Search Results (12,489)

Highway traffic officers (HTOs) are often exposed to life-threatening workplace incidents while performing their duties. However, scant research has been undertaken to address these safety concerns. This research explores case study data from highway incident reports (held by National Highways, a UK government company) and employs deep neural network (DNN) in unearthing patterns which inform safety decision makers on pertinent safety challenges confronting HTOs. A mixed philosophical stance of positivism and interpretivism was adopted to synthesise the findings made. A four-phase sequential method was implemented to evaluate the validity of the research viz.: (i) architectural design; (ii) data exploration; (iii) predictive modelling; and (iv) performance evaluation. The DNN model’s predictive performance is benchmarked against three other machine learning models, namely Support Vector Machines (SVM), Random Forest (RF), and Naïve Bayes (NB). The DNN model outperformed the other three models. Findings from the data exploration also show that most work operations undertaken by HTOs have a medium risk level with night shifts posing the greatest risk challenges. Carriageways and traffic management enclosures had the highest incident occurrence. This is the first study to uncover such hidden patterns and predict risk levels using a database specifically for HTOs. This study presents evidence-based information for proactive risk management for HTOs. Full article

Micro-expressions are very brief, involuntary facial expressions that reveal hidden emotions, lasting less than a second, while macro-expressions are more prolonged facial expressions that align with a person’s conscious emotions, typically lasting several seconds. Micro-expressions are difficult to detect in lengthy videos because they have tiny amplitudes, short durations, and frequently coexist alongside macro-expressions. Nevertheless, micro- and macro-expression analysis has sparked interest in researchers. Existing methods use optical flow features to capture the temporal differences. However, these optical flow features are limited to two successive images only. To address this limitation, this paper proposes LGNMNet-RF, which integrates a Lite General Network with MagFace CNN and a Random Forest classifier to predict micro-expression intervals. Our approach leverages Motion History Images (MHI) to capture temporal patterns across multiple frames, offering a more comprehensive representation of facial dynamics than optical flow-based methods, which are restricted to two successive frames. The novelty of our approach lies in the combination of MHI with MagFace CNN, which improves the discriminative power of facial micro-expression detection, and the use of a Random Forest classifier to enhance interval prediction accuracy. The evaluation results show that this method outperforms baseline techniques, achieving micro-expression F1-scores of 0.3019 on CAS(ME)2 and 0.3604 on SAMM-LV. The results of our experiment indicate that MHI offers a viable alternative to optical flow-based methods for micro-expression detection. Full article

Debris flow disasters frequently occur and pose considerable hazards; thus, it is essential to thoroughly evaluate their risks. This study constructs a database comprising 20 assessment indicators, utilizing comprehensive natural disaster risk assessment theory and incorporating the triggering factors of Huokou Lake in the Changbaishan Mountains. This research employs a hybrid ANP-CRITIC methodology to allocate weights to the assessment indicators efficiently. For hazard assessment, this research utilizes both the Information Quantity and Random Forest models for comparative analysis. The ROC curve was employed to validate the outcomes, ultimately favoring the Random Forest model due to its superior accuracy in assessing debris flow hazards. In this study, the risk of debris flow disasters in Antu County is comparatively assessed under scenarios with and without an outburst event. The findings indicate that areas of high and very high risk are predominantly located within the central regions of economically prosperous and densely populated townships. Additionally, the risk in Erdao Baihe Township escalates significantly when considering the outburst of Huokou Lake. The significance of this study lies in its ability to furnish a robust scientific basis for decision-makers aimed at preventing future debris flow disasters. Furthermore, it serves as a crucial reference for advancing sustainable regional development and facilitates the equilibrium between economic growth and environmental protection within disaster management strategies. Full article

This paper presents the experimental and numerical results of a study on producing axisymmetric parts made of the C60-grade steel by skew rolling. The experimental part of this study involved conducting the skew rolling process with varying parameters, including the forming angle α, tool angle θ, chuck velocity V_u, and reduction ratio δ. Their effect on the quality of produced parts was examined and described by the roughness parameter Ra. Numerical calculations involved the use of machine learning models to predict the quality class of produced parts. The highest prediction accuracy of the results was obtained with the random forest and logistic regression models. Metrics such as precision, recall and accuracy were used to evaluate the performance of individual models. Confusion matrices and ROC curves were also employed to illustrate the performance of the classification models. The results of this study will make it possible to prevent the formation of spiral grooves on the circumference of steel parts during the rolling process. Full article

