Search

Background: Acute upper gastrointestinal bleeding (AUGIB) is a major cause of morbidity and mortality. This presentation however is not universally high risk as only 20–30% of bleeds require urgent haemostatic therapy. Nevertheless, the current standard of care is for all patients admitted to an inpatient bed to undergo endoscopy within 24 h for risk stratification which is invasive, costly and difficult to achieve in routine clinical practice. Objectives: To develop novel non-endoscopic machine learning models for AUGIB to predict the need for haemostatic therapy by endoscopic, radiological or surgical intervention. Design: A retrospective cohort study Method: We analysed data from patients admitted with AUGIB to hospitals from 2015 to 2020 (n = 970). Machine learning models were internally validated to predict the need for haemostatic therapy. The performance of the models was compared to the Glasgow-Blatchford score (GBS) using the area under receiver operating characteristic (AUROC) curves. Results: The random forest classifier [AUROC 0.84 (0.80–0.87)] had the best performance and was superior to the GBS [AUROC 0.75 (0.72–0.78), p < 0.001] in predicting the need for haemostatic therapy in patients with AUGIB. A GBS cut-off of ⩾12 was associated with an accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) of 0.74, 0.49, 0.81, 0.41 and 0.85, respectively. The Random Forrest model performed better with an accuracy, sensitivity, specificity, PPV and NPV of 0.82, 0.54, 0.90, 0.60 and 0.88, respectively. Conclusion: We developed and validated a machine learning algorithm with high accuracy and specificity in predicting the need for haemostatic therapy in AUGIB. This could be used to risk stratify high-risk patients to urgent endoscopy. [ABSTRACT FROM AUTHOR]

A new analytical method for chronic kidney disease (CKD) detection utilizing paper spray mass spectrometry (PS-MS) combined with machine learning is presented. The analytical protocol is rapid and simple, based on metabolic profile alterations in urine. Anonymized raw urine samples were deposited (10 μL each) onto pointed PS-MS sample strips. Without waiting for the sample to dry, 75 μL of acetonitrile and high voltage were applied to the strips, using high resolution mass spectrometry measurement (15 s per sample) with polarity switching to detect a wide range of metabolites. Random forest machine learning was used to classify the resulting data. The diagnostic performance for the potential diagnosis of CKD was evaluated for accuracy, sensitivity, and specificity, achieving results >96% for the training data and >91% for validation and test data sets. Metabolites selected by the classification model as up- or down-regulated in healthy or CKD samples were tentatively identified and in agreement with previously reported literature. The potential utilization of this approach to discriminate albuminuria categories (normo, micro, and macroalbuminuria) was also demonstrated. This study indicates that PS-MS combined with machine learning has the potential to be used as a rapid and simple diagnostic tool for CKD. [ABSTRACT FROM AUTHOR]

Background: The global evolution of pre-hospital care systems faces dynamic challenges, particularly in multinational settings. Machine learning (ML) techniques enable the exploration of deeply embedded data patterns for improved patient care and resource optimisation. This study's objective was to accurately predict cases that necessitated transportation versus those that did not, using ML techniques, thereby facilitating efficient resource allocation. Methods: ML algorithms were utilised to predict patient transport decisions in a Middle Eastern national pre-hospital emergency medical care provider. A comprehensive dataset comprising 93,712 emergency calls from the 999-call centre was analysed using R programming language. Demographic and clinical variables were incorporated to enhance predictive accuracy. Random Forest (RF), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), and Adaptive Boosting (AdaBoost) algorithms were trained and validated. Results: All the trained algorithm models, particularly XGBoost (Accuracy = 83.1%), correctly predicted patients' transportation decisions. Further, they indicated statistically significant patterns that could be leveraged for targeted resource deployment. Moreover, the specificity rates were high; 97.96% in RF and 95.39% in XGBoost, minimising the incidence of incorrectly identified "Transported" cases (False Positive). Conclusion: The study identified the transformative potential of ML algorithms in enhancing the quality of pre-hospital care in Qatar. The high predictive accuracy of the employed models suggested actionable avenues for day and time-specific resource planning and patient triaging, thereby having potential to contribute to pre-hospital quality, safety, and value improvement. These findings pave the way for more nuanced, data-driven quality improvement interventions with significant implications for future operational strategies. [ABSTRACT FROM AUTHOR]

Background: Neurodegenerative diseases, such as Parkinson's disease (PD), necessitate frequent clinical visits and monitoring to identify changes in motor symptoms and provide appropriate care. By applying machine learning techniques to video data, automated video analysis has emerged as a promising approach to track and analyze motor symptoms, which could facilitate more timely intervention. However, existing solutions often rely on specialized equipment and recording procedures, which limits their usability in unstructured settings like the home. In this study, we developed a method to detect PD symptoms from unstructured videos of clinical assessments, without the need for specialized equipment or recording procedures. Methods: Twenty-eight individuals with Parkinson's disease completed a video-recorded motor examination that included the finger-to-nose and hand pronation-supination tasks. Clinical staff provided ground truth scores for the level of Parkinsonian symptoms present. For each video, we used a pre-existing model called PIXIE to measure the location of several joints on the person's body and quantify how they were moving. Features derived from the joint angles and trajectories, designed to be robust to recording angle, were then used to train two types of machine-learning classifiers (random forests and support vector machines) to detect the presence of PD symptoms. Results: The support vector machine trained on the finger-to-nose task had an F1 score of 0.93 while the random forest trained on the same task yielded an F1 score of 0.85. The support vector machine and random forest trained on the hand pronation-supination task had F1 scores of 0.20 and 0.33, respectively. Conclusion: These results demonstrate the feasibility of developing video analysis tools to track motor symptoms across variable perspectives. These tools do not work equally well for all tasks, however. This technology has the potential to overcome barriers to access for many individuals with degenerative neurological diseases like PD, providing them with a more convenient and timely method to monitor symptom progression, without requiring a structured video recording procedure. Ultimately, more frequent and objective home assessments of motor function could enable more precise telehealth optimization of interventions to improve clinical outcomes inside and outside of the clinic. [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]

Petrographic prediction is crucial in identifying target areas and understanding reservoir lithology in oil and gas exploration. Traditional logging methods often rely on manual interpretation and experiential judgment, which can introduce subjectivity and constraints due to data quality and geological variability. To enhance the precision and efficacy of lithology prediction, this study employed a Savitzky–Golay filter with a symmetric window for anomaly data processing, coupled with a residual temporal convolutional network (ResTCN) model tasked with completing missing logging data segments. A comparative analysis against the support vector regression and random forest regression model revealed that the ResTCN achieves the smallest MAE, at 0.030, and the highest coefficient of determination, at 0.716, which are indicative of its proximity to the ground truth. These methodologies significantly enhance the quality of the training data. Subsequently, a Transformer–long short-term memory (T-LS) model was applied to identify and classify the lithology of unexplored wells. The input layer of the Transformer model follows an embedding-like principle for data preprocessing, while the encoding block encompasses multi-head attention, Add & Norm, and feedforward components, integrating the multi-head attention mechanism. The output layer interfaces with the LSTM layer through dropout. A performance evaluation of the T-LS model against established rocky prediction techniques such as logistic regression, k-nearest neighbor, and random forest demonstrated its superior identification and classification capabilities. Specifically, the T-LS model achieved a precision of 0.88 and a recall of 0.89 across nine distinct lithology features. A Shapley analysis of the T-LS model underscored the utility of amalgamating multiple logging data sources for lithology classification predictions. This advancement partially addresses the challenges associated with imprecise predictions and limited generalization abilities inherent in traditional machine learning and deep learning models applied to lithology identification, and it also helps to optimize oil and gas exploration and development strategies and improve the efficiency of resource extraction. [ABSTRACT FROM AUTHOR]

