considering only structural properties or ground motion characteristics. Thus, in this study, the applicability of different machine learning techniques is explored using real-world earthquake damage datasets considering both the structural properties and ground motion characteristics. Initially, the entire dataset is used to train the ML models to classify the building's damage into five categories ranging from null to slight damage to collapse. Later, the dataset is divided into three traffic light damage tags: green, yellow, and red. The performance of the ML model to classify the building's damage into three damage tags is found better than that of classifying it into five damage categories. This research aims to be beneficial in planning and decision-making for emergency response and recovery following an earthquake. [ABSTRACT FROM AUTHOR]

The estimation of postmortem interval (PMI) is a complex and challenging problem in forensic medicine. In recent years, many studies have begun to use machine learning methods to estimate PMI. However, research combining postmortem computed tomography (PMCT) with machine learning models for PMI estimation is still in early stages. This study aims to establish a multi-tissue machine learning model for PMI estimation using PMCT data from various tissues. We collected PMCT data of seven tissues, including brain, eyeballs, myocardium, liver, kidneys, erector spinae, and quadriceps femoris from 10 rabbits after death. CT images were taken every 12 h until 192 h after death, and HU values were extracted from the CT images of each tissue as a dataset. Support vector machine, random forest, and K-nearest neighbors were performed to establish PMI estimation models, and after adjusting the parameters of each model, they were used as first-level classification to build a stacking model to further improve the PMI estimation accuracy. The accuracy and generalized area under the receiver operating characteristic curve of the multi-tissue stacking model were able to reach 93% and 0.96, respectively. Results indicated that PMCT detection could be used to obtain postmortem change of different tissue densities, and the stacking model demonstrated strong predictive and generalization abilities. This approach provides new research methods and ideas for the study of PMI estimation. [ABSTRACT FROM AUTHOR]

This study investigates the effectiveness of six prominent machine learning models—random forest, decision trees, K-nearest neighbor, logistic regression, support vector machines, and Naïve Bayes—for intrusion detection systems in industrial Internet of Things environments. The evaluation encompasses the effects of data preprocessing techniques, including feature engineering, data normalization, recoding, and missing data mitigation. Furthermore, the research delves into dataset balancing, examining the effects of six different techniques on model performance. The investigations are conducted using the domain-specific WUSTL-IIOT-2021 dataset, which captures the unique characteristics of IIoT data. The study also investigates multi-class attack identification utilizing an innovative SMOTE-based multi-class balancing approach to tackle dataset imbalances. The results indicate that data preprocessing and intelligent dataset balancing produce consistent enhancements in the classification performance of the selected models across binary and multi-classification tasks. Random forest emerges as the standout algorithm, delivering consistently high performance with computational efficiency. [ABSTRACT FROM AUTHOR]

Current measurement systems based on the IEEE-1159 standard have some limitations and robustness problems under noisy and fast-changing conditions. Besides, applying different methods for each Power Quality Disturbance (PQD) to every window is required but time-consuming and not feasible. Therefore, different kinds of two-stage methods, Detection and Classification (D&C), have been improved in many studies. Then, the required measurement can be performed to define disturbance. For this purpose, a new approach based on features of subcomponents with Machine Learning Algorithms (MLAs) to detect and classify PQDs is proposed. 21-class dataset including single and multiple PQDs under different noisy conditions was prepared randomly. Of this dataset, determined features were extracted and some of these were selected. Then, selected features were trained and tested with some MLAs in a workstation. Results obtained from comparative MLAs and the other classification methods show that the best MLA with related features is Random Forest with 96.97% while LightGBM, k-Nearest Neighbors, and XGBoost 96.85%, 96.73%, and 92.82% accuracy, respectively. Because the selected features, optimized parameters, and the related MLA were obtained by investigating for features provided from the PQDs in the whole parameter space, this approach brings the advantages of high accuracy, low D&C complexity, and computing load. [ABSTRACT FROM AUTHOR]

The estimation of material performance plays a crucial role in practical life, enabling the rational allocation of time and resources while enhancing the practical application of materials. Therefore, this study investigates the analytical and predictive capabilities of five machine learning (ML) algorithms (the Random Forest algorithm – RF, the Adaboost algorithm – AB, the Gradient Boosting algorithm – GB, the Extra Trees algorithm – ET and linear models – LM) for comprehensive performance parameters of wood ceramics (ammonia nitrogen adsorption quantity - Q , open porosity - P , burn-off , and hardness). In the analysis of model prediction capabilities, five key statistical parameters (Root Mean Square Error - RMSE , Mean Square Error - MSE , Coefficient of Correlation - R , Determination Coefficient - R 2 , and Mean Absolute Relative Error - MARE) were calculated. The results indicate the following: (1) Among various ML models, the GB model exhibits the most superior performance with an R 2 ≥ 0.9594. (2) However, in predicting the four performance parameters of wood ceramics, the AB model with an R 2 ranging from 0.0078 to 0.45, indicating notably poor predictive capabilities. Despite integrating the Support Vector Regression (SVR) module, no enhancement in predictive accuracy was observed. (3) While forecasting the four performance parameters of wood ceramics, the LM model demonstrates predictive accuracy relatively akin to that of the RF and ET models among the ML models. (4) Though the feature importance scores vary across distinct input variable models, there is a consistent trend of change. (5) Variables B and D exhibit some level of correlation with other variables. In summary, the results of this study suggest that, for the analysis and prediction of wood ceramic performance, the GB model among the five regression models demonstrates outstanding simulation performance. [ABSTRACT FROM AUTHOR]

• This study examined the genes related to PD pathogenesis by tissues and blood samples datasets. • WGCNA and protein–protein interaction (PPI) network were used to pinpoint hub genes. • Elevation of FOXO3 , HIST2H2BE , and HDAC1 expression associated with PD pathogenesis. Parkinson's disease (PD) represents a multifaceted neurological disorder whose genetic underpinnings warrant comprehensive investigation. This study focuses on identifying genes integral to PD pathogenesis and evaluating their diagnostic potential. Initially, we screened for differentially expressed genes (DEGs) between PD and control brain tissues within a dataset comprising larger number of specimens. Subsequently, these DEGs were subjected to weighted gene co-expression network analysis (WGCNA) to discern relevant gene modules. Notably, the yellow module exhibited a significant correlation with PD pathogenesis. Hence, we conducted a detailed examination of the yellow module genes using a cytoscope-based approach to construct a protein–protein interaction (PPI) network, which facilitated the identification of central hub genes implicated in PD pathogenesis. Employing two machine learning techniques, including XGBoost and LASSO algorithms, along with logistic regression analysis, we refined our search to three pertinent hub genes: FOXO3 , HIST2H2BE , and HDAC1 , all of which demonstrated a substantial association with PD pathogenesis. To corroborate our findings, we analyzed two PD blood datasets and clinical plasma samples, confirming the elevated expression levels of these genes in PD patients. The association of the genes with PD, as reflected by the area under the curve (AUC) values for FOXO3 , HIST2H2BE , and HDAC1 , were moderate for each gene. Collectively, this research substantiates the heightened expression of FOXO3 , HIST2H2BE , and HDAC1 in both PD brain and blood samples, underscoring their pivotal contribution to the pathogenesis of PD. [ABSTRACT FROM AUTHOR]

