Search

Quiet eye (QE), the visual fixation on a target before initiation of a critical action, is associated with improved performance. While QE is trainable, it is unclear whether QE can directly predict performance, which has implications for training interventions. This study predicted basketball shot outcome (make or miss) from visuomotor control variables using a decision tree classification approach. Twelve basketball athletes completed 200 shots from six on-court locations while wearing mobile eye-tracking glasses. Training and testing data sets were used for modeling eight predictors (shot location, arm extension time, and absolute and relative QE onset, offset, and duration) via standard and conditional inference decision trees and random forests. On average, the trees predicted over 66% of makes and over 50% of misses. The main predictor, relative QE duration, indicated success for durations over 18.4% (range: 14.5%–22.0%). Training to prolong QE duration beyond 18% may enhance shot success. [ABSTRACT FROM AUTHOR]

Significant bridge inspection data has been collected over the years at the component and element level to improve management practices in the United States. A widely adopted systematic approach to correlate the weight or importance of the bridge elements to the overall bridge performance, which influences the maintenance, repair, and replacement (MRR) schedule and resource allocation for structures, does not exist given the existing data. Some transportation agencies use a cost-based approach to assign weights to bridge elements, which can be in terms of the loss accrued during downtime or the amount needed for the replacement of the element. However, this approach does not consider the bridge elements' structural relevance to the overall performance of the bridge. This study proposes a novel framework to synthesize component and element-level bridge data to showcase their relationship using the random forest algorithm, which is essentially an ensemble of decision trees to evaluate the importance of different elements relative to the overall condition of the bridge. The analysis focused on eight bridge design types predominant in Delaware, Maryland, Pennsylvania, Virginia, and West Virginia, and analyzed 104,699 bridge records consisting of the condition rating and element-level data from the National Bridge Inventory (NBI). The random forest algorithm showed that bridge elements' weight (or importance) is not constant as implied by the cost-based approach; rather, bridge elements' weight varies based on their relevance to the bridge's structural performance. The resultant bridge elements' weight, which is the element weight multiplied by the component weight, can be used to improve the existing Bridge Health Index (BHI) equation found in the Manual for Bridge Evaluation (MBE) using this data-driven approach. Given more available component and element-level bridge data, this formulation provides a framework for transportation personnel to determine which set of bridge elements to prioritize in their maintenance actions and ascertain if the elements receiving the highest priority in the MRR schedule and budget allocation are also the same set of elements that bridge inspection reports regard as needing attention. Practical Applications: The United States bridge inventory is made up of several bridge design types with distinct deterioration characteristics based on their structural configuration and needed to make decisions about maintenance and repair strategies. However, the method currently adopted by bridge owners to prioritize the repair of the many bridge parts (or elements) is largely dependent on the cost of repair and economic loss at the downtime of such elements as decided by experts, which introduces personal bias and does not account for the distinctions among the different bridge types available in the inventory (Chase et al. 2016; Inkoom and Sobanjo 2018). Given nationwide efforts to collect bridge inspection data, it is essential to consider a data-driven approach that derives the bridge elements' importance from historical bridge inspection data and separates the bridge inventory into design types to innovatively determine the bridge elements' importance (or weight) needed to compute the overall bridge health using historical condition state and condition rating data of bridge elements and components. This helps to capture in real time how the deterioration of one bridge part affects another part, which in turn helps to identify the bridge elements that most influence the overall condition of the bridge when prioritizing bridge repairs using the random forest algorithm. This paper showcases a data-driven approach within a novel framework used to assess the overall bridge health using random forest algorithms that track how the deterioration of small bridge elements affects the condition of the bridge components they are attached to, and the overall bridge condition, thus potentially improving the method for computing bridge element weights within the existing Bridge Health Index (BHI) formulation documented in the Manual for Bridge Evaluation (MBE). [ABSTRACT FROM AUTHOR]

Accurate predictive daily global horizontal irradiation models are essential for diverse solar energy applications. Their long-term performances can be assessed using average years. This study scrutinized 70 machine learning and 44 empirical models using two disjoint 5-year average daily training and validation datasets, each comprising 365 records and ten features. The features included day number, minimum and maximum air temperature, air temperature amplitude, theoretical and observed sunshine hours, theoretical extraterrestrial horizontal irradiation, relative sunshine, cloud cover, and relative humidity. Fourteen machine learning algorithms, namely, multiple linear regression, ridge regression, Lasso regression, elastic net regression, Huber regression, k-nearest neighbors, decision tree, support vector machine, multilayer perceptron, extreme learning machine, generalized regression neural network, extreme gradient boosting, gradient boosting machine, and light gradient boosting machine were trained, validated, and instantiated as base learners in four strategically designed homogeneous parallel ensembles--variants of pasting, random subspace, bagging, and random patches--which also were scrutinized, producing 70 models. Specific hyperparameters from the algorithms were optimized. Validation showed that at least two ensembles outperformed its individual model. Huber-subspace ranked first with a root mean square error of 1.495 MJ/m2/day. The multilayer perceptron was most robust to the random perturbations of the ensembles which extrapolate to good tolerance to ground-truth data noise. The best empirical model returned a validation root mean square error of 1.595 MJ/m2/day but was outperformed by 93% of the machine learning models with the homogeneous parallel ensembles producing superior predictive accuracies. [ABSTRACT FROM AUTHOR]

This study presents a new tool for predicting the compressive strength of alkali-activated concrete (AAC) based on its binder mineralogy. It was made using a machine-learning (ML) framework. To achieve this challenging task, the authors collected 45 data sources from the literature to build a data set of 809 samples that included nine effective features, such as binder content, alkaline-to-binder ratio, binder chemical compositions (CaO, SiO2 , Al2O3 , and MgO contents), NaOH molarity and percentage in alkaline solution, age, and compressive strength. To assess the accuracy of the prediction tool, the authors trained and evaluated the data set using the most relevant ML methods: Lasso regression, random forest regression, decision tree, AdaBoost, extreme gradient boosting (XGB), and long short-term memory with recurrent neural network (LSTM-RNN). An experimental program was also conducted using the ML approaches to further validate the accuracy of the predictions. Overall, the XGB and LSTM-RNN methods were observed to significantly outperform the other methods in terms of accuracy when predicting compressive strength. Particularly impressive results were seen, with R2 values of 0.93 and 0.96 for compressive strength prediction being recorded. Further analysis of the binder mineralogy showed that increasing calcite content percentage led to an increase in AAC compressive strength, whereas increasing silicates in the binder mineralogy caused a decrease in AAC compressive strength due to the shortage of calcites. The Shapley additive explanations (SHAP) analysis revealed that calcite and silicate had the highest SHAP values for the AAC compressive strength. In contrast, the Al2O3 and MgO percentages had only a minor impact on the compressive strength of AAC. [ABSTRACT FROM AUTHOR]

BACKGROUND: Determining the freshness of chilled pork is of paramount importance to consumers worldwide. Established freshness indicators such as total viable count, total volatile basic nitrogen and pH are destructive and time‐consuming. Color change in chilled pork is also associated with freshness. However, traditional detection methods using handheld colorimeters are expensive, inconvenient and prone to limitations in accuracy. Substantial progress has been made in methods for pork preservation and freshness evaluation. However, traditional methods often necessitate expensive equipment or specialized expertise, restricting their accessibility to general consumers and small‐scale traders. Therefore, developing a user‐friendly, rapid and economical method is of particular importance. RESULTS: This study conducted image analysis of photographs captured by smartphone cameras of chilled pork stored at 4 °C for 7 days. The analysis tracked color changes, which were then used to develop predictive models for freshness indicators. Compared to handheld colorimeters, smartphone image analysis demonstrated superior stability and accuracy in color data acquisition. Machine learning regression models, particularly the random forest and decision tree models, achieved prediction accuracies of more than 80% and 90%, respectively. CONCLUSION: Our study provides a feasible and practical non‐destructive approach to determining the freshness of chilled pork. © 2024 Society of Chemical Industry. [ABSTRACT FROM AUTHOR]

