ABSTRACT
Non-specific lipid-transfer proteins (nsLTPs) are a group of small, cysteine-rich proteins that are involved in the transport of cuticular wax and other lipid compounds. Accumulating evidence suggests that dynamic changes in cuticular waxes are strongly associated with fruit russeting, an undesirable visual quality that negatively affects consumer appeal in pears. Currently, the regulatory role of nsLTPs in cuticular wax deposition and pear fruit skin russeting remains unclear. Here, we characterized the variations of cuticular waxes in non-treated (russeted) and preharvest bagging treated (non-russeted) pear fruits throughout fruit development and confirmed that the contents of cuticular waxes were significantly negatively correlated with the occurrence of pear fruit russeting. Based on RNA-Sequencing (RNA-Seq) and quantitative real-time PCR (qRT-PCR) analyses, two nsLTP genes (PpyLTP36 and PpyLTP39) were identified, which exhibited high expression levels in non-russeted pear fruit skins and were significantly repressed during fruit skin russeting. Subcellular localization analysis demonstrated that PpyLTP36 and PpyLTP39 were localized to the plasma membrane (PM). Further, transient Virus-Induced Gene Silencing (VIGS) analyses of PpyLTP36 and PpyLTP39 in pear fruits significantly reduced cuticular wax deposition. In conclusion, PpyLTP36 and PpyLTP39 are involved in the transmembrane transport of cuticular wax and are associated with pear fruit skin russeting.
ABSTRACT
BACKGROUND: Transcranial magnetic stimulation (TMS) is a valuable technique for assessing the function of the motor cortex and cortico-muscular pathways. TMS activates the motoneurons in the cortex, which after transmission along cortico-muscular pathways can be measured as motor-evoked potentials (MEPs). The position and orientation of the TMS coil and the intensity used to deliver a TMS pulse are considered central TMS setup parameters influencing the presence/absence of MEPs. NEW METHOD: We sought to predict the presence of MEPs from TMS setup parameters using machine learning. We trained different machine learners using either within-subject or between-subject designs. RESULTS: We obtained prediction accuracies of on average 77â¯% and 65â¯% with maxima up to up to 90â¯% and 72â¯% within and between subjects, respectively. Across the board, a bagging ensemble appeared to be the most suitable approach to predict the presence of MEPs. CONCLUSIONS: Although within a subject the prediction of MEPs via TMS setup parameter-based machine learning might be feasible, the limited accuracy between subjects suggests that the transfer of this approach to experimental or clinical research comes with significant challenges.
Subject(s)
Evoked Potentials, Motor , Machine Learning , Motor Cortex , Transcranial Magnetic Stimulation , Transcranial Magnetic Stimulation/methods , Humans , Evoked Potentials, Motor/physiology , Motor Cortex/physiology , Male , Adult , Female , Young Adult , Electromyography/methodsABSTRACT
Accurate crop yield predictions are crucial for farmers and policymakers. Despite the widespread use of ensemble machine learning (ML) models in computer science, their application in crop yield prediction remains relatively underexplored. This study, conducted in Canada, aims to assess the potential of five distinct ensemble ML models-Adaptive Boosting (AdaBoost), Gradient Boosting Machine (GBM), XGBoost, LightGBM, and Random Forest (RF)-in predicting crop yields chosen for their ability to manage complex datasets and their strong performance potential. The study integrated various factors, including climate variables, satellite-derived vegetation indices, soil characteristics, and honeybee census data. Data preparation comprised two main steps: first, climate variables were interpolated and averaged for croplands in ArcGIS Pro, along with averaging vegetation indices and soil characteristics. Honeybee census data was also incorporated. Second, the data was organized in Python to create a structured format for models' input. The models' accuracy was assessed using Root Mean Squared Error (RMSE), R-squared, and Mean Absolute Error (MAE). XGBoost emerged as the most accurate model, with the lowest MAE (68.70 for canola and 39.47 for soybeans), lowest RMSE (119.48 for canola and 102.39 for soybeans), and highest R-squared values (0.95 for canola and 0.96 for soybeans) on the test dataset. The study also assessed crop yields under various climate change scenarios, finding minimal variations across the scenarios, but significant negative impacts on canola and soybean yields across Canada. Honeybee colonies were identified as the most influential factor on crop yields, contributing 52.34 % to canola and 57.18 % to soybean yields. This research provides detailed crop yield maps of canola and soybeans at the Census Consolidated Subdivisions (CCS) level across Canada's agricultural landscape, offering valuable forecasts for localized decision-making. Additionally, it offers a proactive strategy for climate change preparedness, assisting farmers and stakeholders optimise resource allocation and manage risks effectively.
