Search

In recent years, machine learning (ML) has become increasingly popular in various fields of activity. Cloud platforms have also grown in popularity, as they offer services that are more secure and accessible worldwide. In this context, cloud-based technologies emerged to support ML, giving rise to the machine learning as a service (MLaaS) concept. However, the clients accessing ML services in order to obtain classification results on private data may be reluctant to upload sensitive information to cloud. The model owners may also prefer not to outsource their models in order to prevent model inversion attacks and to protect intellectual property. The privacy-preserving evaluation of ML models is possible through multi-key homomorphic encryption (MKHE), that allows both the client data and the model to be encrypted under different keys. In this paper, we propose an MKHE evaluation method for decision trees and we extend the proposed method for random forests. Each decision tree is evaluated as a single lookup table, and voting is performed at the level of groups of decision trees in the random forest. We provide both theoretical and experimental evaluations for the proposed method. The aim is to minimize the performance degradation introduced by the encrypted model compared to a plaintext model while also obtaining practical classification times. In our experiments with the proposed MKHE random forest evaluation method, we obtained minimal (less than 0.6%) impact on the main ML performance metrics considered for each scenario, while also achieving reasonable classification times (of the order of seconds). [ABSTRACT FROM AUTHOR]

Background: Despite the clear clinical diagnostic criteria for necrozoospermia in andrology, the fundamental mechanisms underlying it remain elusive. This study aims to profile the lipid composition in seminal plasma systematically and to ascertain the potential of lipid biomarkers in the accurate diagnosis of necrozoospermia. It also evaluates the efficacy of a lipidomics-based random forest algorithm model in identifying necrozoospermia. Methods: Seminal plasma samples were collected from patients diagnosed with necrozoospermia (n = 28) and normozoospermia (n = 28). Liquid chromatography–mass spectrometry (LC–MS) was used to perform lipidomic analysis and identify the underlying biomarkers. A lipid functional enrichment analysis was conducted using the LION lipid ontology database. The top 100 differentially significant lipids were subjected to lipid biomarker examination through random forest machine learning model. Results: Lipidomic analysis identified 46 lipid classes comprising 1267 lipid metabolites in seminal plasma. The top five enriched lipid functions as follows: fatty acid (FA) with ≤ 18 carbons, FA with 16–18 carbons, monounsaturated FA, FA with 18 carbons, and FA with 16 carbons. The top 100 differentially significant lipids were subjected to machine learning analysis and identified 20 feature lipids. The random forest model identified lipids with an area under the curve > 0.8, including LPE(20:4) and TG(4:0_14:1_16:0). Conclusions: LPE(20:4) and TG(4:0_14:1_16:0), were identified as differential lipids for necrozoospermia. Seminal plasma lipidomic analysis could provide valuable biochemical information for the diagnosis of necrozoospermia, and its combination with conventional sperm analysis may improve the accuracy and reliability of the diagnosis. [ABSTRACT FROM AUTHOR]

We propose a random forest based estimation procedure for Quantile-Oriented Sensitivity Analysis—QOSA. In order to be efficient, a cross-validation step on the leaf size of trees is required. Our full estimation procedure is tested on both simulated data and a real dataset. Our estimators use either the bootstrap samples or the original sample in the estimation. Also, they are either based on a quantile plug-in procedure (the R-estimators) or on a direct minimization (the Q-estimators). This leads to 8 different estimators which are compared on simulations. From these simulations, it seems that the estimation method based on a direct minimization is better than the one plugging the quantile. This is a significant result because the method with direct minimization requires only one sample and could therefore be preferred. [ABSTRACT FROM AUTHOR]

Large-scale digital soil maps are essential for rational and sustainable land management as well as accurate fertilizer application. This study focuses on digital mapping of soil properties, namely soil organic carbon (SOC), pH, nitrogen (N), phosphorus (P), and potassium (K) in Chernozem topsoil and subsoil. The study was conducted on two arable fields in the Cis-Ural forest-steppe zone of the Republic of Bashkortostan (Russia). The random forest algorithm in combination with terrain attributes and Sentinel-2A satellite data was applied for spatial prediction of soil properties. The root-mean-square error (RMSE) and coefficient of determination (R2) were used to determine the model performance. According to the Pearson correlation, a significant positive relationship between SOC and N content was found at all sites and depths (R = 0.76–0.92). A cross-validation revealed that SOC (R2 = 0.22–0.62, RMSE = 0.35–0.89%) and N (R2 = 0.16–0.60, RMSE = 21.11–36.6 mg kg−1) were best predicted among other properties at all depths using remote sensing data, whereas the performance of predictive models decreased with depth. However, a relationship between the content of some soil properties and their spatial distribution at study depths was observed, which can be used as an additional explanatory variable. We suppose that digital mapping of soil properties at the arable field scale should not be limited to topographic and remote sensing variables. Based on this information, the use of auxiliary variables, such as collocated soil information in combination with relief and remote sensing data can be effective in more accurately estimating the spatial distribution of properties across arable fields at different depths. Overall, this study provides valuable insights into spatial modelling of the vertical distribution of soil properties, highlighting the significance of remote sensing data at the arable field scale. The findings can be valuable for land managers, agronomists, and policymakers seeking sustainable land management practices and efficient fertilizer application, as well as for developing further mapping procedures for arable fields. [ABSTRACT FROM AUTHOR]

Early monitoring of within-field yield variability and forecasting yield potential is critical for farmers and other key stakeholders such as policymakers. Remote sensing techniques are progressively being used in yield prediction studies due to easy access and affordability. Despite the increasing use of remote sensing techniques for yield prediction in agriculture, there is still a need for medium-resolution satellite imagery when predicting canola yield using a combination of crop and soil information. In this study, we investigated the utility of remotely sensed flowering information from PlanetScope (at 4 m) satellite imagery combined with derived soil and topography parameters to predict canola yield. Our yield prediction model was trained and validated using data from 21 fields managed under variable rate seed and fertilizer application, including cleaned harvester yield maps, soil, and topography maps. To quantify the flowering intensity of canola, 9 vegetation indices (VIs) were calculated using spectral bands from PlanetScope imagery acquired for the reproductive stages of canola. We created five random forest regression models using different subsets of covariates, including VIs, soil, and topography features, to predict canola yield within the season. Using a random forest regression algorithm, we recorded accuracies ranging from poor to best performing using coefficient of determination and root mean squared error (R2: 0.47 to 0.66, RMSE: 325 to 399 kg ha−1). The optimal subset of covariates identified electrical conductivity (EC), Normalized Difference Yellowness Index, and Canola Index as the key variables explaining within-spatial variability in canola yield. Our final model exhibited a validation R2 of 0.46 (RMSE = 730 kg ha−1), demonstrating the potential of medium-resolution satellite imagery during the flowering stage to detect and quantify sub-field spatial and temporal floral phenology changes when predicting canola yield. [ABSTRACT FROM AUTHOR]

Background: Parkinson's disease (PD) ranks as the second most prevalent neurodegenerative disorder globally, and its incidence is rapidly rising. The diagnosis of PD relies on clinical characteristics. Although current treatments aim to alleviate symptoms, they do not effectively halt the disease's progression. Early detection and intervention hold immense importance. This study aimed to establish a new PD diagnostic model. Methods: Data from a public database were adopted for the construction and validation of a PD diagnostic model with random forest and artificial neural network models. The CIBERSORT platform was applied for the evaluation of immune cell infiltration in PD. Quantitative real-time PCR was performed to verify the accuracy and reliability of the bioinformatics analysis results. Results: Leveraging existing gene expression data from the Gene Expression Omnibus (GEO) database, we sifted through differentially expressed genes (DEGs) in PD and identified 30 crucial genes through a random forest classifier. Furthermore, we successfully designed a novel PD diagnostic model using an artificial neural network and verified its diagnostic efficacy using publicly available datasets. Our research also suggests that mast cells may play a significant role in the onset and progression of PD. Conclusion: This work developed a new PD diagnostic model with machine learning techniques and suggested the immune cells as a potential target for PD therapy. [ABSTRACT FROM AUTHOR]