Objective: Prediction of lymph node metastasis (LNM) for intrahepatic cholangiocarcinoma (ICC) is critical for the treatment regimen and prognosis. We aim to develop and validate machine learning (ML)-based predictive models for LNM in patients with ICC. Methods: A total of 345 patients with clinicopathological characteristics confirmed ICC from Jan 2007 to Jan 2019 were enrolled. The predictors of LNM were identified by the least absolute shrinkage and selection operator (LASSO) and logistic analysis. The selected variables were used for developing prediction models for LNM by six ML algorithms, including Logistic regression (LR), Gradient boosting machine (GBM), Extreme gradient boosting (XGB), Random Forest (RF), Decision tree (DT), Multilayer perceptron (MLP). We applied 10-fold cross validation as internal validation and calculated the average of the areas under the receiver operating characteristic (ROC) curve to measure the performance of all models. A feature selection approach was applied to identify importance of predictors in each model. The heat map was used to investigate the correlation of features. Finally, we established a web calculator using the best-performing model. Results: In multivariate logistic regression analysis, factors including alcoholic liver disease (ALD), smoking, boundary, diameter, and white blood cell (WBC) were identified as independent predictors for LNM in patients with ICC. In internal validation, the average values of AUC of six models ranged from 0.820 to 0.908. The XGB model was identified as the best model, the average AUC was 0.908. Finally, we established a web calculator by XGB model, which was useful for clinicians to calculate the likelihood of LNM. Conclusion: The proposed ML-based predicted models had a good performance to predict LNM of patients with ICC. XGB performed best. A web calculator based on the ML algorithm showed promise in assisting clinicians to predict LNM and developed individualized medical plans. [ABSTRACT FROM AUTHOR]

(1) Background: Neck pain intensity, psychosocial factors, and physical function have been identified as potential predictors of neck disability. Machine learning algorithms have shown promise in classifying patients based on their neck disability status. So, the current study was conducted to identify predictors of neck disability in patients with neck pain based on clinical findings using machine learning algorithms. (2) Methods: Ninety participants with chronic neck pain took part in the study. Demographic characteristics in addition to neck pain intensity, the neck disability index, cervical spine contour, and surface electromyographic characteristics of the axioscapular muscles were measured. Participants were categorised into high disability and low disability groups based on the median value (22.2) of their neck disability index scores. Several regression and classification machine learning models were trained and assessed using a 10-fold cross-validation method; also, MANCOVA was used to compare between the two groups. (3) Results: The multilayer perceptron (MLP) revealed the highest adjusted R2 of 0.768, while linear discriminate analysis showed the highest receiver characteristic operator (ROC) area under the curve of 0.91. Pain intensity was the most important feature in both models with the highest effect size of 0.568 with p < 0.001. (4) Conclusions: The study findings provide valuable insights into pain as the most important predictor of neck disability in patients with cervical pain. Tailoring interventions based on pain can improve patient outcomes and potentially prevent or reduce neck disability. [ABSTRACT FROM AUTHOR]

Many object‐oriented metrics have been proposed in the literature to measure various structural properties of object‐oriented software. Furthermore, many centrality measures have been introduced to identify central nodes in large networks. However, few studies have used them to measure dependencies in software systems. In fact, centrality measures, as opposed to most traditional object‐oriented metrics that mainly focus on intrinsic properties of classes, can be used to better model the control flow and to identify the most important classes in a software system. This paper aims (1) to investigate the relationships between object‐oriented metrics and centrality measures and (2) to explore the ability of their combination to support fault‐proneness prediction from different perspectives (fault‐prone classes, fault severity, and number of faults). Many studies in the literature have addressed the prediction of fault‐prone classes, from different perspectives, using object‐oriented metrics. The main motivation here is in fact to investigate if the information captured by centrality measures is related to fault proneness and complementary to the information captured by object‐oriented metrics and to investigate if the combination of object‐oriented metrics and centrality measures improves the performance of fault‐proneness prediction significantly. We used size, complexity, and coupling object‐oriented metrics in addition to various centrality measures. We collected data from 20 different versions of five open‐source Java software systems. We first studied the relationships between selected metrics and their relationships to fault proneness. Then, we built different models to predict fault‐prone classes using several machine learning algorithms. In addition, we built models to predict if a class contains a high severity fault, and the number of faults in a class. Results indicate that using centrality measures in combination with object‐oriented metrics improves the prediction of fault‐prone classes as well as the prediction of the number of faults in a class. However, the combination has no significant impact, according to the data we collected, on the quality of the prediction of fault severity. Moreover, using centrality measures in combination with object‐oriented metrics also improves the prediction performance of fault proneness and the number of faults in both cross‐version and cross‐system validation. [ABSTRACT FROM AUTHOR]

Rice is an annual plant from the family of Oryzeae, provides the main food for about 2.5 billion people. The quality of this product is under the influence of various factors. Quality control and adulteration detection are among the main issues in the rice industry for which, various methods have been developed. Some of these methods are costly or with low accuracy. Therefore, this study aimed to investigate and detect adulteration with spectroscopic devices and chemometric methods as well as neural network approach. The results of this study indicated the highest accuracy (100%) in the detection of authentic rice for Fouriertransform infrared combined with C-support vector machine (linear and polynomial functions) and visible-near-infrared device with quadratic discriminant analysis, multivariate discriminant analysis, Bayesian, and Decision Tree. The lowest accuracy was also related to support vector machine method with Sigmoid function for both devices. Principal component analysis method also provided very high accuracy for both devices (accuracy of 100% for visible-near-infrared and 99% for Fourier-transform infrared). [ABSTRACT FROM AUTHOR]

Price changes in construction materials have a significant impact on building construction projects. Such price variations occur at random and at varying rates over time. A system that can estimate the magnitude and quantity of the change in material prices with reasonable accuracy is required. The primary goal is to create a machine-learning model that can predict the type of building material chosen based on environmental factors. The compressive strength of concrete is critical in defining its mechanical qualities. Long laboratory testing is needed to determine the compressive strength of concrete. The capacity of powerful machine learning algorithms to forecast concrete compressive strength speeds up these lengthy experimental methods while also lowering expenses. This study provides abilities to precisely anticipate and categorize numerous qualities and traits of distinct materials. The framework includes a broad dataset that details materials, composition, and performance characteristics. Machine learning algorithms such as logistic regression (LR), decision trees (DT), and random forests (RF) train models on the training data. The models are hyper-parameter tweaked and feature developed to achieve the most outstanding performance. The k-fold method is used throughout the training and assessment phase to guarantee robustness and reduce bias. The F1 score and Receiver Operating Characteristic-Area Under Curve (ROC-AUC) curve are two performance measures used to measure how accurate and predictive the trained models are. The study findings provide insights into the qualities of the materials, facilitating improved material selection, quality assurance, and decision-making in the building sector. In the analyses, the best accuracy value was 99.92%, and the precision value was 88.83% using the LR algorithm. As a result, it was determined that the LR algorithm had the least execution 57.826 ms, and is thus the most suitable for use in concrete compressive strength estimation. [ABSTRACT FROM AUTHOR]

