Search

Metamaterial absorbers (MMAs) have tremendous potential for controlling and modulating Terahertz electromagnetic (EM) waves. It is challenging to design MMAs for optimal performance using conventional methods due to their time-consuming and computationally demanding nature. Machine learning (ML) regressor approaches have emerged as potential tools for optimizing the predictive modeling of MMAs in recent years. This article examined different regression techniques, such as Decision Tree, k-Nearest Neighbors, Random Forest, Extra Trees (ET), Extreme Gradient Boosting, Bagging, and Categorical Boosting. The primary goal is to assess the effectiveness of each regressor technique in forecasting the performance of MMAs using various performance metrics. The study focuses on a representative spectrum of MMAs, chosen for its key features that are common across a wide range of MMAs. The extra tree Regressor outperforms other models in the comparative analysis due to its capacity to integrate multiple decision trees and include randomness into the feature selection process, resulting in improved predictive skills. The ET regressor forecasts MMA performance remarkably well for a 70 % test size, with a Root Mean Squared Error of 0.0251, a Mean Absolute Error of 0.0074, a Mean Squared Error of 0.006, and an Adjusted R-squared of 0.9873. These findings can assist researchers in optimizing metamaterial absorber designs for Terahertz applications using ML regressor techniques and provide insights into how these methods can be generalized to other spectra with similar characteristics. [ABSTRACT FROM AUTHOR]

• Soil moisture of a semi-humid region was estimated from Sentinel-1 data. • Three machine learning algorithms were compared. • Random forest performed better than SVM and ANN. • Soil moisture is higher in the Yellow River National Wetland Park. • Soil moisture is affected by precipitation, temperature, and vegetation. Soil moisture (SM) plays a critical role in the growth and management of grain in semi-humid regions. However, little is known about how to integrate satellite data with machine learning to accurately retrieve SM information in these areas. This study compares the capability of three machine learning algorithms, Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Network (ANN), to extract SM information over the Northwest Shandong Plain using multi-phase dual-polarized Sentinel-1A satellite data. The backscattering coefficients were obtained through standard intensity and phase processing to calculate the SAR indices, and several characteristic parameters were extracted as impact factors using the Cloude-Pottier decomposition. The importance of these factors was analyzed, while the performance of each machine learning algorithm was comprehensively evaluated using the K-fold cross-validation method. The best-performing model was utilized to retrieve the spatio-temporal changes in SM in the study area. The findings indicate the following: (1) The first eigenvalue has the greatest impact on retrieval accuracy, followed by entropy, where the intensity component of Shannon's entropy is more important than its polarization component; (2) The addition of more impact factors does not bring a continuous improvement in model performance, but the optimal factor combinations differ for different machine learning retrieval models; (3) The RF model trained using the IM12 combination demonstrates better performance than SVM and ANN in retrieving SM information, with a coefficient of determination (R2) of 0.55 and a root mean square error of 6.12 vol% on the validation set. The level of SM in the Yellow River National Wetland Park is higher than that of the surrounding areas, with substantial seasonal changes. Precipitation, temperature, and vegetation significantly influence the regional variations in SM at the macroscopic level. [ABSTRACT FROM AUTHOR]

The escalating consumption of fossil fuels has given rise to a substantial upsurge in greenhouse gas concentrations and global temperatures, which, in turn, has triggered severe climate-related consequences. The critical imperative to reduce CO 2 emissions and combat global warming has spurred extensive investigations into clean energy alternatives, with hydrogen emerging as a compelling zero-emission energy source. As a pivotal component of clean energy strategies, hydrogen requires designing compact, lightweight, and efficient storage systems. This study focuses on the development and evaluation of machine learning models for predicting the efficiency of Metal-Organic Frameworks (MOFs) in hydrogen storage, a key aspect of advancing clean energy technologies. MOFs, a class of nanoporous materials, show remarkable potential for hydrogen storage due to their high surface area and porosity. However, selecting the most suitable MOF for this application from a vast array of possible structures is a daunting task. In this context, machine learning algorithms offer an efficient alternative for predicting MOF suitability by considering their structural and chemical properties. We used ensemble learning methods, specifically Light Gradient Boosting Machine (LightGBM) and Random Forest (RF), to predict hydrogen uptake of MOFs based on a dataset of 219 experimentally tested samples. Two modeling scenarios were considered: one using the entire dataset, and the other involving strategic data pre-processing, including outlier removal and feature engineering. The results demonstrate that the measures taken to refine the dataset significantly enhance the predictive performance of the developed models, reducing prediction errors and improving overall goodness of fit. Specifically, the Mean Absolute Error (MAE) values for both the LightGBM and random forest models were reduced from 0.48 and 0.94, respectively, to 0.16 for both models, and the coefficients of determination (R2) increased substantially from 0.84 and 0.72 to 0.95, in both cases. Moreover, feature importance analysis unveiled that pressure-related features make the most significant contributions to the formation of tree ensembles during the model training process. A parametric sensitivity analysis was conducted revealing that H 2 uptake in MOFs is most sensitive to changes in adsorption enthalpy, followed by surface area and temperature, while showing lower sensitivity to variations in pressure, consistent with established literature. These results underscore the pivotal role of data enhancement methods in refining machine learning models and can be instrumental in accelerating the development and optimization of MOF materials for clean energy applications. [Display omitted] • Effective connectionist tools are used to assess H 2 storage with MOF. • LightGBM model exhibits a better prediction accuracy, compared to RF. • H 2 uptake in MOFs is most sensitive to changes in adsorption enthalpy. • Increased surface area and pressure lead to higher H 2 uptake. • Data pre-processing steps considerably improve the model predictive performance. [ABSTRACT FROM AUTHOR]

One of the most dangerous threats in WSNs is botnet attacks, in which attackers use mutual communications between IoT devices to launch large-scale malicious activities. In this regard, developments in the field of effective and reliable means of defence against this type of threat, in particular, reliable methods for detecting, identifying, and countering botnet attacks, are becoming increasingly important and relevant. This paper presents a comprehensive study that applies machine learning techniques, namely Random Forest and XGBoost, to identify botnet attacks on IoT effectively. These algorithms are analyzed, compared, and shown to be highly effective in detecting complex patterns indicative of botnet activity, thus achieving a significant improvement in IoT security. The conducted research aims to make a useful contribution to the problem of securing WSNs and IoT in general. The results of the study demonstrated high accuracy in detecting attacks with an accuracy of 99.18% for XGBoost and Random Forest showed an accuracy of 99.21%. Thus, it was shown that the significance of applying machine learning techniques such as Random Forest and XGBoost can be one of the key approaches in combating botnet attacks and securing the IoT. The results of the work emphasize the promising application of machine learning techniques for effective defense against cyber threats and highlight the importance of further. [ABSTRACT FROM AUTHOR]

Rock physics plays an important role in the oil, gas, and water industries by providing essential data for reservoir management. This study focuses on predicting Shear Wave Velocity (Vs), a key geophysical parameter, using the Deep Belief Network (DBN) and Random Forest (RF) algorithms. The dataset is divided for training, validation, and testing, revealing that the DBN model surpasses the RF and empirical models in accuracy. With a low RMSE value of 0.0398 km/s in testing and an R2 of 0.9775, the DBN model demonstrates precision in Vs prediction. The analysis identifies specific parameters—Measure Depth (MD), Caliper (CALL), Gamma Ray (GR), Shallow Electrical Resistivity (RES-S), Medium Electrical Resistivity (RES-M), Deep Electrical Resistivity (RES-D), Compressional Wave Velocity (DCT), Neutron Porosity (NPHI), and Photoelectric Coefficient Index (PEF)—as significantly influencing Vs, while CALI and GR have a relatively lesser effect. The results of the Vs prediction indicated that the DBN algorithm excels in deep feature extraction, unsupervised pretraining, and efficient handling of complex data. Ultimately, the DBN algorithm proves to be a superior and time-saving alternative for Vs prediction and analysis in subsurface reservoirs. • Rock physics aids oil, gas, and water industries through crucial reservoir data. • Deep Belief Network (DBN) excels in Vs prediction with superior performance. • DBN model achieves remarkable precision with a low RMSE of 0.0398 km/s. • Correlation analysis identifies key parameters influencing shear wave velocity (Vs). • DBN algorithm proves a time-saving, reliable alternative for Vs prediction in subsurface reservoirs. [ABSTRACT FROM AUTHOR]

