Search

The huge volume of data from the Ice, Cloud and land Elevation Satellite-2 (ICESat-2), designed for mapping polar ice, sea ice, and continental vegetation, requires a highly automated data analysis and reliable terrain classification. In particular, we have developed a method to identify 4 distinct terrain categories in observed terrain, namely ocean, land, sea ice, and ice sheets. This study performed the following efforts: first, the spatial distribution characteristics for each of the 4 categories within individual ICESat-2 "major frames" along the orbit were extracted; second, these features were fed into Classification and Regression Tree (CART) and Random Forest (RF) for training; and lastly, post-processing enhancement was used to improve the classification results. Based on the 76,891 major frame samples (10,764,740 m along track) acquired via various ICESat-2 datasets, the accuracy of the two model were calculated using ten-fold cross-validation. The results indicate that the RF algorithm obtained higher classification accuracy (average accuracy [AA] = 0.9353, overall accuracy [OA] = 0.9342, and Cohen's Kappa coefficient [kappa] = 0.9122) when compared with the CART algorithm (AA = 0.9066, OA = 0.9057, and kappa = 0.8743). Overall, our approach can effectively reduce the workload of human field investigation or visual inspection of altimetry data, improve the accuracy for Earth surface classification, and add to the variety of ways to obtain global surface information from ICESat-2 data. [ABSTRACT FROM AUTHOR]

Identifying farmland use has long been an important topic in large-scale agricultural production management. This study used multi-temporal visible RGB images taken from agricultural areas in Taiwan by UAV to build a model for classifying field types. We combined color and texture features to extract more information from RGB images. The vectorized gray-level co-occurrence matrix (GLCMv), instead of the common Haralick feature, was used as texture to improve the classification accuracy. To understand whether changes in the appearance of crops at different times affect image features and classification, this study designed a labeling method that combines image acquisition times and land use type to observe it. The Extreme Gradient Boosting (XGBoost) algorithm was chosen to build the classifier, and two classical algorithms, the Support Vector Machine and Classification and Regression Tree algorithms, were used for comparison. In the testing results, the highest overall accuracy reached 82%, and the best balance accuracy across categories reached 97%. In our comparison, the color feature provides the most information about the classification model and builds the most accurate classifier. If the color feature were used with the GLCMv, the accuracy would improve by about 3%. In contrast, the Haralick feature does not improve the accuracy, indicating that the GLCM itself contains more information that can be used to improve the prediction. It also shows that with combined image acquisition times in the label, the within-group sum of squares can be reduced by 2–31%, and the accuracy can be increased by 1–2% for some categories, showing that the change of crops over time was also an important factor of image features. [ABSTRACT FROM AUTHOR]

This study focuses on the multiscale calculation of different plan curvature forms to enhance the modeling of soil penetration resistance and gravimetric soil water content utilizing the classification and regression trees algorithm in a low-relief watershed. To that end, three forms of plan curvature were derived using the Wood method from a two-meter digital elevation model on six neighborhood sizes. The results showed that the neighborhood size influenced the plan curvature values and there was little difference between the utilization of three forms of plan curvature in the landform determination. The modeling results indicated that the three forms of plan curvature on most neighborhood scales have different contributions to each other in modeling the spatial variability of each soil property. The neighborhood scale was a critical factor in soil modeling because it controls the smoothing rate of plan curvature. The overall results suggest that soil models with poor performance could be constructed if the plan curvature forms and the neighborhood size are not considered in the geomorphometric analysis. Therefore, it is recommended to use the procedure implemented in this study for digital soil mapping in various regions. [ABSTRACT FROM AUTHOR]