Background: The specific microbiota and associated metabolites linked to non-alcoholic fatty liver disease (NAFLD) are still controversial. Thus, we aimed to understand how the core gut microbiota and metabolites impact NAFLD. Methods: The data for the discovery cohort were collected from the Guangzhou Nutrition and Health Study (GNHS) follow-up conducted between 2014 and 2018. We collected 272 metadata points from 1546 individuals. The metadata were input into four interpretable machine learning models to identify important gut microbiota associated with NAFLD. These models were subsequently applied to two validation cohorts [the internal validation cohort (n = 377), and the prospective validation cohort (n = 749)] to assess generalizability. We constructed an individual microbiome risk score (MRS) based on the identified gut microbiota and conducted animal faecal microbiome transplantation experiment using faecal samples from individuals with different levels of MRS to determine the relationship between MRS and NAFLD. Additionally, we conducted targeted metabolomic sequencing of faecal samples to analyse potential metabolites. Results: Among the four machine learning models used, the lightGBM algorithm achieved the best performance. A total of 12 taxa-related features of the microbiota were selected by the lightGBM algorithm and further used to calculate the MRS. Increased MRS was positively associated with the presence of NAFLD, with odds ratio (OR) of 1.86 (1.72, 2.02) per 1-unit increase in MRS. An elevated abundance of the faecal microbiota (f__veillonellaceae) was associated with increased NAFLD risk, whereas f__rikenellaceae, f__barnesiellaceae, and s__adolescentis were associated with a decreased presence of NAFLD. Higher levels of specific gut microbiota-derived metabolites of bile acids (taurocholic acid) might be positively associated with both a higher MRS and NAFLD risk. FMT in mice further confirmed a causal association between a higher MRS and the development of NAFLD. Conclusions: We confirmed that an alteration in the composition of the core gut microbiota might be biologically relevant to NAFLD development. Our work demonstrated the role of the microbiota in the development of NAFLD. [ABSTRACT FROM AUTHOR]

Currently, the information on the structural attributes of forests, such as the diameter at breast height (DBH) and the aboveground biomass (AGB), is being used widely in various disciplines. In this study, we first proposed a novel tree detection algorithm called multi‐scale individual tree detection (MSITD) algorithm, which combines the strengths of raster‐based and point‐based approaches in order to detect individual trees from LiDAR data accurately. After tree detection, the DBH and AGB attributes were estimated using the ground control data and metrics extracted from LiDAR data, adopting the safe semi‐supervised regression (SAFER) algorithm specifically designed for addressing regression problems with limited sample data. The performances of these algorithms were evaluated within a 10‐fold nested cross‐validation approach, utilizing the LiDAR data available in the NEWFOR project. The evaluation of the obtained results revealed that both the MSITD algorithm and the SAFER algorithm demonstrate substantial superiority compared to the benchmark algorithms in tree detection, especially for the understory trees, and forest structural attributes estimation, respectively. On average, the MSITD algorithm exhibited a 13% better performance in terms of extraction rate and an 11% better performance in terms of matching rate compared to the benchmark individual tree detection algorithms. For forest structural attributes estimation, the SAFER algorithm provided superior predictions compared to the benchmark ML algorithms, with the average RMSE of 3.38 cm, MAE of 2.84 cm, and R2 of 0.59 for DBH and the average RMSE of 75.79 kg, MAE of 70.02 kg, and R2 of 0.56 for AGB. Key Points: We developed a novel approach within a multi‐scale framework to detect individual trees from LiDAR data accuratelyA semi‐supervised regression algorithm has been employed to estimate the diameter at breast height and aboveground biomass attributes using the limited reference ground dataA 10‐fold nested cross‐validation approach has been implemented to evaluate the performance of the regression algorithms [ABSTRACT FROM AUTHOR]

Chronic social isolation (CSIS) generates two stress-related phenotypes: resilience and susceptibility. However, the molecular mechanisms underlying CSIS resilience remain unclear. We identified altered proteome components and biochemical pathways and processes in the prefrontal cortex cytosolic fraction in CSIS-resilient rats compared to CSIS-susceptible and control rats using liquid chromatography coupled with tandem mass spectrometry followed by label-free quantification and STRING bioinformatics. A sucrose preference test was performed to distinguish rat phenotypes. Potential predictive proteins discriminating between the CSIS-resilient and CSIS-susceptible groups were identified using machine learning (ML) algorithms: support vector machine-based sequential feature selection and random forest-based feature importance scores. Predominantly, decreased levels of some glycolytic enzymes, G protein-coupled receptor proteins, the Ras subfamily of GTPases proteins, and antioxidant proteins were found in the CSIS-resilient vs. CSIS-susceptible groups. Altered levels of Gapdh, microtubular, cytoskeletal, and calcium-binding proteins were identified between the two phenotypes. Increased levels of proteins involved in GABA synthesis, the proteasome system, nitrogen metabolism, and chaperone-mediated protein folding were identified. Predictive proteins make CSIS-resilient vs. CSIS-susceptible groups linearly separable, whereby a 100% validation accuracy was achieved by ML models. The overall ratio of significantly up- and downregulated cytosolic proteins suggests adaptive cellular alterations as part of the stress-coping process specific for the CSIS-resilient phenotype. [ABSTRACT FROM AUTHOR]

Since viruses are one of the main causes of infectious illnesses, prophylaxis is essential for efficient disease control. Vaccines play a pivotal role in mitigating the transmission of various viral infections and fortifying our defenses against them. The initial step in modern vaccine design and development involves the identification of potential vaccine targets through computational techniques. Here, using datasets of 1588 known viral immunogens and 468 viral non-immunogens, we apply machine learning algorithms to develop models for the prediction of protective immunogens of viral origin. The datasets are split into training and test sets in a 4:1 ratio. The protein structures are encoded by E-descriptors and transformed into uniform vectors by the auto- and cross-covariance methods. The most relevant descriptors are selected by the gain/ratio technique. The models generated by Random Forest, Multilayer Perceptron, and XGBoost algorithms demonstrate superior predictive performance on the test sets, surpassing predictions made by VaxiJen 2.0—an established gold standard in viral immunogenicity prediction. The key attributes determining immunogenicity in viral proteins are specific fingerprints in hydrophobicity and steric properties. [ABSTRACT FROM AUTHOR]

In this study, we present a two-step method for predicting price bubbles in precious metals, which combines a widely recognized right-tailed unit root test to detect bubbles with various machine learning algorithms to pinpoint the potential predictors of bubble formation and their relative significance. We utilize logistic regression, support vector machines, CART, random forests, extreme gradient boosting, and neural networks algorithms, which are more precise than traditional methods in making predictions and can handle binary classification and regression issues. Our analysis covers monthly prices for gold, silver, palladium, and platinum from 1990M1-2022M10. The study extends the literature by utilizing the Generalized Supremum Augmented Dickey-Fuller test to identify potential price bubbles and analyzing the effect of macroeconomic, financial, and uncertainty factors on the likelihood of bubbles using machine learning algorithms. The findings indicate that macroeconomic factors play a significant role in the formation of price bubbles in precious metals; specifically the consumer confidence index in the USA was a common factor that had a positive impact on the likelihood of bubbles in gold, platinum, and silver. However, the leading factors in the formation of bubbles in palladium were found to be financial variables and uncertainty variables. As predicting bubbles is crucial for regulators and policymakers to take preventive measures against future crises, identifying the key predictors of bubble formation and forecasting them in the early stages is essential. [ABSTRACT FROM AUTHOR]