Machine learning applications in the medical field has proliferated in the past decade. One of the main usages of machine learning in medical field is the detection of diseases from text and image data. In this work, a new hybrid multi-layer algorithm (MLHA) based on machine learning algorithms is proposed to predict diabetes. The algorithm consists of two layers. The first layer consists of three different machine learning algorithms; SVM, random forest and K-mean, that work in parallel on the dataset. The output of this layer is fed into the second layer that consists of only one algorithm; XGBoost, that is trained from the output data of the first layer. We trained the proposed model with two different datasets and its accuracy has been compared with three different common well-known algorithms; feed forward back propagation neural network, logistic regression and random forest. Our results show that the accuracy of MLHA reached 86.5% for the first dataset and approximately 84.6% for the second dataset. This reported accuracy outperformed all the classical models. [ABSTRACT FROM AUTHOR]

An enormous number of deaths occur every year as a result of heart disease, making it a major concern in world health. Improving patient outcomes and lowering death rates, early detection and correct diagnosis of cardiac disease play a key role. When the heart's arteries become blocked, oxygen-poor blood cannot reach the heart properly, resulting in coronary heart disease. Early detection of cardiac disease is viable because it reduces medical costs and potentially saves the patient's life. Recently presented methods have improved heart failure detection accuracy on testing data without sacrificing accuracy on training data, yet most of these algorithms are suffering from the issue of overfitting. Models that were created end up fitting the test data too well. In this study, we create a novel diagnostic system to address this issue, and the resulting system demonstrates high intelligence and excellent performance on both training and testing data. Machine learning (ML) algorithms have demonstrated promising potential in assisting healthcare professionals with timely and accurate diagnosis. In this paper, is based on supervised machine learning methods are decision tree (DT), random forest (RF), Support vector Machine (SVM), Principal Component Analysis(PCA). We compare their accuracy with each other by using bar plot. [ABSTRACT FROM AUTHOR]

Proteolysis is a complex biochemical event during cheese storage that affects both functionality and quality, yet there are few tools that can accurately predict proteolysis for Mozzarella and Cheddar cheese across a range of parameters and storage conditions. Machine learning models were developed with input features from the literature. A gradient boosting method outperformed random forest and support vector regression methods in predicting proteolysis for both Mozzarella (R2 = 92%) and Cheddar (R2 = 97%) cheese. Storage time was the most important input feature for both cheese types, followed by coagulating enzyme concentration and calcium content for Mozzarella cheese and fat or moisture content for Cheddar cheese. The ability to predict proteolysis could be useful for manufacturers, assisting in inventory management to ensure optimum Mozzarella functionality and Cheddar with a desired taste, flavor and texture; this approach may also be extended to other types of cheese. [ABSTRACT FROM AUTHOR]

Globally, the building sector is a significant consumer of energy. Implementing effective energy management system (EMS) strategies is crucial for reducing energy consumption and optimizing energy usage across all building elements. Moreover, solar energy is increasingly recognized as essential for sustainable building and urban development. Thus, the energy production forecast from photovoltaic systems installed on buildings is pivotal for a smart EMS's realization and optimal functioning. By incorporating accurate energy production forecasts, we can optimize energy consumption by fitting consumption patterns with production peaks and valleys. This study presents a comparative analysis of five widely used machine learning regressing models, including Random Forest, Decision Trees, XGBoost, LightGBM, and CatBoost for predicting the hourly energy production from a PV system mounted on a building. In this investigation, weather data and time-related characteristics were utilized as predictors. The results showed that LightGBM outperformed the other models, proving its suitability for PV energy forecasting tasks. [ABSTRACT FROM AUTHOR]

Predicting the property insurance claim has become very important due to the increasing demand for property and the fluctuating number of monthly claims. However, current prediction methods suffer from limited feature important information and imbalanced claim data. This research introduces a machine learning approach by considering demographic factors of insured objects and marketing strategies to predict claim trends. The study also tackles data imbalance using the SMOTE technique. Results reveal that random forest outperforms logistic regression, achieving a recall value of 96%. The research findings enable insurance companies to better analyze insured risk profiles and manage the number of claims. [ABSTRACT FROM AUTHOR]

Mental well-being is critical to an individual's health and quality of life. It encompasses emotional, psychological, and social dimensions, making it a complex and multifaceted construct. Traditionally, assessing and forecasting mental well-being has relied on self-report measures, clinical evaluations, and surveys, which can be subjective, time-consuming, and limited scope. To overcome these drawbacks and offer more precise and timely insights into mental well-being, this study presents a novel approach that uses the power of machine learning. This has been achieved by creating a comprehensive dataset containing various variables relevant to mental health. These variables include behavioral traits like exercise routines, sleep patterns, and social interactions and psychological traits like mood, stress levels, and emotional states. Environmental factors, such as geographic location, climate, and accessibility to mental health care, are also considered. A comprehensive understanding of the elements affecting mental well-being is made possible by this diversified dataset. The data is analyzed using machine learning models, such as deep learning neural networks, support vector machines, and random forests. These models were selected since they can capture intricate correlations and patterns in data, making them suitable for forecasting mental health. [ABSTRACT FROM AUTHOR]

India is the world's second-largest exporter of agricultural products. Agriculture is India's most populated sector of the economy which plays a key part in the country's overall socio-economic fabric. Crop yield prediction is crucial yet desirable for every country to ensure food security. Machine learning can be a very important decision support tool for the prediction of crop yield which can help in preparing for the future in a much more substantial way. Many studies have been conducted for crop yield prediction using multi-source data, still, the predictions of the crop of the Rajasthan region in India have not been investigated. In the present study well-known machine learning techniques, decision tree, random forest, lasso regression, and support vector regression have been implemented for crop yield prediction using multi-source data. Machine learning techniques were implemented on data set that consists of Vegetation Indices, extracted from remote sensing data and Weather data. Random forest attained the more accurate prediction with the coefficient of determination (R2) of 0.77, root mean square error of 0.39 t/ha and mean absolute error of 0.28 t/ha. The research obtained a good estimation of crop yield prior to the harvest. The crop yield is impacted by the change in environmental factors, this research would assist the farmers to have a prior estimation of the yield. The study also reveals that gradually adding more data to the model increases the overall prediction rate. [ABSTRACT FROM AUTHOR]

• It is possible to obtain good classification results of cardiovascular autonomic neuropathy using supervised machine learning. • The best classifier is the random forest classifier with a F1-score of 60% on the reduced dataset. • In the ensembled data no standard clinical biochemical analytes were present in the 10 best classifiers. Using supervised machine learning to classify the severity of cardiovascular autonomic neuropathy (CAN). The aims were 1) to investigate which features contribute to characterising CAN 2) to generate an ensembled set of features that best describes the variation in CAN classification. Eighty-two features from demographic, beat-to-beat, biochemical, and inflammation were obtained from 204 people with diabetes and used in three machine-learning-classifiers, these are: support vector machine, decision tree, and random forest. All data were ensembled using a weighted mean of the features from each classifier. The 10 most important features derived from the domains: Beat-to-beat, inflammation markers, disease-duration, and age. Beat-to-beat measures associate with CAN as diagnosis is mainly based on cardiac reflex responses, disease-duration and age are also related to CAN development throughout disease progression. The inflammation markers may reflect the underlying disease process, and therefore, new treatment modalities targeting systemic low-grade inflammation should potentially be tested to prevent the development of CAN. Cardiac reflex responses should be monitored closely to diagnose and classify severity levels of CAN accurately. Standard clinical biochemical analytes, such as glycaemic level, lipidic level, or kidney function were not included in the ten most important features. Beat-to-beat measures accounted for approximately 60% of the features in the ensembled data. [ABSTRACT FROM AUTHOR]