This study employs machine learning models to predict the adsorption characteristics of biochar-activated carbon derived from waste wood. Activated carbon is a high-performance adsorbent utilized in various fields such as air purification, water treatment, energy production, and storage. However, its characteristics vary depending on the activation conditions or raw materials, making explaining or predicting them challenging using physicochemical or mathematical methods. Therefore, using machine learning techniques to determine the adsorption characteristics of activated carbon in advance will provide economic and time benefits for activated carbon production. Datasets, consisting of 108 points, were used to predict the adsorption characteristics of biochar-activated carbon derived from waste wood. The input variables were the activation conditions, and the iodine number of activated carbon was used as the output variable. The datasets were randomly split into 75% for training and 25% for model validation and normalized by the min-max function. Four models, including artificial neural networks, random forests, extreme gradient boosting, and support vector machines, were used to predict the adsorption properties of biochar-activated carbon. After optimization, the artificial neural network model was identified as the best model, with the highest coefficient determination (0.96) and the lowest mean squared error (0.004017). As a result of the SHAP analysis, activation time was the most crucial variable influencing the adsorption properties. The machine learning model precisely predicts the adsorption characteristics of biochar-activated carbon and can optimize the activated carbon production process. Full article

Chronic cough is associated with several respiratory diseases and is a significant burden on physical, social, and psychological health. Non-invasive, real-time, continuous, and quantitative monitoring tools are highly desired to assess cough severity, the effectiveness of treatment, and monitor disease progression in clinical practice and research. There are currently limited tools to quantitatively measure spontaneous coughs in daily living settings in clinical trials and in clinical practice. In this study, we developed a machine learning model for the detection and classification of cough sounds. Mel spectrograms are utilized as a key feature representation to capture the temporal and spectral characteristics of coughs. We applied this approach to automate cough analysis using 300 h of audio recordings from cough challenge clinical studies conducted in a clinical lab setting. A number of machine learning algorithms were studied and compared, including decision tree, support vector machine, k-nearest neighbors, logistic regression, random forest, and neural network. We identified that for this dataset, the CRNN approach is the most effective method, reaching 98% accuracy in identifying individual coughs from the audio data. These findings provide insights into the strengths and limitations of various algorithms, highlighting the potential of CRNNs in analyzing complex cough patterns. This research demonstrates the potential of neural network models in fully automated cough monitoring. The approach requires validation in detecting spontaneous coughs in patients with refractory chronic cough in a real-life setting. Full article

With increasing global concerns related to global warming, air pollution, and environmental health, South Korea is actively implementing various particulate matter (PM) reduction policies to improve air quality. Accurate data analysis, including the investigation of weather phenomena, monitoring, and integrated prediction, is essential for effective PM reduction. However, the factors influencing the PM generated from domestic road sections have not yet been systematically analyzed, and currently, no predictive models utilize weather and traffic data. This study analyzed the correlations among factors influencing PM to develop models for estimating fine and coarse PM (PM_2.5 and PM₁₀, respectively) concentrations in road sections. Regression analysis models were used to assess the sensitivity of PM_2.5 and PM₁₀ concentrations to the traffic volume, whereas machine learning-based models, including linear regression, convolutional neural networks, and random forest models, were constructed and compared. The random forest models outperformed the other models, with coefficients of determination of 0.74 and 0.71 and mean absolute errors of 5.78 and 9.60 for PM_2.5 and PM₁₀, respectively. These results indicate that the random forest model provides the most accurate PM concentration estimates for road sections. The practical applications of the developed models were considered to inform effective transportation policies aimed at reducing PM. The developed model has practical applications in the formulation of transportation policies aimed at reducing PM. In particular, the model will play an important role in data-driven policymaking for sustainable urban development and environmental protection. By analyzing the correlation between traffic volume and weather conditions, policymakers can formulate more effective and sustainable strategies for reducing air pollution. Full article

Climate change is increasing the occurrence of extreme weather events, such as intense windstorms, with a trend expected to worsen due to global warming. The growing intensity and frequency of these events are causing a significant number of failures in power distribution grids. However, understanding the nature of extreme wind events and predicting their impact on distribution grids can help and prevent these issues, potentially mitigating their adverse effects. This study analyzes a structured method to predict distribution grid disruptions caused by extreme wind events. The method utilizes Machine Learning (ML) models, including K-Nearest Neighbors (KNN), Random Forest (RF), Support Vector Machine (SVM), Decision Trees (DTs), Gradient Boosting Machine (GBM), Gaussian Process (GP), Deep Neural Network (DNN), and Ensemble Learning which combines RF, SVM and GP to analyze synthetic failure data and predict power grid outages. The study utilized meteorological information, physical fragility curves, and scenario generation for distribution systems. The approach is validated by using five-fold cross-validation on the dataset, demonstrating its effectiveness in enhancing predictive capabilities against extreme wind events. Experimental results showed that the Ensemble Learning, GP, and SVM models outperformed other predictive models in the binary classification task of identifying failures or non-failures, achieving the highest performance metrics. Full article