In this study, an action recognition system was developed to identify fundamental basketball movements using a single Inertial Measurement Unit (IMU) sensor embedded in a wearable vest. This study aims to enhance basketball training by providing a high-performance, low-cost solution that minimizes discomfort for athletes. Data were collected from 21 collegiate basketball players, and movements such as dribbling, passing, shooting, layup, and standing still were recorded. The collected IMU data underwent preprocessing and feature extraction, followed by the application of machine learning algorithms including KNN, decision tree, Random Forest, AdaBoost, and XGBoost. Among these, the XGBoost algorithm with a window size of 250 and a 75% overlap yielded the highest accuracy of 96.6%. The system demonstrated superior performance compared to other single-sensor systems, achieving an overall classification accuracy of 96.9%. This research contributes to the field by presenting a new dataset of basketball movements, comparing the effectiveness of various feature extraction and machine learning methods, and offering a scalable, efficient, and accurate action recognition system for basketball. [ABSTRACT FROM AUTHOR]

Background: Cardiovascular diseases (CVD) are major contributors to maternal mortality and morbidity during pregnancy and increased atherogenic index of plasma levels is associated with a higher risk of CVD and obesity. Methods: In this study, we utilized three different machine learning algorithms (boosting, random forest, and decision tree regression) to predict dyslipidemia-associated cardiovascular disease using atherogenic index and lipid profile parameters based on a cross-sectional study datasets of 112 pregnant women aged between 15 and 49 conducted at Aminu Kano Teaching Hospital. Results: The results showed that random forest regression outperformed both boosting and decision tree regression, recording the lowest error criteria (MSE = 0.071 and RMSE = 0.266) for evaluating the model. These findings indicated that all the three algorithms have the potential to effectively model the data from atherogenic indices and lipid profile parameters but random forest and boosting were found to outperform decision tree models with respective R2 values of 0.95 and 0.92. Conclusions: Overall, the study highlights the accuracy of machine learning models (random forest, boosting, and decision trees) in predicting dyslipidemia-associated cardiovascular diseases and the findings could contribute to the development of effective strategies for the prevention and treatment of dyslipidemia-associated cardiovascular diseases. [ABSTRACT FROM AUTHOR]

Surface roughness is a critical factor in evaluating the quality of a product's surface. To predict surface roughness, researchers have employed statistical and empirical methodologies, both of which often lack generalizability when applied to unseen data. To overcome the limitations of existing models, scholars have turned to machine learning and artificial intelligence approaches. Machine learning can accurately predict the surface roughness of machined parts and demonstrates strong generalization ability when applied to new, unseen data. For instance, this research develops a super-learner machine learning model designed to predict surface roughness by leveraging a diverse array of techniques, including kernel ridge regression (KRR), support vector machine (SVM), K-nearest neighbors (KNN), decision trees (DT), random forests (RF), adaptive boosting (ADB), gradient boosting (GB), and extreme gradient boosting (XGB). The optimization of these models was achieved through grid search hyperparameter tuning and K-fold cross-validation. The predictive efficacy of the proposed super-learner model was compared to that of all alternative models. With a coefficient of determination (R2) of 99.8% between the experimental and predicted values for surface roughness on the test dataset, the super-learner model demonstrated superior predictive capabilities. It emerged as the most accurate model, distinguished by the highest R2, the lowest mean absolute error (1.92%), the lowest mean absolute percentage error (1.76%), and the lowest root mean square error (2.29%). Additionally, the model's predictions were further interpreted using the Shapley additive explanations (SHAP) technique, which provided valuable insight into the significant variables influencing the surface roughness of tempered steel AISI 1060. [ABSTRACT FROM AUTHOR]

AbstractChemical release data are essential for performing chemical risk assessments to understand the potential exposures arising from industrial processes. Often, these data are unknown or unavailable and must be estimated. A case study of volatile organic compound releases during extrusion-based additive manufacturing is used here to explore the viability of various regression methods for predicting chemical releases to inform chemical assessments. The methods assessed in this work include linear Least Squares, Least Absolute Shrinkage and Selection Operator (LASSO) and Ridge regression, classification and regression tree, random forest model, and neural network analysis. Secondary data describing polymeric extrusion in multiple applications are curated and assembled in a dataset to support regression modeling using default parameters for the various approaches. The potential to add noise to the dataset and improve regression is evaluated using synthetic data generation. Evaluation of model performance for a common test set found all methods were able to achieve predictions within 10%-error for up to 98% of the test sample population. The degree to which this level of performance was maintained when varying the number and type of features for regression was dependent on the model type. Linear methods and neural network analysis predicted the most test samples within 10%-error for smaller numbers of features while tree-based approaches could accommodate a larger number of features. The number and type of features can be important if the desire is to make chemical-specific release predictions. The inclusion of release data from related processes generally improved test set predictions across all models while the use of synthetic data as implemented here resulted in smaller increases in test sample predictions within 10%-error. Future work should focus on improving access to primary data and optimizing models to achieve maximum predictive performance of environmental releases to support chemical risk assessment. [ABSTRACT FROM AUTHOR]

Despite their significant environmental benefits, solar photovoltaic (PV) systems are susceptible to malfunctions and performance degradation. This paper addresses detecting and diagnosing faults from a dataset representing a 250 kW PV power plant with three types of faults. A comprehensive dataset analysis is conducted to improve the dataset quality and uncover intricate relationships between features and the target variable. By introducing novel feature importance averaging techniques, a two-phase fault detection and diagnosis framework employing tree-based models is proposed to identify faults from normal cases and diagnose the fault type. An ensemble of six tree-based classifiers, including decision trees, random forest, Stochastic Gradient Boosting, LightGBM, CatBoost, and Extra Trees, is trained in both phases. The results show 100% accuracy in the first phase, particularly with the Extra Trees classifier. In the second phase, Extra Trees, XGBoost, LightGBM, and CatBoost achieve similar accuracy, with Extra Trees demonstrating superior training and convergence speed. This study then incorporates Explainable Artificial Intelligence (XAI), utilizing LIME and SHAP analyzers to validate the research findings. The results highlight the superiority of the proposed approach over others, solidifying its position as an innovative and effective solution for fault detection and diagnosis in PV systems. [ABSTRACT FROM AUTHOR]

Fault detection and classification in transmission lines are critical for maintaining the reliability and stability of electrical power systems. Quick and accurate fault detection allows for timely intervention, minimizing equipment damage, and reducing downtime. This study addresses the challenge of effective fault classification, particularly when dealing with smaller, more practical datasets. Initially, the study examined the performance of conventional machine learning algorithms on a comprehensive dataset of 7681 samples, demonstrating high accuracy owing to the inherent symmetry of sinusoidal voltage and current signals. However, the true efficacy of these algorithms was evaluated by minimizing the dataset to 231 training samples, with the remainder being used for testing. A novel Multi-Target Ensemble Classifier was developed to improve classification accuracy. The proposed algorithm achieved an impressive overall accuracy of 0.829165, outperforming traditional methods, including the K-Nearest Neighbors Classifier, support vector classification, random forest classifier, decision tree classifier, AdaBoost classifier, gradient boosting classifier, and Gaussian NB. This research highlights the importance of efficient fault classification techniques in power systems and proposes a superior solution in the form of a multitarget ensemble classifier. [ABSTRACT FROM AUTHOR]