This research provides a comprehensive analysis of the spatiotemporal evolution of the regional cropping structure and its influencing factors. Using Landsat satellite images, field surveys, and yearbook data, we developed a planting structure extraction model employing the classification regression tree algorithm to obtain data on the major crop cultivation and structural characteristics of Alar reclamation from 1990 to 2023. A dynamic model and transfer matrix were used to analyze temporal changes, and a centroid migration model was used to study spatial changes in the cropping structure. Nonparametric mutation tests and through-traffic coefficient analysis were utilized to quantify the main driving factors influencing the cropping structure. During the period of 1990–2023, the cotton area in the Alar reclamation region expanded by 722.08 km2, while the jujube exhibited an initial increase followed by a decrease in the same period. The primary reasons are linked to the cost of purchase, agricultural mechanization, and crop compatibility. In the Alar reclamation area, cotton, chili, and jujube are the primary cultivated crops. Cotton is mainly grown on the southern side of the Tarim River, while chili cultivation is concentrated on the northern bank of the river. Over the years, there has been a noticeable spatial complementarity in the distribution and density of rice and cotton crops in this region. In the Alar reclamation, the main factors influencing the change in cultivated land area are cotton price, agricultural machinery gross power, and population. Consequently, implementing measures such as providing planting subsidies and other policy incentives to enhance planting income can effectively stimulate farmers' willingness to engage in planting activities. [ABSTRACT FROM AUTHOR]

The progression of SARS-CoV-2 infection has been linked to a hospitalization rate of 20%. The susceptibility of SARS-CoV-2 infection increases with age, resulting in severe and atypical clinical forms of the disease. The severity of SARS-CoV-2 infection in the elderly population can be attributed to several factors, including the overexpression of angiotensin-converting enzyme 2 (ACE2) receptors, immunosenescence, and alterations in the intestinal microbiota that facilitate the cytokine storm. In light of these observations, we conducted a retrospective analysis based on prospectively collected data between 23 December 2021 and 30 April 2022 (the fourth wave of SARS-CoV-2 infection). We analyzed patients aged over 60 years who were hospitalized in a county hospital in Romania. The primary objective of our study was to assess the risk factors for an unfavorable outcome, while the secondary objective was to assess the clinical and baseline characteristics of the enrolled patients. We included 287 cases with a complete electronic medical record from this available cohort of patients. We aimed to retrospectively evaluate a group of 127 patients that progressed, unfortunately, toward an unfavorable outcome versus 160 patients with a favorable outcome. We used the Combined Ordinal Scale of Severity that combines the WHO ordinal scale and the degrees of inflammation to assess the severity of the patients at the time of the initial assessment. The age group between 70 and 79 years had the highest percentage, accounting for 48.0%—61 patients, of the deceased patients. We noted statistically significant differences between groups related to other cardiovascular diseases, nutritional status, hematological diseases, other neurological/mental or digestive disorders, and other comorbidities. Regarding the nutritional status of the patients, there was a statistically significant unfavorable outcome for all the age groups and the patients with a BMI > 30 kg/m2, p = 0.004. The presence of these factors was associated with an unfavorable outcome. Our results indicate that with the presence of cough, there was a statistically significant favorable outcome in the age group over 80 years, p ≤ 0.049. In terms of the presence of dyspnea in all groups of patients, it was associated with an unfavorable outcome, p ≤ 0.001. In our study, we analyzed laboratory test results to assess the level of inflammation across various WHO categories, focusing on the outcome groups determined by the average values of specific biomarkers. Our findings show that, with the exception of IL-6, all other biomarkers tend to rise progressively with the severity of the disease. Moreover, these biomarkers are significantly higher in patients experiencing adverse outcomes. The differences among severity categories and the outcome group are highly significant (p-values < 0.001). CART algorithm revealed a specific cut-off point for the WHO ordinal scale of 4 to stand out as an important reference value for patients at a high risk of developing critical forms of COVID-19. The high death rate can be attributed to proinflammatory status, hormonal changes, nutritional and vitamin D deficiencies, comorbidities, and atypical clinical pictures. [ABSTRACT FROM AUTHOR]