Despite medical advancements in recent years, cardiovascular diseases (CVDs) remain a major factor in rising mortality rates, challenging predictions despite extensive expertise. The healthcare sector is poised to benefit significantly from harnessing massive data and the insights we can derive from it, underscoring the importance of integrating machine learning (ML) to improve CVD prevention strategies. In this study, we addressed the major issue of class imbalance in the Behavioral Risk Factor Surveillance System (BRFSS) 2021 heart disease dataset, including personal lifestyle factors, by exploring several resampling techniques, such as the Synthetic Minority Oversampling Technique (SMOTE), Adaptive Synthetic Sampling (ADASYN), SMOTE-Tomek, and SMOTE-Edited Nearest Neighbor (SMOTE-ENN). Subsequently, we trained, tested, and evaluated multiple classifiers, including logistic regression (LR), decision trees (DTs), random forest (RF), gradient boosting (GB), XGBoost (XGB), CatBoost, and artificial neural networks (ANNs), comparing their performance with a primary focus on maximizing sensitivity for CVD risk prediction. Based on our findings, the hybrid resampling techniques outperformed the alternative sampling techniques, and our proposed implementation includes SMOTE-ENN coupled with CatBoost optimized through Optuna, achieving a remarkable 88% rate for recall and 82% for the area under the receiver operating characteristic (ROC) curve (AUC) metric. [ABSTRACT FROM AUTHOR]

Predictive models of psychotic symptoms could improve ecological momentary interventions by dynamically providing help when it is needed. Wearable sensors measuring autonomic arousal constitute a feasible base for predictive models since they passively collect physiological data linked to the onset of psychotic experiences. To explore this potential, we investigated whether changes in autonomic arousal predict the onset of hallucination spectrum experiences (HSE) and paranoia in individuals with an increased likelihood of experiencing psychotic symptoms. For 24 h of ambulatory assessment, 62 participants wore electrodermal activity and heart rate sensors and were provided with an Android smartphone to answer questions about their HSE-, and paranoia-levels every 20 min. We calculated random forests to detect the onset of HSEs and paranoia. The generalizability of our models was tested using leave-one-assessment-out and leave-one-person-out cross-validation. Leave-one-assessment-out models that relied on physiological data and participant ID yielded balanced accuracy scores of 80 % for HSE and 66 % for paranoia. Adding baseline information about lifetime experiences of psychotic symptoms increased balanced accuracy to 82 % (HSE) and 70 % (paranoia). Leave-one-person-out models yielded lower balanced accuracy scores (51 % to 58 %). Using passively collectible variables to predict the onset of psychotic experiences is possible and prediction models improve with additional information about lifetime experiences of psychotic symptoms. Generalizing to new individuals showed poor performance, so including personal data from a recipient may be necessary for symptom prediction. Completely individualized prediction models built solely with the data of the person to be predicted might increase accuracy further. [ABSTRACT FROM AUTHOR]

The precise determination of minimum miscible pressure is of great importance for CO2 enhanced oil recovery and storage as it directly influences the efficiency of pore-scale oil displacement and CO2 trapping. In this study, an interpretable machine learning framework is developed, enabling the reliable evaluation of nano-confined minimum miscible pressure. Four machine learning algorithms (Random Forest, Multi-layer Perceptron, Support Vector Regression, and eXtreme Gradient Boosting) are employed to accurately predict the nanoconfined minimum miscible pressure of a CO2-oil system. The results demonstrate that, excluding support vector regression, the determination coefficients for all models surpass 94%, signifying the robust predictive performance of our model. Subsequently, Shapley Additive exPlanations is used to analyze the feature importance ranking and the impact of each input feature on minimum miscible pressure in these models. Based on the interpretation results, our multi-layer perceptron model is superior in mining the inputoutput relationship and reflecting the petrophysical laws, rendering it highly suitable for predicting the minimum miscible pressure while considering nano-confinement. In addition, it is found that pore size significantly influences minimum miscible pressure prediction and that minimum miscible pressure decreases with decreasing pore size when the pore size is =75 nm. Single-factor sensitivity analysis is applied to validate the trend patterns between input features and minimum miscible pressure in the multi-layer perceptron model. [ABSTRACT FROM AUTHOR]

The research conducted focused on the capabilities of various non-linear and machine learning (ML) models in estimating the higher heating value (HHV) of biomass using proximate analysis data as inputs. The research was carried out to identify the most appropriate model for the estimation of HHV, which was determined by a statistical analysis of the modeling error. In this sense, artificial neural networks (ANNs), support vector machine (SVM), random forest regression (RFR), and higher-degree polynomial models were compared. After statistical analysis of the modeling error, the ANN model was found to be the most suitable for estimating the HHV biomass and showed the highest specific regression coefficient, with an R2 of 0.92. SVM (R2 = 0.81), RFR, and polynomial models (R2 = 0.84), on the other hand, also exhibit a high degree of estimation, albeit with somewhat larger modelling errors. The study conducted suggests that ANN models are best suited for the non-linear modeling of HHV of biomass, as they can generalize and search for links between input and output data that are more robust but also more complex in structure. [ABSTRACT FROM AUTHOR]

This study focuses on the prediction of concrete cover separation (CCS) in reinforced concrete beams strengthened by fiber-reinforced polymer (FRP) in flexure. First, machine learning models were constructed based on linear regression, support vector regression, BP neural networks, decision trees, random forests, and XGBoost algorithms. Secondly, the most suitable model for predicting CCS was identified based on the evaluation metrics and compared with the codes and the researcher's model. Finally, a parametric study based on SHapley Additive exPlanations (SHAP) was carried out, and the following conclusions were obtained: XGBoost is best-suited for the prediction of CCS and codes, and researchers' model accuracy needs to be improved and suffers from over or conservative estimation. The contributions of the concrete to the shear force and the yield strength of the reinforcement are the most important parameters for the CCS, where the shear force at the onset of CCS is approximately proportional to the contribution of the concrete to the shear force and approximately inversely proportional to the yield strength of the reinforcement. [ABSTRACT FROM AUTHOR]

Invasive noxious weed species (INWS) are typical poisonous plants and forbs that are considered an increasing threat to the native alpine grassland ecosystems in the Qinghai–Tibetan Plateau (QTP). Accurate knowledge of the continuous cover of INWS across complex alpine grassland ecosystems over a large scale is required for their control and management. However, the cooccurrence of INWS and native grass species results in highly heterogeneous grass communities and generates mixed pixels detected by remote sensors, which causes uncertainty in classification. The continuous coverage of INWS at the pixel level has not yet been achieved. In this study, objective 1 was to test the capability of Senginel-2 imagery at estimating continuous INWS cover across complex alpine grasslands over a large scale and objective 2 was to assess the performance of the state-of-the-art convolutional neural network-based regression (CNNR) model in estimating continuous INWS cover. Therefore, a novel CNNR model and a random forest regression (RFR) model were evaluated for estimating INWS continuous cover using Sentinel-2 imagery. INWS continuous cover was estimated directly from Sentinel-2 imagery with an R2 ranging from 0.88 to 0.93 using the CNNR model. The RFR model combined with multiple features had a comparable accuracy, which was slightly lower than that of the CNNR model, with an R2 of approximately 0.85. Twelve green band-, red-edge band-, and near-infrared band-related features had important contributions to the RFR model. Our results demonstrate that the CNNR model performs well when estimating INWS continuous cover directly from Sentinel-2 imagery, and the RFR model combined with multiple features derived from the Sentinel-2 imager can also be used for INWS continuous cover mapping. Sentinel-2 imagery is suitable for mapping continuous INWS cover across complex alpine grasslands over a large scale. Our research provides information for the advanced mapping of the continuous cover of invasive species across complex grassland ecosystems or, more widely, terrestrial ecosystems over large spatial areas using remote sensors such as Sentinel-2. [ABSTRACT FROM AUTHOR]