ABSTRACT
The limited recyclability of fibre-reinforced thermoset composites has fostered the development of alternative thermoplastic-based composites and their manufacturing processes. The most common thermoplastic-based composites are often costly due to their availability in the form of prepreg materials and to the high pressure and temperatures required for their manufacturing. Yet, the manufacturing of economic and recyclable composites, made of semi-preg composite materials using traditional composite manufacturing technologies, has only been proved at a laboratory scale through the manufacturing of flat plates. This work reports the manufacturing of a real structural part, a wing spar section with complex geometry, made of commingled polyamide 12 (PA12) fibres and carbon fibres (CFs) semi-preg and by oven vacuum bagging (OVB). The composite layup was studied using finite element analysis, and processing simulation assisted in the determination of the PA12/CF preform for OVB. Processing of two forms of semi-preg materials was first evaluated and optimised. The material selection for part manufacturing was mainly defined by the materials' processability. The spar section was manufactured in two OVB stages and was then mechanically tested. The mechanical test showed a linear strain response of the prototype up to the maximum load and validated the optimised layup configuration of the composite structure.
ABSTRACT
Steady-state visually evoked potential is one of the active explorations in the brain-computer interface research. Electroencephalogram based brain computer interface studies have been widely applied to perceive solutions for real-world problems in the healthcare domain. The classification of externally bestowed visual stimuli of different frequencies on a human was experimented to identify the need of paralytic people. Although many classifiers are at the fingertip of machine learning technology, recent research has proven that ensemble learning is more efficacious than individual classifiers. Despite its efficiency, ensemble learning technology exhibits certain drawbacks like taking more time on selecting the optimal classifier subset. This research article utilizes the Harris Hawk Optimization algorithm to select the best classifier subset from the given set of classifiers. The objective of the research is to develop an efficient multi-classifier model for electroencephalogram signal classification. The proposed model utilizes the Boruta Feature Selection algorithm to select the prominent features for classification. Thus selected prominent features are fed into the multi-classifier subset which has been generated by the Harris Hawk Optimization algorithm. The results of the multi-classifier ensemble model are aggregated using Stacking, Bagging, Boosting, and Voting. The proposed model is evaluated against the acquired dataset and produces a promising accuracy of 96.1%, 98.7%, 91.91%, and 99.01% with the ensemble techniques respectively. The proposed model is also validated with other performance metrics such as sensitivity, specificity, and F1-Score. The experimental results show that the proposed model proves its supremacy in segregating the multi-class classification problem with high accuracy.
Subject(s)
Algorithms , Electroencephalography , Evoked Potentials, Visual , Signal Processing, Computer-Assisted , Electroencephalography/methods , Humans , Evoked Potentials, Visual/physiology , Automation , Brain-Computer Interfaces , Machine LearningABSTRACT
This study was conducted to investigate the profound impact of human activities on the environment, based on scientific data, recognizing the potential of environmental problems to turn into devastating crises if appropriate measures are not taken. It emphasizes the important role of education in developing environmental awareness, knowledge and sensitivity to counter adverse environmental consequences. For this purpose, a dataset was created for the emotional tendencies of university students, who represent a demographic that has the potential to influence the sustainable future of the world. A survey data including 34 different variables was collected from 388 university students in Turkey. Environmental Sensory Tendencies Dataset is intended to provide valuable guidance for the development of effective environmental education programs and policies aimed at increasing university students' awareness and participation in environmental issues. Our research underlines the vital importance of developing responsible attitudes and behaviors to effectively address environmental challenges and thereby contribute to a healthier and more sustainable global ecosystem. This study will make a significant contribution to the literature and highlight the interconnection between human actions and environmental well-being.