A machine learning model was proposed to accelerate the preparation of Al 2 O 3 –SiO 2 porous ceramics (ASPC) based on few-shot datasets. Phosphate tailings and bauxite were used as raw materials to prepare ASPC and obtain the initial dataset. The accuracy and generalization ability of the model are heavily influenced by the dataset partitioning method. 10-fold cross-validation and random sampling were compared to identify the optimal approach for training and testing the model on the limited data. Four commonly used regression algorithms of RF, KNN, SVR and BPNN were selected to predict the mechanical properties of ASPC. Based on the evaluation of model performance, the random forest algorithm was found to be the most suitable for small sample datasets. Using the trained random forest model, the feature importance of ASPC performance was analyzed, and a new ASPC database was established. Experimental schemes with the desired performance were obtained through screening from ASPC database. Finally, the ASPC with the target performance was prepared experimentally. The result demonstrated that employing machine learning techniques on few-shot datasets could effectively tackle the issues of low efficiency and insufficient data samples. [ABSTRACT FROM AUTHOR]

An accurate carbon price prediction is vital for governments to formulate emission reduction policies and for corporate managers to carry out sustainable management. Although many models have been proposed to meet this purpose, there is still a lack of comprehensive comparisons among the key competing models in a single study. This study conducted a comprehensive evaluation of six feature selection methods and six machine learning models for carbon price prediction, and then proposed a novel data-driven hybrid model that integrates singular spectrum analysis, random forest, and long short-term memory neural network. The results show that random forest and long short-term memory neural networks are the most competitive feature selection and prediction models, respectively. It is more reasonable to construct the model's input by comprehensively considering variables' short-, medium-, and long-term features. When the recombination value is approximately half the length of the embedding window, the singular spectrum analysis is most conducive to improving the prediction accuracy. The hybrid model proposed is always significantly superior to other benchmark models. Our work contributes to guiding carbon price modeling to help regulators and managers accurately grasp carbon price signals. [ABSTRACT FROM AUTHOR]

Our study aimed to develop a machine learning ensemble to distinguish "at-risk mental states for psychosis" (ARMS) subjects from control individuals from the general population based on facial data extracted from video-recordings. 58 non-help-seeking medication-naïve ARMS and 70 healthy subjects were screened from a general population sample. At-risk status was assessed with the Structured Interview for Prodromal Syndromes (SIPS), and "Subject's Overview" section was filmed (5–10 min). Several features were extracted, e.g., eye and mouth aspect ratio, Euler angles, coordinates from 51 facial landmarks. This elicited 649 facial features, which were further selected using Gradient Boosting Machines (AdaBoost combined with Random Forests). Data was split in 70/30 for training, and Monte Carlo cross validation was used. Final model reached 83 % of mean F1-score, and balanced accuracy of 85 %. Mean area under the curve for the receiver operator curve classifier was 93 %. Convergent validity testing showed that two features included in the model were significantly correlated with Avolition (SIPS N2 item) and expression of emotion (SIPS N3 item). Our model capitalized on short video-recordings from individuals recruited from the general population, effectively distinguishing between ARMS and controls. Results are encouraging for large-screening purposes in low-resource settings. [ABSTRACT FROM AUTHOR]

Internet traffic prediction plays a significant role in network management, network planning, utilization of the network resources, and quality of service. Internet future traffic can be predicted based on past traffic characteristics, it is possible only when we have accurate statistics of the network parameters. Prediction of the network traffic can be for the dynamic allocation and deallocation of the network resoureces as well as the congestion avoidance. We aim to predict the Software defined network(SDN) traffic. SDN is the enhanced architecture of the traditional network which separates the control plane with the data plane. In SDN the control plane has centralized control over the network. In this paper we applied Random Forest(RF), eXtreme Gradient Boosting(XGBoost), Light Gradient Boosting Model(LightGBM) as three base ensemble machine learning models, and proposed an advanced ensemble machine learning model which is a combination of these three models on the real world data with different sampling intervals and showed that the proposed model outperforms the other base models. [ABSTRACT FROM AUTHOR]

In this work, a detailed dataset containing 4051 data points gathered from 527 distinct experiments in 100 published articles for catalytic CO 2 methanation was analyzed using machine learning methods. A pre-analysis of the database was performed using simple descriptive statistics while a random forest (RF) model was developed to predict CO 2 conversion as the function of 23 descriptors including catalyst properties, preparation methods, and reaction conditions. Boruta analysis was also performed to identify the significant variables. The random forest model was found to be quite successful in predicting CO 2 conversion with the training and testing root mean square error (RMSE) of 6.4 and 12.7 respectively; R2 was 0.97 for training while it was 0.85 for testing. The success of the model was also verified by computing CO 2 conversion profiles for individual experiments in test data and comparing them with those reported in the related papers. [Display omitted] • Catalytic CO 2 methanation was studied using machine learning. • Dataset contained 4051 data points from 100 published paper. • Simple descriptive statistics and random forest (RF) were used as tools. • RF successfully predicted CO 2 conversion profiles for the test cases. [ABSTRACT FROM AUTHOR]

This study is targeted to use AI (artificial intelligence) to predict the English proficiency test scores (CET-4) of students in private universities. The study will train and test multiple machine learning models using a dataset of students' demographic information, English language background, and test scores. These models will use different algorithms such as linear regression, decision trees, and neural networks to identify patterns and relationships in the data and make accurate predictions. The study aims to develop a reliable and effective predictive tool for educators to assess students' language proficiency levels and provide targeted teaching strategies. Comprehensive evaluation of students' overall quality will play a crucial role in the prediction model. Factors such as educational resources, teaching methods, student learning habits, and learning atmosphere in each college will affect the accuracy of the prediction. The full-coverage classification prediction of student performance using modern scientific and technological strategies holds great research significance for private universities' educational tasks and targeted teaching plans. [ABSTRACT FROM AUTHOR]

Near-surface air temperature is a key variable used in a wide range of applications showing the environmental conditions of the Earth. Standard meteorological observations generally provide the best estimation with high accuracy over time for a small area of influence. However, considerable uncertainty arises when point measurements are extrapolated or interpolated over much larger areas. Satellite and reanalysis products have emerged as a viable alternative or supplement to in situ observations due to their availability over vast ungauged regions. Thus, spatial patterns of air temperature can be derived from these products. In this study, we evaluate the performance of several reanalysis products of near-surface air temperature to determine the best product in estimating daily and monthly air temperatures across the complex terrain of Turkey. European Center for Medium-Range Weather Forecasts Reanalysis version 5 (ERA5), (AgERA5), (ERA5-Land), the Modern-Era Retrospective Analysis for Research and Applications version 2 (MERRA2), and the Japanese 55-year Reanalysis (JRA-55) products are assessed with 1120 ground-based gauge stations for the period 2015–2019 over complex terrain having different climate classes according to Köppen-Geiger classification scheme and land surface types. Moreover, several traditional and more sophisticated machine learning downscaling algorithms are applied to increase the products' spatial resolution. The agreement between ground observations and the different products and the downscaled temperature product is investigated by using a set of commonly employed statistical estimators of mean absolute error (MAE), correlation coefficient (CC), root-mean-square error (RMSE), and bias. Performance analysis of reanalysis air temperature products with ground-based observations on daily and monthly time series has shown that among the five datasets, the AgERA5 product is superior in estimating air temperature over Turkey, both seasonally and annually. Compared to the other datasets, ERA5 and ERA5-Land show similar performance and reach the second highest performance score at both daily and monthly time steps. In terms of improving product performance with spatial downscaling, among the distance-based methods, the best overall performance is obtained by bicubic interpolation with a slight increase in the product performance in monthly and daily time series. However, depending on the season, the Random Forest algorithm's performance is far superior to all other methods used in this study. [ABSTRACT FROM AUTHOR]