Powdery mildew significantly impacts the yield of natural rubber by being one of the predominant diseases that affect rubber trees. Accurate, non-destructive recognition of powdery mildew in the early stage is essential for the cultivation management of rubber trees. The objective of this study is to establish a technique for the early detection of powdery mildew in rubber trees by combining spectral and physicochemical parameter features. At three field experiment sites and in the laboratory, a spectroradiometer and a hand-held optical leaf-clip meter were utilized, respectively, to measure the hyperspectral reflectance data (350–2500 nm) and physicochemical parameter data of both healthy and early-stage powdery-mildew-infected leaves. Initially, vegetation indices were extracted from hyperspectral reflectance data, and wavelet energy coefficients were obtained through continuous wavelet transform (CWT). Subsequently, significant vegetation indices (VIs) were selected using the ReliefF algorithm, and the optimal wavelengths (OWs) were chosen via competitive adaptive reweighted sampling. Principal component analysis was used for the dimensionality reduction of significant wavelet energy coefficients, resulting in wavelet features (WFs). To evaluate the detection capability of the aforementioned features, the three spectral features extracted above, along with their combinations with physicochemical parameter features (PFs) (VIs + PFs, OWs + PFs, WFs + PFs), were used to construct six classes of features. In turn, these features were input into support vector machine (SVM), random forest (RF), and logistic regression (LR), respectively, to build early detection models for powdery mildew in rubber trees. The results revealed that models based on WFs perform well, markedly outperforming those constructed using VIs and OWs as inputs. Moreover, models incorporating combined features surpass those relying on single features, with an overall accuracy (OA) improvement of over 1.9% and an increase in F1-Score of over 0.012. The model that combines WFs and PFs shows superior performance over all the other models, achieving OAs of 94.3%, 90.6%, and 93.4%, and F1-Scores of 0.952, 0.917, and 0.941 on SVM, RF, and LR, respectively. Compared to using WFs alone, the OAs improved by 1.9%, 2.8%, and 1.9%, and the F1-Scores increased by 0.017, 0.017, and 0.016, respectively. This study showcases the viability of early detection of powdery mildew in rubber trees. [ABSTRACT FROM AUTHOR]

Quaking aspen is an important deciduous tree species across interior western U.S. forests. Existing maps of aspen distribution are based on Landsat imagery and often miss small stands (<0.09 ha or 30 m2), which rapidly regrow when managed or following disturbance. In this study, we present methods for deriving a new regional map of aspen forests using one year of Sentinel-1 (S1) and Sentinel-2 (S2) imagery in Google Earth Engine. Using observed annual phenology of aspen across the Southern Rockies and leveraging the frequent temporal resolution of S1 and S2, ecologically relevant seasonal imagery composites were developed. We derived spectral indices and radar textural features targeting the canopy structure, moisture, and chlorophyll content. Using spatial block cross-validation and Random Forests, we assessed the accuracy of different scenarios and selected the best-performing set of features for classification. Comparisons were then made with existing landcover products across the study region. The resulting map improves on existing products in both accuracy (0.93 average F1-score) and detection of smaller forest patches. These methods enable accurate mapping at spatial and temporal scales relevant to forest management for one of the most widely distributed tree species in North America. [ABSTRACT FROM AUTHOR]

Obtaining accurate and real-time spatial distribution information regarding crops is critical for enabling effective smart agricultural management. In this study, innovative decision fusion strategies, including Enhanced Overall Accuracy Index (E-OAI) voting and the Overall Accuracy Index-based Majority Voting (OAI-MV), were introduced to optimize the use of diverse remote sensing data and various classifiers, thereby improving the accuracy of crop/vegetation identification. These strategies were utilized to integrate crop/vegetation classification outcomes from distinct feature sets (including Gaofen-6 reflectance, Sentinel-2 time series of vegetation indices, Sentinel-2 time series of biophysical variables, Sentinel-1 time series of backscatter coefficients, and their combinations) using distinct classifiers (Random Forests (RFs), Support Vector Machines (SVMs), Maximum Likelihood (ML), and U-Net), taking two grain-producing areas (Site #1 and Site #2) in Haixi Prefecture, Qinghai Province, China, as the research area. The results indicate that employing U-Net on feature-combined sets yielded the highest overall accuracy (OA) of 81.23% and 91.49% for Site #1 and Site #2, respectively, in the single classifier experiments. The E-OAI strategy, compared to the original OAI strategy, boosted the OA by 0.17% to 6.28%. Furthermore, the OAI-MV strategy achieved the highest OA of 86.02% and 95.67% for the respective study sites. This study highlights the distinct strengths of various remote sensing features and classifiers in discerning different crop and vegetation types. Additionally, the proposed OAI-MV and E-OAI strategies effectively harness the benefits of diverse classifiers and multisource remote sensing features, significantly enhancing the accuracy of crop/vegetation classification. [ABSTRACT FROM AUTHOR]

Reliable and up-to-date training reference samples are imperative for land cover (LC) classification. However, such training datasets are not always available in practice. The sample migration method has shown remarkable success in addressing this challenge in recent years. This work investigated the application of Sentinel-1 (S1) and Sentinel-2 (S2) data in training sample migration. In addition, the impact of various spectral bands and polarizations on the accuracy of the migrated training samples was also assessed. Subsequently, combined S1 and S2 images were classified using the Support Vector Machines (SVM) and Random Forest (RF) classifiers to produce annual LC maps from 2017 to 2021. The results showed a higher accuracy (98.25%) in training sample migrations using both images in comparison to using S1 (87.68%) and S2 (96.82%) data independently. Among the LC classes, the highest accuracy in migrated training samples was found for water, built-up, bare land, grassland, cropland, and wetland. Inquiries on the efficiency of different spectral bands and polarization used in training sample migration showed that bands 4 and 8 and VV polarization in the water class were more important, while for the wetland class, bands 5, 6, 7, 8, and 8A together with VV polarization showed superior performance. The results showed that the RF classifier provided better performance than the SVM (higher overall, producer, and user accuracy). Overall, our findings suggested that shared use of S1 and S2 data can be used as a suitable means for producing up-to-date and high-quality training samples. [ABSTRACT FROM AUTHOR]