The sparse matrix–vector product (SpMV) is a fundamental computational kernel utilized in a diverse range of scientific and engineering applications. It is commonly used to solve linear and partial differential equations. The parallel computation of the SpMV product is a challenging task. Existing solutions often employ a fixed number of threads assignment to rows based on empirical formulas, leading to sub-optimal configurations and significant performance losses. Elegante, our proposed machine learning-powered tool, utilizes a data-driven approach to identify the optimal thread configuration for SpMV computations within a shared memory architecture. It accomplishes this by predicting the best thread configuration based on the unique sparsity pattern of each sparse matrix. Our approach involves training and testing using various base and ensemble machine learning algorithms such as decision tree, random forest, gradient boosting, logistic regression, and support vector machine. We rigorously experimented with a dataset of nearly 1000+ real-world matrices. These matrices originated from 46 distinct application domains, spanning fields like robotics, power networks, 2D/3D meshing, and computational fluid dynamics. Our proposed methodology achieved 62% of the highest achievable performance and is 7.33 times faster, demonstrating a significant disparity from the default OpenMP configuration policy and traditional practice methods of manually or randomly selecting the number of threads. This work is the first attempt where the structure of the matrix is used to predict the optimal thread configuration for the optimization of parallel SpMV computation in a shared memory environment. Full article

Background: Heart failure poses a significant global health challenge, with high rates of readmission and mortality. Accurate models to predict these outcomes are essential for effective patient management. This study investigates the impact of data pre-processing techniques on XGBoost model performance in predicting all-cause readmission and mortality among heart failure patients. Methods: A dataset of 168 features from 2008 heart failure patients was used. Pre-processing included handling missing values, categorical encoding, and standardization. Four imputation techniques were compared: Mean, Multivariate Imputation by Chained Equations (MICEs), k-nearest Neighbors (kNNs), and Random Forest (RF). XGBoost models were evaluated using accuracy, recall, F1-score, and Area Under the Curve (AUC). Robustness was assessed through 10-fold cross-validation. Results: The XGBoost model with kNN imputation, one-hot encoding, and standardization outperformed others, with an accuracy of 0.614, recall of 0.551, and F1-score of 0.476. The MICE-based model achieved the highest AUC (0.647) and mean AUC (0.65 ± 0.04) in cross-validation. All pre-processed models outperformed the default XGBoost model (AUC: 0.60). Conclusions: Data pre-processing, especially MICE with one-hot encoding and standardization, improves XGBoost performance in heart failure prediction. However, moderate AUC scores suggest further steps are needed to enhance predictive accuracy. Full article

Heavy metal pollution in agricultural land poses significant threats to both the ecological environment and human health. Therefore, the rapid and accurate prediction of heavy metal content in agricultural soil is crucial for environmental protection and soil remediation. Acknowledging the limitations of traditional single linear or nonlinear machine learning models in terms of prediction accuracy, this study developed an ensemble learning model that integrates multiple linear or nonlinear learning models with a random forest (RF) model to improve both the prediction accuracy and reliability. In this study, we selected a typical copper (Cu) polluted area in the Pearl River Delta of Guangdong Province as the research site and collected Cu content data and indoor soil reflectance spectral data from 269 surface soil samples. First, the soil spectral data were preprocessed using Savitzky–Golay (SG) smoothing, multiplicative scattering correction (MSC), and continuous wavelet transform (CWT) to reduce noise interference. Next, principal components analysis (PCA) was employed to reduce the dimensionality of the preprocessed spectral data, eliminating redundant features and lowering the computational complexity. Finally, based on the dimensionality-reduced data and Cu content, we established a stacked ensemble learning model, where the base models included SVR, PLSR, BPNN, and XGBoost, with RF serving as the meta-model to estimate the soil heavy metal content. To evaluate the performance of the stacking model, we compared its prediction accuracy with that of individual models. The results indicate that, compared to the traditional machine learning models, the prediction accuracy of the stacking model was superior (R² = 0.77; RMSE = 7.65 mg/kg; RPD = 2.29). This suggests that the integrated algorithm demonstrates a greater robustness and generalization capability. This study presents a method to improve soil heavy metal content estimation using hyperspectral technology, ensuring a robust model that supports policymakers in making informed decisions about land use, agriculture, and environmental protection. Full article