The rockburst hazard induced by the extreme release of the stress concentrated in rock mass in deep underground mines poses a significant threat to the safety and economy of the mining projects. Therefore, properly managing this hazard is critical for ensuring rock engineering projects' sustainability. This study proposes comprehensible and practical classifiers for rockburst risk level appraisal by hybridizing K-means clustering with gene expression programming, GEP, logistic regression, LR, and classification and regression tree, CART (i.e., K-mean-GEP-LR and K-means-CART classifiers). A database containing 246 rockburst events with four risk levels of none, light, moderate, and severe was compiled from previous practices. Preliminary statistical analyses were conducted to detect the extreme outliers and determine the critical rockburst indicators. The K-means clustering analysis was performed to identify the main clusters within the database and relabel the rockburst events. The GEP algorithm was then utilized to develop binary models for predicting the occurrence of each class. Then, the likelihood of each class occurrence was determined using LR. Furthermore, the K-means clustering was combined with the CART algorithm to provide another visual tree structure model. The classifiers' performance evaluation showed 96% and 95% accuracy values in the training and testing stages, respectively, for the K-means-GEP-LR model, while the accuracy values of 98.8% and 93.0% were obtained for the foregoing stages for the K-means-CART classifier. The results showed the robustness and high classification capability of both models. MatLab codes were also provided for the K-means-GEP-LR model, which assists other researchers/engineers in implementing the model in practice. [ABSTRACT FROM AUTHOR]

The aim of this study was to estimate honey quality based on proline and Brix content using a thermal imaging and machine learning algorithm. The proline, Brix and color properties of twenty honey samples were determined. Proline and Brix values were classified and estimated using the classification and regression tree (CART) algorithm. The mean proline and Brix content in honey samples was 678.83±192.16 mg/kg and 83.2±0.79%, respectively. CART analysis revealed that high proline honey samples had L values above 48.143 and b* values below 35.416. In contrast, honey samples with low Brix values were characterized by L and a* values below 55.860 and 53.660, respectively, and were identified as freshly harvested. The CART algorithm classified the proline and Brix values with an accuracy of 95% and 100%, respectively (p< 0.001). As a result, whitish, bluish, blackish and greenish honeys are of higher quality due to high proline and low Brix content. However, to accurately assess honey quality based on its color traits, comprehensive studies with more honey samples and origin, are required. [ABSTRACT FROM AUTHOR]

The north coast of Java is the center of economic activity in Indonesia. This area is dynamic and sensitive to various geo-bio-physical aspects. Therefore, a vulnerability study in this area is necessary. This study proposes a machine learning tree-based algorithms modeling approach for Coastal Vulnerability Assessment (CVA) and mapping. The tree-based algorithms used are Gradient Tree Boost (GTB), Classification and Regression Trees (CART), and Random Forest (RF). The study utilized the Google Earth Engine (GEE) platform and twelve variables as input. The prediction results of each of these modeling algorithms have been compared and evaluated to determine the most optimal performance and accuracy. Reference data was obtained from the Ministry of Maritime Affairs and Fisheries of the Republic of Indonesia (KKP). Approximately 70% of the reference data was allocated for training, while the remaining 30% was designated for validation. The CVA assessment yielded overall accuracies of 80.22%, 77.40%, and 71.18% based on the RF, GTB, and CART algorithms, respectively. Meanwhile, the Kappa Index for these three algorithms was 0.72, 0.67, and 0.58, indicating that the models have adequately classified the data. The research outcomes are anticipated to offer insights into the potential utilization of machine learning technology for vulnerability assessment and mapping, contributing to the management of coastal environmental issues. [ABSTRACT FROM AUTHOR]

The use of multivariate adaptive regression splines (MARS) and classification and regression tree (CART) to estimate the live body weight at weaning age of the Sussex cattle breed remain poorly understood in South Africa. This study was conducted to examine the effect of linear body measurements on body weight at weaning using MARS and CART algorithms. The body weight and linear body measurements included sternum height, withers height, heart girth, hip height, body length, rump length and rump width were collected from 101 Sussex cattle (female = 57 and male = 44) at weaning. Goodness of fit criterions was used to select the best data mining algorithms. The results showed that MARS showed higher predictive performance in the criteria as compared to CART algorithm. The findings of the study suggest that MARS algorithm can be used to estimate the BW at weaning age in Sussex cattle breed. These findings might be helpful to cattle farmers in the selection criterions of breeding stock at weaning age. [ABSTRACT FROM AUTHOR]