Soil organic carbon (SOC) measurements are an indicator of soil health and an important parameter for the study of land-atmosphere carbon fluxes. Field sampling provides precise measurements at the sample location but entails high costs and cannot provide detailed maps unless the sampling density is very high. Remote sensing offers the possibility to quantify SOC over large areas in a cost-effective way. As a result, numerous studies have sought to quantify SOC using Earth observation data with a focus on inter-field or regional distributions. This study took a different angle and aimed to map the spatial distribution of SOC at the intra-field scale, since this distribution provides important insights into the biophysiochemical processes involved in the retention of SOC. Instead of solely using spectral measurements to quantify SOC, topographic and spectral features act as predictor variables. The necessary data on study fields in South-East England was acquired through a detailed SOC sampling campaign, including a LiDAR survey flight. Multi-spectral Sentinel-2 data of the study fields were acquired for the exact day of the sampling campaign, and for an interval of 18 months before and after this date. Random Forest (RF) and Support Vector Regression (SVR) models were trained and tested on the spectral and topographical data of the fields to predict the observed SOC values. Five different sets of model predictors were assessed, by using independently and in combination, single and multidate spectral data, and topographical features for the SOC sampling points. Both, RF and SVR models performed best when trained on multi-temporal Sentinel-2 data together with topographic features, achieving validation root-mean-square errors (RMSEs) of 0.29% and 0.23% SOC, respectively. These RMSEs are competitive when compared with those found in the literature for similar models. The topographic wetness index (TWI) exhibited the highest permutation importance for virtually all models. Given that farming practices within each field are the same, this result suggests an important role of soil moisture in SOC retention. Contrary to findings in dryer climates or in studies encompassing larger areas, TWI was negatively related to SOC levels in the study fields, suggesting a different role of soil wetness in the SOC storage in climates characterized by excess rainfall and poorly drained soils. [ABSTRACT FROM AUTHOR]

Crop mapping using satellite imagery is crucial for agriculture applications. However, a fundamental challenge that hinders crop mapping progress is the scarcity of samples. The latest foundation model, Segment Anything Model (SAM), provides an opportunity to address this issue, yet few studies have been conducted in this area. This study investigated the parcel segmentation performance of SAM on commonly used medium-resolution satellite imagery (i.e., Sentinel-2 and Landsat-8) and proposed a novel automated sample generation framework based on SAM. The framework comprises three steps. First, an image optimization automatically selects high-quality images as the inputs for SAM. Then, potential samples are generated based on the masks produced by SAM. Finally, the potential samples are subsequently subjected to a sample cleaning procedure to acquire the most reliable samples. Experiments were conducted in Henan Province, China, and southern Ontario, Canada, using six proven effective classifiers. The effectiveness of our method is demonstrated through the combination of field-survey-collected samples and differently proportioned generated samples. Our results indicated that directly using SAM for parcel segmentation remains challenging, unless the parcels are large, regular in shape, and have distinct color differences from surroundings. Additionally, the proposed approach significantly improved the performance of classifiers and alleviated the sample scarcity problem. Compared to classifiers trained only by field-survey-collected samples, our method resulted in an average improvement of 16% and 78.5% in Henan and Ontario, respectively. The random forest achieved relatively good performance, with weighted-average F1 of 0.97 and 0.996 obtained using Sentinel-2 imagery in the two study areas, respectively. Our study contributes insights into solutions for sample scarcity in crop mapping and highlights the promising application of foundation models like SAM. [ABSTRACT FROM AUTHOR]

This study addresses a crucial gap in understanding the impact of urban morphologies on the canopy urban heat islands (CUHI) effect. The selection of reference stations lacks a unified standard, and their surface air temperature (SAT) sequences are also inevitably influenced by urbanization. However, synchronous observational data from relocated meteorological stations could provide high-quality sample data for studying CUHI. Utilizing remote sensing techniques, the findings of this paper revealed that the observation environment of stations after relocation exhibited remarkable representativeness, with their observation sequences accurately reflecting the local climatic background. The differences in synchronized observation sequences could characterize the CUHI intensity (CUHII). Among the various factors, land use parameters and landscape parameters played particularly significant roles. Furthermore, the fitting performance of the random forest (RF) model for both training and testing data was significantly superior to that of the linear model and support vector regression (SVR) model. Additionally, the influence of local circulation on CUHI could not be overlooked. The mechanisms by which urban morphologies affect CUHII under different circulation backgrounds deserve further investigation. [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]

Low-cost ambient sensors have been identified as a promising technology for monitoring air pollution at a high spatio-temporal resolution. However, the pollutant data captured by these cost-effective sensors are less accurate than their conventional counterparts and require careful calibration to improve their accuracy and reliability. In this paper, we propose to leverage temporal information, such as the duration of time a sensor has been deployed and the time of day the reading was taken, in order to improve the calibration of low-cost sensors. This information is readily available and has so far not been utilized in the reported literature for the calibration of cost-effective ambient gas pollutant sensors. We make use of three data sets collected by research groups around the world, who gathered the data from field-deployed low-cost CO and NO2 sensors co-located with accurate reference sensors. Our investigation shows that using the temporal information as a co-variate can significantly improve the accuracy of common machine learning-based calibration techniques, such as Random Forest and Long Short-Term Memory. [ABSTRACT FROM AUTHOR]

Red-light running (RLR) is one of the riskiest behaviors at signalized intersections. This study utilizes intersection- and corridor-level characteristics to identify variables that impact the frequency and severity of RLR violations. The severity of RLR is defined based on the time when the violations happened. That is, less severe violations are the ones that occur within 3 seconds of the signal light turning red (RLR3), while more severe violations happen between 3 and 10 seconds of the signal light turning red (RLR10). Results of the zero-inflated negative binomial model showed that an increase in intersection delay and split failure increases the frequency of both types of RLR severities. An increase in the yellow interval, cycle length, and number of lanes reduces the frequency of RLR3 but increases the frequency of RLR10. Furthermore, based on the factor importance analysis conducted through the random forest, it was shown that split failure is one of the most predictive variables for RLR3 and RLR10. The findings of this research could help transportation agencies in different geographic jurisdictions utilize the calibrated models to understand the impact of varying intersection- and corridor-based characteristics on the frequency and severity of RLR. [ABSTRACT FROM AUTHOR]

As the power source of the engine, the Fuel Pump(FP) plays a vital role in the safe operation of the aircraft. Due to the complexity of the working mechanism of Aviation Fuel Pumps (AFP) and the strong correlation between the components, the assessment model cannot reflect the health state of the FPs better, while the initial parameters in the assessment model will affect the assessment effect of the model. Therefore, this paper proposes a health status assessment model that can fully integrate monitoring data. To improve the accuracy of the model parameters, the Random Forest algorithm is used to give the feature weights to make up for the limitation of relying on expert knowledge, and the model parameters are optimized by the Covariance Matrix Adaptive Evolutionary Strategy algorithm, which achieves an accurate assessment of the state. Finally, the AFP test bed was built and the AFP was tested. Compared with other methods, the accuracy of the proposed method in this question reaches 96%, which is greatly superior to other methods and verifies the effectiveness of the proposed method. It also provides an outlook on future research directions for health state assessment. [ABSTRACT FROM AUTHOR]