Classification methods with Machine Learning have been used in various fields, including volcanology. This method makes it possible to automatically perform data processing and classification on large scale data in a short time. Seismic time series data from volcanic earthquakes of Mt. Merapi are classified into five types of earthquakes, i.e.: Volcanic Type A (VTA), Volcanic Type B (VTB), Multiphase (MP), Low-frequency (LF) and Rockfall (RF), with a total sample data of 266 earthquakes, could be classified automatically using machine learning. The features of the signal are taken from the dominant frequency value, the spectral pattern that is formed, and the amplitude value to differentiate the earthquake dataset into each class. Classification is done using the XGBoost algorithm. Tests were carried out using various data test–train percentage to get the best result. Based on the XGBoost function test, which the best value obtained with an accuracy of testing the data is 76.67% using the 70%:30% train–test scenario. The results of this accuracy value are greater when compared to the accuracy value of previous studies with the SVM method which is 74.4% accuracy. This research also has better results in spectral analysis with the results of spectral comparison plots that appear to show more significant differences. [ABSTRACT FROM AUTHOR]

Electronic waste (e-waste) is considered a major issue that our world is tackling nowadays. This electronic waste causes various health issues to animals as well as human beings which further results in environmental pollution in developing countries like India. To overcome these issues, proper e-waste collection is proposed by using the dynamic sine cosine-based neural network optimization (DSCNN) approach. The major objective of this approach involves collecting waste from the individual, hence handling the widespread adoption and use of smartphones. To enhance waste planning collection, residents upload a photograph of their waste to the waste collection company's server, which mechanically recognizes and categorizes the image. A new classification and detection scheme using the DSCNN approach is proposed for efficient e-waste collection planning and correctly detects the type and quantity of waste components in images. The identification and classification accuracy of the uploaded images is very accurate; this method describes the e-waste collection process in various streets and buildings in Maharashtra, India. Experimental results describe that the proposed approach readily achieves the proper allocation of vehicle collection, vehicle routing plan, and household e-waste collection, resulting in reduced collection costs. Moreover, the proposed DSCNN method is compared to various other methods like random forest algorithm (RFA), fractional henry gas optimization (FHGO), behavior-based swarm model by the fuzzy controller (BSFC), and deep learning convolutional neural network (DL-CNN). The DSCNN approach yielded an e-waste collection detection accuracy of 97%. The accuracy rates of 94%, 95%, 93%, and 92.15% are obtained from the DL-CNN, FHGO, BSFC, and RFA. [ABSTRACT FROM AUTHOR]

Luster is one of the vital indexes in pearl grading. To find a fast, nondestructive, and low-cost grading method, optical coherence tomography (OCT) is introduced to predict the luster grade through the texture features. After background removal, flattening, and segmentation, the speckle pattern of the region of interest is described by seven kinds of feature textures, including center-symmetric auto-correlation (CSAC), fractal dimension (FD), Gabor, gray level co-occurrence matrix (GLCM), histogram of oriented gradients (HOG), laws texture energy (LAWS), and local binary patterns (LBP). To find the relations between speckle-derived texture features and luster grades, four Four groups of pearl samples were used in the experiment to detect texture differences based on support vector machines (SVMs) and random forest classifier (RFC)) for investigating the relations between speckle-derived texture features and luster grades. The precision, recall, F1-score, and accuracy are more significant than 0.9 in several simulations, even after dimension reduction. This demonstrates that the texture feature from OCT images can be applied to class the pearl luster based on speckle changes. [ABSTRACT FROM AUTHOR]

This study investigates the application of cavitation in non-invasive abdominal fat reduction and body contouring, a topic of considerable interest in the medical and aesthetic fields. We explore the potential of cavitation to alter abdominal fat composition and delve into the optimization of fat prediction models using advanced hyperparameter optimization techniques, Hyperopt and Optuna. Our objective is to enhance the predictive accuracy of abdominal fat dynamics post-cavitation treatment. Employing a robust dataset with abdominal fat measurements and cavitation treatment parameters, we evaluate the efficacy of our approach through regression analysis. The performance of Hyperopt and Optuna regression models is assessed using metrics such as mean squared error, mean absolute error, and R-squared score. Our results reveal that both models exhibit strong predictive capabilities, with R-squared scores reaching 94.12% and 94.11% for post-treatment visceral fat, and 71.15% and 70.48% for post-treatment subcutaneous fat predictions, respectively. Additionally, we investigate feature selection techniques to pinpoint critical predictors within the fat prediction models. Techniques including F-value selection, mutual information, recursive feature elimination with logistic regression and random forests, variance thresholding, and feature importance evaluation are utilized. The analysis identifies key features such as BMI, waist circumference, and pretreatment fat levels as significant predictors of post-treatment fat outcomes. Our findings underscore the effectiveness of hyperparameter optimization in refining fat prediction models and offer valuable insights for the advancement of non-invasive fat reduction methods. This research holds important implications for both the scientific community and clinical practitioners, paving the way for improved treatment strategies in the realm of body contouring. [ABSTRACT FROM AUTHOR]

The creation of protected areas (PAs) is not always based on science; consequently, some aquatic species may not receive the same level of protection as terrestrial ones. The objective of this study was to identify priority areas for the conservation of chelonians in the Brazilian Amazon basin and assess the contribution of PAs, distinguishing between Full Protection Areas, Sustainable Use Areas, and Indigenous Lands for group protection. The entire species modeling procedure was carried out using Species Distribution Models. Location records were obtained from platforms such as SpeciesLink, GBIF, the Hydroatlas database, and WorldClim for bioclimatic variables adjusted with algorithms like Maximum Entropy, Random Forest, Support Vector Machine, and Gaussian-Bayesian. Indigenous lands cover more than 50% of the distribution areas of chelonian species in the Brazilian Amazon. Protected areas with higher conservation importance (Full Protection Areas and Sustainable Use Areas) hold less than 15% of the combined species distribution. Researchers face significant challenges when making decisions with models, especially in conservation efforts involving diverse taxa that differ significantly from one another within a group of individuals. [ABSTRACT FROM AUTHOR]

This study aims at utilizing machine learning (ML) in predicting the fire resistance and spalling degree of reinforced concrete (RC) columns with improved accuracy and reliability. A database with 119 test specimens was created for the development of ML-based regression models, and a database with 101 test specimens was created for the development of ML-based classification models. Six ML algorithms—support vector machine (SVM), random forest (RF), multilayer perceptron (MLP), extreme gradient boosting (XGBoost), adaptive boosting (AdaBoost), and light gradient boosting machine (LightGBM). The hyperparameters of the ML-based models were optimized through Bayes optimization search (BayesSearchCV) with ten-fold cross-validation. The results indicated that the AdaBoost not only accurately predicted the spalling degree of RC columns with an accuracy of 87%, but also performed best in predicting the fire resistance of RC columns with R2 = 0.96 and RMSE = 16.58. The AdaBoost model achieved high accuracy without significant bias, surpassing existing design equations. SHAP method was utilized to produce global explanations for the predictions. The results revealed that concrete compressive strength, loading ratio, slenderness ratio, and column width were the most critical features for spalling degree identification. Meanwhile, those were slenderness ratio, concrete cover, loading ratio, part of the fired column, and longitudinal reinforcement for fire resistance prediction. The parametric study demonstrated that the fire resistance of RC columns is positively affected by only concrete cover. [ABSTRACT FROM AUTHOR]

In this work, we used the convolutional neural network (CNN) method to invert sea surface height (SSH) from the Global Navigation Satellite System (GNSS) delayed Doppler map (DDM) data during 2009–2017 and compared the CNN inversion data with those obtained from traditional simple random forest (RF) method. SSH observations from the OSTM/Jason-2 satellite were used to judge the merits of the two methods. The results show that both methods yield good SSH inversion results, but when the training set is 9000, the root mean square errors of the SSH inversion results based on the CNN and the RF method are 16.78 and 15.96 respectively; as the training set increases above 9000, the accuracy of the CNN method is significantly better than that of the RF method. This suggests that SSH inversion based on the CNN method will become more advantageous as more data become available. [ABSTRACT FROM AUTHOR]