Leading edge (LE) erosion is a type of damage that inhibits the aerodynamic performance of a wind turbine, resulting in high operation and maintenance (O&M) costs. This paper makes use of a small dataset consisting of 50 images of LE erosion and healthy blades for feature extraction and the training of four types of classifiers, namely, support vector machine (SVM), random forest, K-nearest neighbour (KNN), and multi-layer perceptron (MLP). Six feature extraction methods were used with these classifiers to train 24 models. The dataset has also been used to train a convolutional neural network (CNN) model developed using Keras. The purpose of this work is to determine whether classical machine learning (ML) classifiers trained with extracted features can produce higher-accuracy results, train faster, and classify faster than deep learning (DL) models for the application of LE damage detection of wind turbine blades. The oriented fast and rotated brief (ORB)-trained SVM achieved an accuracy of 90% ± 0.01, took 80.4 s to train, and achieved inference speeds of 63 frames per second (FPS), compared to the CNN model, which achieved an accuracy of 79.4% ± 2.07, took 4667.4 s to train, and achieved an inference speed of 1.3 FPS. These results suggest that classical ML models can be more accurate and efficient than DL models if the appropriate feature extraction method is used. Full article

The aim of this study was to narrow the research gap of ambiguity in which machine learning algorithms should be selected for evaluation in digital soil organic carbon (SOC) mapping. This was performed by providing a comprehensive assessment of prediction accuracy for 15 frequently used machine learning algorithms in digital SOC mapping based on studies indexed in the Web of Science Core Collection (WoSCC), providing a basis for algorithm selection in future studies. Two study areas, including mainland France and the Czech Republic, were used in the study based on 2514 and 400 soil samples from the LUCAS 2018 dataset. Random Forest was first ranked for France (mainland) and then ranked for the Czech Republic regarding prediction accuracy; the coefficients of determination were 0.411 and 0.249, respectively, which was in accordance with its dominant appearance in previous studies indexed in the WoSCC. Additionally, the K-Nearest Neighbors and Gradient Boosting Machine regression algorithms indicated, relative to their frequency in studies indexed in the WoSCC, that they are underrated and should be more frequently considered in future digital SOC studies. Future studies should consider study areas not strictly related to human-made administrative borders, as well as more interpretable machine learning and ensemble machine learning approaches. Full article

Corn (Zea mays L.) silage yield monitor data offer crucial insights into spatial and temporal yield variability. However, equipment’s sensor malfunctioning can result in data loss, and yield sensor systems are expensive to purchase and maintain. In this study, we analyzed corn silage yield data from two fields and three years each for two dairy farms (Farm A and B). We aimed to explore the potential of integrating high-resolution satellite data, topography, and climate data with machine learning models to estimate missing yield data for a field or a year. Our objectives were to identify key yield-explaining features and assess the accuracy of different machine learning models in estimating silage yield. Results showed that the features differed among farms with a Two-Band Enhanced Vegetation Index, EVI2 (Farm A), and elevation (Farm B) emerging as the most prominent predictors. Ensemble-based models like XGBoost, Random Forest, and Extra Tree regressors exhibited superior predictive performance. However, XGBoost performed poorly when applied to unseen fields or years, whereas Extra Tree regressor, followed closely by Random Forest, emerged as a more reliable model for predicting missing data. Despite achieving reasonable accuracy, the best performance for estimating data for a missing field (6.46 Mg/ha) and year (5.51 Mg/ha) fell short of the acceptable error threshold of 4.9 Mg/ha currently used in state policy to evaluate if a management change resulted in a yield increase. These findings emphasize the need for higher-resolution data and extended years of yield records to better capture the trends in farm-scale yield applications. Full article

In the field of aeronautics, aircraft, as a critical aviation tool, exert a decisive influence on the structural integrity and safety of the entire system. Accurate prediction of the stress field distribution and variations within the aircraft structure is of great importance to ensuring its safety performance. To facilitate such predictions, a rapid assessment method for stress fields based on a multilayer perceptron (MLP) neural network is proposed. Compared to the traditional machine learning algorithm, the random forest algorithm, MLP demonstrates superior accuracy and computational efficiency in stress field prediction, particularly exhibiting enhanced adaptability when handling high-dimensional input data. This method is applied to predict stresses in the wing rib structure. By performing finite element meshing on the wing ribs, the angle of attack, inflow velocity, and node coordinates are utilized as input tensors for the model, enabling it to learn the stress distribution in the wing ribs. Additionally, a peak stress prediction model is separately established for regions experiencing peak stresses. The results indicate that the MAPE of the stress field prediction model is within 5%, with a coefficient of determination R² exceeding 0.994. For the peak stress model, the MAPE is within 2%, with an R² exceeding 0.995. This method offers faster computation and greater flexibility, presenting a novel approach for structural strength assessment. Full article