Background: Patients with oropharyngeal cancer (OPC) treated with chemoradiation can experience weight loss and tumor shrinkage, altering the prescribed treatment. Treatment replanning ensures patients do not receive excessive doses to normal tissue. However, it is a time‐ and resource‐intensive process, as it takes 1 to 2 weeks to acquire a new treatment plan, and during this time, overtreatment of normal tissues could lead to increased toxicities. Currently, there are limited prognostic factors to determine which patients will require a replan. There remains an unmet need for predictive models to assist in identifying patients who could benefit from the knowledge of a replan prior to treatment. Purpose: We aimed to develop and evaluate a CT‐based radiomic model, integrating clinical and dosimetric information, to predict the need for a replan prior to treatment. Methods: A dataset of patients (n = 315) with OPC treated with chemoradiation was used for this study. The dataset was split into independent training (n = 220) and testing (n = 95) datasets. Tumor volumes and organs at risk (OARs) were contoured on planning CT images. PyRadiomics was used to compute radiomic image features (n = 1218) on the original and filtered images from each of the primary tumor, nodal volumes, and ipsilateral and contralateral parotid glands. Nine clinical features and nine dose features extracted from the OARs were collected and those significantly (p < 0.05) associated with the need for a replan in the training dataset were used in a baseline model. Random forest feature selection was applied to select the optimal radiomic features to predict replanning. Logistic regression, Naïve Bayes, support vector machine, and random forest classifiers were built using the non‐correlated selected radiomic, clinical, and dose features on the training dataset and performance was assessed in the testing dataset. The area under the curve (AUC) was used to assess the prognostic value. Results: A total of 78 patients (25%) required a replan. Smoking status, nodal stage, base of tongue subsite, and larynx mean dose were found to be significantly associated with the need for a replan in the training dataset and incorporated into the baseline model, as well as into the combined models. Five predictive radiomic features were selected (one nodal volume, one primary tumor, two ipsilateral and one contralateral parotid gland). The baseline model comprised of clinical and dose features alone achieved an AUC of 0.66 [95% CI: 0.51–0.79] in the testing dataset. The random forest classifier was the top‐performing radiomics model and achieved an AUC of 0.82 [0.75–0.89] in the training dataset and an AUC of 0.78 [0.68–0.87] in the testing dataset, which significantly outperformed the baseline model (p = 0.023, testing dataset). Conclusions: This is the first study to use radiomics from the primary tumor, nodal volumes, and parotid glands for the prediction of replanning for patients with OPC. Radiomic features augmented clinical and dose features for predicting the need for a replan in our testing dataset. Once validated, this model has the potential to assist physicians in identifying patients that may benefit from a replan, allowing for better resource allocation and reduced toxicities. [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]

High-throughput phenotyping brings new opportunities for detailed genebank accessions characterization based on image-processing techniques and data analysis using machine learning algorithms. Our work proposes to improve the characterization processes of bean and peanut accessions in the CIAT genebank through the identification of phenomic descriptors comparable to classical descriptors including methodology integration into the genebank workflow. To cope with these goals morphometrics and colorimetry traits of 14 bean and 16 forage peanut accessions were determined and compared to the classical International Board for Plant Genetic Resources (IBPGR) descriptors. Descriptors discriminating most accessions were identified using a random forest algorithm. The most-valuable classification descriptors for peanuts were 100-seed weight and days to flowering, and for beans, days to flowering and primary seed color. The combination of phenomic and classical descriptors increased the accuracy of the classification of Phaseolus and Arachis accessions. Functional diversity indices are recommended to genebank curators to evaluate phenotypic variability to identify accessions with unique traits or identify accessions that represent the greatest phenotypic variation of the species (functional agrobiodiversity collections). The artificial intelligence algorithms are capable of characterizing accessions which reduces costs generated by additional phenotyping. Even though deep analysis of data requires new skills, associating genetic, morphological and ecogeographic diversity is giving us an opportunity to establish unique functional agrobiodiversity collections with new potential traits. [ABSTRACT FROM AUTHOR]

Spectral diversity (SD) in reflectance can be used to estimate plant taxonomic diversity (TD) according to the Spectral Variation Hypothesis (SVH). However, contrasting relationships between SD and TD have been reported by different studies. Indeed, multiple factors may affect SD, including spatial and spectral scales, vegetation characteristics and the adopted SD computational method. Here, we tested the SVH over 171 plots within a large and heterogeneous forest area in North-Eastern Italy using Sentinel-2 data, aiming at identifying possible factors affecting the strength and direction of SD-TD relationship. SD was determined using 'biodivMapR' (BD) and 'rasterdiv' (RD) R packages and 38 possible combinations of SD indices, at both α (within a community) and β (among communities) levels, and computational parameters accounting for spatial and spectral scales. Information on vegetation structure was either retrieved from ground-based or LiDAR data. A Random Forest approach was used to disentangle the relationships between SD, TD and vegetation structure, and to identify the best combination of SD computational parameters. At the α-level, we found negative relationship between TD and RD SD indices, which was mainly driven by the presence of gaps within the forest canopy. As regards BD, we found that this algorithm reduced background contribution on SD and was able to differentiate major forest types (broadleaves vs conifers), but derived α-SD indices were marginally correlated with α-TD. At the β-level, we observed a statistically significant positive correlation between BD SD indices and TD (maximum r = 0.24). Finally, we found stronger correlations and R2 when SD indices were calculated using smaller computation windows and over a larger pixels extraction area. Our findings suggest that vegetation cover and structure play a major role, with respect to inter-species spectral differences, in determining α-SD, and that SD might better capture differences in species composition at the landscape-level rather than the richness of individual communities. [ABSTRACT FROM AUTHOR]

Effective winter road maintenance relies on precise road friction estimation. Machine learning (ML) models have shown significant promise in this; however, their inherent complexity makes understanding their inner workings challenging. This paper addresses this issue by conducting a comparative analysis of road friction estimation models using four ML methods, including regression tree, random forest, eXtreme Gradient Boosting (XGBoost), and support vector regression (SVR). We then employ the SHapley Additive exPlanations (SHAP) explainable artificial intelligence (AI) to enhance model interpretability. Our analysis on an Alberta dataset reveals that the XGBoost model performs best with an accuracy of 91.39%. The SHAP analysis illustrates the logical relationships between predictor features and friction within all three tree-based models, but it also uncovers inconsistencies within the SVR model, potentially attributed to insufficient feature interactions. Thus, this paper not only showcase the role of explainable AI in improving the ML interpretability of models for road friction estimation, but also provides practical insights that could improve winter road maintenance decisions. [ABSTRACT FROM AUTHOR]

Background: Identifying predictive biomarkers for allergen immunotherapy response is crucial for enhancing clinical efficacy. This study aims to identify such biomarkers in patients with allergic rhinitis (AR) undergoing subcutaneous immunotherapy (SCIT) for house dust mite allergy. Methods: The Tongji (discovery) cohort comprised 72 AR patients who completed 1‐year SCIT follow‐up. Circulating T and B cell subsets were characterized using multiplexed flow cytometry before SCIT. Serum immunoglobulin levels and combined symptom and medication score (CSMS) were assessed before and after 12‐month SCIT. Responders, exhibiting ≥30% CSMS improvement, were identified. The random forest algorithm and logistic regression analysis were used to select biomarkers and establish predictive models for SCIT efficacy in the Tongji cohort, which was validated in another Wisco cohort with 43 AR patients. Results: Positive SCIT response correlated with higher baseline CSMS, allergen‐specific IgE (sIgE)/total IgE (tIgE) ratio, and frequencies of Type 2 helper T cells, Type 2 follicular helper T (TFH2) cells, and CD23+ nonswitched memory B (BNSM) and switched memory B (BSM) cells, as well as lower follicular regulatory T (TFR) cell frequency and TFR/TFH2 cell ratio. The random forest algorithm identified sIgE/tIgE ratio, TFR/TFH2 cell ratio, and BNSM frequency as the key biomarkers discriminating responders from nonresponders in the Tongji cohort. Logistic regression analysis confirmed the predictive value of a combination model, including sIgE/tIgE ratio, TFR/TFH2 cell ratio, and CD23+ BSM frequency (AUC = 0.899 in Tongji; validated AUC = 0.893 in Wisco). Conclusions: A T‐ and B‐cell signature combination efficiently identified SCIT responders before treatment, enabling personalized approaches for AR patients. [ABSTRACT FROM AUTHOR]