COVID-19, originating in Wuhan, China, in December 2019 declared a pandemic by the World Health Organization on March 11, 2020, rapidly spread worldwide, significantly impacting human life and the health sector. This study aims to develop a WHO (World Health Organization) oriented disease severity prediction model using laboratory and demographic data from COVID-19 patients upon admission to Marmara University Hospital. The relationship between oxygen and intensive care needs with laboratory results on the data set was analyzed using K-nearest neighbor, Bagging, Random Forest and Decision Tree machine learning methods. The dataset's unbalanced class distribution was balanced using the SMOTE method, and the impact of data multiplication on classification performance was evaluated. In the data set without SMOTE, the patient's oxygen requirement during the first hospitalization was estimated with 16 features at 91.67% accuracy, the oxygen requirement at hospitalization with 18 features at 91.96%, and the intensive care need at hospitalization with 12 features at 92.17% accuracy. After SMOTE data multiplication, an increase of 6%, 24% and 21% was observed in F1-Score values, respectively. This study significantly contributes to the field by utilizing machine learning methods on patient data, essential for COVID-19 diagnosis, monitoring, and clinical management through required laboratory tests. makine öğrenmesi laboratuvar verisi prognoz [ABSTRACT FROM AUTHOR]

Water has a complex relationship with agricultural activities, economy, health, use of energy resources and hygiene. In parallel with climate change and population growth, the inadequacy of our water resources in the coming years is one of the major problems we are likely to face. Estimating how much of the available water can be used and how much the water potential will change in the future can enable more accurate water planning. The average flow, total precipitation and average temperature values of Tagar Stream Küçükkumluk and Porsuk Stream Porsuk Çiftliği Station were analyzed together and the river flow rate was estimated. Linear Regression, Support Vector, Decision Trees, Random Forest and Extra Trees methods were applied for flow estimation. In order to improve the performance of each of the applied models, a hybrid method was developed using Wavelet Transform. Approximately 65% of the dataset is divided into training, 15% validation and 20% test data. ETR was found to be the most successful prediction method with 70.8% for Tagar Stream Küçükkumluk and 67.67% for Porsuk Stream Porsuk Farm. The developed hybrid model increased the success rate for all methods; the highest increase was obtained in SVR method with 20.82% for Küçükkumluk and 30.64% for Porsuk Farm. The most successful method was obtained in the ETR method with 91.46% and 86.39%. [ABSTRACT FROM AUTHOR]

A classification prediction model is established based on a nonlinear method—Gradient Boosting Decision Tree (GBDT) to investigate the factors contributing to a perpetrator's escape behavior in hit-and-run crashes. Given the U.S. Crash Report Sampling System (CRSS) dataset, the model is trained and compared with the state-of-art methods (Classification and Regression Tree, Random Forest, and Logistic Regression). The results show that the GBDT outperforms other methods, achieving the lowest negative log-likelihood (0.282), misclassification rate (0.096), and the highest AUC (0.803). GBDT also demonstrates superior computational efficiency, with a LIFT value of 4.087, making it a more accurate and efficient model for predicting hit-and-run crashes compared to CART, Random Forest, and Logistic Regression. The results obtained from the GBDT show that the relative importance of crash type and relation to trafficway rank 4th and 5th, respectively. Neither is mentioned in previous studies, indicating that GBDT has the ability to mine hidden information. In addition, the interaction between influencing variables can also be obtained to investigate the joint effect of various variables. The results of this study have practical applications in hit-and-run incident prevention, accident safety analysis, and other engineering applications. [ABSTRACT FROM AUTHOR]

This study aims to find reliable vertical environmental variables for modeling the fishing grounds of albacore (Thunnus alalunga) in the tropical waters of the Atlantic Ocean. Logbook data of 13 Chinese longliners operating in the high seas of the Atlantic Ocean from 2016 to 2019 were collected and matched with vertical environmental variables including dissolved oxygen, temperature, and salinity from 0 to 500 m at 50‐m depth intervals. Then four machine learning (ML) models: decision tree (DT), random forest (RF), light gradient boosting (LGB) and categorical boosting (CGB) were constructed and compared with generalized additive models (GAMs) within spatial resolutions of.5° ×.5°, 1° × 1°, and 2° × 2° grids to find the significant features. The importance of each variable was ranked and compared based on Shapley additive explanations (SHAP) approach across five ML models at three resolutions. Results showed that (1) the vertical environmental variables—temperature at the depth of 100 m and dissolved oxygen concentration at the depth of 100 and 150 m—were the significant features that contributed most to all the ML models at three spatial resolutions; (2) the models with a spatial resolution of 2° × 2° grid exhibited higher accuracy compared to the models with.5° ×.5° and 1° × 1° grids; (3) the RF model had the best prediction performance among all the models tested. Our results suggested that significant vertical environmental variables showed similar importance across different ML models at different resolutions, and these specific variables can be relied upon for accurately predicting the fishing grounds of albacore in the tropical waters of the Atlantic Ocean. [ABSTRACT FROM AUTHOR]

Worldwide terrorist activities continue to pose a significant threat to global security and stability. The unpredictable nature of these acts necessitates advanced analytical approaches to enhance prevention and response strategies. This study examines undetectable word extensions across multiple datasets, using terrorism‐related datasets as a case study. This research aims to overcome constraints in current predictive models associated with terrorist attack prediction. While many studies have used the GTD for predicting global terrorist attacks, this study expands beyond GTD by evaluating a corpus of terrorism incidents to enhance predictive analysis through lexical usage. The study employs several machine learning algorithms including Decision Tree (DT), Bootstrap Aggregating (BA), Random Forest (RF), Extra Trees (ET) and XGBoost (XG) algorithms for evaluation. Our approach integrates multiple datasets to reduce dependence on GTD alone. Findings indicate that RF performs best on the GTD database, with 90.20% accuracy in predicting worldwide terrorist attacks. DT achieves 90.40% accuracy when applied to the TF–IDF dataset. XG demonstrates superior performance across various aggregation settings and feature sets, achieving 95.77% accuracy in forecasting worldwide terrorist acts. XG's consistent and effective performance across various contexts highlights its versatility. Its high adaptability and robust performance position it as the preferred algorithm for conducting predictive research on global terrorist acts using the available datasets. Our research findings underscore the importance of incorporating diverse datasets to enhance understanding of terrorist activities and improve predictive capabilities. [ABSTRACT FROM AUTHOR]

Despite a wealth of research, the etiology of the abdominal wall defect gastroschisis remains largely unknown. The strongest known risk factor is young maternal age. Our objective was to conduct a hypothesis-generating analysis regarding gastroschisis etiology using random forests. Data were from the Slone Birth Defects Study (case-control, United States and Canada, 1998–2015). Cases were gastroschisis-affected pregnancies (n = 273); controls were live-born infants, frequency-matched by center (n = 2591). Potential risk factor data were ascertained via standardized interviews. We calculated adjusted odds ratios (aOR) and 95 % confidence intervals (CIs) using targeted maximum likelihood estimation. The strongest associations were observed with young maternal age (aOR 3.4, 95 % CI 2.9, 4.0) and prepregnancy body-mass-index < 30 kg/m2 (aOR 3.3, 95 % CI 2.4, 4.5). More moderate increased odds were observed for parents not in a relationship, non-Black maternal race, young paternal age, marijuana use, cigarette smoking, alcohol intake, lower parity, oral contraceptive use, nonsteroidal anti-inflammatory drug use, daily fast food/processed foods intake, lower poly- or monounsaturated fat, higher total fat, and lower parental education. Our research provides support for established risk factors and suggested novel factors (e.g., certain aspects of diet), which warrant further investigation. • Gastroschisis is a serious congenital anomaly from unknown causes. • Potential to identify new possible risk factors using decision tree learning. • Known risk factors (young maternal age, lower body-mass-index) confirmed. • Some modifiable risk factors (substance use, use of oral contraceptives or NSAIDs) suggested in prior research. • Novel factors (e.g., certain aspects of diet) warrant further investigation. [ABSTRACT FROM AUTHOR]