For hydrogen-powered vehicles, the efficiency cost brought about by the current industry choices of hydrogen storage methods greatly reduces the system's overall efficiency. The physisorption of hydrogen fuel onto metal–organic frameworks (MOFs) is a promising alternative storage method due to their large surface areas and exceptional tunability. However, the massive selection of MOFs poses a challenge for the efficient screening of top-performing MOF structures that are capable of meeting target hydrogen uptakes. This study examined the performance of 13 machine learning (ML) models in the prediction of the gravimetric and volumetric hydrogen uptakes of real MOF structures for comparison with simulated and experimental results. Among the 13 models studied, 12 models gave an R2 greater than 0.95 in the prediction of both the gravimetric and the volumetric uptakes in MOFs. In addition, this study introduces a 4-20-1 ANN model that predicts the bulk, shear, and Young's moduli for the MOFs. The machine learning models with high R2 can be used in choosing MOFs for hydrogen storage. [ABSTRACT FROM AUTHOR]

Social media platforms play a vital role in determining valuable tourist objectives, which greatly aids in optimizing tourist path planning. As data classification and analysis methods have advanced, machine learning (ML) algorithms such as the k-means algorithm have emerged as powerful tools for sorting through data collected from social media platforms. However, traditional k-means algorithms have drawbacks, including challenges in determining initial seed values. This paper presents a novel approach to enhance the k-means algorithm based on survey and social media tourism data for tourism path recommendations. The main contribution of this paper is enhancing the traditional k-means algorithm by employing the genetic algorithm (GA) to determine the number of clusters (k), select the initial seeds, and recommend the best tourism path based on social media tourism data. The GA enhances the k-means algorithm by using a binary string to represent initial centers and to apply GA operators. To assess its effectiveness, we applied this approach to recommend the optimal tourism path in the Red Sea State, Sudan. The results clearly indicate the superiority of our approach, with an algorithm optimization time of 0.01 s. In contrast, traditional k-means and hierarchical cluster algorithms required 0.27 and 0.7 s, respectively. [ABSTRACT FROM AUTHOR]

VEGF is prototypic marker of neovascularization, repeatedly proposed as intrinsic characteristic of peri-implantitis. This study aimed to assess pattern of VEGF in peri-implantitis, its correlation with titanium particles (TPs) and capacity as respective biomarker. Pathological specificity of VEGF was assessed in peri-implant granulations using immunohistochemistry, periodontal granulations represented Ti-free positive controls. VEGF was correlated to TPs, identified using scanning electron microscopy coupled with dispersive x-ray spectrometry. Diagnostic accuracy, sensitivity and specificity of VEGF were estimated in PICF specimens from peri-implantitis, peri-implant mucositis (PIM) and healthy peri-implant tissues (HI) using machine learning algorithms. Peri-implantitis exhibited rich neovascular network with expressed density in contact zones toward neutrophil infiltrates without specific pattern variations around TPs, identified in all peri-implantitis specimens (mean particle size 8.9 ± 24.8 µm2; Ti-mass (%) 0.380 ± 0.163). VEGF was significantly more expressed in peri-implantitis (47,065 ± 24.2) compared to periodontitis (31,14 ± 9.15), and positively correlated with its soluble concentrations in PICF (p = 0.01). VEGF was positively correlated to all clinical endpoints and significantly increased in peri-implantitis compared to both PIM and HI, but despite high specificity (96%), its overall diagnostic capacity was average. Two patient clusters were identified in peri-implantitis, one with 8-fold higher VEGF values compared to HI, and second with lower values comparable to PIM. VEGF accurately reflects neovascularization in peri-implantitis that was expressed in contact zones toward implant surface without specific histopathological patter variation around TPs. VEGF answered requests for biomarker of peri-implantitis but further research is necessary to decrypt its exact underlying cause. [Display omitted] • Neovascularization was expressed in contact zones toward implant surface. • VEGF is highly specific to peri-implantitis and accurately reflects neovascularization. • VEGF could not be directly associated to titanium particles. • In-depth research is required to decipher the specific VEGF pattern in peri-implantitis. [ABSTRACT FROM AUTHOR]

Simple Summary: Tumor cells shed pieces of DNA that circulate in biofluids like blood and urine. The amount of circulating tumor DNA is related to the amount of cancer in the body. Knowing the amount of cancer helps doctors predict outcomes and decide treatments for patients. Tumor DNA has methylation patterns that makes it distinct from non-cancer DNA. In this study, we describe a new method called tumor methylated fraction (TMeF) that quantifies the cancer-indicative methylation patterns within circulating tumor DNA from blood samples. This method is non-invasive because it does not need tumor tissue to estimate the amount of cancer in the body. In the future, doctors could use TMeF to supplement current cancer screening methods. Estimating the abundance of cell-free DNA (cfDNA) fragments shed from a tumor (i.e., circulating tumor DNA (ctDNA)) can approximate tumor burden, which has numerous clinical applications. We derived a novel, broadly applicable statistical method to quantify cancer-indicative methylation patterns within cfDNA to estimate ctDNA abundance, even at low levels. Our algorithm identified differentially methylated regions (DMRs) between a reference database of cancer tissue biopsy samples and cfDNA from individuals without cancer. Then, without utilizing matched tissue biopsy, counts of fragments matching the cancer-indicative hyper/hypo-methylated patterns within DMRs were used to determine a tumor methylated fraction (TMeF; a methylation-based quantification of the circulating tumor allele fraction and estimate of ctDNA abundance) for plasma samples. TMeF and small variant allele fraction (SVAF) estimates of the same cancer plasma samples were correlated (Spearman's correlation coefficient: 0.73), and synthetic dilutions to expected TMeF of 10−3 and 10−4 had estimated TMeF within two-fold for 95% and 77% of samples, respectively. TMeF increased with cancer stage and tumor size and inversely correlated with survival probability. Therefore, tumor-derived fragments in the cfDNA of patients with cancer can be leveraged to estimate ctDNA abundance without the need for a tumor biopsy, which may provide non-invasive clinical approximations of tumor burden. [ABSTRACT FROM AUTHOR]

The accurate assessment of nitrogen (N) status is important for N management and yield improvement. The N status in plants is affected by plant densities and N application rates, while the methods for assessing the N status in drip-irrigated cotton under reduced nitrogen treatment and different plant densities are lacking. Therefore, this study was conducted with four different N treatments (195.5, 299, 402.5, and 506 kg N ha−1) and three sowing densities (6.9 × 104, 13.8 × 104, and 24 × 104 plants ha−1) by using a low-cost Unmanned Aerial Vehicle (UAV) system to acquire RGB imagery at a 10 m flight altitude at cotton main growth stages. We evaluated the performance of different ground resolutions (1.3, 2.6, 5.2, 10.4, 20.8, 41.6, 83.2, and 166.4 cm) for image textures, vegetation indices (VIs), and their combination for leaf N concentration (LNC) estimation using four regression methods (stepwise multiple linear regression, SMLR; support vector regression, SVR; extreme learning machine, ELM; random forest, RF). The results showed that combining VIs (ExGR, GRVI, GBRI, GRRI, MGRVI, RGBVI) and textures (VAR, HOM, CON, DIS) yielded higher estimation accuracy than using either alone. Specifically, the RF regression models had a higher accuracy and stability than SMLR and the other two machine learning algorithms. The best accuracy (R2 = 0.87, RMSE = 3.14 g kg−1, rRMSE = 7.00%) was obtained when RF was applied in combination with VIs and texture. Thus, the combination of VIs and textures from UAV images using RF could improve the estimation accuracy of drip-irrigated cotton LNC and may have a potential contribution in the rapid and non-destructive nutrition monitoring and diagnosis of other crops or other growth parameters. [ABSTRACT FROM AUTHOR]