[Display omitted] • CC16 is an anti-inflammatory, immunomodulatory protein expressed in respiratory club cells. • Severe abdominal obesity and arterial hypertension robustly decrease serum CC16. • ACEi/ARBs, uricosurics and chronic heart failure robustly increase serum CC16. • Effects might be mediated by adipose tissue inflammation as well as RAAS and uric acid disturbance. • Findings indicate a complex interplay of the metabolic, respiratory and cardiovascular system. Clara cell 16-kDa protein (CC16) is an anti-inflammatory, immunomodulatory secreted pulmonary protein with reduced serum concentrations in obesity according to recent data. Studies focused solely on bodyweight, which does not properly reflect obesity-associated implications of the metabolic and reno-cardio-vascular system. The purpose of this study was therefore to examine CC16 in a broad physiological context considering cardio-metabolic comorbidities of primary pulmonary diseases. CC16 was quantified in serum samples in a subset of the FoCus (N = 497) and two weight loss intervention cohorts (N = 99) using ELISA. Correlation and general linear regression analyses were applied to assess CC16 effects of lifestyle, gut microbiota, disease occurrence and treatment strategies. Importance and intercorrelation of determinants were validated using random forest algorithms. CC16 A38G gene mutation, smoking and low microbial diversity significantly decreased CC16. Pre-menopausal female displayed lower CC16 compared to post-menopausal female and male participants. Biological age and uricosuric medications increased CC16 (all p < 0.01). Adjusted linear regression revealed CC16 lowering effects of high waist-to-hip ratio (est. −11.19 [−19.4; −2.97], p = 7.99 × 10−3), severe obesity (est. −2.58 [−4.33; −0.82], p = 4.14 × 10−3) and hypertension (est. −4.31 [−7.5; −1.12], p = 8.48 × 10−3). ACEi/ARB medication (p = 2.5 × 10−2) and chronic heart failure (est. 4.69 [1.37; 8.02], p = 5.91 × 10−3) presented increasing effects on CC16. Mild associations of CC16 were observed with blood pressure, HOMA-IR and NT-proBNP, but not manifest hyperlipidemia, type 2 diabetes, diet quality and dietary weight loss intervention. A role of metabolic and cardiovascular abnormalities in the regulation of CC16 and its modifiability by behavioral and pharmacological interventions is indicated. Alterations by ACEi/ARB and uricosurics could point towards regulatory axes comprising the renin-angiotensin-aldosterone system and purine metabolism. Findings altogether strengthen the importance of interactions among metabolism, heart and lungs. [ABSTRACT FROM AUTHOR]

Software effort estimation is a vital process in the software industry for successfully administering 5Ds of the software development life cycle (SDLC). The 5Ds stand for demand, development, direction, deployment, and designated cost of the software. Software development effort estimation (SDEE) is an effort prediction mechanism to calculate the effort for the development of the software product in order to minimize the challenges in the software field. Academics and practitioners are striving to identify which machine learning estimation technique yields more accurate results based on evaluation metrics, datasets, and other pertinent aspects. The feature selection techniques impact accuracy by selecting the main and relevant features in the dataset and eliminating the redundant and irrelevant features in the dataset. To achieve accurate estimations, the paper utilizes feature selection algorithms, along with various machine learning techniques, which predict the desired effort and the performance of the model has been measured in terms of prediction accuracy, R2 value, relative error, and mean absolute error. The datasets China and Maxwell are trained with the relevant features by applying feature selection algorithms, and estimation techniques are applied to predict the effort. The performance is compared with the regression models and feature selection techniques utilized by many authors previously. The result of the proposed methodology significantly gives the best performance with the combination of feature selection and estimation models than all regression models when applied alone, to both datasets. From the results, it is perceptible that random forest is performing well with the feature selection techniques and obtains the highest prediction accuracy of 99.33% with the China and 89.47% with the Maxwell datasets. [ABSTRACT FROM AUTHOR]

• Our random forest quantitative EEG (qEEG) classifier could classify delirium versus no delirium with an AUC of 0.76. • The most important delirium classification features were: theta peak frequency, relative alpha power and theta autocorrelation. • There was no evidence that qEEG features differed between postoperative and non-postoperative delirium. This exploratory study examined quantitative electroencephalography (qEEG) changes in delirium and the use of qEEG features to distinguish postoperative from non-postoperative delirium. This project was part of the DeltaStudy, a cross-sectional, multicenter study in Intensive Care Units (ICUs) and non-ICU wards. Single-channel (Fp2-Pz) four-minutes resting-state EEG was analyzed in 456 patients. After calculating 98 qEEG features per epoch, random forest (RF) classification was used to analyze qEEG changes in delirium and to test whether postoperative and non-postoperative delirium could be distinguished. An area under the receiver operating characteristic curve (AUC) of 0.76 (95% Confidence Interval (CI) 0.71–0.80) was found when classifying delirium with a sensitivity of 0.77 and a specificity of 0.63 at the optimal operating point. The classification of postoperative versus non-postoperative delirium resulted in an AUC of 0.50 (95%CI 0.38–0.61). RF classification was able to discriminate delirium from no delirium with reasonable accuracy, while also identifying new delirium qEEG markers like autocorrelation and theta peak frequency. RF classification could not distinguish postoperative from non-postoperative delirium. Single-channel EEG differentiates between delirium and no delirium with reasonable accuracy. We found no distinct EEG profile for postoperative delirium, which may suggest that delirium is one entity, whether it develops postoperatively or not. [ABSTRACT FROM AUTHOR]

Cloud computing has revolutionized the way IT industries work. Most modern‐day companies rely on cloud services to accomplish their day‐to‐day tasks. From hosting websites to developing platforms and storing resources, cloud computing has tremendous use in the modern information technology industry. Although an emerging technique, it has many security challenges. In structured query language injection attacks, the attacker modifies some parts of the user query to still sensitive user information. This type of attack is challenging to detect and prevent. In this article, we have reviewed 65 research articles that address the issue of its prevention and detection in cloud and Traditional Networks, of which 11 research articles are related to general cloud attacks, and the rest of the 54 research articles are specifically on web security. Our result shows that Random Forest has an accuracy of 99.8% and a Precision rate of 99.9%, and the worst‐performing model is Multi‐Layer Perceptron (MLP) in the SQLIA Model. For recall value, Random Forest performs best while TensorFlow Linear Classifier performs worst. F1 score is best in Random Forest, while MLP is the most diminutive performer. [ABSTRACT FROM AUTHOR]

The compressive strength (CS) of crumb rubber concrete (CRC) can be improved through a chemical pretreatment involving immersion of the crumb rubber particles in a NaOH solution. Despite the potential benefits of this treatment, accurately estimating the CS value of NaOH-pretreated CRC remains challenging. To address this issue, a comprehensive database encompassing 118 entries on the fundamental mixtures of CRC along with NaOH concentration and pretreatment duration has been meticulously compiled for machine learning analysis. The random forest (RF) algorithm is employed to predict the 28-day CS value of NaOH-pretreated CRC. The model hyperparameters are optimized using a random search technique with 10-fold cross-validation. The findings reveal that the optimized RF attains acceptable predictive performance, yielding RMSE, MAE, and R2 values of 3.83 MPa, 2.84 MPa, and 0.85, respectively, on the testing dataset. Additionally, the model is interpreted using multiple techniques, including permutation importance, RF model-based feature importance, and Shapley additive explanation from global or local perspectives. The feature importance analyses consistently highlight the crucial role of crumb rubber content in determining the 28-day CS value of NaOH-pretreated CRC, and the influence of NaOH concentration and pretreatment time appear relatively inconsequential compared to features associated with the CRC mixture. This research contributes to a deeper understanding and better mixture design of CS for NaOH-pretreated CRC. [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]