This study aims to employ machine learning algorithms to analyze the axial bearing capacity of rubberized alkali-activated concrete filled steel tubes. A dataset encompassing 327 synthesized instances and seven input features is adopted for training and testing six machine learning models, including Decision Tree, Random Forest, Extremely Randomized Trees, Adaptive Boosting, Gradient Boosting Decision Trees (GBDT), and eXtreme Gradient Boosting Trees (XGBoost). The SHapley Additive exPlanation algorithm is employed to elucidate the prediction process of machine learning models and to analyze the influence of each parameter on axial bearing capacity. Comparison of evaluating metrics shows that GBDT and XGBoost models achieve highest accuracy and generalization capabilities when their Coefficient of Determination values surpassing 0.98 and Mean Absolute Percent Error remaining below 3%. Moreover, the explanation analysis of machine learning models reveals that diameter/width of the cross section, rubber content, yielding strength and thickness of steel tubes are critical variables that affect the axial bearing capacity, while compressive strength of alkali-activated concrete, specimen height, and shape of cross section show negligible impact. Besides, GBDT model overemphasizes the effect of specimen height and might lead a conservative prediction for specimens with smaller heights. Finally, compressive strength of alkali-activated concrete and diameter/width, thickness, and yielding strength of steel tubes are positively correlated with axial bearing capacity, and the increase of rubber content in alkali-activated concrete leads to the decrease of capacity. [ABSTRACT FROM AUTHOR]

The continuous evolution of deep learning has garnered significant attention in spectroscopy. This study focuses on identifying wheat flour, presenting a more efficient and accurate method by combining two-dimensional correlation spectroscopy (2D-COS) and deep learning techniques. A data set of 316 near-infrared (NIR) spectral samples of four types of wheat flour was collected. By applying three disparate 2D-COS techniques, i.e., synchronous, asynchronous, and integrated, we crafted 948 2D-COS images. These images, obtained by transforming the original one-dimensional spectra into 2D representations, offer richer information for deep learning analysis. The study introduced an 18-layer residual network incorporating a convolutional attention mechanism, specifically tailored for the 2D-COS analysis of wheat flour, aimed at enhancing the model's discriminative capabilities by refining the residual neural network's structure. Achieving an unprecedented recognition accuracy of 100% through methodical optimization and rigorous training on the synchronous 2D-COS data set of wheat flour, the proposed model is a testament to the efficacy of deep learning in spectroscopic analysis. To further exhibit the confluence of 2D-COS with deep learning, t-distributed stochastic neighbor embedding was employed to visualize the distinctive 2D-COS features within the deep learning architecture. Additionally, the model's performance was juxtaposed with prevailing NIR spectral recognition methods, including random forest, gradient boosting decision tree, and artificial neural network. This comparison cemented the proposed approach's superiority in wheat flour categorization. The findings of this study not only introduce a novel and efficient solution for wheat flour quality analysis but also underscore the significant potential of deep learning techniques in spectroscopy applications. [ABSTRACT FROM AUTHOR]

Predicting the metastatic direction of primary breast cancer (BC), thus assisting physicians in precise treatment, strict follow-up, and effectively improving the prognosis. The clinical data of 293,946 patients with primary BC diagnosed between 2010 and 2015 were collected from the Surveillance, Epidemiology, and End Results database. Multiple interpolations and Multi-label Synthetic Minority Over-sampling Technique methods were used for data analysis, and machine learning model was established for multi-label classification. Finally, Surgical information, lymph node status, distant metastasis, tumor size, chemotherapy, histological type, and radiotherapy had significant influence as inputs. Compared with the k-nearest neighbor model, average accuracies of the decision tree and random forest (RF) models increased from 88.84% to 93.59% and 94.14%, respectively. Their average precision, recall rate, F1 score, area under the receiver operating characteristic curve and weighted-F1 increased from 87.24%to 95.85%and 94.74%, 87.73% to 90.40% and 91.76%, 87.07% to 92.16% and 93.45%, 97.11% to 99.53% and 99.95%, 82.13% to 89.44% and 90.48%, respectively. In conclusion, the RF model, which showed the best performance, can be used in multi-label prediction of BC metastasis directions, and can assist physicians in diagnosing and treating patients with primary BC. [ABSTRACT FROM AUTHOR]

Traffic accidents occur frequently, causing significant losses to people's lives and property safety. Accurately predicting the severity level of traffic accidents is of great significance. Based on traffic accident data, this study comprehensively considers various influencing factors such as the geographical location, road conditions, and environment. The data are divided into accident-related categories, weather-related categories, and road- and environment-related categories. The machine learning method is improved through integration for the accident level prediction. In the experiment, effective preprocessing measures were taken for problems such as data imbalance, missing values, the encoding of categorical variables, and the standardization of numerical features. The unbalanced distribution of "Severity" was improved through under-sampling and over-sampling techniques. Firstly, we adopted a multi-stage fusion strategy. A multi-layer perceptron (MLP) was used for the preliminary prediction, and then its result was combined with the original features to form a new feature. Decision tree, XGBoost, and random forest algorithms, respectively, were applied for the secondary prediction. The analysis results show that the improved machine learning model is significantly superior to a single model in the overall performance. The "MLP + random forest" model performs well in evaluation indicators such as the accuracy, recall rate, and F1 value. The accuracy rate is as high as 94%. In the prediction of different traffic accident severity levels (minor, moderate, and severe), the improved machine learning model also generally shows better performance and stability. The research results of this study have broad prospects in the field of intelligent driving. It can realize real-time accident prediction and early warnings, and provide decision support for drivers and autonomous driving systems. The research also provides a scientific basis for traffic planning and management departments to improve driving conditions and reduce the probability and losses of traffic accidents. [ABSTRACT FROM AUTHOR]

Fault detection in charging piles is crucial for the widespread adoption of electric vehicles and the reliability of charging infrastructure. Currently, due to the lack of sufficient fault data for charging piles, achieving stable and accurate fault identification is challenging. Moreover, distinctive fault features are key to accurate fault recognition. To address this, we designed a simulated charging pile system and collected fault data at multiple power levels by manually introducing faults. Furthermore, we proposed a fault identification algorithm based on spatiotemporal feature fusion using machine learning. This algorithm first collects fault data through a sliding window and utilizes Fourier transform to extract frequency domain information to construct temporal features. These features are then fused with spatial current amplitude information to form a distinctive feature set, enabling fault identification based on a machine learning model. Extensive experiments conducted on the constructed dataset show that this method can accurately identify charging pile faults. Compared with random forest and gradient boosted decision tree, the proposed method improves the macro-average score by 2.99% and 7.28%, respectively. We also explored the importance of each feature for fault identification results and the impact of window length on identification outcomes, demonstrating the necessity of the extracted features and the robustness of the proposed method to data resolution. [ABSTRACT FROM AUTHOR]