Farming is the primary lifestyle in numerous nations, particularly India. Assuming they have never worked, youthful ranchers may not realize which yields to plant and which ones to pick. We're taking care of on this problem, which should be fixed. In the event that you can foresee the right yield and result, you can go with better choices, set aside cash, and hold the gamble of cost changes under wraps. Rather than our framework, which utilizes classification and relapse to sort out crop assortment ideas and result appraises, the ongoing framework isn't being utilized. ML strategies ought to be utilized in the cultivation business to foresee the quantity of harvests that will become in view of a bunch of information. The directed ML technique is utilized to take a gander at a dataset and pull information from various sources, like variable unmistakable confirmation, univariate examination, bivariate and multivariate investigation, missing worth frameworks, and so forth. To figure out which program was supposed to give the best return, ML recipes were investigated. While seeing entropy precision, accuracy, recall, F1 Score, sensitivity, specificity, and entropy, the outcomes show that the recommended ML strategy is the most reliable. [ABSTRACT FROM AUTHOR]

The problem of recognition and classification of loads at the output of generating and transmitting distributed parameter lines (DPL) in devices of high-power pulse technology (HPPT) by the amplitude and shape of the output signal using mathematical models based on machine learning methods and neural networks has been considered. A web application that recognizes parasitic parameters occurring in the devices based on DPL has been developed. [ABSTRACT FROM AUTHOR]

The rapid development of infinite networks and information technology has promoted the wide deployment and rapid growth of intelligent interactive devices. However, at the same time, touch interaction technology also faces many challenges such as lack of precision. This study combines federated learning with LayerGesture technology to optimize and design a touch interaction system with higher interaction accuracy and applies it to practice. The analysis results show that with the increase in the number of iterations of the federated model, the accuracy of the human–computer recognition interaction and the amount of information contained in it increases, and the accuracy curve reaches stability at about 2800 times and is at the optimal interaction adaptation. At this point, the loss function also decreases gradually, while the loss factor tends to 0, which verifies the stability of the optimized model. According to the participants' interaction experience and experimental results, the optimized LayerGesture technique of the federated learning model has an average correctness rate of 90.4% and the lowest average selection time, while the average selection time of LayerGesture in the interaction area at the edge of the screen is 2510 ms and the average correctness rate is 93.60%, which is better than the Shift technique. In addition, the subjective survey results indicated that more participants favored the optimized LayerGesture technique. In summary, this paper's joint learning algorithm contributes to the recognition effectiveness and efficiency of intelligent interactive systems. [ABSTRACT FROM AUTHOR]

Lightning Electromagnetic Pulses, or LEMPs, propagate in the Earth–ionosphere waveguide and can be detected remotely by ground-based lightning electric field sensors. LEMPs produced by different types of lightning processes have different signatures. A single thunderstorm can produce thousands of LEMPs, which makes their classification virtually impossible to carry out manually. The lightning classification is important to distinguish the types of thunderstorms and to know their severity. Lightning type is also related to aerosol concentration and can reveal wildfires. Artificial Intelligence (AI) is a good approach to recognizing patterns and dealing with huge datasets. AI is the general denomination for different Machine Learning Algorithms (MLAs) including deep learning and others. The constant improvements in the AI field show us that most of the Lightning Location Systems (LLS) will soon incorporate those techniques to improve their performance in the lightning-type classification task. In this study, we assess the performance of different MLAs, including a SVM (Support Vector Machine), MLP (Multi-Layer Perceptron), FCN (Fully Convolutional Network), and Residual Neural Network (ResNet) in the task of LEMP classification. We also address different aspects of the dataset that can interfere with the classification problem, including data balance, noise level, and LEMP recorded length. [ABSTRACT FROM AUTHOR]

Electromyography (EMG) signals hold critical significance in biomedical research, capturing muscle electrical activity during rest and contraction in the upper limb. Their versatility in applications, particularly in human-assisting robotic tools, drives ongoing exploration and research. This paper presents an original study focusing on leveraging machine learning techniques to classify EMG datasets and efficiently control a robotic arm based on predicted gestures. Data acquisition involves strategically placing an EMG muscle sensor on the forearm to ensure precise measurement of signals associated with hand gestures and movements. Diverse classifiers including random forest, support vector machine (SVM), K-nearest neighbors (KNN), Gaussian naïve Bayes, gated recurrent unit (GRU), long short-term memory (LSTM), artificial neural network (ANN), recurrent neural network (RNN), convolutional neural network (CNN), and vision transformer (ViT) are employed. Performance results are meticulously analyzed and presented in tabular format, showcasing the ViT classifier as the most successful, achieving an impressive 97.7% accuracy in robotic arm control. Notably, ANN, RNN, and CNN also exhibit high accuracy exceeding 90%. Furthermore, this work is comprehensively compared with existing literature, laying the groundwork for future advancements in human-robot interaction and cutting-edge assistive technologies that markedly enhance the quality of life for individuals with motor impairments or disabilities. The findings carry significant implications for designing and implementing intuitive, responsive robotic systems based on EMG signals. [ABSTRACT FROM AUTHOR]

Landslides are considered one of the most frequent natural disasters that cause human loss and damage property, affecting the sustainability of communities worldwide. Mapping landslide susceptibility has gained a lot of interest from researchers. Using machine learning methods to yield landslide susceptibility maps (LSMs) has been extensively studied in the last decade. However, the problems of sampling non-landslides and weighting classes of conditioning factors are not thoroughly investigated in landslide susceptibility models. Moreover, the process of zoning LSMs for different susceptible areas is often overlooked. To address this gap, we present a study on sampling non-landslides and computing appropriate weights, which are used to train machine learning models to obtain accurate outputs. The outputs are clustered into different susceptible levels by K-means clustering method. Our study was conducted in Nam Pam area, Vietnam. A landslide inventory of 71 landslide points and 44 delineated landslide polygons, and 13 conditioning factors were selected in this study area. Furthermore, three regression methods, i.e., Bayesian, K-Nearest Neighbors, and Support vector machine (SVM), were taken to generate LSMs. We assessed three models based on various metrics, including 5 statistical metrics and AUC. The reliability of LSMs was evaluated by MFR value. Empirical results have shown that SVM method and the 2:1 ratio of non-landslides to landslides are recommended to build landslide susceptibility models. [ABSTRACT FROM AUTHOR]

Escalation in flash floods and the enhanced devastations, especially in the arid and semiarid regions of the world has required precise mapping of the flash flood susceptible zones. In this study, we applied six novel credal decision tree (CDT)-based ensemble models—1. CDT, 2. CDT Alternative Decision Tree (ADTree), 3. CDT- Reduced Error Pruning Tree (REPT), 4. CDT- Rotational Forest (RF), 5. CDT-FT, 6. CDT- Naïve Bias Tree (NBTree). For preparing the flash flood susceptibility maps (FFSM), 206 flood locations were selected in the Neka-roud watershed of Iran with 70% as training data and 30% as testing data. Moreover, 18 flood conditing factors were considered for FFSM and a multi-colinearity test was performed for determining the role of the factors. Our results show that the distance from the stream plays a vital role in flash floods. The CDT-FT is the best-fit model out of the six novel algorithms employed in this study as demonstrated by the highest values of the area under the curve (AUC) of the receiver operating curve (ROC) (AUROC 0.986 for training data and 0.981 for testing data). Our study provides a novel approach and useful tool for flood management. [ABSTRACT FROM AUTHOR]