Ecological restoration of rare earth element (REE) mining areas has become a key component in the sustainable development of the ion-adsorption-type REE industry. Current studies on ecological restoration assessments are mainly based on a comparison of REE mining ranges conducted over two or more periods, therefore, the dynamic evolution of spatial patterns for REE mining and vegetation recovery remains to be elucidated. Rapid advances in remote sensing techniques, along with the cloud-based Google Earth Engine (GEE), can provide an effective and convenient observation strategy for monitoring the environment in mining areas. In this study, we propose a hybrid method consisting of a random forest (RF) classifier and Landsat-based detection of trends in disturbance and recovery (LandTrendr) to identify and monitor the disturbance of REE mining and vegetation recovery in REE mining areas in the southern Jiangxi Province of China from 1988 to 2021 based on the GEE platform. The results reveal that REE mining activities were widespread in the study area, and the spatial distribution of REE mining areas was highly dispersed. The total area of REE mining in the study region was 93.14 km2, and the greatest REE mining activity was observed in the year 2006. As of 2021, the vegetation coverage area in the REE mining zone reached 47.44 km2, with a recovery rate of 50.93%. Among the seven counties in the study area, Longnan county had the lowest level of vegetation recovery in REE mining areas. A total of 95% of the vegetation recovery events in REE mining areas lasted between 1 and 18 years. These observations suggest that LandTrendr efficiently captured REE mining-induced disturbances and vegetation recovery and offers important reference data for the formulation of mining area restoration strategies. The results can provide a referable basis for the ecological restoration of southern Jiangxi Province, China. [ABSTRACT FROM AUTHOR]

This paper proposes a synchrophasor measurement-assisted integrated scheme to enhance power grid stability via transient stability assessment and emergency control of power systems in real-time. The synchrophasor measurements are time-stamped network information available from Phasor Measurement Units (PMUs). The Transient Stability Assessment (TSA) is based on measured generator bus angles obtained directly by PMUs at the control center. These synchronized angle measurements are utilized to construct features, and a Random Forest classifier is implemented to infer the TSA in real-time. The TSA results are determined within the first three cycles following the fault clearance. For operating scenarios that are unstable, an effective emergency control scheme is developed to avoid system degradation. The control strategy utilizes wide-area measurements to formulate a proportional sharing principle-based methodology in real-time. The composite scheme estimates the location and magnitude of the emergency measures to enhance grid stability. The performance of the proposed composite scheme is tested on an IEEE 39-bus test system. The results highlight that the scheme is computationally efficient and robust to topological changes. [ABSTRACT FROM AUTHOR]

Cytochrome P450 (P450)-mediated bioactivation, which can lead to the hepatotoxicity through the formation of reactive metabolites (RMs), has been regarded as the major problem of drug failures. Herein, we purposed to establish machine learning models to predict the bioactivation of P450. On the basis of the literature-derived bioactivation dataset, models for Benzene ring, Nitrogen heterocycle and Sulfur heterocycle were developed with machine learning methods, i.e., Random Forest, Random Subspace, SVM and Naïve Bayes. The models were assessed by metrics like "Precision", "Recall", "F-Measure", "AUC" (Area Under the Curve), etc. Random Forest algorithms illustrated the best predictability, with nice AUC values of 0.949, 0.973 and 0.958 for the test sets of Benzene ring, Nitrogen heterocycle and Sulfur heterocycle models, respectively. 2D descriptors like topological indices, 2D autocorrelations and Burden eigenvalues, etc. contributed most to the models. Furthermore, the models were applied to predict the occurrence of bioactivation of an external verification set. Drugs like selpercatinib, glafenine, encorafenib, etc. were predicted to undergo bioactivation into toxic RMs. In vitro, IC50 shift experiment was performed to assess the potential of bioactivation to validate the prediction. Encorafenib and tirbanibulin were observed of bioactivation potential with shifts of 3–6 folds or so. Overall, this study provided a reliable and robust strategy to predict the P450-mediated bioactivation, which will be helpful to the assessment of adverse drug reactions (ADRs) in clinic and the design of new candidates with lower toxicities. [ABSTRACT FROM AUTHOR]

A brain tumor is one of the most lethal diseases that can affect human health and cause death. Invasive biopsy techniques are one of the most common methods of identifying brain tumor disease. As a result of this procedure, bleeding may occur during the procedure, which could harm some brain functions. Consequently, this invasive biopsy process may be extremely dangerous. To overcome such a dangerous process, medical imaging techniques, which can be used by experts in the field, can be used to conduct a thorough examination and obtain detailed information about the type and stage of the disease. Within the scope of the study, the dataset was examined, and this dataset consisted of brain images with tumors and brain images of normal patients. Numerous studies on medical images were conducted and obtained with high accuracy within the hybrid model algorithms. The dataset's images were enhanced using three distinct local binary patterns (LBP) algorithms in the developed model within the scope of the study: the LBP, step-LBP (nLBP), and angle-LBP (αLBP) algorithms. In the second stage, classification algorithms were used to evaluate the results from the LBP, nLBP and αLBP algorithms. Among the 11 classification algorithms used, four different classification algorithms were chosen as a consequence of the experimental process since they produced the best results. The classification algorithms with the best outcomes are random forest (RF), optimized forest (OF), rotation forest (RF), and instance-based learner (IBk) algorithms, respectively. With the developed model, an extremely high success rate of 99.12% was achieved within the IBk algorithm. Consequently, the clinical service can use the developed method to diagnose tumor-based medical images. [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]

Mass-spectrometry-based non-targeted analysis (NTA), in which mass spectrometric signals are assigned chemical identities based on a systematic collation of evidence, is a growing area of interest for toxicological risk assessment. Successful NTA results in better identification of potentially hazardous pollutants within the environment, facilitating the development of targeted analytical strategies to best characterize risks to human and ecological health. A supporting component of the NTA process involves assessing whether suspected chemicals are amenable to the mass spectrometric method, which is necessary in order to assign an observed signal to the chemical structure. Prior work from this group involved the development of a random forest model for predicting the amenability of 5517 unique chemical structures to liquid chromatography–mass spectrometry (LC-MS). This work improves the interpretability of the group's prior model of the same endpoint, as well as integrating 1348 more data points across negative and positive ionization modes. We enhance interpretability by feature engineering, a machine learning practice that reduces the input dimensionality while attempting to preserve performance statistics. We emphasize the importance of interpretable machine learning models within the context of building confidence in NTA identification. The novel data were curated by the labeling of compounds as amenable or unamenable by expert curators, resulting in an enhanced set of chemical compounds to expand the applicability domain of the prior model. The balanced accuracy benchmark of the newly developed model is comparable to performance previously reported (mean CV BA is 0.84 vs. 0.82 in positive mode, and 0.85 vs. 0.82 in negative mode), while on a novel external set, derived from this work's data, the Matthews correlation coefficients (MCC) for the novel models are 0.66 and 0.68 for positive and negative mode, respectively. Our group's prior published models scored MCC of 0.55 and 0.54 on the same external sets. This demonstrates appreciable improvement over the chemical space captured by the expanded dataset. This work forms part of our ongoing efforts to develop models with higher interpretability and higher performance to support NTA efforts. [ABSTRACT FROM AUTHOR]

In real-world classification problems, it is important to build accurate prediction models and provide information that can improve decision-making. Decision-support tools are often based on network models, and this article uses information encoded by social networks to solve the problem of employer turnover. However, understanding the factors behind black-box prediction models can be challenging. Our question was about the predictability of employee turnover, given information from the multilayer network that describes collaborations and perceptions that assess the performance of organizations that indicate the success of cooperation. Our goal was to develop an accurate prediction procedure, preserve the interpretability of the classification, and capture the wide variety of specific reasons that explain positive cases. After a feature engineering, we identified variables with the best predictive power using decision trees and ranked them based on their added value considering their frequent co-occurrence. We applied the Random Forest using the SMOTE balancing technique for prediction. We calculated the SHAP values to identify the variables that contribute the most to individual predictions. As a last step, we clustered the sample based on SHAP values to fine-tune the explanations for quitting due to different background factors. [ABSTRACT FROM AUTHOR]