ABSTRACT
PURPOSE: Liver disease causes two million deaths annually, accounting for 4% of all deaths globally. Prediction or early detection of the disease via machine learning algorithms on large clinical data have become promising and potentially powerful, but such methods often have some limitations due to the complexity of the data. In this regard, ensemble learning has shown promising results. There is an urgent need to evaluate different algorithms and then suggest a robust ensemble algorithm in liver disease prediction. METHOD: Three ensemble approaches with nine algorithms are evaluated on a large dataset of liver patients comprising 30,691 samples with 11 features. Various preprocessing procedures are utilized to feed the proposed model with better quality data, in addition to the appropriate tuning of hyperparameters and selection of features. RESULTS: The models' performances with each algorithm are extensively evaluated with several positive and negative performance metrics along with runtime. Gradient boosting is found to have the overall best performance with 98.80% accuracy and 98.50% precision, recall and F1-score for each. CONCLUSIONS: The proposed model with gradient boosting bettered in most metrics compared with several recent similar works, suggesting its efficacy in predicting liver disease. It can be further applied to predict other diseases with the commonality of predicate indicators.
Subject(s)
Liver Diseases , Machine Learning , Humans , AlgorithmsABSTRACT
Advancements in imaging, computer vision, and automation have revolutionized various fields, including field-based high-throughput plant phenotyping (FHTPP). This integration allows for the rapid and accurate measurement of plant traits. Deep Convolutional Neural Networks (DCNNs) have emerged as a powerful tool in FHTPP, particularly in crop segmentation-identifying crops from the background-crucial for trait analysis. However, the effectiveness of DCNNs often hinges on the availability of large, labeled datasets, which poses a challenge due to the high cost of labeling. In this study, a deep learning with bagging approach is introduced to enhance crop segmentation using high-resolution RGB images, tested on the NU-Spidercam dataset from maize plots. The proposed method outperforms traditional machine learning and deep learning models in prediction accuracy and speed. Remarkably, it achieves up to 40% higher Intersection-over-Union (IoU) than the threshold method and 11% over conventional machine learning, with significantly faster prediction times and manageable training duration. Crucially, it demonstrates that even small labeled datasets can yield high accuracy in semantic segmentation. This approach not only proves effective for FHTPP but also suggests potential for broader application in remote sensing, offering a scalable solution to semantic segmentation challenges. This paper is accompanied by publicly available source code.
Subject(s)
Crops, Agricultural , Deep Learning , Image Processing, Computer-Assisted , Neural Networks, Computer , Phenotype , Zea mays , Image Processing, Computer-Assisted/methods , SemanticsABSTRACT
The weighted nearest neighbors (WNN) estimator has been popularly used as a flexible and easy-to-implement nonparametric tool for mean regression estimation. The bagging technique is an elegant way to form WNN estimators with weights automatically generated to the nearest neighbors (Steele, 2009; Biau et al., 2010); we name the resulting estimator as the distributional nearest neighbors (DNN) for easy reference. Yet, there is a lack of distributional results for such estimator, limiting its application to statistical inference. Moreover, when the mean regression function has higher-order smoothness, DNN does not achieve the optimal nonparametric convergence rate, mainly because of the bias issue. In this work, we provide an in-depth technical analysis of the DNN, based on which we suggest a bias reduction approach for the DNN estimator by linearly combining two DNN estimators with different subsampling scales, resulting in the novel two-scale DNN (TDNN) estimator. The two-scale DNN estimator has an equivalent representation of WNN with weights admitting explicit forms and some being negative. We prove that, thanks to the use of negative weights, the two-scale DNN estimator enjoys the optimal nonparametric rate of convergence in estimating the regression function under the fourth-order smoothness condition. We further go beyond estimation and establish that the DNN and two-scale DNN are both asymptotically normal as the subsampling scales and sample size diverge to infinity. For the practical implementation, we also provide variance estimators and a distribution estimator using the jackknife and bootstrap techniques for the two-scale DNN. These estimators can be exploited for constructing valid confidence intervals for nonparametric inference of the regression function. The theoretical results and appealing finite-sample performance of the suggested two-scale DNN method are illustrated with several simulation examples and a real data application.