This work focused on developing a methodology for using machine learning (ML) approaches to establish a pre-harvest yield prediction model for sugarcane at field level by integrating time-series remote sensing imagery data with ML techniques. Ground truth agro data and thirty-one spectral vegetation indices were extracted from Sentinel-2 imagery and were considered for yield modeling. A two-level feature selection technique was used to determine the most significant variables that best correlated with sugarcane yield to predict yield in advance. Seven ML algorithms, including those based on regularization, decision trees, and ensemble methods like boosting, were used to predict yield. The approach achieved the highest R2 score of 0.73 and the lowest root mean squared error (RMSE) of 13.45 t/ha with random forest (RF) among the seven ML models tested. Furthermore, all feature selection procedures identified normalized difference red edge (NDRE), red edge chlorophyll index (RECI), and ratio vegetation index (RVI) as major yield-driving variables. The experiments during feature selection demonstrated the potential of red edge spectral bands in development of a reliable sugarcane-yield prediction approach. The RF model obtained using the proposed methodology outperforms the two baseline models developed using NDVI and GNDVI indices, with an improved RMSE of 16-18%. [ABSTRACT FROM AUTHOR]

This study introduces a sophisticated intelligent predictive maintenance system for industrial conveyor belts powered by a random forest machine learning model. The random forest model was evaluated against established models such as logistic regression, neural networks, decision trees, and gradient boosting, demonstrating superior performance. The model achieved 100% accuracy in classifying gearbox lubricant levels and sprocket conditions, highlighting its potential for addressing critical challenges in predictive maintenance, such as avoiding unexpected downtime. However, further validation with larger datasets and varied operational environments is recommended to confirm robustness. This performance highlights its effectiveness in multiclass fault detection and overfitting mitigation, establishing a new standard in predictive maintenance technology. The system, enhanced by a comprehensive sensor array, not only adeptly captures but also intelligently analyzes critical operational data, providing proactive and data-driven insights for maintenance decision-making. This study not only affirms the dominance of the random forest model in predictive analytics but also underscores its pivotal role in optimizing maintenance strategies, enhancing operational efficiency, and ensuring the reliability of conveyor systems in industrial settings. [ABSTRACT FROM AUTHOR]

This research article presents a thorough and all-encompassing examination of predictive models utilized in the estimation of viscosity for ionic liquid solutions. The study focuses on crucial input parameters, namely the type of cation, the type of anion, the temperature (measured in Kelvin), and the concentration of the ionic liquid (expressed in mol%). This study assesses three influential machine learning algorithms that are based on the Decision Tree methodology. These algorithms include Random Forest (RF), Gradient Boosting (GB), and XGBoost (XGB). Furthermore, the study incorporates the use of Glowworm Swarm Optimization (GSO) for hyper-parameter optimization, thereby further elevating the efficacy of the models. The results obtained from the evaluation showcase the exceptional predictive capabilities of the models, with Random Forest (RF) achieving an impressive R2 value of 0.9971, Gradient Boosting (GB) attaining an R2 value of 0.9916, and XGBoost (XGB) yielding an R2 value of 0.9911. In addition to the R2 metric, the study also presents other performance metrics, such as RMSE and MAPE, for each model. This comprehensive assessment of accuracy further solidifies the credibility and effectiveness of the models employed in the estimation of viscosity for ionic liquid solutions. [ABSTRACT FROM AUTHOR]

Background: High triglyceride (TG) affects and is affected of other hematological factors. The determination of serum fasted triglycerides concentrations, as part of a lipid profile, is crucial key point in hematological factors and significantly affect various systemic diseases. This study was carried out to assess the potential relation between the concentration of TG and hematological factors. Method: Our sample size was 9704 participants beginning in 2007 and ending in 2020 aged between 35 and 65 years, sourced from the MASHAD cohort (northeastern Iran). Machine learning methodologies, specifically logistic regression, decision tree, and random forest algorithms, were utilized for data analysis in the investigation of individuals with normal and high TG levels. Results: The highest Gini score belongs to RLR (Red cell distribution width/Lymphocyte) (236.10), RPR (Red cell distribution width/Platelets) (215.78), and PHR (Platelets/high-density lipoprotein) (273.66). We also found that factors such as age are statistically associated with the level of TG in women probably due to the drop in menopausal estrogen. RF model showed to have higher accuracy in predicting the TG level in both males and females. Conclusion: Our model assessed the association between serum TG with several hematological factors like RLR, RPR, and PHR. Other hematological factors also have been reported to be related to the TG level. As these results give us new insights into the association of TG on various hematological factors and their possible interactions with each other. future studies are needed to provide sufficient data for the mechanism and the pathophysiology of the findings. [ABSTRACT FROM AUTHOR]

The traditional machine learning methods such as decision tree (DT), random forest (RF), and support vector machine (SVM) have low classification performance. This paper proposes an algorithm for the dry bean dataset and obesity levels dataset that can balance the minority class and the majority class and has a clustering function to improve the traditional machine learning classification accuracy and various performance indicators such as precision, recall, f1-score, and area under curve (AUC) for imbalanced data. The key idea is to use the advantages of borderline-synthetic minority oversampling technique (BLSMOTE) to generate new samples using samples on the boundary of minority class samples to reduce the impact of noise on model building, and the advantages of K-means clustering to divide data into different groups according to similarities or common features. The results show that the proposed algorithm BLSMOTE + K-means + SVM is superior to other traditional machine learning methods in classification and various performance indicators. The BLSMOTE + K-means + DT generates decision rules for the dry bean dataset and the the obesity levels dataset, and the BLSMOTE + K-means + RF ranks the importance of explanatory variables. These experimental results can provide scientific evidence for decision-makers. [ABSTRACT FROM AUTHOR]

This research is imperative due to the pressing need for improved patient recruitment in clinical trials, addressing challenges such as delays and high costs. By introducing a classification model and a game theoretic approach for clinical trial setting, we aim to boost trial efficiency, advance healthcare research, and enhance patient outcomes. Patient recruitment for clinical trials is a critical aspect of advancing medical research but has traditionally relied on manual or semi-automated methods, such as advertisements, referrals, and eligibility screening through databases. These approaches often suffer from inefficiencies, including high costs, prolonged timelines, and suboptimal participant matching, leading to delays in trial completion. These challenges highlight the limitations of traditional methods in meeting the growing demand for efficient and effective recruitment. Motivated by these shortcomings, this study proposes an advanced AI-driven system leveraging a Random Forest Classifier within a hybrid framework to address these issues. The proposed model integrates Logistic Regression, Support Vector Machines, Decision Trees, and Random Forests through a stacking classifier and employs Autoencoders for feature extraction to enhance predictive accuracy. Additionally, a game-theoretic approach involving Patients, Clinical Investigators, and Research Firms optimizes recruitment strategies through strategic interaction, providing equilibrium-seeking solutions for balanced payoffs among stakeholders. This AI-based approach offers a transformative solution, addressing inefficiencies in traditional recruitment methods and significantly advancing the field of healthcare research by streamlining the recruitment process. [ABSTRACT FROM AUTHOR]

Background: Anemia during pregnancy is a significant public health concern, particularly in resource-limited settings. Machine learning (ML) offers promising avenues for improved anemia detection and management. This study investigates the potential of ML models in predicting anemia severity among pregnant women attending Antenatal Care (ANC) visits in Ethiopia. Methods: Data from the Ethiopian Demographic Health Survey, specialized hospitals, and public hospitals were utilized. The dataset included individuals diagnosed with severe (65.12%), moderate (15.63%), mild (16.65%) anemia, and non-anemic (2.61%) cases. Feature selection employed filter methods based on mutual information, and F-score was used to assess anemia severity prediction across four classes. Six ML models (MLP-NN, XGBoost, GNB, Decision Tree, Random Forest, and KNN) were evaluated using accuracy, precision, recall, and F1-score. Results: The Random Forest classifier achieved the best overall performance across all categories, with an accuracy of 97%, precision of 93%, recall of 93%, and F1-score of 93%. This indicates high true positive rates and low false positive rates. While other models like XGBoost, MLP-NN, and Decision Tree showed good performance, they weren't quite as strong as Random Forest. Classifiers like KNN and GNB had lower overall accuracy and a tendency to misclassify some cases. Conclusions: This study demonstrates the promising potential of Random Forest in predicting anemia severity among pregnant women in Ethiopia. The findings contribute to a more holistic understanding of anemia risk factors and pave the way for improved early detection and targeted interventions. [ABSTRACT FROM AUTHOR]