• Machine learning has the potential to improve the positive predictive value of neonatal screening for primary and central congenital hypothyroidism. • Currently, detection of central congenital hypothyroidism is accompanied by a high number of false-positives. • In order of importance, variables determining detection of congenital hypothyroidism were TSH, T4/TBG, (gestational) age, TBG, T4, and age at NBS sampling. • From the current routine screening parameters, T4/TBG is the most important parameter to detect central congenital hypothyroidism with a low positive predictive value. • New screening parameters are needed to improve the detection of central congenital hypothyroidism. The Dutch Congenital hypothyroidism (CH) Newborn Screening (NBS) algorithm for thyroidal and central congenital hypothyroidism (CH-T and CH-C, respectively) is primarily based on determination of thyroxine (T4) concentrations in dried blood spots, followed by thyroid-stimulating hormone (TSH) and thyroxine-binding globulin (TBG) measurements enabling detection of both CH-T and CH-C, with a positive predictive value (PPV) of 21%. A calculated T4/TBG ratio serves as an indirect measure for free T4. The aim of this study is to investigate whether machine learning techniques can help to improve the PPV of the algorithm without missing the positive cases that should have been detected with the current algorithm. NBS data and parameters of CH patients and false-positive referrals in the period 2007–2017 and of a healthy reference population were included in the study. A random forest model was trained and tested using a stratified split and improved using synthetic minority oversampling technique (SMOTE). NBS data of 4668 newborns were included, containing 458 CH-T and 82 CH-C patients, 2332 false-positive referrals and 1670 healthy newborns. Variables determining identification of CH were (in order of importance) TSH, T4/TBG ratio, gestational age, TBG, T4 and age at NBS sampling. In a Receiver-Operating Characteristic (ROC) analysis on the test set, current sensitivity could be maintained, while increasing the PPV to 26%. Machine learning techniques have the potential to improve the PPV of the Dutch CH NBS. However, improved detection of currently missed cases is only possible with new, better predictors of especially CH-C and a better registration and inclusion of these cases in future models. [ABSTRACT FROM AUTHOR]

Among the different contactless techniques for medical diagnosis, hyperspectral imaging has gained relevance due to the high accuracy in tissues classification. Several techniques have been proposed to elaborate these images, ranging from traditional machine learning methods to deep learning algorithms. This paper evaluates three popular machine learning methods, namely Support Vector Machine (SVM), Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) considering a dataset of hyperspectral skin cancer images. The study demonstrates that the proposed algorithms are suitable for medical hyperspectral data classification, particularly when considering a small dataset. [ABSTRACT FROM AUTHOR]

Under the pressure of energy and environmental protection, new energy vehicles have become the future direction of automotive development. However, the safety performance of the power battery has always been the most critical indicator in the new energy vehicle industry. The battery will be aged in the continuous charging and discharging cycle, and the aging will cause safety hazards when it reaches a limit. A model that can predict the battery life can be obtained using Machine Learning. To obtain models that can predict power battery life relatively accurately, this paper revolves around the chaos sparrow search optimization algorithm, Random Forest, XGBoost, LightGBM, CatBoost, and NN, the importance assessment of the features, the hyperparameter search process, and the comparison of the differences and performance between the different algorithms are discussed. CatBoost has the highest prediction accuracy, with the amount of predicted data with a relative error of less than 10% being 88.44%. (a total of 10,275 data in the test set). And finally comes up with a general approach to predicting power battery life using Machine Learning. [ABSTRACT FROM AUTHOR]

Forest resources are the primary components of the ecosystem environment. Poplars (Populus sp.), a member of the fast-growing trees, are one of the most productive forest tree species for industrial production thanks to their desirable traits comprising rapid growth, hybridization ability, and ease of propagation. Determining poplar cultivated areas and mapping their geographical distributions is critical for planners and decision-makers to increase the ecological and economic benefits of poplar trees. Due to the biodiversity of each geographical region and seasonal vegetation variations, classification based on remotely sensed imagery is essential for cropland monitoring. The main goal of this study is to evaluate the potential of high-resolution multi-temporal (growing season and end of the growing season) Worldview-3 imagery in mapping poplar plantations in the Akyazı district of Sakarya, Turkey. For this purpose, pixel- and object-based image analysis with up-to-date ensemble learning algorithms, namely random forest (RF), categorical boosting (CB), and extreme gradient boosting tree (XGB), were employed for mapping poplar fields. Results indicated that the object-based classification approach provided statistically significant improvements in map-level (about 4%) and class-level accuracy (e.g., approximately 7% and %2 for poplar and young poplar classes, respectively) than pixel-based classification. While the CB performed superior classification performance for the object-based approach (92.56%), the highest classification performance was obtained with the XGB algorithm for the pixel-based approach (90.42%) for the end of the growing season data. McNemar's statistical test also confirmed that the performances of CB and XGB algorithms were statistically similar in pixel-based classification. Finally, analysis of multi-season images revealed that sensitivity of the vegetation phenology and seasonal effects considerably affect the separability of poplar tree species. [ABSTRACT FROM AUTHOR]

A robust short-term significant wave height (Hs) modelling framework based on an ensemble local mean decomposition method integrated with random forest (i.e. , En-RLMD-RF) is developed. The robust local mean decomposition (RLMD) decomposed the Hs data series into three subseries; amplitude modulation, frequency modulation and the low-frequency product function (PFs). The partial autocorrelation function was employed to determine the correlation-based significant predictor signals between the PFs at t 0 and t 1. Then the statistically significant PFs were incorporated into the random forest (RF) to construct the RLMD-RF model. The RLMD-RF based forecasted PFs were used again in the RF model as input predictors resulting in an ensemble-based RLMD-RF (i.e. , En-RLMD-RF) model for forecasting short-term Hs. The En-RLMD-RF model is validated and compared with RF, extreme learning machine (ELM) and multiple linear regression (MLR) models and their hybrids RLMD-RF, RLMD-ELM, RLMD-MLR, En-RLMD-ELM and En-RLMD-MLR counterparts using a set of performance metrics. The results demonstrated that the En-RLMD-RF model generates better forecasting accuracy against the benchmarking models. This study is beneficial for the application and optimization of more clean energy resources worldwide for sustained energy generation. [ABSTRACT FROM AUTHOR]

Distributed Denial of Service (DDoS) is a type of attack that leverages many compromised systems or computers, as well as multiple Internet connections, to flood targeted resources simultaneously. A DDoS attack's main purpose is to disrupt website traffic and cause it to crash. As traffic grows over time, detecting a Distributed Denial of Service (DDoS) assault is a challenging task. Furthermore, a dataset containing a large number of features may degrade machine learning's detection performance. Therefore, in machine learning, it is necessary to prepare a relevant list of features for the training phase in order to obtain good accuracy performance. With far too many possibilities, choosing the relevant feature is complicated. This study proposes the Boruta algorithm as a suitable approach to achieve accuracy in identifying the relevant features. To evaluate the Boruta algorithm, multiple classifiers (J48, random forest, naïve bayes, and multilayer perceptron) were used so as to determine the effectiveness of the features selected by the the Boruta algorithm. The outcomes obtained showed that the random forest classifier had a higher value, with a 100% true positive rate, and 99.993% in the performance measure of accuracy, when compared to other classifiers. [ABSTRACT FROM AUTHOR]

[Display omitted] • The odor production of domestic waste with various component is investigated experimentally. • Prediction for odor gas generation from domestic waste is established based on machine learning. • Prediction results are further discussed based on the microbial fermentation of domestic waste. Domestic waste is prone to produce a variety of volatile organic compounds (VOCs), which often has unpleasant odors. A key process in treating odor gases is predicting the production of odors from domestic waste. In this study, four factors of domestic waste (weight, wet composition, temperature, and fermentation time) were adopted to be the prediction indicators in the prediction for domestic waste odor gases. Machine learning models (Random Forest, XGBoost, LightGBM) were established using the odor intensity values of 512 odor gases from domestic waste. Based on these data, the regression prediction with supervised machine learning was achieved, in which three different algorithmic models were evaluated for prediction performance. A Random Forest model with a R2 value of 0.8958 demonstrated the most accurate prediction of the production of domestic waste odor gas based on our data. Furthermore, the prediction results in the Random Forest model were further discussed based on the microbial fermentation of domestic waste. In addition to enhancing our knowledge of the production of odor from domestic waste, we also explore the application of machine learning to odor pollution in our study. [ABSTRACT FROM AUTHOR]