ABSTRACT
The economic impact of fruit cracking in pomegranate products is substantial. In this study, we present the inaugural comprehensive analysis of transcriptome and metabolome in the outermost pericarp of pomegranate fruit in bagging conditions. Our investigation revealed a notable upregulation of differentially expressed genes (DEGs) associated with the calcium signaling pathway (76.92%) and xyloglucan endotransglucosylase/hydrolase (XTH) genes (87.50%) in the fruit peel of non-cracking fruit under bagging. Metabolomic analysis revealed that multiple phenolics, flavonoids, and tannins were identified in pomegranate. Among these, calmodulin-like 23 (PgCML23) exhibited a significant correlation with triterpenoids and demonstrated a marked upregulation under bagging treatment. The transgenic tomatoes overexpressing PgCML23 exhibited significantly higher cellulose content and xyloglucan endotransglucosylase (XET) enzyme activity in the pericarp at the red ripening stage compared to the wild type. Conversely, water-soluble pectin content, polygalacturonase (PG), and ß-galactosidase (ß-GAL) enzyme activities were significantly lower in the transgenic tomatoes. Importantly, the heterologous expression of PgCML23 led to a substantial reduction in the fruit cracking rate in tomatoes. Our findings highlight the reduction of fruit cracking in bagging conditions through the manipulation of PgCML23 expression.
Subject(s)
Fruit , Metabolomics , Plant Proteins , Pomegranate , Transcriptome , Fruit/chemistry , Fruit/genetics , Fruit/metabolism , Fruit/growth & development , Pomegranate/chemistry , Pomegranate/genetics , Pomegranate/metabolism , Pomegranate/growth & development , Plant Proteins/genetics , Plant Proteins/metabolism , Solanum lycopersicum/genetics , Solanum lycopersicum/metabolism , Solanum lycopersicum/chemistry , Solanum lycopersicum/growth & development , Plants, Genetically Modified/genetics , Plants, Genetically Modified/metabolism , Plants, Genetically Modified/chemistry , Gene Expression Regulation, PlantABSTRACT
Pre-harvest bagging can improve fruit color and protects against diseases. However, it was discovered that improper bagging times could lead to peel browning in production. Using the Ruixue apple variety as the research model, a study was conducted to compare the external and internal quality of fruits bagged at seven different timings between 50 and 115 days after full bloom (DAFB). Our findings indicate that delaying the bagging time can reduce the occurrence of peel browning in Ruixue apples. Compared to the control, the special bag reduced the browning index by 22.95%. However, the fruit point index of Ruixue fruits increased by 65.05% at 115 DAFB compared to 50 DAFB when bagging was delayed. The chlorophyll content of Ruixue fruits in special bags generally increased and then decreased, with the highest chlorophyll content of Ruixue fruits in special bags at 90 DAFB, which was 26.02 mg·kg-1. When the bagging process was delayed, the soluble solids, total phenols, and flavonoids content in the fruits increased, while the number of control volatiles decreased by 10. After two years of testing, results show that using special fruit bags at 90 DAFB bagging can significantly improve the fruit quality of Ruixue apple.