This research requires to improve the accuracy of early diabetic forecasting in a human body or patient by applying diverse machine learning approaches. Approaching to creation of machine learning models by using patient datasets to produce predictions with improved accuracy. This work will use machine learning classification and ensemble approaches, such as Random Forest (RF), Gradient Boosting (GB), Decision Tree (DT), K-nearest neighbour (KNN), Logistic Regression (LR), and Support Vector Machine (SVM), on a dataset to predict diabetes. The accuracy of each model differs in comparison to other models. This work demonstrates the model's capability by providing an accurate or greater accuracy. This research paper reported different performance metrics like precision, recall, accuracy, F1 score, and sensitivity for various machine learning algorithms. Final experimental results indicate that the Random Forest classifier outperforms other methods. [ABSTRACT FROM AUTHOR]

To improve radar-based quantitative precipitation estimation (QPE) methods, this study investigated the relationship between radar reflectivity (Z) and hourly rainfall intensity (R) using data from 289 precipitation events in Shanghai between September 2020 and March 2024. Two Z-R relationship models were compared in terms of their fitting performance: Z = 270.81 R1.09 (empirically fitted relationship) and Z = 300 R1.4 (standard relationship). The results show that the Z = 270.81 R1.09 model outperforms the Z = 300 R1.4 model in terms of fitting accuracy. Specifically, the Z = 270.81 R1.09 model more effectively captures the nonlinear relationship between radar reflectivity and rainfall intensity, with a higher degree of agreement between the fitted curve and the observed data points. This model demonstrated superior performance across all 289 precipitation events. This study evaluated the performance of four machine learning approaches while incorporating five meteorological features: specific differential phase shift (KDP), echo-top height (ET), vertical liquid water content (VIL), differential reflectivity (ZDR), and correlation coefficient (CC). Nine QPE models were constructed using these inputs. The key findings are as follows: (1) For models with a single-variable input, the KAN deep learning model outperformed Random Forest, Gradient Boosting Decision Trees, Support Vector Machines, and the traditional Z-R relationship. (2) When six features were used as inputs, the accuracy of the machine learning models improved significantly, with the KAN deep learning model outperforming other machine learning methods. Compared to using only radar reflectivity, the KAN deep learning model reduced the MRE by 20.78%, MAE by 4.07%, and RMSE by 12.74%, while increasing the coefficient of determination (R2) by 18.74%. (3) The integration of multiple meteorological features and machine learning optimization significantly enhanced QPE accuracy, with the KAN deep learning model performing best under varying meteorological conditions. This approach offers a promising method for improving radar-based QPE, particularly considering seasonal, weather system, and precipitation stage differentiation. [ABSTRACT FROM AUTHOR]

Cold radial forging (CRF) is recognized as one of the most effective manufacturing processes for the production of hollow components. Nonetheless, even minor alterations in the alloy composition during the cold deformation processing phase can significantly influence the material's manufacturability. This study addresses the challenges associated with high optimization costs, complex data acquisition, and the prediction of forming quality when integrating multiple processes, such as heat treatment and material composition. We propose the development of an intelligent predictive model aimed at forecasting the forming quality of the 20CrMnTiH alloy during CRF, utilizing a back-propagation neural network optimized by genetic algorithm (GA-BP). The assessment of forming quality is based on parameters such as damage, residual stress, and equivalent strain. The study investigates the impact of alloy composition and spheroidal annealing (SA) process parameters on forming quality. The performance of the three GA-BP prediction models is superior in terms of the coefficient of determination (R2) and mean square error (MSE), when compared to a conventional BP neural network and four other machine learning techniques, including gradient-boosted decision trees, random forests, support vector regression, and logistic regression. A comprehensive comparative analysis of the evaluation metrics across all three prediction models, alongside multi-objective optimization, indicates that the Pareto solution set generated by NSGA-II exhibits optimal distribution uniformity. The optimized process parameters (0.17%C-0.24%Si-0.81%Mn-0.03%P-0.03%S-1.15%Cr-0.05%Ni-0.06%Ti, Te: 60℃, ATi: 4.57 h) resulted in a reduction of residual stresses by 12%, equivalent strain by 15%, and component damage by 30%. The results demonstrate that the methodology proposed in this paper not only enhances the quality of CRF molding but also significantly improves the accuracy of the predictive model for forming quality. [ABSTRACT FROM AUTHOR]

This article devises the Artificial Intelligence (AI) methods of designing models of short-term forecasting (in 12 h and 24 h horizons) of electricity production in a selected Small Hydropower Plant (SHP). Renewable Energy Sources (RESs) are difficult to predict due to weather variability. Electricity production by a run-of-river SHP is marked by the variability related to the access to instantaneous flow in the river and weather conditions. In order to develop predictive models of an SHP facility (installed capacity 760 kW), which is located in Southern Poland on the Skawa River, hourly data from nearby meteorological stations and a water gauge station were collected as explanatory variables. Data on the water management of the retention reservoir above the SHP were also included. The variable to be explained was the hourly electricity production, which was obtained from the tested SHP over a period of 3 years and 10 months. Obtaining these data to build models required contact with state institutions and private entrepreneurs of the SHP. Four AI methods were chosen to create predictive models: two types of Artificial Neural Networks (ANNs), Multilayer Perceptron (MLP) and Radial Base Functions (RBFs), and two types of decision trees methods, Random Forest (RF) and Gradient-Boosted Decision Trees (GBDTs). Finally, after applying forecast quality measures of Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Coefficient of Determination (R2), the most effective model was indicated. The decision trees method proved to be more accurate than ANN models. The best GBDT models' errors were MAPE 3.17% and MAE 9.97 kWh (for 12 h horizon), and MAPE 3.41% and MAE 10.96 kWh (for 24 h horizon). MLPs had worse results: MAPE from 5.41% to 5.55% and MAE from 18.02 kWh to 18.40 kWh (for 12 h horizon), and MAPE from 7.30% to 7.50% and MAE from 24.12 kWh to 24.83 kWh (for 24 h horizon). Forecasts using RBF were not made due to the very low quality of training and testing (the correlation coefficient was approximately 0.3). [ABSTRACT FROM AUTHOR]

Featured Application: This research can be used to improve Highway Traffic Law of the Republic of Turkey. The number of traffic accidents in a region rises as the vehicle–km value in traffic increases. Furthermore, since automobiles make up the highest proportion of vehicles in traffic, they represent the greatest weight in traffic accidents. This study aims to establish a model to predict the driver's status (survived–injured–dead) as a result of the fatal-injury type of accident. The size of the vehicles suppresses the direct factors related to drivers by having a significant and dominant effect on the analysis of the results of the accidents by concealing the other important factors which must be taken into consideration with regard to the casualty levels of the drivers. Consequently, this paper focuses on automobiles, which are the most frequently involved vehicle type in accidents. Furthermore, the dataset representing the accidents that occurred in Turkey between 2015 and 2021 was employed for the analysis of the effects of the attributes of the drivers on the outcome of casualties for automobile-related accidents alone. The uniqueness of this research stems from being the first study in Turkey to investigate the severity levels of the drivers involved in automobile-related accidents. In addition, this study highlights the preventable factors investigated relatively less than other factors in the literature in order to establish a successful model. The difference between the success of the models with regard to accuracy obtained through dominant and investigated factors is only 5.0%. Random Forests, Naïve Bayes, and CHAID (Chi-squared Automatic Interaction Detection) models were established and compared as decision tree algorithms. The results revealed the fact that the CHAID model produced the most successful outcomes among them. Driver fault, gender, education level, and age, along with alcohol usage and surface condition, were found to be significant influential factors for the severity of traffic accidents. [ABSTRACT FROM AUTHOR]