There is a demand for flowers globally all year round, more particularly roses, necessitating increased production for flowers. Demand for roses has increased due to their year-long availability as well as its uses in cosmetic, perfume, medicinal products, food raw materials and decoration industry. Rose plants are prone to drastic fluctuations in temperature, drought stress damages, and low precipitations. These resulted to an increase in greenhouse production to generate optimum supply to meet growing demands as controlled environment provides several advantages. In this study, four machine learning models (random forest, support vector machine, multinomial logistic regression, and artificial neural networks) were applied to roses greenhouse cultivation dataset. The study aims to classify the most suitable greenhouse environment to upgrade the roses state leading to the optimal production of roses. Four model configurations corresponding to the pre-processing techniques were tested. These were scaling only, scaling plus removal of outliers, scaling plus SMOTE, and scaling with removal of outliers plus SMOTE. Random forest with all pre-processing steps applied to the dataset obtained the best performance with the highest weighted F1- scores, weighted-average precision, weighted-average recall, and Cohen's kappa statistic. This indicates that machine learning models can predict corrective actions leading to improved conditions of roses. The notable contribution of this research is to find valid and reliable classification models that assist growers in predicting the best greenhouse micro-environment. [ABSTRACT FROM AUTHOR]

Parkinson's disease (PD) is a neurodegenerative disorder affecting 60% of people over the age of 50 years. Patients with Parkinson's (PWP) face mobility challenges and speech difficulties, making physical visits for treatment and monitoring a hurdle. PD can be treated through early detection, thus enabling patients to lead a normal life. The rise of an aging population over the world emphasizes the need to detect PD early, remotely and accurately. This paper highlights the use of machine learning techniques in telemedicine to detect PD in its early stages. Research has been carried out on the MDVP audio data of 30 PWP and healthy people during training of 4 ML models. Comparison of results of classification by Support Vector Machine (SVM), Random Forest, K-Nearest Neighbors (KNN) and Logistic Regression models, yield Random Forest classifier as the ideal Machine Learning (ML) technique for detection of PD. Random Forest classifier model has a detection accuracy of 91.83% and sensitivity of 0.95. Through the findings of this paper, we aim to promote the use of ML in telemedicine, thereby providing a new lease of life to patients suffering from Parkinson's disease. [ABSTRACT FROM AUTHOR]

Anomaly-based network intrusion detection systems are highly significant in detecting network attacks. Robust machine learning and deep learning models for identifying network intrusion and attack types are proposed in this paper. Proposed models have experimented with the UNSW-NB15 dataset of 49 features for nine different attack samples. Decision Tree classifier produced the best accuracy of 99.05% compared to ensemble models - Random forest(98.96%), Adaboost(97.87%), and XGBoost(98.08%). K-Nearest Neighbour classifier trained for various values of K and best performance obtained for K=7 with the accuracy of 95.58%. A Deep Learning model with two dense layers with ReLU activation and a third dense layer with a Sigmoid activation function is designed for binary classification and produced good accuracy of 98.44% with ADAM optimizer, 80:20 Train-Test Split Ratio. Network attack exploits are detected with an accuracy 95% by XGBoost, Fuzzers attack with 90% accuracy by Random Forest, Generic attacks with 99% accuracy by Random Forest, and Reconnaissance attacks with 79% by Decision Trees. All features are relevant and strong in network attack detection, which eliminates the requirement of feature selection. [ABSTRACT FROM AUTHOR]

Students face problems that might hinder their academic pursuit toward success, problems ranging from trivial matters such as class condition, feeling of the student to severe matters such as family breakdown, economic reasons, and many more. This is a major problem because students shape the future of a nation – which will affect many things in the future. Teachers are looking for an effective way to find what might generally be the best solution for solving certain problems, as each student may face different problems, solving one at a time is not possible with the number of students each year. In this paper, we will try to find factors that might hinder or improve student performance using Pearson correlation between each feature toward the student G3 result. Based on the result, past failures will negatively impact student grades with -0.360415 correlation, and then Mother's Education will positively impact student grades with 0.217147. After finding out which factor affects student grade, we try to predict student grade using ML models to prove whether that factor actually affects student grade. Our MLP 12-Neuron model performs the best with RMSE value of 4.32, followed by Random Forest with RMSE value of 4.52, and finally Decision Tree with RMSE value of 5.69. [ABSTRACT FROM AUTHOR]

Geogrids embedded in fill materials are checked against pullout failure through standard pullout testing methodology. The test determines the pullout interaction coefficient which is critical in fixing the embedment length of geogrids in mechanically stabilized earth walls. This paper proposes prediction of pullout interaction coefficient using data driven machine learning regression algorithms. The study primarily focusses on using extreme gradient boosting (XGBoost) method for prediction. A data set containing 220 test results from the literature has been used for training and testing. Predicted results of XGBoost have been compared with the results of random forest (RF) ensemble learning based algorithm. The predictions of XGBoost model indicates 85% accuracy and that of RF model shows 77% accuracy, indicating significantly superior and robust prediction through XGBoost above RF model. The importance analysis indicates that normal stress is the most significant factor that influences the pullout interaction coefficients. Subsequently pullout tests have been performed on geogrid embedded in four different fill materials at three normal stresses. The proposed XGBoost model gives 90% accuracy in prediction of pullout interaction coefficient compared to laboratory test results. Finally, an open-source graphical user interface based on the XGBoost model has been created for preliminary estimation of the pullout interaction coefficient of geogrid at different test conditions. • This study applies machine learning algorithms for prediction of pullout interaction coefficient of geogrids. • Ensemble learning algorithms have been used on 220 laboratory pullout test results. • Laboratory pullout tests have also been conducted and results have been compared with predicted results for verification. • Open-source graphical user interface has been developed for predicting interaction coefficient values. [ABSTRACT FROM AUTHOR]

• A spatiotemporal risk prediction of wildlife-vehicle collisions (WVCs) is presented. • A Bavarian dataset of around 731,000 accidents over a period of 10 years (2010–2019) was used. • Heterogenous datasets of impact factors are pre-processed using GIS. • Different machine learning (ML) approaches are applied - random forest, feedforward neural networks, and support vector machine classifier to predict the risk of WVCs. • ML algorithms provide high risk prediction quality of over 86% (double-weighted sensitivity and single-weighted specificity rate). • Spatial transferability and temporal forecast of WVC prediction was verified. Introduction: The technology in the automotive industry is becoming increasingly safer in the age of automated driving, but the number of accidents is still high, especially in wildlife-vehicle collisions (WVCs). To better avoid these accidents, patterns involved in these accidents must be detected. Method : This paper presents a spatiotemporal risk prediction of WVCs, including various road and environmental characteristics. A process of data preparation using GIS automated by Python scripts was developed to enable a spatiotemporal link of diverse features for the subsequent predictive data analysis. Different machine learning (ML) approaches were applied- random forest (RF), feedforward neural networks (FNN), and support vector machine classifier (SVM) - including automated ML to predict the risk of WVCs. Therefore, a dataset of approximately 731,000 accidents reported to the police in Bavaria over a period of 10 years (2010–2019) was used. In addition, non-accidents were randomly generated in Python over time and space for the supervised ML processes. As the actual risk probability for WVCs and non-WVCs is not entirely known, the impact of different training ratios between accidents and non-accidents was tested on the risk prediction quality (RPQ) (25%, 50%, 75%, 90% WVCs) of the double-weighted sensitivity and single-weighted specificity rate. Results: The test yielded high mean values of RPQ as an indicator for a suitable WVC prediction. Both RF (86.6%) and FNN (86.7%) were identified as suitable choices for WVC risk prediction in terms of RPQ. The SVM yielded a lower prediction quality, even though acceptable results could be achieved within a shorter runtime. Practical Applications: Spatial transferability was verified since the algorithm was trained on the dataset of Bavaria (excluding Upper Bavaria) and successfully tested in Upper Bavaria. WVC forecasts were also proven through training with datasets from 2010-2017 and in prediction for 2018 and 2019. [ABSTRACT FROM AUTHOR]