Mangrove forests, mostly found in the intertidal zone, are among the highest-productivity ecosystems and have great ecological and economic value. The accurate mapping of mangrove forests is essential for the scientific management and restoration of mangrove ecosystems. However, it is still challenging to perform the rapid and accurate information mapping of mangrove forests due to the complexity of mangrove forests themselves and their environments. Utilizing multi-source remote sensing data is an effective approach to address this challenge. Feature extraction and selection, as well as the selection of classification models, are crucial for accurate mangrove mapping using multi-source remote sensing data. This study constructs multi-source feature sets based on optical (Sentinel-2) and SAR (synthetic aperture radar) (C-band: Sentinel-1; L-band: ALOS-2) remote sensing data, aiming to compare the impact of three feature selection methods (RFS, random forest; ERT, extremely randomized tree; MIC, maximal information coefficient) and four machine learning algorithms (DT, decision tree; RF, random forest; XGBoost, extreme gradient boosting; LightGBM, light gradient-boosting machine) on classification accuracy, identify sensitive feature variables that contribute to mangrove mapping, and formulate a classification framework for accurately recognizing mangrove forests. The experimental results demonstrated that using the feature combination selected via the ERT method could obtain higher accuracy with fewer features compared to other methods. Among the feature combinations, the visible bands, shortwave infrared bands, and the vegetation indices constructed from these bands contributed the greatest to the classification accuracy. The classification performance of optical data was significantly better than SAR data in terms of data sources. The combination of optical and SAR data could improve the accuracy of mangrove mapping to a certain extent (0.33% to 4.67%), which is essential for the research of mangrove mapping in a larger area. The XGBoost classification model performed optimally in mangrove mapping, with the highest overall accuracy of 95.00% among all the classification models. The results of the study show that combining optical and SAR remote sensing data with the ERT feature selection method and XGBoost classification model has great potential for accurate mangrove mapping at a regional scale, which is important for mangrove restoration and protection and provides a reliable database for mangrove scientific management. [ABSTRACT FROM AUTHOR]

Remote sensing has emerged as a promising tool for monitoring water quality (WQ) in aquatic ecosystems. This study evaluates the effectiveness of remote sensing in assessing WQ parameters in Cajititlán and Zapotlán lakes in the state of Jalisco, Mexico. Over time, these lakes have witnessed a significant decline in WQ, necessitating the adoption of advanced monitoring techniques. In this research, satellite-based remote sensing data were combined with ground-based measurements from the National Water Quality Monitoring Network of Mexico (RNMCA). These data sources were harnessed to train and evaluate the performance of six distinct categories of machine learning (ML) algorithms aimed at estimating WQ parameters with active spectral signals, including chlorophyll-a (Chl-a), turbidity, and total suspended solids (TSS). Various limitations were encountered during the study, primarily due to atmospheric conditions and cloud cover. These challenges affected both the quality and quantity of the data. However, these limitations were overcome through rigorous data preprocessing, the application of ML techniques designed for data-scarce scenarios, and extensive hyperparameter tuning. The superlearner algorithm (SLA), which leverages a combination of individual algorithms, and the multilayer perceptron (MLP), capable of handling complex and non-linear problems, outperformed others in terms of predictive accuracy. Notably, in Lake Cajititlán, these models provided the most accurate predictions for turbidity (r2 = 0.82, RMSE = 9.93 NTU, MAE = 7.69 NTU), Chl-a (r2 = 0.60, RMSE = 48.06 mg/m3, MAE = 37.98 mg/m3), and TSS (r2 = 0.68, RMSE = 13.42 mg/L, MAE = 10.36 mg/L) when using radiometric data from Landsat-8. In Lake Zapotlán, better predictive performance was observed for turbidity (r2 = 0.75, RMSE = 2.05 NTU, MAE = 1.10 NTU) and Chl-a (r2 = 0.71, RMSE = 6.16 mg/m3, MAE = 4.97 mg/m3) with Landsat-8 radiometric data, while TSS (r2 = 0.72, RMSE = 2.71 mg/L, MAE = 2.12 mg/L) improved when Sentinel-2 data were employed. While r2 values indicate that the models do not exhibit a perfect fit, those approaching unity suggest that the predictor variables offer valuable insights into the corresponding responses. Moreover, the model's robustness could be enhanced by increasing the quantity and quality of input variables. Consequently, remote sensing emerges as a valuable tool to support the objectives of WQ monitoring systems. [ABSTRACT FROM AUTHOR]

Bending is one of the widely used forming processes for sheet metals. However, due to the metal elasticity, the springback characteristic is unavoidable, leading to deviations from the desired final shapes and causing cumulative fitting problems in the assembly stages. Thus, precise predictions of the springback responses will enhance the sheet metal forming and the overall manufacturing processes. This is achieved by employing tree-based machine learning algorithms. These algorithms are used for their simplicity, preciseness, and consistency. Based on the tree-based algorithms, many prediction models are constructed and evaluated. First, experimental setup is established to measure the springback angles for different manufacturing conditions such as: the bending angle, the sheet metal's width and thickness, the machine settings, etc. Then, these data sets are divided into training and testing groups for the prediction models. This division is carried randomly, where 90 % of the data sets are used for training, and 10 % are left for testing the models' accuracy. The models are evaluated by comparing their predicted springback angles with the experimental values. The deviation errors are measured using the Mean Square Error (MSE), the Mean Absolute Error (MAE), and the Root Mean Square Error (RMSE). It isrevealed that the LightGBM prediction model is the most accurate model with 0.42 deg., 0.26 deg., and 0.52 deg. for MAE, MSE, and RMSE, respectively. The Gradient boosting comes in the second place with 0.66 deg., 0.760 deg., and 0.80 deg. for MAE, MSE, and RMSE, respectively. [ABSTRACT FROM AUTHOR]

The objective of this study was to distinguish leek seeds belonging to the Starozagorski kamush variety and two breeding lines based on the selected fluorescence spectroscopic data. The classification models were developed for three classes of Starozagorski kamush vs. breeding line 4 vs. breeding line 39 and pairs of classes of Starozagorski kamush vs. breeding line 4, Starozagorski kamush vs. breeding line 39, and breeding line 4 vs. breeding line 39. The traditional machine learning algorithms, such as PART, Logistic, Naive Bayes, Random Forest, IBk, and Filtered Classifier were applied. All three classes were distinguished with an average accuracy of up to 93.33% for models built using IBk and Filtered Classifier. In the case of each model, Starozagorski kamush variety was completely different (accuracy of 100%, precision, and F-measure, MCC (Matthews correlation coefficient), and ROC (receiver operating characteristic) area of 1.000) from breeding lines, and the mixing of cases was observed between breeding line 4 and breeding line 39. The models built for pairs of leek seed classes distinguished Starozagorski kamush and breeding line 4 with an average accuracy reaching 100% (Logistic, Naive Bayes, Random Forest, IBk). The classification accuracy of Starozagorski kamush and breeding line 39 also reached 100% (Logistic, Naive Bayes, Random Forest, IBk), whereas breeding line 4 and breeding line 39 were classified with an average accuracy of up to 80% (Logistic, Naive Bayes, Random Forest, Filtered Classifier). The proposed approach combining fluorescence spectroscopy and machine learning may be used in practice to distinguish leek seed varieties and breeding lines. [ABSTRACT FROM AUTHOR]