Estimating penetration rates of Jumbo drills is crucial for optimizing underground mining drilling processes, aiming to reduce costs and time. This study investigates various regression and machine learning methods, including Multilayer Perceptron (MLP), Support Vector Regression (SVR), and Random Forests (RF), to predict the penetration rates (ROP) using multivariate inputs such as operation parameters and rock mass characteristics. The Rock Mass Drillability Index (RDi), incorporating both intact rock properties and structural parameters, was utilized to characterize the rock mass. The dataset was split into 80% for training and 20% for testing. Performance metrics including correlation coefficient (R2), variance accounted for (VAF), mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean square error (RMSE) were calculated for each method to evaluate the accuracy of the predictions. SVR exhibited the best prediction performance for ROP, achieving the highest R2, lowest RMSE, MAE, and MAPE, as well as the largest VAF values of 0.94, 0.15, 0.11, 4.84, and 94.13 during training, and 0.91, 0.19, 0.13, 6.02, and 91.11 during testing, respectively. With this high accuracy, we conclude that the proposed machine learning algorithms are valuable and efficient predictors for estimating jumbo drill penetration rates in underground mining operations. [ABSTRACT FROM AUTHOR]

Ischemic stroke (IS) is a common cerebrovascular disease whose pathogenesis involves a variety of immune molecules, immune channels and immune processes. 6-methyladenosine (m6A) modification regulates a variety of immune metabolic and immunopathological processes, but the role of m6A in IS is not yet understood. We downloaded the data set GSE58294 from the GEO database and screened for m6A-regulated differential expression genes. The RF algorithm was selected to screen the m6A key regulatory genes. Clinical prediction models were constructed and validated based on m6A key regulatory genes. IS patients were grouped according to the expression of m6A key regulatory genes, and immune markers of IS were identified based on immune infiltration characteristics and correlation. Finally, we performed functional enrichment, protein interaction network analysis and molecular prediction of the immune biomarkers. We identified a total of 7 differentially expressed genes in the dataset, namely METTL3, WTAP, YWHAG, TRA2A, YTHDF3, LRPPRC and HNRNPA2B1. The random forest algorithm indicated that all 7 genes were m6A key regulatory genes of IS, and the credibility of the above key regulatory genes was verified by constructing a clinical prediction model. Based on the expression of key regulatory genes, we divided IS patients into 2 groups. Based on the expression of the gene LRPPRC and the correlation of immune infiltration under different subgroups, LRPPRC was identified as an immune biomarker for IS. GO enrichment analyses indicate that LRPPRC is associated with a variety of cellular functions. Protein interaction network analysis and molecular prediction indicated that LRPPRC correlates with a variety of immune proteins, and LRPPRC may serve as a target for IS drug therapy. Our findings suggest that LRPPRC is an immune marker for IS. Further analysis based on LRPPRC could elucidate its role in the immune microenvironment of IS. [ABSTRACT FROM AUTHOR]

Understanding and predicting the failure modes of transversely isotropic (TI) rocks is essential for designing stable structures and evaluating rock failure incidents, including ground falls, slope stability, and landslides. Compared to isotropic intact rock, TI intact rock exhibits distinct failure modes. Until now, the failure mode of TI rocks has often been related to layer orientation and confinement pressure, with little consideration given to micro-scale parameters. This study investigates how layer orientation and grain size influence the failure mode of layered sandstone under confined and unconfined conditions. A comprehensive laboratory experiments involved 105 layered sandstone samples, featuring variations in grain sizes (fine, medium, and coarse), application of five distinct confining pressures, and testing at seven different orientations. Through rigorous analyses of the post-failure layered sandstone using a random forest classification method, this study developed a predictive chart capable of determining TI rock failure mode based on layer orientation and confinement pressure. Intriguingly, the study also underscores that grain size exerts an insignificant impact on influencing these failure modes. The resultant predictive chart is expected to significantly enhance our comprehension and interpretation of rock failure in both laboratory and field applications, offering invaluable insights for engineering structures associated with TI rocks. Highlights: Confining pressure and layer orientation significantly influence the failure modes of transversely isotropic rocks, with grain size demonstrating negligible impact. The Random Forest Method constructed a predictive failure mode chart, effectively classifying regions into sliding/non-sliding and tensile/shear boundaries. The classification identifies three primary groups of failure modes: layer failure, matrix failure, and mixed failure. The classification of Type 1 and Type 2 mixed failures between the sliding and non-sliding regions, enhancing the granularity of classification. [ABSTRACT FROM AUTHOR]

Background and Objectives: Ganciclovir (GCV) and valganciclovir (VGCV) show large interindividual pharmacokinetic variability, particularly in children. The objectives of this study were (1) to develop machine learning (ML) algorithms trained on simulated pharmacokinetics profiles obtained by Monte Carlo simulations to estimate the best ganciclovir or valganciclovir starting dose in children and (2) to compare its performances on real-world profiles to previously published equation derived from literature population pharmacokinetic (POPPK) models achieving about 20% of profiles within the target. Materials and Methods: The pharmacokinetic parameters of four literature POPPK models in addition to the World Health Organization (WHO) growth curve for children were used in the mrgsolve R package to simulate 10,800 pharmacokinetic profiles. ML algorithms were developed and benchmarked to predict the probability to reach the steady-state, area-under-the-curve target (AUC0–24 within 40–60 mg × h/L) based on demographic characteristics only. The best ML algorithm was then used to calculate the starting dose maximizing the target attainment. Performances were evaluated for ML and literature formula in a test set and in an external set of 32 and 31 actual patients (GCV and VGCV, respectively). Results: A combination of Xgboost, neural network, and random forest algorithms yielded the best performances and highest target attainment in the test set (36.8% for GCV and 35.3% for the VGCV). In actual patients, the best GCV ML starting dose yielded the highest target attainment rate (25.8%) and performed equally for VGCV with the Franck model formula (35.3% for both). Conclusion: The ML algorithms exhibit good performances in comparison with previously validated models and should be evaluated prospectively. [ABSTRACT FROM AUTHOR]

Tropical forests are the world's most structurally complex ecosystems, providing key functions like biomass accumulation, which is linked to this complexity. Tropical forests are also exposed to chronic, non-severe winds, yet their effect on forest structural complexity is understudied. Here we examine drivers of forest structural complexity in Puerto Rico with a particular focus on chronic wind exposure. We used airborne light detection and ranging data collected in 2016 to quantify canopy height and rugosity (variation in height) in ~ 20,000, 0.28 ha forested sites stratified by forest age. We used random forest models to analyze variation in canopy height and rugosity as a function of chronic wind exposure, forest age, mean annual precipitation, elevation, slope (in degrees), soil type, soil available water storage, and exposure to a previous hurricane. Canopy height was driven by precipitation, forest age, and chronic wind exposure, decreasing by 2.12 m (16%) on average in wind-exposed forests across all forest ages. Canopy height increased by 4.0 m (41%) on average in forests aged 25–66 years, and by 4.0 m between sites with 1000 and 2000 mm y−1 precipitation. Canopy rugosity was driven by canopy height, precipitation, forest age, and elevation, increasing log-linearly with canopy height and precipitation, decreasing with elevation, and was highest in younger forests. Chronic wind exposure did not drive variation in canopy rugosity. Our results suggest that chronic wind exposure plays an integral role in limiting canopy height, potentially reducing aboveground carbon accumulation in older tropical forests. [ABSTRACT FROM AUTHOR]

This article aims to predict the mid-span displacements of reinforced concrete (RC) columns exposed to blast loading with machine learning models. Machine learning models including the gradient boosting decision tree (GBDT) model and the random forest (RF) model are developed. The model hyperparameters in the machine learning models are globally optimized using Bayesian optimization method. The dataset used to train and test the models is constructed by collecting data from shock-tube-simulated experiments. Results show that the performance of the optimized models is significantly improved. By comparing the performance metrics of two models, it is evident that the GBDT model is superior to the RF model in predicting mid-span displacements. The optimized GBDT model is then used to predict the displacements of columns during field tests, and the experimental results and predictive results are relatively consistent, which verifies the effectiveness of GBDT model with Bayesian optimization in damage assessment for RC columns. [ABSTRACT FROM AUTHOR]