As distributed and multi-organization Machine Learning emerges, new challenges must be solved, such as diverse and low-quality data or real-time delivery. In this paper, we use a distributed learning environment to analyze the relationship between block size, parallelism, and predictor quality. Specifically, the goal is to find the optimum block size and the best heuristic to create distributed Ensembles. We evaluated three different heuristics and five block sizes on four publicly available datasets. Results show that using fewer but better base models matches or outperforms a standard Random Forest, and that 32 MB is the best block size. [ABSTRACT FROM AUTHOR]

Cognitive deficits are a core symptom of schizophrenia, but research on their neural underpinnings has been challenged by the heterogeneity in deficits' severity among patients. Here, we address this issue by combining logistic regression and random forest to classify two neuropsychological profiles of patients with high (HighCog) and low (LowCog) cognitive performance in two independent samples. We based our analysis on the cortical features grey matter volume (VOL), cortical thickness (CT), and mean curvature (MC) of N = 57 patients (discovery sample) and validated the classification in an independent sample (N = 52). We investigated which cortical feature would yield the best classification results and expected that the 10 most important features would include frontal and temporal brain regions. The model based on MC had the best performance with area under the curve (AUC) values of 76% and 73%, and identified fronto-temporal and occipital brain regions as the most important features for the classification. Moreover, subsequent comparison analyses could reveal significant differences in MC of single brain regions between the two cognitive profiles. The present study suggests MC as a promising neuroanatomical parameter for characterizing schizophrenia cognitive subtypes. [ABSTRACT FROM AUTHOR]

Aim: In salt‐affected environments, salinity shapes ecosystem functions and species composition. Apart from salinity, however, we know little about how soil chemical factors affect plant species. We hypothesized that specific ions, most of which contribute to salinity, co‐determine plant niche differentiation. We asked if the importance of ions differs for species with (halophytes) and without (associated species) physiological adaptations to saline soils. Location: Carpatho‐Pannonian region (Central and Eastern Europe). Time period: 2005–2021. Major taxa studied: Vascular plants. Methods: We recorded species occurrences and collected soil samples in 433 plots in saline habitats. We measured pH, salinity (electrical conductivity), and concentrations of Ca2+, K+, Mg2+, Na+, SO42− Cl−, CO32− and mineral nitrogen (mN) and calculated the sodium adsorption ratio (SAR). For 88 species, we fitted response curves with Huisman–Olff–Fresco (HOF) models. To study ions' effects on species composition and ions' variance, we compared unconstrained and constrained ordinations and performed a principal component analysis. We used random forests to analyse the importance of ions for individual species and created two‐dimensional species niche plots for key ions. Results: Ion concentration niches varied among species and did not necessarily correspond to soil salinity or alkalinity. We frequently observed monotonic, sigmoidal model responses, while skewed unimodal responses were rare. Ions explained a considerable proportion of species compositional variation. Particularly, Na+, SO42−, Cl−, and CO32− contributed to the ions' variance. Na+, followed by SO42−, Cl−, CO32−, Ca2+, Mg2+, and mN, was most important for the occurrence of individual species. Compared to associated species, Na+, SO42−, and mN were significantly less important for halophytes, whereas Cl− and CO32− played a significant role. Main conclusions: We show that ion composition co‐determines niche differentiation in saline soils, suggesting evolved physiological adaptations in halophytes. Our study calls for incorporating high‐resolution data on soil ion composition in ecological research. [ABSTRACT FROM AUTHOR]

This study examines the feature space of seismic waveforms often used in machine learning applications for seismic event detection and classification problems. Our investigation centres on the southern Alaska region, where the seismic record captures diverse seismic activity, notably from the calving of marine-terminating glaciers and tectonic earthquakes along active plate boundaries. While the automated discrimination of earthquakes and glacier quakes is our nominal goal, this data set provides an outstanding opportunity to explore the general feature space of regional seismic phases. That objective has applicability beyond ice quakes and our geographic region of study. We make a noteworthy discovery that features rooted in the spectral content of seismic waveforms consistently outperform statistical and temporal features. Spectral features demonstrate robust performance, exhibiting resilience to class imbalance while being minimally impacted by factors such as epicentral distance and signal-to-noise ratio. We also conduct experiments on the transferability of the model and find that transferability primarily depends on the appearance of the waveforms. Finally, we analyse misclassified events and find examples that are identified incorrectly in the original regional catalogue. [ABSTRACT FROM AUTHOR]

Aims: To investigate high‐risk sociodemographic and environmental determinants of health (SEDH) potentially associated with adult obesity in counties in the United States using machine‐learning techniques. Materials and Methods: We performed a cross‐sectional analysis of county‐level adult obesity prevalence (body mass index ≥30 kg/m2) in the United States using data from the Diabetes Surveillance System 2017. We harvested 49 county‐level SEDH factors that were used in a classification and regression trees (CART) model to identify county‐level clusters. The CART model was validated using a 'hold‐out' set of counties and variable importance was evaluated using Random Forest. Results: Overall, we analysed 2752 counties in the United States, identifying a national median (interquartile range) obesity prevalence of 34.1% (30.2%, 37.7%). The CART method identified 11 clusters with a 60.8% relative increase in prevalence across the spectrum. Additionally, seven key SEDH variables were identified by CART to guide the categorization of clusters, including Physically Inactive (%), Diabetes (%), Severe Housing Problems (%), Food Insecurity (%), Uninsured (%), Population over 65 years (%) and Non‐Hispanic Black (%). Conclusion: There is significant county‐level geographical variation in obesity prevalence in the United States, which can in part be explained by complex SEDH factors. The use of machine‐learning techniques to analyse these factors can provide valuable insights into the importance of these upstream determinants of obesity and, therefore, aid in the development of geo‐specific strategic interventions and optimize resource allocation to help battle the obesity pandemic. [ABSTRACT FROM AUTHOR]

Background: A lack of consensus exists in linking demographic, behavioral, and cognitive characteristics to biological stages of dementia, defined by the ATN (amyloid, tau, neurodegeneration) classification incorporating amyloid, tau, and neuronal injury biomarkers. Methods: Using a random forest classifier we investigated whether 27 demographic, behavioral, and cognitive characteristics allowed distinction between ATN‐defined groups with the same cognitive profile. This was done separately for three cognitively unimpaired (CU) (112 A‐T‐N‐; 46 A+T+N+/−; 65 A‐T+/‐N+/−) and three mild cognitive impairment (MCI) (128 A‐T‐N‐; 223 A+T+N+/−; 94 A‐T+/‐N+/−) subgroups. Results: Classification‐balanced accuracy reached 39% for the CU and 52% for the MCI subgroups. Logical Delayed Recall (explaining 16% of the variance), followed by the Alzheimer's Disease Assessment Scale 13 (14%) and Everyday Cognition Informant (10%), were the most relevant characteristics for classification of the MCI subgroups. Race and ethnicity, marital status, and Everyday Cognition Patient were not relevant (0%). Conclusions: The demographic, behavioral, and cognitive measures used in our model were not informative in differentiating ATN‐defined CU profiles. Measures of delayed memory, general cognition, and activities of daily living were the most informative in differentiating ATN‐defined MCI profiles; however, these measures alone were not sufficient to reach high classification performance. [ABSTRACT FROM AUTHOR]