ABSTRACT
Introduction: Fresh Aareca nut fruit for fresh fruit chewing commonly found in green or dark green hues. Despite its economic significance, there is currently insufficient research on the study of color and luster of areca. And the areca nut fruits after bagging showed obvious color change from green to tender yellow. In the study, we tried to explain this interesting variation in exocarp color. Methods: Fruits were bagged (with a double-layered black interior and yellow exterior) 45 days after pollination and subsequently harvested 120 days after pollination. In this study, we examined the the chlorophyll and carotenoid content of pericarp exocarp, integrated transcriptomics and metabolomics to study the effects of bagging on the carotenoid pathway at the molecular level. Results: It was found that the chlorophyll and carotenoid content of bagged areca nut (YP) exocarp was significantly reduced. A total of 21 differentially expressed metabolites (DEMs) and 1784 differentially expressed genes (DEGs) were screened by transcriptomics and metabolomics. Three key genes in the carotenoid biosynthesis pathway as candidate genes for qPCR validation by co-analysis, which suggested their role in the regulation of pathways related to crtB, crtZ and CYP707A. Discussion: We described that light intensity may appear as a main factor influencing the noted shift from green to yellow and the ensuing reduction in carotenoid content after bagging.
ABSTRACT
A very low incidence of acute kidney injury (AKI) has been observed in COVID-19 patients purposefully treated with early pressure support ventilation (PSV) compared to those receiving mainly controlled ventilation. The prevention of subdiaphragmatic venous congestion through limited fluid intake and the lowering of intrathoracic pressure is a possible and attractive explanation for this observed phenomenon. Both venous congestion, or "venous bagging", and a positive fluid balance correlate with the occurrence of AKI. The impact of PSV on venous return, in addition to the effects of limiting intravenous fluids, may, at least in part, explain this even more clearly when there is no primary kidney disease or the presence of nephrotoxins. Optimizing the patient-ventilator interaction in PSV is challenging, in part because of the need for the ongoing titration of sedatives and opioids. The known benefits include improved ventilation/perfusion matching and reduced ventilator time. Furthermore, conservative fluid management positively influences cognitive and psychiatric morbidities in ICU patients and survivors. Here, it is hypothesized that cranial lymphatic congestion in relation to a more positive intrathoracic pressure, i.e., in patients predominantly treated with controlled mechanical ventilation (CMV), is a contributing risk factor for ICU delirium. No studies have addressed the question of how PSV can limit AKI, nor are there studies providing high-level evidence relating controlled mechanical ventilation to AKI. For this perspective article, we discuss studies in the literature demonstrating the effects of venous congestion leading to AKI. We aim to shed light on early PSV as a preventive measure, especially for the development of AKI and ICU delirium and emphasize the need for further research in this domain.
ABSTRACT
Background: Traditional Common Spatial Pattern (CSP) algorithms for Electroencephalogram (EEG) signal classification are sensitive to noise and can produce low accuracy in small sample datasets. New method: To solve the problem, an improved Empirical Mode Decomposition (EMD) Bagging Regularized CSP (RCSP) algorithm is proposed. It filters EEG signals through improved EMD, inhibits high-frequency noise, retains effective information in the characteristic frequency band, and uses Bagging algorithm for data reconstruction. Feature extraction is performed with regularization of spatial patterns and Fisher linear discriminant analysis for feature classification. T-test is used for classification. Results: The improved EMD Bagging RCSP algorithm has improved accuracy and robustness compared to CSP and its derivatives. The average classification rate is increased by about 6%, demonstrating the effectiveness and correctness of the proposed algorithm.Comparison with existing methods: The proposed algorithm outperforms CSP and its derivatives by retaining effective information and inhibiting high-frequency noise in small sample EEG datasets. Conclusions: The proposed EMD Bagging RCSP algorithm provides a reliable and effective method for EEG signal classification and can be used in various applications, including brain-computer interfaces and clinical EEG diagnosis.