Applications for machine learning (ML), deep learning, and other artificial intelligence models have shown great promise in nuclear physics, including not only in classification systems but also in the analysis of numerical data. This study used various ML algorithms to estimate the concentrations of six rare earth elements (Sm, La, Ce, Sc, Eu, and Tb) in both archaeological and marine sediment samples. An interesting aspect of this analysis is that 80% of the 235 data points were used for training data, which included two parameters: specific activity ( A sp ) and concentration (ρ ) by the k0-method for the purpose of model development. The remaining 20% of the dataset was held out for testing the model's accuracy. The fundamental principle of this approach is the use of regression analysis between A sp and ρ to construct a machine learning regression model. This machine learning model was subsequently applied to estimate element concentrations based on A sp values obtained from gamma spectra. The mean absolute error (MAE), root mean square error (RMSE) and the statistical measure R-squared (R2) were employed for evaluating the accuracy of the predicted models. The random forest (RF) algorithm produces smaller MAE and RMSE values and achieves better R2 values compared to other algorithms. In addition, RF shows the lowest relative bias of the concentration values of elements in reference material (NIST 2711a) compared to other prediction models. The work focuses on demonstrating that machine learning models can effectively predict the concentrations of rare earth elements, even though this is a fundamental issue in NAA and one previous study has addressed this issue for one single element. The extension of the current work and potential directions for further development will be presented in the results and discussion section. [ABSTRACT FROM AUTHOR]

Heart disease is a complex disease, and many people around the world suffer from this disease. Due to the lack of a healthy lifestyle, it is the most common cause of death worldwide. Machine learning plays an important role in medical treatment. The goal of this research is to develop a machine learning model to help diagnose heart disease quickly and accurately. In this article, an effective and improved machine learning method is proposed to diagnose heart disease. We designed a novel and robust ensemble model that combines the top three classifiers, namely Random Forest, XGBoost and Gradient Boosting Machine, to effectively diagnose heart disease. We used an ensemble voting method to combine the results of the top three classifiers to improve the prediction of heart disease. We used a combined heart disease dataset containing five different datasets (Hungary, Statlog, Switzerland, VA Long Beach and Cleveland). Feature selection algorithms (Pearson Correlation, Univariate Feature Selection, Recursive Feature Elimination, Boruta Feature Selection, Random forest, and LightGBM) are used to select highly relevant features based on rankings to improve classification accuracy. The proposed ensemble model is designed using seven highly relevant features, and a comparison of machine learning algorithms and ensemble learning techniques is applied to the selected features. Different performance evaluation methods are used to evaluate the proposed model: accuracy, sensitivity, precision, F1-score, MCC, NPV and AUC. Results analysis shows that the ensemble model achieves excellent classification accuracy, sensitivity, and precision of 96.17%, 98.37%, and 94.53%. Our proposed model performs better than existing models and individual classifiers. The results show that the proposed ensemble method can effectively predict the risk of heart disease. [ABSTRACT FROM AUTHOR]

Background: Shortages of mechanical ventilation have become a constant problem in Emergency Departments (EDs), thereby affecting the timely deployment of medical interventions that counteract the severe health complications experienced during respiratory disease seasons. It is then necessary to count on agile and robust methodological approaches predicting the expected demand loads to EDs while supporting the timely allocation of ventilators. In this paper, we propose an integration of Artificial Intelligence (AI) and Discrete-event Simulation (DES) to design effective interventions ensuring the high availability of ventilators for patients needing these devices. Methods: First, we applied Random Forest (RF) to estimate the mechanical ventilation probability of respiratory-affected patients entering the emergency wards. Second, we introduced the RF predictions into a DES model to diagnose the response of EDs in terms of mechanical ventilator availability. Lately, we pretested two different interventions suggested by decision-makers to address the scarcity of this resource. A case study in a European hospital group was used to validate the proposed methodology. Results: The number of patients in the training cohort was 734, while the test group comprised 315. The sensitivity of the AI model was 93.08% (95% confidence interval, [88.46 − 96.26%]), whilst the specificity was 85.45% [77.45 − 91.45%]. On the other hand, the positive and negative predictive values were 91.62% (86.75 − 95.13%) and 87.85% (80.12 − 93.36%). Also, the Receiver Operator Characteristic (ROC) curve plot was 95.00% (89.25 − 100%). Finally, the median waiting time for mechanical ventilation was decreased by 17.48% after implementing a new resource capacity strategy. Conclusions: Combining AI and DES helps healthcare decision-makers to elucidate interventions shortening the waiting times for mechanical ventilators in EDs during respiratory disease epidemics and pandemics. [ABSTRACT FROM AUTHOR]

In order to improve the control performance and reliability of the pulse-width modulation (PWM) rectifiers in electric vehicle (EV) charging systems, the evaluation of DC bus capacitor health status is critical. In order to accurately monitor the health status of DC bus capacitors, a data-driven model fusion method is developed. In the method, multi-layer perceptron, random forest, and XGBoost are adopted as the base learners that produce separate row predictions. The second-level learner, support vector machine (SVM) accepts the outputs of the previous learners and integrates them into the final health status prediction. Meanwhile, the feature vector is constructed by only collecting the grid voltage, the grid current and the AC component of DC bus voltage. With the feature vector as input, the proposed method is able to accurately predict the health status of DC bus capacitor. Finally, we built a three-phase PWM rectifier as an experimental platform for validation. The experimental results verify that the proposed method fully utilizes the advantages of data-driven and model fusion, and achieves a high accuracy in the health state evaluation of DC bus capacitor. [ABSTRACT FROM AUTHOR]

The automotive industry continues to grow rapidly with technological developments. Vehicles are being equipped with new software and sensors which assist drivers. People have become familiar with the L1 and L2 vehicles with advanced driver assistance systems. However, the idea of full automation is still new to most people. In Türkiye, AVs are not present on roads. Thus, neither pedestrians nor drivers have been in interaction with AVs yet. This study investigates the preliminary perception of AVs among road users in Türkiye. The data were collected via a face-to-face survey. A binary logit and a random forest model were used to identify the critical factors in the positive attitudes toward AVs. Binary logit and random forest models resulted in similar findings. Age, education level, people who would feel safe driving in an AV, and who believed that urban traffic congestion would decrease were positive about AVs. The random forest model showed the same accuracy when the two models were compared. Most public opinion studies about AVs have been investigated in developed countries. It is believed that this study will help to understand the perception of AVs in developing countries. [ABSTRACT FROM AUTHOR]

Afforestations provide cost-effective and environmentally friendly protection against natural hazards, compared to technical measures. In Austria, more than 3000 afforestation sites for hazard protection covering 9000 ha have been established between 1906 and 2017, mainly for snow avalanche protection. The actual protective effect depends on avalanche predisposing factors and land cover, i.e. whether forest is present. In this study, predisposing factors and land cover classes were identified and analysed in selected afforestation sites. The protective effect of forest was attributed to the presence of forest cover and tree species. Using RGB images with a ground resolution of 20 × 20 cm, nine land cover categories have been distinguished by means of supervised classification with the random forest algorithm. Those land cover categories were classified with an overall accuracy of 0.87–0.98 and Kappa-values, ranging between 0.81 and 0.93. Images were filtered using a 3 pixel by 3 pixel majority filter, which assigns each cell in the output grid the most commonly occurring value in a moving window centred on each grid cell. This filter further increased the overall accuracy by removing noise pixels while preserving the fine elements of the classified grid. Our results indicate a protective effect for about half of the analysed afforestation sites. The dominance of the land use class "Meadow" at most sites with little avalanche protection effect suggests grazing as a limiting factor. The spatial information provided with the described method allows to identify critical areas in terms of avalanche protection even years after the initial afforestation. [ABSTRACT FROM AUTHOR]