To develop an artificial intelligence, machine learning prediction model for estimating in-hospital mortality and stroke in patients undergoing balloon aortic valvuloplasty (BAV). The National Inpatient Sample (NIS) database was used to identify patients who underwent BAV from 2005 to 2017. Outcomes analyzed were in-hospital all-cause mortality and stroke after BAV. Predictors of mortality and stroke were selected using LASSO regularization. A conventional logistic regression and a random forest machine learning algorithm were used to train the models for predicting outcomes. The performance of all the modeling algorithms for predicting in-hospital mortality and stroke was compared between models using c-statistic, F1 score, brier score loss, diagnostic accuracy, and Kolmogorov-Smirnov plots. A total of 6962 patients with severe aortic stenosis who underwent BAV were identified. The performance of random forest classifier was comparable with logistic regression for predicting in-hospital mortality for all measures of performance (F1 score 0.422 vs 0.409, ROC-AUC 0.822 [95 % CI 0.787–0.855] vs 0.815 [95 % CI 0.779–0.849], diagnostic accuracy 70.42 % vs 70.93 %, KS-statistic 0.513 vs 0.494 and brier score loss 0.295 vs 0.291). The random forest algorithm significantly outperformed logistic regression in predicting in-hospital stroke with respect to all performance metrics: F1 score 0.225 vs 0.095, AUC 0.767 [0.662–0.858] vs 0.637 [0.499–0.754], brier score loss [0.399 vs 0.407], and KS-statistic [0.465 vs 0.254]. The good discrimination of machine learning models reveal the potential of artificial intelligence to improve patient risk stratification for BAV. • Random forest (RF) algorithm had similar diagnostic accuracy as logistic regerssion (LR) for predicting mortality amongst the patients undergoing BAV, however RF was superior to LR for predicting stroke after BAV. [ABSTRACT FROM AUTHOR]

Sludge pyrolysis has sparked the interest of researchers because of its capability to dispose of hazardous residues while producing valuable bioproducts. Numerous expensive and laborious experiments are conducted to understand sludge pyrolysis. Machine learning technology can eliminate the need for experimental measurements by systematically learning relationships between variables from historical data. This research aimed to propose a machine learning model to characterize sludge pyrolysis products. A comprehensive database covering various sludge types and pyrolysis reaction conditions was constructed from experimental data. The k-nearest neighbor algorithm was used to reconstruct the missing inputs of sludge composition. The principal component analysis method was then used to decrease dataset dimensionality and acquire relevant information. The obtained scores were normalized and introduced into three machine learning models. The input variables were the chemical properties of sludge and reaction conditions. The response parameters were the distribution and composition of pyrolysis products. Based on descriptive data analysis, the optimum bio-oil yield was obtained at temperatures between 500 and 600 °C. At higher temperatures (700–800 °C), a transition was observed in the product distribution towards more syngas. The random forest regression model showed the highest accuracy among the applied models, with a correlation coefficient higher than 0.813 and a relative mean squared error lower than 12.51. The SHAP analysis using the random forest algorithm was successfully conducted to understand the importance of input variables on output responses. The five top significant features affecting bio-oil yield were ash content, fixed carbon content, operating temperature, and volatile matter content. [Display omitted] • Machine learning technology was used to characterize wastewater sludge pyrolysis. • Random forest regression could predict the product distribution of sludge pyrolysis. • The best model estimated the process with a correlation coefficient higher than 0.813. • The importance of inputs on outputs was investigated by the random forest algorithm. • An easy-to-use software interface was developed for future research applications. [ABSTRACT FROM AUTHOR]

A comprehensive multi-scale computational strategy was developed in this study based on mass transfer and machine learning for simulation of drug concentration distribution in a biomaterial matrix. The controlled release was modeled and validated via the hybrid model. Mass transfer equations along with kinetics models were solved numerically and the results were then used for machine learning models. We investigated the performance of three regression models, namely Decision Tree (DT), Random Forest (RF), and Extra Tree (ET) in predicting medicine concentration (C) based on r and z data. Hyper-parameter optimization is conducted using Glowworm Swarm Optimization (GSO). Results revealed high predictive accuracy across all models, with ET demonstrating superior performance, achieving a coefficient of determination value (R2) of 0.99854, an RMSE of 1.1446E-05, and a maximum error of 6.49087E-05. DT and RF also exhibit notable performance, with coefficients of determination equal to 0.99571 and 0.99655, respectively. These results highlight the effectiveness of ensemble tree-based methods in accurately predicting chemical concentrations, with Extra Tree (ET) Regression emerging as the most promising model for this specific dataset. • Developing a comprehensive computational strategy for drug release modeling. • Simulation of the distribution of drug concentrations in a biomaterial matrix. • Investigation of the performance of three regression models for drug release. • Use of Glowworm Swarm Optimization (GSO) for Hyper-parameter optimization. [ABSTRACT FROM AUTHOR]

Accurate predictions of significant wave heights are crucial in the field of marine and ocean engineering. This paper presents two hybrid intelligent models, EN-1 and EN-2, that combine random forest (RF) and extreme learning machine (ELM) methods through direct linear weighting and gene expression programming-based nonlinear weighting methods, respectively, for the prediction of weekly mean significant wave heights. The performances of the EN-1 and EN-2 models were compared with those of 11 reference models. The results showed that the coefficient of determination (R2), mean absolute error (MAE), root mean squared error (RMSE) and mean absolute percentage error (MAPE) of the EN-1 and EN-2 models were 0.9850, 0.0567, 0.0736 and 3.7107%, 0.9940, 0.0335, 0.0487 and 2.2373%, respectively, for the training datasets and 0.9802, 0.0627, 0.0847 and 4.1461%, 0.9754, 0.0707, 0.0966 and 4.2614%, respectively, for the testing datasets, indicating that the EN-1 and EN-2 models have good predictive performance and can be effectively used for the prediction of weekly mean significant wave heights. In addition, a sensitivity analysis was conducted to investigate the influence of the input variables on the model performance. • Two hybrid models are proposed for the prediction of weekly mean significant wave heights. • The differences of the two weighting methods in improving the performance of the model are compared. • Sensitivity analysis is conducted to investigate the influence of input variables on the model performance. [ABSTRACT FROM AUTHOR]

Plastic pollution requires advances in the production, use, and recovery of plastics to minimize environmental and human-health impacts. Machine Learning (ML) has been applied to accelerate the replacement of existing plastics with sustainable plastics. However, a comprehensive overview of how ML has been applied to promote sustainable plastics from a life cycle perspective is lacking. This article reviews the current literature on ML and its applications in sustainable polymers, representing a significant departure from previous knowledge. A comprehensive and systematic understanding of ML applications in the sustainable-plastic life cycle is provided by analyzing 47 articles on the subject published between 2019 and 2024. This review aims to increase knowledge of ML methods that are used to enhance sustainable plastics and to highlight the various challenges and opportunities. The findings revealed that ML has been applied at every stage of the polymer life cycle, with a higher incidence in the end-of-life and product-manufacturing stages. The application of ML was lowest in the assessment of the environmental impact of plastics. Neural networks and random forests are the most widely used algorithms because of their ability to deal with complex data patterns. Challenges must be addressed to increase the use of ML, namely the polymer complexity and interdependency of the polymer life cycle, the scarcity and low quality of data, and the validation of results by plastics value-chain specialists to increase trustability. [ABSTRACT FROM AUTHOR]

• 512 pedotransfer functions were developed using the machine learner Random Forest. • 27 models were used to estimate bulk density values missing from the dataset. • These models had concordance correlation coefficients ranging from 0.63 to 0.92. • Quantile regression provides uncertainty estimates of pedotransfer functions. Legacy soil datasets are a valuable resource and should be used to the greatest extent possible. However, such datasets may be incomplete, and lack observations for every attribute, as the dataset may be compiled from multiple studies. To use these datasets in soil mapping and modeling work, it is useful to fill the gaps in the dataset with estimated values. Machine learning is an approach that can provide estimates with high accuracy. In this study, the machine learner Random Forest (RF) was used to estimate bulk density values in an existing dataset from the province of British Columbia (BC), Canada, which was used as a case study dataset. As the dataset had missing observations across all attributes, multiple models needed to be generated and tested to determine the accuracy of the estimated values produced. A total of 512 models were tested using RF, which were then ranked based on the concordance correlation coefficient (CCC) of their estimates; the CCC of all models ranged from 0.51 to 0.92. The estimates of 27 of these models were then used to fill the missing observations in the dataset; the accuracy of these models ranged from a CCC of 0.63 to 0.92. Further, uncertainty estimates for the predictions were generated using quantile regression, which was coupled with the RF approach. Each model tested therefore had an accuracy measurement and an uncertainty estimate. This approach, of using multiple models developed in RF, can be applied to other legacy soil datasets with inconsistently missing values to produce estimates which can fill the missing observations, and produce uncertainty estimates for those estimates. [ABSTRACT FROM AUTHOR]