ABSTRACT
The 'Huangguan' pear is one of the high-quality pear cultivars produced in China. However, the bagged fruit of the 'Huangguan' pear often suffers from peel browning spots after rain during their mature period. In this study, in an effort to discover the impact of bagging treatments on the occurrence of peel browning spots and fruit quality, fruits were covered by single-layer, two-layer, or triple-layer paper bags six weeks after reaching full bloom. The results showed that the bagged fruits were characterized by smooth surfaces and reduced lenticels compared with the unbagged ones. The unbagged and the two-layer bagged fruits had yellow/green peels, while the single- and triple-layer bagged ones had yellow/white peels. Compared with the unbagged fruits, the bagged fruits had higher vitamin C (Vc) contents and values of peel color indexes L and a and lower soluble solid contents (SSCs), titratable acid (TA) contents, absorbance index differences (IAD), and b values. Additionally, the triple-layer bagged group was superior to other groups in terms of fruit quality, but it also had the maximum incidence of peel browning spots. Before and after the appearance of peel browning spots, the bagged fruits had smoother and thinner cuticles compared with the unbagged ones. Furthermore, the triple-layer bagged fruits had minimum lignin contents and maximum phenolic contents in their peels, with minimum activity of lignin synthesis-related enzymes such as phenylalanine ammonia lyase (PAL), peroxidase (POD), and polyphenol oxidase (PPO), as well as minimum expressions of relevant genes such as cinnamyl alcohol dehydrogenase (CAD), cinnamoyl CoA reductase (CCR), 4-coumarate: coenzyme A ligase (4CL6), and cinnamate 4-hydroxylase (C4H1). It was deduced that POD activity and the relative expressions of CAD9, CCR3, CCR4, and CCR5 may play key roles in the occurrence of peel browning spots. In summary, lignin synthesis affected the incidence of peel browning spots in bagged 'Huangguan' pears. This study provides a theoretical basis for understanding the incidence of peel browning spots in 'Huangguan' pears.
ABSTRACT
This study aims to explore the effects of different non-landslide sampling strategies on machine learning models in landslide susceptibility mapping. Non-landslide samples are inherently uncertain, and the selection of non-landslide samples may suffer from issues such as noisy or insufficient regional representations, which can affect the accuracy of the results. In this study, a positive-unlabeled (PU) bagging semi-supervised learning method was introduced for non-landslide sample selection. In addition, buffer control sampling (BCS) and K-means (KM) clustering were applied for comparative analysis. Based on landslide data from Qiaojia County, Yunnan Province, China, collected in 2014, three machine learning models, namely, random forest, support vector machine, and CatBoost, were used for landslide susceptibility mapping. The results show that the quality of samples selected using different non-landslide sampling strategies varies significantly. Overall, the quality of non-landslide samples selected using the PU bagging method is superior, and this method performs best when combined with CatBoost for predicting (AUC = 0.897) landslides in very high and high susceptibility zones (82.14%). Additionally, the KM results indicated overfitting, displaying high accuracy for validation but poor statistical outcomes for zoning. The BCS results were the worst.
ABSTRACT
Mitochondrial toxicity has been implicated in the development of various toxicities, including hepatotoxicity. Therefore, mitochondrial toxicity has become a major screening factor in the early discovery phase of drug development. Several models have been developed to predict mitochondrial toxicity based on chemical structures. However, they only provide a binary classification of positive or negative results and do not provide the substructures that contribute to a positive decision. Therefore, we developed an artificial intelligence (AI) model to predict mitochondrial toxicity and visualize structural alerts. To construct the model, we used the open-source software library kMoL, which employs a graph neural network approach that allows learning from chemical structure data. We also utilized the integrated gradient method, which enables the visualization of substructures that contribute to positive results. The dataset used to construct the AI model exhibited a significant imbalance, with significantly more negative than positive data. To address this, we employed the bagging method, which resulted in a model with high predictive performance, as evidenced by an F1 score of 0.839. This model can also be used to visualize substructures that contribute to mitochondrial toxicity using the integrated gradient method. Our AI model predicts mitochondrial toxicity based on chemical structures and may contribute to screening mitochondrial toxicity in the early stages of drug discovery.