The application of interdisciplinary non-invasive diagnostic methods combining fluorescence spectroscopy with multiple machine learning algorithms as tools for rapid application in tomato breeding programs is essential when crossing specific genotypes or parental samples to obtain representatives with better performance. Non-destructive distinguishing tomato species is of great importance for the preservation of product quality. This study aimed at combining fluorescence spectroscopic data and machine learning algorithms for distinguishing greenhouse tomatoes. The models for the discrimination of greenhouse tomato samples were built based on selected spectroscopic data using different machine learning algorithms from the groups of Meta, Functions, Bayes, Trees, Rules, and Lazy. The confusion matrices with accuracy for each sample, average accuracy, time taken to build the model, Kappa statistic, mean absolute error, root mean squared error and relative absolute error were determined. The greenhouse tomato samples were discriminated with an accuracy reaching 100% for the models built using Multi-Class Classifier (Meta), Logistic (Function), Bayes Net (Bayes), PART (Rules), and J48 (Trees). In the case of these algorithms, Kappa statistic was 1.0 and mean absolute error, root mean squared error and relative absolute error were equal to 0. [ABSTRACT FROM AUTHOR]

This study presents a new model to predict the static formation temperature in multiple geothermal fields using multiple machine learning algorithms. Both artificial intelligence and non-artificial intelligent algorithms were used for this prediction. The model developed in this study predicts static formation temperature using several machine learning algorithms, including artificial neural networks, fuzzy logic, k-nearest neighbors, and random forest algorithms. Results are compared with the real temperatures obtained from two geothermal wells. The random forest, fuzzy logic, and k-nearest neighbors algorithms outperformed the artificial neural network, with the random forest algorithm achieving higher accuracy. The MAE of the random forest algorithm was 0.7% and the RMSE was 0.9%. The MAE values for the other machine learning algorithms ranging from 1.5 to 8.4%, and the RMSE values ranged from 2 to 20.8%. Artificial intelligence methods were found to be more accurate than non-artificial intelligence (mathematical) methods, with varying percentages. The results generated by the unique new model computation and the measured test data are substantially matched when compared to computed data and observed temperature data. The novelty of this newly developed artificial intelligence model is that it serves as a practical and inexpensive tool for static formation temperature determination in geothermal and petroleum wells. [ABSTRACT FROM AUTHOR]

In today's world, Internet of Things (IoT) technology has revolutionized various fields - including agriculture - by offering smart solutions that enhance crop yield and quality. One crucial aspect of smart farming is the application of IoT for disease detection and prevention. Crop diseases caused by bacteria and viruses can have devastating effects, leading to significant financial losses for farmers. Early detection plays a crucial role in managing these diseases, and IoT technology provides reliable and efficient methods to achieve this goal. To aid in the research on disease recognition in corn or maize plants, a large-scale dataset comprising 4188 images across four disease categories - namely, healthy, common rust, gray-leaf spot, and blight - is utilized. This dataset is used to train various machine learning algorithms such as K-nearest neighbor (KNN), support vector machine (SVM), random forest (RF), decision tree (DT), convolutional neural network (CNN), naïve Bayes (NB), gradient boosting trees (GBT), long short-term memory (LSTM), and the algorithms from recent literature such as genetic algorithm-based ensemble classifier, XGBoost, AdaBoost and XGBoost + KNN to accurately identify disease patterns in plants and is loaded into the Raspberry Pi. By interfacing a camera with a Raspberry Pi, leaf diseases can be detected, and the farm's status can be sent to the farmer's webpage using a Wi-Fi server. This information empowers farmers to take immediate action to control the disease such as activating sprinklers or applying pesticides. Through manually controllable on/off mechanisms, farmers can remotely manage these actions, ensuring the health and disease-free state of their crops. Among the selected algorithms, the XGBoost + KNN algorithm demonstrates the highest accuracy, reaching an impressive 98.77%. [ABSTRACT FROM AUTHOR]

The study's findings showed that link prediction utilizing the similarity learning model in dynamic networks (LSDN) performed better than other learning techniques including neural network learning and decision tree learning in terms of the three criteria of accuracy, coverage, and efficiency., Compared to the random forest approach, the LSDN learning algorithm's link prediction accuracy increased from 97% to 99%. The proposed method's use of oversampling, which improved link prediction accuracy, was the cause of the improvement in area under the curve (AUC). To bring the ratio of the classes closer together, the suggested strategy attempted to produce more samples from the minority class. In addition, similarity criteria were chosen utilizing feature selection techniques based on correlation that had a strong link with classes. This technique decreased over-fitting and improved the suggested method's test data generalizability. Based on the three criteria (accuracy, coverage, and efficiency), the research's findings demonstrated that link prediction utilizing the similarity LSDN outperformed other learning techniques including neural network learning and decision tree learning. Compared to the random forest algorithm, the LSDN algorithm's link prediction accuracy increased from 97% to 99%. The oversampling in the suggested strategy, which increased link prediction accuracy, is what caused the increase in AUC. To bring the ratio of the classes closer together, the suggested strategy attempted to produce more samples from the minority class. In addition, similarity criteria were chosen utilizing feature selection techniques based on correlation that had a strong link with classes. This technique decreased over-fitting and improved the suggested method's test data generalizability. [ABSTRACT FROM AUTHOR]

Multiple studies have investigated bibliometric features and uncategorized scholarly documents for the influential scholarly document prediction task. In this paper, we describe our work that attempts to go beyond bibliometric metadata to predict influential scholarly documents. Furthermore, this work also examines the influential scholarly document prediction task over categorized scholarly documents. We also introduce a new approach to enhance the document representation method with a domain-independent knowledge graph to find the influential scholarly document using categorized scholarly content. As the input collection, we use the WHO corpus with scholarly documents on the theme of COVID-19. This study examines different document representation methods for machine learning, including TF-IDF, BOW, and embedding-based language models (BERT). The TF-IDF document representation method works better than others. From various machine learning methods tested, logistic regression outperformed the other for scholarly document category classification, and the random forest algorithm obtained the best results for influential scholarly document prediction, with the help of a domain-independent knowledge graph, specifically DBpedia, to enhance the document representation method for predicting influential scholarly documents with categorical scholarly content. In this case, our study combines state-of-the-art machine learning methods with the BOW document representation method. We also enhance the BOW document representation with the direct type (RDF type) and unqualified relation from DBpedia. From this experiment, we did not find any impact of the enhanced document representation for the scholarly document category classification. We found an effect in the influential scholarly document prediction with categorical data. [ABSTRACT FROM AUTHOR]

Sex estimation from skeletal remains is one of the crucial issues in forensic anthropology. Long bones can be a valid alternative to skeletal remains for sex estimation when more dimorphic bones are absent or degraded, preventing any estimation from the first intention methods. The purpose of this study was to generate and compare classification models for sex estimation based on combined measurement of long bones using machine learning classifiers. Eighteen measurements from four long bones (radius, humerus, femur, and tibia) were taken from a total of 2141 individuals. Five machine learning methods were employed to predict the sex: a linear discriminant analysis (LDA), penalized logistic regression (PLR), random forest (RF), support vector machine (SVM), and artificial neural network (ANN). The different classification algorithms using all bones generated highly accuracy models with cross-validation, ranging from 90 to 92% on the validation sample. The classification with isolated bones ranked between 83.3 and 90.3% on the validation sample. In both cases, random forest stands out with the highest accuracy and seems to be the best model for our investigation. This study upholds the value of combined long bones for sex estimation and provides models that can be applied with high accuracy to different populations. [ABSTRACT FROM AUTHOR]