High dimensionality can lead to overfitting and affect the modeling power of classification algorithms, resulting an increase in false positive rate (FPR) and false negative rate (FNR). Therefore, feature selection is a critical issue to deal with by means of efficient techniques when developing Intrusion Detection Systems. This study seeks to assess and compare the impacts of five univariate filters (Relieff, Pearson Correlation, Mutual Information, ANOVA, and Chi2) with different selection thresholds, and three multivariate filters (Correlation-based feature subset selection, Double Input Symmetric Relevance and Consistency-based subset selection) on the performances of four classifiers (Multilayer Perceptron, Support Vector Machines, XGBoost and Random Forest) over CIC-IDS2017, CSE-CIC-IDS2018 and CIC-ToN-IoT intrusion detection datasets. We evaluate 228 variants of classifiers to determine the features that positively impact the classification efficiency of all the cyber-attack scenarios used. The obtained results show that using XGBoost and Random Forest trained with multivariate methods, such as CON and DISR, can effectively reduce the number of features without affecting the classification performance and detection rate, compared to other filtering methods. [ABSTRACT FROM AUTHOR]

Summary: An independent correlation between pre-RDW and 1-year mortality after surgery in elderly hip fracture can be used to predict mortality in elderly hip fracture patients and has predictive significance in anemia patients. With further research, a treatment algorithm can be developed to potentially identify patients at high risk of preoperative mortality. Introduction: Red blood cell distribution width (RDW) is an independent predictor of various disease states in elderly individuals, but its association with the prognosis of elderly hip fracture patients is controversial. This study aimed to evaluate the prognostic value of RDW in such patients, construct a prediction model containing RDW using random survival forest (RSF) and Cox regression analysis, and compare RDW in patients with and without anemia. Methods: We retrospectively analyzed the data of elderly patients who underwent hip fracture surgery, selected the best variables using RSF, stratified the independent variables by Cox regression analysis, constructed a 1-year mortality prediction model of elderly hip fracture with RDW, and conducted internal validation and external validation. Results: Two thousand one hundred six patients were included in this study. The RSF algorithm selects 12 important influencing factors, and Cox regression analysis showed that eight variables including preoperative RDW (pre-RDW) were independent risk factors for death within 1-year after hip fracture surgery in elderly patients. Stratified analysis showed that pre-RDW was still independently associated with 1-year mortality in the non-anemia group and not in the anemia group. The nomogram prediction model had high differentiation and fit, and the prediction model constructed by the total cohort of patients was also used for validation of patients in the anemia patients and obtained good clinical benefits. Conclusion: An independent correlation between pre-RDW and 1-year mortality after surgery in elderly hip fracture can be used to predict mortality in elderly hip fracture patients and has predictive significance in anemia patients. [ABSTRACT FROM AUTHOR]

Objectives: Currently, the BRAF status of pediatric low-grade glioma (pLGG) patients is determined through a biopsy. We established a nomogram to predict BRAF status non-invasively using clinical and radiomic factors. Additionally, we assessed an advanced thresholding method to provide only high-confidence predictions for the molecular subtype. Finally, we tested whether radiomic features provide additional predictive information for this classification task, beyond that which is embedded in the location of the tumor. Methods: Random forest (RF) models were trained on radiomic and clinical features both separately and together, to evaluate the utility of each feature set. Instead of using the traditional single threshold technique to convert the model outputs to class predictions, we implemented a double threshold mechanism that accounted for uncertainty. Additionally, a linear model was trained and depicted graphically as a nomogram. Results: The combined RF (AUC: 0.925) outperformed the RFs trained on radiomic (AUC: 0.863) or clinical (AUC: 0.889) features alone. The linear model had a comparable AUC (0.916), despite its lower complexity. Traditional thresholding produced an accuracy of 84.5%, while the double threshold approach yielded 92.2% accuracy on the 80.7% of patients with the highest confidence predictions. Conclusion: Models that included radiomic features outperformed, underscoring their importance for the prediction of BRAF status. A linear model performed similarly to RF but with the added benefit that it can be visualized as a nomogram, improving the explainability of the model. The double threshold technique was able to identify uncertain predictions, enhancing the clinical utility of the model. Clinical relevance statement: Radiomic features and tumor location are both predictive of BRAF status in pLGG patients. We show that they contain complementary information and depict the optimal model as a nomogram, which can be used as a non-invasive alternative to biopsy. Key Points: • Radiomic features provide additional predictive information for the determination of the molecular subtype of pediatric low-grade gliomas patients, beyond what is embedded in the location of the tumor, which has an established relationship with genetic status. • An advanced thresholding method can help to distinguish cases where machine learning models have a high chance of being (in)correct, improving the utility of these models. • A simple linear model performs similarly to a more powerful random forest model at classifying the molecular subtype of pediatric low-grade gliomas but has the added benefit that it can be converted into a nomogram, which may facilitate clinical implementation by improving the explainability of the model. [ABSTRACT FROM AUTHOR]

Reference crop evapotranspiration (ETO) is a basic component of the hydrological cycle and its estimation is critical for agricultural water resource management and scheduling. In this study, three tree-based machine learning algorithms (random forest [RF], gradient boosting decision tree [GBDT], and extreme gradient boosting [XGBoost]) were adopted to determine the essential factors for ETO prediction. The tree-based models were optimized using the Bayesian optimization (BO) algorithm and were compared with three standalone models in terms of daily ETO and monthly mean ETO estimations in North China, with different input combinations of essential variables. The results indicated that solar radiation (Rs) and air temperature (Ts), including the maximum, minimum, and average temperatures, in daily ETO were the key variables affecting model prediction accuracy. Rs was the most influential factor in the monthly average ETO model followed by Ts. Both relative humidity (RH) and wind speed at 2 m (U2) had little impact on ETO prediction at different scales, although their importance differed. Compared with the GBDT and RF models, the XGBoost model exhibited the best performance for daily ETO and monthly mean ETO estimations. The hybrid tree-based models with the BO algorithm outperformed standalone tree-based models. Overall, compared with the other inputs, the model with three inputs (Rs, Ts, and RH/U2) had the highest accuracy. The BO-XGBoost model exhibited superior performance in terms of the global performance index (GPI) for daily ETO and monthly mean ETO predictions and is recommended as a more accurate model for predicting daily ETO and monthly mean ETO in North China or areas with a similar climate. [ABSTRACT FROM AUTHOR]

This study explores the application of machine learning algorithms for the prediction of pan evaporation (Ep), which is a critical factor in water resource management for the assessment of water demand and usage. Specifically, this research evaluates the effectiveness of two base models: Random Forest (RF) and Multi-Layer Perceptron (MLP) and their optimized counterparts using a Genetic Algorithm (GA), designated as GA-RF and GA-MLP, for modeling Ep at a target station using data from adjacent stations. The datasets were split into a training set (70%) and a testing set (30%). The models' performances were judged using three statistical measures: Correlation Coefficient (CC), Scattered Index (SI), and Willmott's Index of agreement (WI). The enhanced models, particularly GA-MLP-5, showed superior performance with a CC of 0.8704, SI of 0.2539, and WI of 0.9212, indicating the potent ability of GA to refine RF and MLP models for predictive accuracy. Additionally, sensitivity analysis via the GA-RF indicates the varying influence of Ep from neighboring stations on the target station, shedding light on key predictors for effective water management. Conclusively, this study demonstrates that the hybrid models have significant potential in accurate Ep estimation and can be expanded to predict other meteorological variables, offering valuable tools for water resource management strategies. [ABSTRACT FROM AUTHOR]

Machine Learning (ML) has become pivotal across various fields, offering innovative solutions to complex data challenges. Professionals typically seek models that excel in both performance and reliability, aiming to achieve optimal generalization on future data. Since, then a variety of methods such as dummy coding, up/down-sampling, and bin-counting have been explored. However, finding a solution that effectively navigates the intricacies of limited and complex datasets still remains a challenge. This study introduces the K-Means Featurizer (KMF), an innovative algorithm crafted to enhance model performance and reliability, especially in scenarios involving complex and limited datasets. KMF employs K-Means clustering to generate enriched features that provide a nuanced understanding of the data, effectively balancing the similarity between the target variable and the feature space. This results in a more efficient predictive task by minimizing Euclidean distances and enhancing model generalizability. Our research validates KMF's effectiveness through an experiment in geoscience engineering, focusing on hydraulic conductivity (K) prediction, a vital parameter in well monitoring and infrastructure planning. Traditionally, K extraction is laborious and costly, requiring extensive pumping tests. KMF's application in this context demonstrates its potential to substantially reduce data losses during such operations. Applying KMF to the Extreme Gradient Boosting, Random Forest, K-Neighbors, Support Vector Machines, and Multiple Layers Neural Networks resulted in a significant improvement in prediction accuracy, with K-scores reaching up to 90%. While our experiment centers on geoscience engineering, KMF's utility extends to various domains facing similar data intricacies. Its adaptability to different types of complex datasets positions it as a valuable tool for diverse data-driven applications. [ABSTRACT FROM AUTHOR]