Cyber-attacks using malicious uniform resource locator (URL) propagation are very common and serious. Statistics indicate that there is a need to research and apply techniques and methods for identifying and preventing malicious URLs. The main objective of this research is to train machine learning models on selected dataset to predict phishing websites based on URL-related features. The accuracy level of each model is measured and compared. Finally, the best performing model will be used to develop a web application that provide internet users with an easy way to check suspicious URLs. We have used five different machine learning models to classify URLs as legitimate or phishing, these models are eXtreme Gradient Boosting (XGBoost), k-nearest neighbors (KNN), support vector machine (SVM), Decision Tree, and Random Forest. Finally, we used Voting Classifier to combine the work of Random Forest (RF) algorithm with other two models, Gaussian Naive Bayes, and Logistic Regression, to check if we can increase the accuracy of RF as suggested in the literature, but we found that the accuracy of RF alone was higher than the accuracy of the combined models. This project can be implemented as a browser extension or mobile application to classify suspicious URLs to legitimate or phishing with the use of the saved model. [ABSTRACT FROM AUTHOR]

Self‐direction has become an important skill in the 21st century. To cultivate learners with a high level of self‐direction, it is necessary to diagnose their self‐directed learning (SDL) ability. This study diagnosed and predicted learners' SDL ability based on their actual SDL behaviours. The study was performed in a self‐directed 3D design class lasting 90 minutes. A total of 193 middle school students participated in the study. The results of the Pearson correlation analysis (p < 0.001) showed that the reported perception of SDL ability was significantly correlated with SDL behaviours. The results of the hierarchical multiple linear regression analysis showed that the SDL behaviours explained 84.9% of the variance in SDL ability (adjusted R2 = 0.849, p < 0.001). Therefore, SDL behaviours had significant predictive effects on the reported perception of SDL ability. Moreover, based on the random forest algorithm, the study built an SDL ability prediction model with high performance (accuracy = 0.83, precision = 0.82, recall = 0.84) using SDL behaviours as features. The study provides evidence for the design of effective strategies to enhance SDL ability and promote SDL behaviours.Practitioner notesWhat is already known about this topicTo cultivate learners with a high level of self‐direction, it is necessary to diagnose their self‐directed learning (SDL) ability.SDL is a combination of internal personal attributes and external autonomous behaviours.Few studies have focused on diagnosing SDL ability based on learners' external SDL behaviours occurring during the learning process.What this paper addsThe reported perception of SDL ability was significantly correlated with SDL behaviours.SDL behaviours had significant predictive effects on the reported perception of SDL ability.Based on the random forest algorithm, the study built an SDL ability prediction model with high performance using SDL behaviours as features.Implications for practice and/or policyThe findings indicate that instructors could design effective strategies to promote SDL behaviours for the purpose of enhancing learners' SDL ability.The method and process of building an SDL ability prediction model might provide a reference for related research on ability prediction with behaviours. [ABSTRACT FROM AUTHOR]

Differential item functioning (DIF) is a common challenge when examining latent traits in large scale surveys. In recent work, methods from the field of machine learning such as model-based recursive partitioning have been proposed to identify subgroups with DIF when little theoretical guidance and many potential subgroups are available. On this basis, we propose and compare recursive partitioning techniques for detecting DIF with a focus on measurement models with multiple latent variables and ordinal response data. We implement tree-based approaches for identifying subgroups that contribute to DIF in multidimensional latent variable modeling and propose a robust, yet scalable extension, inspired by random forests. The proposed techniques are applied and compared with simulations. We show that the proposed methods are able to efficiently detect DIF and allow to extract decision rules that lead to subgroups with well fitting models. [ABSTRACT FROM AUTHOR]

Background: Non‐anemic thalassemia trait (TT) accounted for a high proportion of TT cases in South China. Objective: To use artificial intelligence (AI) analysis of erythrocyte morphology and machine learning (ML) to identify TT gene carriers in a non‐anemic population. Methods: Digital morphological data from 76 TT gene carriers and 97 controls were collected. The AI technology‐based Mindray MC‐100i was used to quantitatively analyze the percentage of abnormal erythrocytes. Further, ML was used to construct a prediction model. Results: Non‐anemic TT carriers accounted for over 60% of the TT cases. Random Forest was selected as the prediction model and named TT@Normal. The TT@Normal algorithm showed outstanding performance in the training, validation, and external validation sets and could efficiently identify TT carriers in the non‐anemic population. The top three weights in the TT@Normal model were the target cells, microcytes, and teardrop cells. Elevated percentages of abnormal erythrocytes should raise a strong suspicion of being a TT gene carrier. TT@Normal could be promoted and used as a visualization and sharing tool. It is accessible through a URL link and can be used by medical staff online to predict the possibility of TT gene carriage in a non‐anemic population. Conclusions: The ML‐based model TT@Normal could efficiently identify TT carriers in non‐anemic people. Elevated percentages of target cells, microcytes, and teardrop cells should raise a strong suspicion of being a TT gene carrier. [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]

To predict renal tumour growth patterns in von Hippel–Lindau syndrome by utilising radiomic features to assist in developing personalised surveillance plans leading to better patient outcomes. The study evaluated 78 renal tumours in 55 patients with histopathologically-confirmed clear cell renal cell carcinomas (ccRCCs), which were segmented and radiomics were extracted. Volumetric doubling time (VDT) classified the tumours into fast-growing (VDT <365 days) or slow-growing (VDT ≥365 days). Volumetric and diametric growth analyses were compared between the groups. Multiple logistic regression and random forest classifiers were used to select the best features and models based on their correlation and predictability of VDT. Fifty-five patients (mean age 42.2 ± 12.2 years, 27 men) with a mean time difference of 3.8 ± 2 years between the baseline and preoperative scans were studied. Twenty-five tumours were fast-growing (low VDT, i.e., <365 days), and 53 tumours were slow-growing (high VDT, i.e., ≥365 days). The median volumetric and diametric growth rates were 1.71 cm3/year and 0.31 cm/year. The best feature using univariate analysis was wavelet-HLL_glcm_ldmn (area under the receiver operating characteristic [ROC] curve [AUC] of 0.80, p< 0.0001), and with the random forest classifier, it was log-sigma-0-5-mm-3D_glszm_ZonePercentage (AUC: 79). The AUC of the ROC curves using multiple logistic regression was 0.74, and with the random forest classifier was 0.73. Radiomic features correlated with VDT and were able to predict the growth pattern of renal tumours in patients with VHL syndrome. • Median renal tumor doubling time in VHL syndrome was 538 days (278–539). • Median diametric and volumetric growth rates were 0.31 cm/year (0.17–0.51) and 1.71 cm3/year (0.8–4.2). • Radiomic features fairly predicted tumor growth patterns in VHL syndrome patients. • Models employed for feature selection: multiple logistic regression and random forest. • Potential of radiomics to improve outcomes by personalized surveillance strategies. [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]

Long-distance gas pipelines in service inevitably are exposed to harsh conditions such as extreme temperature. It is also recognized that corrosion is one of most influential factors on the structural reliability and safety of pipelines, even coated pipelines. Therefore, there is an important need to investigate the temperature effect on the failure behaviors of gas pipelines with corrosion. In this study, a thermomechanically nonlinear finite-element model of a corroded gas pipeline with a polyethylene protective layer was established, in which a large diameter is considered for the long-distance gas pipeline. Thermal stresses obtained from cases with and without the protective layer were compared. Based on the stress-based failure criterion, the failure pressure values of corroded pipeline at different temperatures were obtained, and the deformation and strain of the corroded pipeline were evaluated. The random forest algorithm was adopted to analyze the parametric sensitivity of failure pressure. Taking temperature into account, an estimation model for predicting the failure pressure of corroded pipelines is proposed using the nonlinear least-squares method, which could be useful for performing a preliminary assessment of the failure pressure of long-distance gas pipelines in practice. [ABSTRACT FROM AUTHOR]