Simple Summary: Intrauterine growth restriction (IUGR) is a disruption in the development of animal embryos or fetal organs in the maternal uterus and is highly regarded because of its serious detrimental effects on animal husbandry. However, there are few diagnostic methods and treatment options for IUGR, and its molecular mechanisms are not fully understood. In this study, a bioinformatics approach was applied to identify four IUGR-related diagnostic genes (IUGR-DGs) in sheep, construct a gene scoring system based on the IUGR-DGs, and evaluate the relationship between the IUGR score and disease risk. A new artificial neural network model was constructed to better diagnose the occurrence of IUGR in sheep based on the four IUGR-DGs. Although future studies will be necessary to elucidate the entire molecular mechanisms involved, we believe that the findings of this paper will facilitate the diagnosis and treatment of IUGR in sheep and improve livestock production levels. Intrauterine growth restriction (IUGR) is a common perinatal complication in animal reproduction, with long-lasting negative effects on neonates and postnatal animals, which seriously negatively affects livestock production. In this study, we aimed to identify potential genes associated with the diagnosis of IUGR through bioinformatics analysis. Based on the 73 differentially expressed related genes obtained by differential analysis and weighted gene co-expression network analysis, we used three machine learning algorithms to identify 4 IUGR-related hub genes (IUGR-HGs), namely, ADAM9, CRYL1, NDP52, and SERPINA7, whose ROC curves showed that they are a good diagnostic target for IUGR. Next, we identified two molecular subtypes of IUGR through consensus clustering analysis and constructed a gene scoring system based on the IUGR-HGs. The results showed that the IUGR score was positively correlated with the risk of IUGR. The AUC value of IUGR scoring accuracy was 0.970. Finally, we constructed a new artificial neural network model based on the four IUGR-HGs to diagnose sheep IUGR, and its accuracy reached 0.956. In conclusion, the IUGR-HGs we identified provide new potential molecular markers and models for the diagnosis of IUGR in sheep; they can better diagnose whether sheep have IUGR. The present findings provide new perspectives on the diagnosis of IUGR. [ABSTRACT FROM AUTHOR]

Tunisia needs judicious water allocation to mitigate drought. Remote sensing tools, such as Sentinel-1 and Sentinel-2, can be used to estimate soil water status and monitor changes in soil moisture and vegetation cover. The study area covers the Kairouan governorate in the center of Tunisia, (35°40′33.29″ N, 10°5′30.26″ E), which is characterized by a flat relief (plain) covering an area of 6800 Km2 and belonging to the 'upper arid bioclimatic stage'. The study proposes a formula called "ER" to estimate soil water status from Sentinel-1 data, two color composition images to control changes in soil moisture and vegetation cover, and unsupervised ISODATA and k-means classifications to monitor the impact of climate change and land use. The data used are nine Sentinel-1 images and twelve Sentinel-2 images downloaded from the Copernicus platform at the dates given. The VV and VH Sentinel-1 GRD Level1 products were selected at different dates based on the daily precipitation amount (PA) of the studied region: PA > 55 mm,18.5 mm < PA < 33.5 mm, PA < 10 mm and PA = 0 mm for Sentinel-2, with results collected on 29/01, 23/2, 25/03, 24/04, 16/05, 11/05, 05/06, 13/06, 23/07, 24/08, 18/09 and 11/10 in 2019. For Sentinel-1, the dates of acquisition of images were 24/01, 23/02, 25/03, 12/04, 24/05, 12/06, 27/07, 15/09 and 09/10 in 2019. We chose cloudless images and we chose close dates for the two sentinels, which correspond to the dates of our field visit carried out in June and October 2019. Validation was carried out using two main criteria: (i) the measured mean precipitation deviation over successive months (EP) and (ii) the three reference land cover types (LC): cereals (LC1), fallow land (LC2) and bare soil (LC3). For this case study, three cases of EP were considered: (1) no precipitation (EP ≤ 0), (2) low precipitation (0 < EP ≤ 20 mm), and (3) high precipitation (EP > 20 mm). The results showed that, considering the VH polarization, we obtain ER < 0 for LC3 and ER ≈ 0 for the LC1 and LC2 terrestrial cultures when EP ≤ 0; ER > 0 for LC3 and ER ≈ 0 for the LC1 and LC2 terrestrial cultures when (0 < EP ≤ 20 mm); and ER > 0 for all LCs and the value increases with high rainfall. We validated these ER results using image composition and classified images. [ABSTRACT FROM AUTHOR]

Aim: Method: This research presents a model combining machine learning (ML) techniques and eXplainable artificial intelligence (XAI) to predict breast cancer (BC) metastasis and reveal important genomic biomarkers in metastasis patients. Method: A total of 98 primary BC samples was analyzed, comprising 34 samples from patients who developed distant metastases within a 5-year follow-up period and 44 samples from patients who remained disease-free for at least 5 years after diagnosis. Genomic data were then subjected to biostatistical analysis, followed by the application of the elastic net feature selection method. This technique identified a restricted number of genomic biomarkers associated with BC metastasis. A light gradient boosting machine (LightGBM), categorical boosting (CatBoost), Extreme Gradient Boosting (XGBoost), Gradient Boosting Trees (GBT), and Ada boosting (AdaBoost) algorithms were utilized for prediction. To assess the models' predictive abilities, the accuracy, F1 score, precision, recall, area under the ROC curve (AUC), and Brier score were calculated as performance evaluation metrics. To promote interpretability and overcome the "black box" problem of ML models, a SHapley Additive exPlanations (SHAP) method was employed. Results: The LightGBM model outperformed other models, yielding remarkable accuracy of 96% and an AUC of 99.3%. In addition to biostatistical evaluation, in XAI-based SHAP results, increased expression levels of TSPYL5, ATP5E, CA9, NUP210, SLC37A1, ARIH1, PSMD7, UBQLN1, PRAME, and UBE2T (p ≤ 0.05) were found to be associated with an increased incidence of BC metastasis. Finally, decreased levels of expression of CACTIN, TGFB3, SCUBE2, ARL4D, OR1F1, ALDH4A1, PHF1, and CROCC (p ≤ 0.05) genes were also determined to increase the risk of metastasis in BC. Conclusion: The findings of this study may prevent disease progression and metastases and potentially improve clinical outcomes by recommending customized treatment approaches for BC patients. [ABSTRACT FROM AUTHOR]

The yield of energy crops has been widely questioned by the public, but few researchers have analyzed the yield prediction of these crops, which has greatly limited their distribution and use. Based on this, in this study, a machine learning algorithm was used to design an energy crop yield simulation and prediction system, and this system was used to analyze the yields of four common energy crops. First the factors that affect the yield of energy crops are discussed, and then, the analysis of the machine learning algorithm and its application in the yield prediction of energy crops is presented, followed by an introduction to the framework of the energy crop yield simulation and prediction system. At the end of this paper, the effect of the energy crop yield simulation and prediction system was analyzed, and the feasibility conclusion was finally reached. The energy crop yield simulation and prediction system designed in this paper can greatly improve the accuracy of yield prediction when forecasting and analyzing energy crop yields. The sugarcane yield measured by the back propagation (BP) neural network model was 8694 kg/hm2, with a relative deviation of 0.86% from the actual. The BP neural network algorithm is widely used in energy crop yield prediction, and can greatly improve the accuracy. In the future, with the maturity and development of a BP neural network algorithm, it would promote the development of crop yield prediction. [ABSTRACT FROM AUTHOR]