Vibrations occurring in transformer are a physical phenomenon that can be used for condition monitoring, since when the amount of vibrations changes significantly, a faulty condition is in progress (or is incipient). Consequently, vibration prediction becomes crucial for condition monitoring of transformers; however accurately predicting them is challenging, especially in complex scenarios like unbalanced loads and current harmonics. To address this challenge, two methodologies are introduced: one employs a Random Forest (RF) algorithm while the second one is a physical based model. Both methodologies use current information as inputs for vibration prediction, with temperature information serving as additional inputs in the machine learning-based model. Experimental tests, conducted on a distribution transformer during real operations and exposed to unbalanced loads and harmonic currents, demonstrate that both methods are capable of predicting the fundamental component of the vibrations, together with higher harmonics with different degrees of accuracy. The proposed methodologies seem promising as techniques for early diagnosis of faults in transformers or used as an aid to implement possible preventive maintenance techniques. [Display omitted] • Vibrations are predicted by utilizing current and temperature information as inputs. • Such technique can be used to perform predictive diagnostics on dry transformers. • A physical based method and a machine learning based method are proposed. • Both methods exhibit smaller errors in predicting the fundamental frequency component. [ABSTRACT FROM AUTHOR]

• Drying GR at 60 °C and storing it at −10 °C conditions enhanced HRY. • Drying GR at 60 °C and storing at −10 °C reduce broken rice during milling. • The quality monitoring of GR during storage is explained using SHAP. • HPT improved the RF model's R2 by 0.3%. • HSI and ML enhance real time quality monitoring in food supply chain. The quality of glutinous rice (GR) is susceptible to deterioration and losses due to biological or environmental factors during storage. Traditional quality assessment techniques are often time-consuming and challenging. In this study, a rapid and reliable hyperspectral imaging (HSI) technique is utilized to monitor GR quality during storage. Paddy samples were dried at 50 °C, 60 °C and 70 °C. Subsequently, these samples were milled and stored under three conditions: freeze storage (−10 °C), cold room (6 °C) and ambient (∼26 °C) for 6 months. The methodology involved data acquisition from both HSI and standard references methods, with data on hyperspectral reflectance, head rice yield (HRY), broken rice yield (BRY) and milled rice yield (MRY) collected every two weeks. Five machine learning (ML) models were evaluated for quality prediction using Python3, with Random Forest (RF) identified as the best performer, achieving a coefficient of determination (R2) of 0.995. Hyperparameter tuning (HPT) further improved the RF model's R2 by 0.3 %. Parity plot analysis confirmed the accuracy of the RF model in describing GR quality during storage. The study demonstrates the significant impacts of different storage and drying temperatures on HSI data and GR quality attributes. Significant differences in reflectance were observed, with higher reflectance for samples dried at 60 °C and freeze-storage, while lower reflectance for samples dried at 70 °C and cold-room storage. These findings align with reference method results and ML predictions, revealing that drying paddy at 60 °C and storing it under freeze conditions enhances HRY and increases the commercial value of GR. Overall, this study highlights the potential of the HSI for real-time quality monitoring of GR and its applicability to other grains. [ABSTRACT FROM AUTHOR]

The lumped plasticity model is widely used in the practical modeling of reinforced concrete (RC) columns because of its computational efficiency. However, existing formulations for estimating the backbone curve and cyclic deterioration parameters often fail to accurately predict new data with high variability and necessitate laborious calibrations. To address it, a machine-learning (ML) approach utilizing the random forest (RF) algorithm to predict seven parameters in the Ibarra–Medina–Krawinkler lumped plasticity model for depicting hysteretic response is proposed in this study, where a comprehensive data of 475 RC columns, encompassing diverse material properties, geometric features, and failure modes, is used. In addition, an active-learning framework is integrated to address the limited availability of labeled data in supervised ML tasks, which reduces the exhausted labeling process. The proposed RF surpasses existing research and commonly used ML models regarding coefficient of determination. Additionally, the predicted parameters more accurately simulate the behavior of strength and stiffness degradation in the hysteretic loop of columns than empirical regression formulas. These results will benefit the high-fidelity seismic risk assessments of RC buildings. • Seven random forest models are proposed to predict the parameters of the IMK model. • 475 RC columns with diverse characteristics are used to develop the ML model. • Proposed models outperform empirical equations for high-strength specimens and varied failure modes. • An active learning approach is adopted to reduce labor-intensive labeling of data. • The proposed work is potentially beneficial to the high-fidelity seismic risk. [ABSTRACT FROM AUTHOR]

In this study, 80 carbapenem-resistant Klebsiella pneumoniae (CR-KP) and 160 carbapenem-susceptible Klebsiella pneumoniae (CS-KP) strains detected in the clinic were selected and their matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) peaks were collected. K-means clustering was performed on the MS peak data to obtain the best "feature peaks", and four different machine learning models were built to compare the area under the ROC curve, specificity, sensitivity, test set score, and ten-fold cross-validation score of the models. By adjusting the model parameters, the test efficacy of the model is increased on the basis of reducing model overfitting. The area under the ROC curve of the Random Forest, Support Vector Machine, Logistic Regression, and Xgboost models used in this study are 0.99, 0.97, 0.96, and 0.97, respectively; the model scores on the test set are 0.94, 0.91, 0.90, and 0.93, respectively; and the results of the ten-fold cross-validation are 0.84, 0.81, 0.81, and 0.85, respectively. Based on the machine learning algorithms and MALDI-TOF MS assay data can realize rapid detection of CR-KP, shorten the in-laboratory reporting time, and provide fast and reliable identification results of CR-KP and CS-KP. [ABSTRACT FROM AUTHOR]

Artificial cavitation, a complex two-phase phenomenon, involves cavity formation by injecting air into a low-pressure region behind the cavitator. Influenced by factors like cavitator shape and angle, ventilation coefficient, etc., its understanding is crucial. While past research primarily focused on large ventilation coefficients, this study explores the impact of cavitator angles on ventilated cavity characteristics at low ventilation coefficients. For this purpose, three experimental, numerical and machine learning methods have been used. Initially, three angles (0°, 12.5°, 25°) were experimentally investigated across ventilation coefficients of 0.017–0.085. Additionally, through numerical simulations, the effects of increasing the cavitator angle up to 40° at small ventilation coefficients were explored. By optimizing random forest (RF) and Extreme Gradient Boosting (XGB) using Bayesian Optimization Algoritm (BOA), the cavitation characteristics under varying cavitator angles were predicted. The results show the appropriate accuracy of the BOA-XGB model compared to the RF model in predicting the characteristics of cavitation. Results indicate at very small ventilation coefficients, the shape of the cavity is not affected by the cavitator angle. However, with the increase of the ventilation coefficient, in addition to its value, the cavitator angle also affects the shape of the cavity. Increasing the cavitator angle under constant ventilation coefficient induces asymmetry in the cavity's end, elongates the cavity, and reduces the cavitation number. • In very small CQ, the cavity shape is not affected by the cavitator angle. • By increasing the CQ, the cavity shape is affected by the cavitator angle. • At high cavitator angles, a significant increment in the cavity observed. • Increasing the cavitation angle decreases the cavitation number. • Using the optimized random forest model provided a good prediction of the cavity. [ABSTRACT FROM AUTHOR]

The current- and H 2 -producing performances of microbial electrolysis cells (MECs) were predicted by constructing machine learning models based on the previous 76 MEC datasets, making it the largest dataset to date. All models showed high correlation efficiency (R2 > 0.92) in predicting MEC performances. When the models were constructed separately based on the organic substrate type used in the anode of MECs, the models based solely on acetate-fed MEC data exhibited higher prediction accuracies compared to those on all kinds of substrate or complex substrate-based data. As a results of the feature importance analysis, the applied voltage and cathode surface area were identified as the two most critical factors in the acetate-fed MEC data models. Still low prediction accuracies in the models here seem to be due to several important features which could not be numerically presented and thus not be considered as input variables such as electrode material types. [Display omitted] • RF models were constructed to predict current and H 2 productions from MECs. • All models showed high prediction accuracies based on total 76 data points. • The models were constructed separately based on the organic substrate type fed. • The E ap and cathode surface area were critical factors in acetate-fed MEC models. • Non-numerical factors need to be considered such as electrode material types. [ABSTRACT FROM AUTHOR]