Landslide susceptibility mapping (LSM) is a major measure for disaster prevention and control. This paper proposes an incremental learning random forest model that uses random forests for incremental training of landslides. The 1652 landslides in Ganzhou, China from year 2015 to 2020 were divided into three equal parts (T1, T2 and T3) considering time series. And the data of T1 part is used to construct incremental learning random forest model ILRF_1, T2 and T3 part as the new part of incremental training. Landslide susceptibility maps were plotted using ILRF, batch learning random forests (BLRF), batch learning support vector machines (BLSVM), respectively. And the accuracy is verified using the receiver operating curve (ROC). The results showed that the ILRF was the most promising model(AUC = 0.937) for the LSM, followed by BLRF(AUC = 0.905), BLSVM(AUC = 0.865). ILRF has better predictive ability in the susceptibility evaluation of this region. It is very high-prone area accounts for the smallest proportion, mainly concentrated in the mountain front area in the northeast of Ganzhou City. The multi-year average rainfall, population density, and normalized difference vegetation index are the first three important factors that control the spatial possibility of landslides. [ABSTRACT FROM AUTHOR]

This paper describes a correlation-based batch process for addressing high dimensional imputation problems. There are relatively few algorithms designed to efficiently handle imputation of missing data in high dimensional contexts. Fewer still are flexible enough to natively handle mixed-type data, often requiring lengthy pre-processing to get the data into proper shape, and then post-processing to return the data to usable form. Such decisions as well as assumptions made by many methods (e.g., data generating process) limit their performance, flexibility, and usability. Built on a set of complementary algorithms for nonparametric imputation via chained random forests, I introduce a batching process to ease computational costs associated with high dimensional imputation by subsetting data based on ranked cross-feature absolute correlations. The algorithm then imputes each batch separately, and joins imputed subsets in the final step. The process, hdImpute, is fast and accurate. As a result, high dimensional imputation is more accessible, and researchers are not forced to decide between speed or accuracy. Complementary software is available in the form of an R package, and is openly developed on Github under the MIT public license. In the spirit of open science, collaboration and engagement with the actively developing software are encouraged. [ABSTRACT FROM AUTHOR]

Accurate evaluation of crop performance and yield prediction at a sub-field scale is essential for achieving high yields while minimizing environmental impacts. Two important approaches for improving agronomic management and predicting future crop yields are the spatial stability of historic crop yields and in-season remote sensing imagery. However, the relative accuracies of these approaches have not been well characterized. In this study, we aim to first, assess the accuracies of yield stability and in-season remote sensing for predicting yield patterns at a sub-field resolution across multiple fields, second, investigate the optimal satellite image date for yield prediction, and third, relate bi-weekly changes in GCVI through the season to yield levels. We hypothesize that historical yield stability zones provide high accuracies in identifying yield patterns compared to within-season remote sensing images. To conduct this evaluation, we utilized biweekly Planet images with visible and near-infrared bands from June through September (2018–2020), along with observed historical yield maps from 115 maize fields located in Indiana, Iowa, Michigan, and Minnesota, USA. We compared the yield stability zones (YSZ) with the in-season remote sensing data, specifically focusing on the green chlorophyll vegetative index (GCVI). Our analysis revealed that yield stability maps provided more accurate estimates of yield within both high stable (HS) and low stable (LS) yield zones within fields compared to any single-image in-season remote sensing model. For the in-season remote sensing predictions, we used linear models for a single image date, as well as multi-linear and random forest models incorporating multiple image dates. Results indicated that the optimal image date for yield prediction varied between and within fields, highlighting the instability of this approach. However, the multi-image models, incorporating multiple image dates, showed improved prediction accuracy, achieving R2 values of 0.66 and 0.86 by September 1st for the multi-linear and random forest models, respectively. Our analysis revealed that most low or high GCVI values of a pixel were consistent across the season (77%), with the greatest instability observed at the beginning and end of the growing season. Interestingly, the historical yield stability zones provided better predictions of yield compared to the bi-weekly dynamics of GCVI. The historically high-yielding areas started with low GCVI early in the season but caught up, while the low-yielding areas with high initial GCVI faltered. In conclusion, the historical yield stability zones in the US Midwest demonstrated robust predictive capacity for in-field heterogeneity in stable zones. Multi-image models showed promise for assessing unstable zones during the season, but it is crucial to link these two approaches to fully capture both stable and unstable zones of crop yield. This study provides opportunities to achieve better precision management and yield prediction by integrating historical crop yields and remote sensing techniques. [ABSTRACT FROM AUTHOR]

The strawberry appearance is an essential standard for judging the quality, so it is crucial to accurately identify the strawberry appearance quality for intelligent picking. This study proposed a new strawberry appearance quality detection based on unsupervised deep learning. Firstly, using deep learning (Resnet18, Resnet50, and Resnet101) to extract the strawberry image feature information. And using the t-SNE (t-distribution stochastic neighbor embedding) to reduce the feature vectors' dimension. Finally, the unsupervised learning method (Gaussian Mixture Model) was used to cluster strawberries' feature points. The results showed that: (1) the clustering performance based on Resnet101 was effective in 2-dimensional space, the cluster accuracy was 94.89%, and the validation accuracy was 91.79%. (2) The clustering method based on Resnet50 had good performance in the 3-dimensional space, the cluster accuracy was 96.10%, and the validation accuracy was 93.08%. (3) The accuracy of deep features plus RF (random forest) was 95.00% under limited data. Thus this method will promote intelligent picking strawberry equipment and it will overcome the supervised learning drawback that divides image datasets according to prior knowledge. [ABSTRACT FROM AUTHOR]

For shallow lakes, the most dramatic ecosystem shift is that from a clear-water, macrophyte-dominated regime to a turbid, phytoplankton-dominated regime. Whereas many studies have focussed on the factors that trigger such shifts, it is still unclear how these changes shape fish diversity. In the present study, we characterised the fish communities taxonomically and functionally in Lake Taihu, China, along a spatial gradient of habitat types, i.e. algal-dominated, macrophyte-dominated, open-lake and aquaculture conversion zones. Random Forests regression was then applied to examine how fish diversities were related to environmental conditions. Our results showed that the taxonomic and functional composition of the fish community varied among different habitat regimes. Macrophyte and water quality were identified as the most important factors affecting the fish diversity indices. Habitats with a high macrophyte biomass and low nutrient concentration supported higher functional diversity. Moreover, our analysis revealed that although functional diversity indices were strongly correlated with species richness, they appeared more sensitive to changes in habitat conditions. Overall, our study highlights the importance of macrophyte-dominated state in maintaining fish diversity in freshwater ecosystems and provides new insight into how functional diversity can improve our understanding of the response of biodiversity to ecological processes. [ABSTRACT FROM AUTHOR]

Cloud top pressure (CTP) is one of the critical cloud properties that significantly affects the radiative effect of clouds. Multi-angle polarized sensors can employ polarized bands (490 nm) or O2 A-bands (763 and 765 nm) to retrieve the CTP. However, the CTP retrieved by the two methods shows inconsistent results in certain cases, and large uncertainties in low and thin cloud retrievals, which may lead to challenges in subsequent applications. This study proposes a synergistic algorithm that considers both O2 A-bands and polarized bands using a random forest (RF) model. LiDAR CTP data are used as the true values and the polarized and non-polarized measurements are concatenated to train the RF model to determine CTP. Additionally, through analysis, we proposed that the polarized signal becomes saturated as the cloud optical thickness (COT) increases, necessitating a particular treatment for cases where COT < 10 to improve the algorithm's stability. The synergistic method was then applied to the directional polarized camera (DPC) and Polarized and Directionality of the Earth's Reflectance (POLDER) measurements for evaluation, and the resulting retrieval accuracy of the POLDER-based measurements (RMSEPOLDER = 205.176 hPa, RMSEDPC = 171.141 hPa, R2POLDER = 0.636, R2DPC = 0.663, respectively) were higher than that of the MODIS and POLDER Rayleigh pressure measurements. The synergistic algorithm also showed good performance with the application of DPC data. This algorithm is expected to provide data support for atmosphere-related fields as an atmospheric remote sensing algorithm within the Cloud Application for Remote Sensing, Atmospheric Radiation, and Updating Energy (CARE) platform. [ABSTRACT FROM AUTHOR]