Subject(s)
Artificial Intelligence , Drug Development , Drug DiscoveryABSTRACT
Cork spot-like physiological disorder (CSPD) is a newly identified issue in 'Kurenainoyume' apples, yet its mechanism remains unclear. To investigate CSPD, we conducted morphological observations on 'Kurenainoyume' apples with and without pre-harvest fruit-bagging treatment using light-impermeable paper bags. Non-bagged fruit developed CSPD in mid-August, while no CSPD symptoms were observed in bagged fruit. The bagging treatment significantly reduced the proportion of opened lenticels, with only 17.9% in bagged fruit compared to 52.0% in non-bagged fruits. In non-bagged fruit, CSPD spots tended to increase from the lenticels, growing in size during fruit development. The cuticular thickness and cross-sectional area of fresh cells in CSPD spots were approximately 16 µm and 1600 µm², respectively. Healthy non-bagged fruit reached these values around 100 to 115 days after full bloom from mid- to late August. Microscopic and computerized tomography scanning observations revealed that many CSPD spots developed at the tips of vascular bundles. Therefore, CSPD initiation between opened lenticels and vascular bundle tips may be influenced by water stress, which is potentially caused by water loss, leading to cell death and the formation of CSPD spots.
ABSTRACT
During pandemic periods, there is an intense flow of patients to hospitals. Depending on the disease, many patients may require hospitalization. In some cases, these patients must be taken to intensive care units and emergency interventions must be performed. However, finding a sufficient number of hospital beds or intensive care units during pandemic periods poses a big problem. In these periods, fast and effective planning is more important than ever. Another problem experienced during pandemic periods is the burial of the dead in case the number of deaths increases. This is also a situation that requires due planning. We can learn some lessons from Covid 19 pandemic and be prepared for the future ones. In this paper, statistical properties of the daily cases and daily deaths in Turkey, which is one of the most affected countries by the pandemic in the World, are studied. It is found that the characteristics are nonstationary. Then, random forest regression is applied to predict Covid-19 daily cases and deaths. In addition, seven other machine learning models, namely bagging, AdaBoost, gradient boosting, XGBoost, decision tree, LSTM and ARIMA regressors are built for comparison. The performance of the models are measured using accuracy, coefficient of variation, root-mean-square score and relative error metrics. When random forest regressors are employed, test data related to daily cases are predicted with an accuracy of 92.30% and with an r2 score of 0.9893. Besides, daily deaths are predicted with an accuracy of 91.39% and with an r2 score of 0.9834. The closest rival in predictions is the bagging regressor. Nevertheless, the results provided by this algoritm changed in different runs and this fact is shown in the study, as well. Comparisons are based on test data. Comparisons with the earlier works are also provided.
ABSTRACT
Flow obstructed by bridge piers can increase sediment transport leading to local scour. This local scour poses a risk to the stability of bridge structures, which could lead to structural failures. There are two main approaches for evaluating the scour depth (ds) of bridge piers. The first is based on understanding hydraulic phenomena and developing relationships with properties affecting scour. The second uses data-driven soft computing models that lack physical interpretations but rely on algorithms to predict outcomes. Methods are chosen by researchers based on their goals and resources. This study aims to create innovative ensemble frameworks comprising support vector machine for regression (SVMR), random forest regression (RFR), and reduced error pruning tree (REPTree) as base learners, alongside bagging regression tree (BRT) and stochastic gradient boosting (SGB) as meta learners. These ensembles were developed to analyse maximum scour depths (dsm) in clear water conditions, utilizing 35 literature's experimental data published in last 63 years. The performance of each machine learning (ML) approach was assessed using statistical performance indicators. The proposed model was also compared with top six empirical equations with strong predictive ability. Results show that among these empirical equations, the equation from Nandi and Das (2023) performs best. Performance evaluation considering training, testing, and the entire dataset, SGB (REPTree), BRT(SVMR-PUK), and SGB (REPTree) exhibited the highest performance, securing the top rank among all ML models and empirical equations. Sensitivity analysis identified sediment gradation and flow intensity as the most influential variables for predicting dsm during both training and testing phases, respectively.