Accurately forecasting ozone levels that exceed specific thresholds is pivotal for mitigating adverse effects on both the environment and public health. However, predicting such ozone exceedances remains challenging due to the infrequent occurrence of high-concentration ozone data. This research, leveraging data from 57 German monitoring stations from 1999 to 2018, introduces an Enhanced Extreme Instance Augmentation Random Forest (EEIA-RF) approach that significantly improves the prediction of days when the maximum daily 8-hour average ozone concentrations exceed 120 μ g/m 3 . A pre-trained machine learning model is used to generate additional high-concentration data, which, combined with selectively reduced low-concentration data, forms a new dataset for training a refined model. This method achieved an improvement of at least 8% in the accuracy of predicting days with ozone exceedances across Germany. Our experiment underscores the approach's value in enhancing atmospheric modeling and supporting public health advisories and environmental policy-making related to ozone pollution. • The study introduce EEIA-RFM to enhance ozone exceedance prediction accuracy. • K-means clustering on data from 57 German stations for regional analysis. • EEIA-RFM outperforms traditional methods in forecasting ozone exceedances. [ABSTRACT FROM AUTHOR]

The number of patients with diabetes continues to grow, and the expense of treating diabetes is enormous. Therefore, predicting medical expenses for diabetes has become a priority in many countries. This paper proposes a new hybrid FSRF model to predict medical expenses. Firstly, in response to the problem of multiple features in medical data, we use a random forest (RF) feature extraction algorithm for feature extraction. Secondly, for complex medical concepts, we develop an improved multi-granularity embedding model for encoding medical concepts. Next, we establish the FA-SSA by optimizing the sparrow search algorithm (SSA) using the firefly algorithm (FA). Then, we employ the FA-SSA algorithm to optimize the parameters of the RF model with multi-granularity medical concept embedding. Finally, we build an improved FSRF model and conduct a case study on a medical dataset in Pingjiang County. This paper performs ablation experiments and four sets of comparative experiments, and the experimental results show the superiority of the FSRF model. • The RF algorithm is introduced to address the problem of massive redundancy in medical features. • A multi-granularity medical concept embedding model is developed for medical concept coding. • An FA-SSA parameter optimization algorithm is proposed. • An improved FSRF model is proposed for medical cost prediction studies. • Validate the model using medical data from Pingjiang County. [ABSTRACT FROM AUTHOR]

This study addresses the challenge of designing hot-mix asphalt by evaluating the impact of aggregate surface area (ASA) and the number of aggregates (NA) in machine learning (ML) models. A dataset of 107 asphalt mixtures containing 0–50 % reclaimed asphalt pavement (RAP) was analyzed. Virgin aggregates and RAP particles were counted and measured via digital photography to calculate NA and ASA, with specific surface areas determined in a physics engine environment. Then, measured average aggregate particle weights were calibrated using 13 specimens. Various ML models were developed with the random forest algorithm, incorporating different input feature sets (IFS), including NA, ASA, and other basic features of the mixtures. Results revealed that including NA and ASA did not significantly improve model performance compared to using only gradation percentage inputs. Consequently, IFS-4, which includes only gradation inputs, was recommended for simplicity. The most crucial features were found to be gradation-related, with R² values around 0.90 and above achieved for stiffness modulus (ITSM), air voids, Marshall stability (MS), and theoretical maximum density (G mm). Specifically, the test R² values for air voids, ITSM, and MS were 0.96, 0.89, and 0.87, with a mean absolute percentage error (MAPE) of 5.8 %, 5.4 %, and 5.6 %, respectively. Predictions for G mm demonstrated the highest performance across all metrics with an R² value of 0.99. Air void content predictions performed better than those for ITSM, MS, and MF regarding R² and mean squared error (MSE) values, although their MAPE values were similar. These findings suggest that while NA and ASA provide additional details, gradation features are the most critical inputs for accurate ML model predictions in asphalt mixture design. [Display omitted] • The number and surface area of aggregates were calculated in different asphalt mixtures. • The number and surface area of aggregates did not make a significant difference in ML models. • Aggregate gradation had the highest feature importance in the ML model. • R2 values around 0.90 and above were obtained for air voids, ITSM, Marshall stability, and G mm. [ABSTRACT FROM AUTHOR]

• Develop a comprehensive index for assessing forest fragmentation. • Theil-Sen and Mann-Kendall has been applied to examine the forest vegetation change dynamics during 2000–2020. • Identify 15 spatial coupling modes of forest vegetation change and fragmentation dynamics. • There are forests experienced recovery, but severe landscape fragmentation. • RF models reveals distinct driver patterns between forest vegetation change and fragmentation dynamics. A comprehensive quantification of the relationships between forest vegetation changes and forest landscape fragmentation is urgently required to provide valuable insights for informed forest management decisions. Previous efforts often focused on these two aspects separately, overlooking their intricate relationships, restricts the formulation of precise forest protection and recovery measures. To address this gap, taking Southeast China as a case, this study employed the Google Earth Engine (GEE) platform to calculate the annual Normalized Difference Vegetation Index (NDVI) from 2000 to 2020, a forest fragmentation comprehensive index (FFCI) was constructed to evaluate the static and dynamic forest landscape fragmentation over the study period, then the Theil-Sen and Mann-Kendall, the two-dimensional framework and the bivariate spatial autocorrelation, and a machine learning algorithm (random forest, RF) were employed to explore the forest vegetation change and forest landscape fragmentation, and their spatial coupling relationships and driving patterns, respectively. The results showed that the temporal trend of the forest vegetation can be categorized into three distinct phases, with the pattern of "decreasing-rising-decreasing", 78.2% of the area improved in forest vegetation, while 11.0% degraded. Approximately 6.0% of forest landscape showed a decline in fragmentation, while 9.3% experienced increased fragmentation trends, including 3.8% of forest landscape with moderate to high static fragmentation and 5.5% of forest landscape with low to very low static fragmentation. Throughout the study period, approximately 66.8% of forest landscape remained stability with the improved forest vegetation; however, there were cases (more than 7% of forests) with improved forest vegetation, but experienced severe landscape fragmentation. The RF outcome revealed that the forest vegetation change dynamics were influenced by the multiple factors, including distance to forest edge, distance to road, and elevation; while distance to forest edge emerged as the overwhelming dominant factor driving the forest landscape fragmentation. This research offers significant insights into the intricate interconnections between the forest vegetation changes and the forest landscape fragmentation dynamics. [ABSTRACT FROM AUTHOR]

[Display omitted] • Machine learning reveals spatiotemporal dynamics of SOC stocks in tidal marshes. • Sediment salinity and tidal range are key factors influencing SOC stocks prediction. • Invasive S. alterniflora contributes over half of SOC stocks in Yangtze Estuary. • S. alterniflora increased SOC stocks within the first 15 years of its invasion. • S. alternifloras high SOC storage capacity is not sustained in the long term. Spatial quantification of blue carbon ecosystem stocks is crucial for developing policies to mitigate climate change, especially in regions experiencing ongoing wetland disturbance from biological invasions. We integrated multiple machine learning models with the space-for-time substitution method to quantify the spatiotemporal impact of Spartina alterniflora invasion on tidal marsh sediment blue carbon (soil organic carbon – 'SOC') stocks at 100 cm depth in the Yangtze Estuary. Our results show that the invasive S. alterniflora contributed more than half of the total SOC stocks (2,056 ± 379 Gg C, 1 Gg = 106 kg) in the 27,600 ha tidal marshes of the Yangtze Estuary, which were estimated to be 1,107 ± 176 Gg C. S. alterniflora increased the SOC stocks in the Yangtze Estuary within the first 15 years, but this gain was not sustained in the long term, with a gradual decline (by 13.14 Mg C/ha) observed after 15 years of S. alterniflora growth. We found that sediment salinity, tidal range, and human accessibility were strong indicators for modeling and predicting SOC stocks, with Random Forest providing the best simulation of tidal marsh SOC stocks (R2 = 0.894, RMSE=7.646 Mg C/ha, and MAPE=9.469 %). Our study provides much needed information on blue carbon stocks in the Yangtze Estuary under biological invasion stress, and offers guidance for targeted S. alterniflora management actions in the future. [ABSTRACT FROM AUTHOR]