Precise and timely prediction of crop yields is crucial for food security and the development of agricultural policies. However, crop yield is influenced by multiple factors within complex growth environments. Previous research has paid relatively little attention to the interference of environmental factors and drought on the growth of winter wheat. Therefore, there is an urgent need for more effective methods to explore the inherent relationship between these factors and crop yield, making precise yield prediction increasingly important. This study was based on four type of indicators including meteorological, crop growth status, environmental, and drought index, from October 2003 to June 2019 in Henan Province as the basic data for predicting winter wheat yield. Using the sparrow search algorithm combined with random forest (SSA-RF) under different input indicators, accuracy of winter wheat yield estimation was calculated. The estimation accuracy of SSA-RF was compared with partial least squares regression (PLSR), extreme gradient boosting (XG-Boost), and random forest (RF) models. Finally, the determined optimal yield estimation method was used to predict winter wheat yield in three typical years. Following are the findings: 1) the SSA-RF demonstrates superior performance in estimating winter wheat yield compared to other algorithms. The best yield estimation method is achieved by four types indicators' composition with SSA-RF) (R2 = 0.805, RRMSE = 9.9%. 2) Crops growth status and environmental indicators play significant roles in wheat yield estimation, accounting for 46% and 22% of the yield importance among all indicators, respectively. 3) Selecting indicators from October to April of the following year yielded the highest accuracy in winter wheat yield estimation, with an R2 of 0.826 and an RAISE of 9.0%. Yield estimates can be completed two months before the winter wheat harvest in June. 4) The predicted performance will be slightly affected by severe drought. Compared with severe drought year (2011) (R2 = 0.680) and normal year (2017) (R2 = 0.790), the SSA-RF model has higher prediction accuracy for wet year (2018) (R2 = 0.820). This study could provide an innovative approach for remote sensing estimation of winter wheat yield, yield. [ABSTRACT FROM AUTHOR]

Existing research on non-suicidal self-injury (NSSI) among adolescents has primarily concentrated on general risk factors, leaving a significant gap in understanding the specific NSSI characteristics that predict diverse psychopathological outcomes. This study aims to address this gap by using Random Forests to discern the significant predictors of different clinical outcomes. The study tracked 348 adolescents (64.7% girls; mean age = 13.31, SD = 0.91) over 6 months. Initially, 46 characteristics of NSSI were evaluated for their potential to predict the repetition of NSSI, as well as depression, anxiety, and suicidal risks at a follow-up (T2). The findings revealed distinct predictors for each psychopathology. Specifically, psychological pain was identified as a significant predictor for depression, anxiety, and suicidal risks, while the perceived effectiveness of NSSI was crucial in forecasting its repetition. These findings imply that it is feasible to identify high-risk individuals by assessing key NSSI characteristics, and also highlight the importance of considering diverse NSSI characteristics when working with self-injurers. [ABSTRACT FROM AUTHOR]

The imbalance of land cover categories is a common problem. Some categories appear less frequently in the image, while others may occupy the vast majority of the proportion. This imbalance can lead the classifier to tend to predict categories with higher frequency of occurrence, while the recognition effect on minority categories is poor. In view of the difficulty of land cover remote sensing image multi-target semantic classification, a semantic classification method of land cover remote sensing image based on depth deconvolution neural network is proposed. In this method, the land cover remote sensing image semantic segmentation algorithm based on depth deconvolution neural network is used to segment the land cover remote sensing image with multi-target semantic segmentation; Four semantic features of color, texture, shape and size in land cover remote sensing image are extracted by using the semantic feature extraction method of remote sensing image based on improved sequential clustering algorithm; The classification and recognition method of remote sensing image semantic features based on random forest algorithm is adopted to classify and identify four semantic feature types of land cover remote sensing image, and realize the semantic classification of land cover remote sensing image. The experimental results show that after this method classifies the multi-target semantic types of land cover remote sensing images, the average values of Dice similarity coefficient and Hausdorff distance are 0.9877 and 0.9911 respectively, which can accurately classify the multi-target semantic types of land cover remote sensing images. [ABSTRACT FROM AUTHOR]

Infection-related consultations on intensive care units (ICU) have a positive impact on quality of care and clinical outcome. However, timing of these consultations is essential and to date they are typically event-triggered and reactive. Here, we investigate a proactive approach to identify patients in need for infection-related consultations by machine learning models using routine electronic health records. Data was retrieved from a mixed ICU at a large academic tertiary care hospital including 9684 admissions. Infection-related consultations were predicted using logistic regression, random forest, gradient boosting machines, and long short-term memory neural networks (LSTM). Overall, 7.8% of admitted patients received an infection-related consultation. Time-sensitive modelling approaches performed better than static approaches. Using LSTM resulted in the prediction of infection-related consultations in the next clinical shift (up to eight hours in advance) with an area under the receiver operating curve (AUROC) of 0.921 and an area under the precision recall curve (AUPRC) of 0.541. The successful prediction of infection-related consultations for ICU patients was done without the use of classical triggers, such as (interim) microbiology reports. Predicting this key event can potentially streamline ICU and consultant workflows and improve care as well as outcome for critically ill patients with (suspected) infections. [ABSTRACT FROM AUTHOR]

This study aims to explore the effects of different non-landslide sampling strategies on machine learning models in landslide susceptibility mapping. Non-landslide samples are inherently uncertain, and the selection of non-landslide samples may suffer from issues such as noisy or insufficient regional representations, which can affect the accuracy of the results. In this study, a positive-unlabeled (PU) bagging semi-supervised learning method was introduced for non-landslide sample selection. In addition, buffer control sampling (BCS) and K-means (KM) clustering were applied for comparative analysis. Based on landslide data from Qiaojia County, Yunnan Province, China, collected in 2014, three machine learning models, namely, random forest, support vector machine, and CatBoost, were used for landslide susceptibility mapping. The results show that the quality of samples selected using different non-landslide sampling strategies varies significantly. Overall, the quality of non-landslide samples selected using the PU bagging method is superior, and this method performs best when combined with CatBoost for predicting (AUC = 0.897) landslides in very high and high susceptibility zones (82.14%). Additionally, the KM results indicated overfitting, displaying high accuracy for validation but poor statistical outcomes for zoning. The BCS results were the worst. [ABSTRACT FROM AUTHOR]

P. ginseng is a precious traditional Chinese functional food, which is used for both medicinal and food purposes, and has various effects such as immunomodulation, anti-tumor and anti-oxidation. The growth year of P. ginseng has an important impact on its medicinal and economic values. Fast and nondestructive identification of the growth year of P. ginseng is crucial for its quality evaluation. In this paper, we propose a FC-CNN network that incorporates spectral and spatial features of hyperspectral images to characterize P. ginseng from different growth years. The importance ranking of the spectra was obtained using the random forest method for optimal band selection. Based on the hyperspectral reflectance data of P. ginseng after radiometric calibration and the images of the best five VNIR bands and five SWIR bands selected, the year-by-year identification of P. ginseng age and its identification experiments for food and medicinal purposes were conducted, and the FC-CNN network and its FCNN and CNN branch networks were tested and compared in terms of their effectiveness in the identification of P. ginseng growth years. It has been experimentally verified that the best year-by-year recognition was achieved by utilizing images from five visible and near-infrared important bands and all spectral curves, and the recognition accuracy of food and medicinal use reached 100%. The FC-CNN network is significantly better than its branching model in the effect of edible and medicinal identification. The results show that for P. ginseng growth year identification, VNIR images have much more useful information than SWIR images. Meanwhile, the FC-CNN network utilizing the spectral and spatial features of hyperspectral images is an effective method for the identification of P. ginseng growth year. [ABSTRACT FROM AUTHOR]