Over the last decade, there have been a lot of advances in the area of human posture recognition. Among multiple approaches proposed to solve this problem, those based on deep learning have shown promising results. Taking another step in this direction, this paper analyzes the performance of deep learning-based hybrid architecture for fall detection, In this regard, the fusion of the residual network (ResNet-50) deep features with support vector machine (SVM) at the classification layer has been considered. The proposed approach outperforms the existing methods yielding an accuracy of 98.82%, 97.95%, and 99.98% on three datasets i.e. Multi-Camera Fall (MCF) using four postures, UR Fall detection (URFD) using four postures, and UP-Fall detection (UPFD) using four postures respectively. It is important to mention that the existing methods achieve accuracies of 97.9%, 97.33%, and 95.64% on the MCF, URDF and UPFD datasets, respectively. Moreover, we achieved 100% accuracy on the UPFD two-posture task. The URFD and MCF datasets have been utilized to assess the fall detection performance of our method under a realistic environment (e.g. camouflage, occlusion, and variation in lighting conditions due to day/night lighting variation). For comparison purposes, we have also performed experiments using six state-of-the-art deep learning networks, namely; ResNet-50, ResNet-101, VGG-19, InceptionV3, MobileNet, and Xception. The results demonstrate that the proposed approach outperforms other network models both in terms of accuracy and time efficiency. We also compared the performance of SVM with Naive Bayes, Decision Tree, Random Forest, KNN, AdaBoost, and MLP used at the classifier layer and found that SVM outperforms or is on par with other classifiers. [ABSTRACT FROM AUTHOR]

Aims: Non-suicidal self-injury (NSSI) is a serious issue that is increasingly prevalent among children and adolescents, especially in rural areas. Developing a suitable predictive model for NSSI is crucial for early identification and intervention. Methods: This study included 2090 Chinese rural children and adolescents. Participants' sociodemographic information, symptoms of anxiety as well as depression, personality traits, family environment and NSSI behaviors were collected through a questionnaire survey. Gender, age, grade, and all survey results except sociodemographic information were used as relevant factors for prediction. Support vector machines, decision tree and random forest models were trained and validated by the train set and valid set, respectively. The metrics of each model were tested and compared to select the most suitable one. Furthermore, the mean decrease Gini index was calculated to measure the importance of relevant factors. Results: The prevalence of NSSI was 38.3%. Out of the 6 models assessed, the random forest model demonstrated the highest suitability in predicting the prevalence of NSSI. It achieved sensitivity, specificity, AUC, accuracy, precision, and F1 scores of 0.65, 0.72, 0.76, 0.70, 0.57, and 0.61, respectively. Anxiety and depression were the top two contributing factors in the prediction model. Neuroticism and conflict were the factors that contributed the most to personality traits and family environment, respectively, in terms of prediction. In addition, demographic factors contributed little to the prediction in this study. Conclusion: This study focused on Chinese children and adolescents in rural areas and demonstrated the potential of using machine learning approaches in predicting NSSI. Our research complements the application of machine learning methods to psychiatric and psychological problems. [ABSTRACT FROM AUTHOR]

Purpose: This research introduces a groundbreaking method for bearing defect detection. It leverages ensemble machine learning (ML) models and conducts comprehensive feature importance analysis. The key innovation is the training and benchmarking of three tree ensemble models—Decision Tree (DT), Random Forest (RF), and Extreme Gradient Boosting (XGBoost)—on an extensive experimental dataset (QU-DMBF) collected from bearing tests with seeded defects of varying sizes on the inner and outer raceways under different operating conditions. Method: The dataset was meticulously prepared with categorical variable encoding and Min–Max data normalization to ensure consistent class distribution and model accuracy. Implementing the ML models involved a grid search method for hyperparameter tuning, focusing on reporting the models' accuracy. The study also explores applying ensemble methods and using supervised and unsupervised learning algorithms for bearing fault detection. It underscores the value of feature importance analysis in understanding the contributions of specific inputs to the model's performance. The research compares the ML models to traditional methods and discusses their potential for advanced fault diagnosis in bearing systems. Results and Conclusions: The XGBoost model, trained on data from actual bearing tests, outperformed the others, achieving 92% accuracy in detecting bearing health and fault location. However, a deeper analysis of feature importance reveals that the models weigh certain experimental conditions differently—such as sensor location and motor speed. This research's primary novelties and contributions are comparative evaluation, experimental validation, accuracy benchmarking, and interpretable feature importance analysis. This comprehensive methodology advances the bearing health monitoring field and has significant practical implications for condition-based maintenance, potentially leading to substantial cost savings and improved operational efficiency. [ABSTRACT FROM AUTHOR]

This study explores the application of machine learning techniques for predicting generic mill liner wear in semi-autogenous grinding (SAG) mills used in mineral processing. Various models were developed and compared using data from 143 liner measurements across 36 liner cycles from ten different SAG mills. The research initially focused on individual mill modeling, employing simple linear regression, first-order kinetic approach, Multiple Linear Regression (MLR), tree-based methods (Decision Trees, Random Forests, XGBoost), and Multilayer Perceptron (MLP). Results showed that simple linear regression provided sufficient accuracy, with other methods only slightly improving performance. This study then developed a combined model using data from multiple mills. MLR and advanced machine learning techniques were applied for this generic model, with XGBoost emerging as the most successful. In the interpolation scenario involving a mill similar to those in the training data, the XGBoost model achieved a mean absolute percentage error (MAPE) of 5.27%. For the extrapolation scenario, with a mill larger than those in the training set, the MAPE increased slightly to 6.12%. These results demonstrate the potential of machine learning approaches in creating effective generic models for mill liner wear prediction. However, this study also highlights the potential for improving predictive models by incorporating additional key parameters such as liner and ball material properties. [ABSTRACT FROM AUTHOR]

One of the issues addressed by machine learning, with applications in various disciplines or fields such as the health sector and the agricultural sector among others, involves data classification. For this purpose, various models within supervised learning have been proposed and developed that allow for the classification of these data. However, one of the implications of the No-Free-Lunch theorems is that there is no optimal general-purpose model, i.e. there is no classifier model that achieves the best results for all problems presented. Hence the importance of proposing and implementing new classifier models, evaluating their performance, and comparing them with other classifier models in order to achieve models with good results in specific problems. This work presents a new classifier model that, by constructing hyperplanes from the training set, generates a decision tree and partitions the dimensional space. The proposed model was applied to different problems such as the $XOR$ XOR logical function problem, where the proposed model managed to solve the problem, it was also applied to the Iris Dataset where one of the trees generated by the model managed to classify with 100% accuracy the test set, and finally, the proposed model was applied to the Pima Indians Diabetes Database and compared with other models using the accuracy value. The proposed model obtained an accuracy of 81.81%, achieving the best result in the same way as the Random Forest Classifier. The results obtained in this work show that the proposed model manages to partition the dimensional space adequately from the training set and thus competitively classify the data with other state-of-the-art models. [ABSTRACT FROM AUTHOR]

Definition: The increasing complexity of social science data and phenomena necessitates using advanced analytical techniques to capture nonlinear relationships that traditional linear models often overlook. This chapter explores the application of machine learning (ML) models in social science research, focusing on their ability to manage nonlinear interactions in multidimensional datasets. Nonlinear relationships are central to understanding social behaviors, socioeconomic factors, and psychological processes. Machine learning models, including decision trees, neural networks, random forests, and support vector machines, provide a flexible framework for capturing these intricate patterns. The chapter begins by examining the limitations of linear models and introduces essential machine learning techniques suited for nonlinear modeling. A discussion follows on how these models automatically detect interactions and threshold effects, offering superior predictive power and robustness against noise compared to traditional methods. The chapter also covers the practical challenges of model evaluation, validation, and handling imbalanced data, emphasizing cross-validation and performance metrics tailored to the nuances of social science datasets. Practical recommendations are offered to researchers, highlighting the balance between predictive accuracy and model interpretability, ethical considerations, and best practices for communicating results to diverse stakeholders. This chapter demonstrates that while machine learning models provide robust solutions for modeling nonlinear relationships, their successful application in social sciences requires careful attention to data quality, model selection, validation, and ethical considerations. Machine learning holds transformative potential for understanding complex social phenomena and informing data-driven psychology, sociology, and political science policy-making. [ABSTRACT FROM AUTHOR]

PURPOSE: In artificial intelligence–based modeling, working with a limited number of patient groups is challenging. This retrospective study aimed to evaluate whether applying synthetic data generation methods to the clinical data of small patient groups can enhance the performance of prediction models. MATERIALS AND METHODS: A data set collected by the Cancer Registry Library Project from the Yonsei Cancer Center (YCC), Severance Hospital, between January 2008 and October 2020 was reviewed. Patients with colorectal cancer younger than 50 years who started their initial treatment at YCC were included. A Bayesian network–based synthesizing model was used to generate a synthetic data set, combined with the differential privacy (DP) method. RESULTS: A synthetic population of 5,005 was generated from a data set of 1,253 patients with 93 clinical features. The Hellinger distance and correlation difference metric were below 0.3 and 0.5, respectively, indicating no statistical difference. The overall survival by disease stage did not differ between the synthetic and original populations. Training with the synthetic data and validating with the original data showed the highest performances of 0.850, 0.836, and 0.790 for the Decision Tree, Random Forest, and XGBoost models, respectively. Comparison of synthetic data sets with different epsilon parameters from the original data sets showed improved performance >0.1%. For extremely small data sets, models using synthetic data outperformed those using only original data sets. The reidentification risk measures demonstrated that the epsilons between 0.1 and 100 fell below the baseline, indicating a preserved privacy state. CONCLUSION: The synthetic data generation approach enhances predictive modeling performance by maintaining statistical and clinical integrity, and simultaneously reduces privacy risks through the application of DP techniques. Synthetic oncology data with differential privacy enhance survival status prediction AI, ensuring data privacy. [ABSTRACT FROM AUTHOR]

This study aims to investigate the application of Machine Learning (ML) methods for predicting the moisture susceptibility of asphalt mixtures containing Reclaimed Asphalt Pavement (RAP) materials. Four ML algorithms were utilised for this purpose, including Decision Tree (M5P), Random Forest (RF), Gradient Boosting (GB) and Extreme Gradient Boosting (XGBoost). The most influential variables in the moisture performance of asphalt mixtures were identified using a comprehensive database comprising mixture properties, binder properties, recycled materials and environmental conditions. The study underscores the potential of ML models in improving the reliability and efficiency of moisture susceptibility predictions, ultimately contributing to the development of more durable and resilient asphalt pavements. The results of this study demonstrated that ML models possess a strong capability in estimating Tensile Strength Ratio (TSR) values, signifying a pivotal step in developing machine-based predictive models for assessing and improving the durability of asphalt pavements. Notably, the XGBoost model exhibited the highest accuracy with 0.96 (training) and 0.75 (testing) R2 values. Comparison of predicted and actual TSR values and residual analysis were explored to assess ML models robustness and validity, demonstrating the potential of ML models in improving the reliability and efficiency of moisture-induced damage predictions. [ABSTRACT FROM AUTHOR]

Pavement condition prediction helps road agencies to schedule maintenance, rehabilitation, and reconstruction, and to allocate limited funds and resources to such activities. Compared to state highways, pavement performance prediction for local roads has received relatively little attention in the literature due to perceptions of low importance, low levels of investment in data collection, poor data quality, and high variation within the data elements. Additionally, local road pavement condition data may suffer from dataset imbalance, often leading to unreliable condition predictions. Hence, this paper introduces a methodology to predict local pavement condition using various single estimator and ensemble machine learning (ML) models along with the adaptive synthetic sampling method. The study develops nine (9) Bayesian-optimised ML models: category boosting (CatBoost), adaptive boosting, decision tree, extra trees, gradient boosting, light gradient-boosting machine, k-nearest neighbour, random forest, and artificial neural network. The ensemble ML and CatBoost were found to exhibit the best model performance, with an average testing accuracy of 0.82, specificity of 0.81, sensitivity of 0.63, and F-measure of 0.61. These results underscore the efficacy of ensemble ML models in pavement condition prediction. The proposed approach can be beneficial to local road agencies in their long-term planning, scheduling, and budgeting. [ABSTRACT FROM AUTHOR]

The present study explores the potential of machine learning to predict the porosity and permeability of pervious concrete constructed on mix parameters (compaction energy, aggregate-to-cement ratio and aggregate size) and ultrasonic velocity. The prediction models use non-destructive measurements and mixed design variables, which can help the construction sector apply the models without any theoretical expertise. The study uses 225 data samples from an experimental study. This study used six machine learning algorithms, namely, linear regression, artificial neural networks, boosted decision tree regression, random forest regression, K-nearest neighbour and support vector regression, to determine the best predictive model. The results show that the ANN model is the best technique for predicting the porosity of pervious concrete (R2 = 0.9502 for training datasets and R2 = 0.8958 for testing datasets) and boosted decision tress for permeability of pervious concrete (R2 = 0.9323 for training datasets and R2 = 0.7574 for testing datasets). The sensitivity analysis of the random forest regression model reveals that ultrasonic pulse velocity is the most influential parameter for the prediction of porosity and permeability of pervious concrete. The proposed models provide a more accurate method for estimating the porosity and permeability of pervious concrete. [ABSTRACT FROM AUTHOR]

Hydrological simulations and predictions are vital aspects of hydrological change research. Accurate predictions of hydrological factors such as stage and discharge are essential for water resources planning, reservoir dispatching and operation, shipping management and flood control. River discharge forecasting during flood seasons is an important issue in water resources planning and management. To improve the calibration accuracy and stability of the stage–discharge relationship model, the feasibility of integrated algorithms for studying the stage–discharge relationship was explored. A random forest (RF) algorithm based on a neural network (NN) was developed using a framework of integrated algorithms. First, the Levenberg–Marquardt (LM) algorithm was used to optimise the weight updating process of a back-propagation (BP) NN and improve the convergence speed. Then, the LM-BP algorithm was used as a decision tree to build an RF algorithm. The model was tested using hydrological data from Hongqi station on the Dadu River in China in the flood season. Results for the classical model, BP NN model, LM-BP NN model and optimised algorithm model were evaluated based on the mean absolute error (MAE), mean square error (MSE) and mean absolute percentage error (MAPE). The performance indicators showed that the optimised algorithm model (MAE = 3.13 m3/s, MSE = 19.28 m3/s and MAPE = 1.8%) was superior to the other models and showed high accuracy and good stability in flood-season flow forecasting. [ABSTRACT FROM AUTHOR]