Based on authorized patents of China's artificial intelligence industry from 2013 to 2022, this paper constructs an Industry–University–Research institution (IUR) collaboration network and an Inter-Firm (IF) collaboration network and used the entropy weight method to take both the quantity and quality of patents into account to calculate the innovation performance of firms. Through the hierarchical clustering algorithm and classification and regression trees (CART) algorithm, in-depth analysis has been conducted on the intricate non-linear influence mechanisms between multiple variables and a firm's innovation performance. The findings indicate the following: (1) Based on the network centrality (NC), structural hole (SH), collaboration breadth (CB), and collaboration depth (CD) of both IUR and IF collaboration networks, two types of focal firms are identified. (2) For different types of focal firms, the combinations of network characteristics affecting their innovation performance are various. (3) In the IUR collaboration network, focal firms with a wide range of heterogeneous collaborative partners can obtain high innovation performance. However, focal firms in the IF collaboration network can achieve the same aim by maintaining deep collaboration with other focal firms. This paper not only helps firms make scientific decisions for development but also provides valuable suggestions for government policymakers. [ABSTRACT FROM AUTHOR]

Predicting the direction (increase or decrease) of stock market indexes and stock prices has long attracted the attention of investors and researchers. Establishing a connection between the past and future data makes this prediction difficult. The mentioned connection is established through econometric or neural network models. Neural network models do not require strict assumptions like econometric models and can utilize qualitative and quantitative data. In this study, monthly average BIST 100 index values were taken between January 2002 and September 2022, and a two-group dependent variable was formed as “1” for cases with an increase compared to the previous month and “0” for cases with a decrease. The 1st and 2nd lagged values of BIST 100, S&P 500, CAC40, FTSE10, NIKKEI225DAX, SHANGAICOMP, ONSUSD, USDTRY, VIX and REPO variables were taken as independent variables. A total of nine different machine learning methods which are Logistic Regression Analysis (LR), Linear Discriminant Analysis (LDA), Naive Bayes Algorithm (NB), Random Forests Algorithm (RF), K-Nearest Neighborhood Algorithm (KNN), Classification and Regression Trees Algorithm (CART), Artificial Neural Networks (NNET), Support Vector Machines with Radial Basis Function (SVM)RBF), Support Vector Machines with Polynomial Kernel Function (SVM-POLY) were used for direction prediction for BIST 100 index in practice. In conclusion, it is observed that linear methods produce more successful estimation results. [ABSTRACT FROM AUTHOR]

Accurate prediction of regional water evapotranspiration can greatly contribute to the rational utilization of regional water resources for the water resources saving. Crop evapotranspiration can be one of the most important indicators for the water evapotranspiration status of crops, in order to evaluate the soil water balance of farmland and the water management of farmland. However, the calculation of crop evapotranspiration requires a large amount of meteorological factor data. There is often redundant data with the low correlation with the evapotranspiration in meteorological data, which seriously affects the prediction accuracy and efficiency of the model. It is a high demand to extract the core environmental factors for the less-factor prediction model. The classification and regression tree (CART) can be used to make feasible for the large data sources in a short time. Then, Less factors can be extracted for the predictive analysis in a more scientific way. In this study, a less-factor water evapotranspiration model was constructed to efficiently and accurately predict the evapotranspiration data. The core factors were selected from multiple meteorological factors. 23 typical stations were selected in the nine agricultural regions, and then collected data on eight meteorological factors, such as precipitation, and sunshine hours. The meteorological factors were ranked in the order of importance using CART. The top 3-5 meteorological factors were then selected to predict the evapotranspiration using the extreme learning machine (ELM) model. At the same time, the ELM model was optimized using genetic algorithm (GA), particle swarm optimization (PSO), sparrow search algorithm (SSA). Three optimization algorithms (GA-ELM, PSO-ELM, SSA-ELM) were used to construct a less-factor hybrid optimization water evapotranspiration prediction model. Relative root mean square error (RMSE), coefficient of determination (R 2 ), mean absolute error (MAE), and NashSutcliffe coefficient (NSE) were used to evaluate the performance of the ELM and optimization model. The results showed that: 1) The main influencing factors were ranked in the order of the precipitation, sunshine duration, mean station pressure, daily maximum temperature, and average relative humidity using the importance ranking of the CART algorithm. 2) The PSOELM model presented the highest prediction accuracy among the three optimization algorithms. Specifically, the RMSE of evapotranspiration prediction for the 23 stations was ranged from 6.608 to 22.077 mm/d, the NSE of 0.824-0.998, R 2 of 0.908- 0.995, and MAE of 5.075-16.677 mm/d. In addition, the RF and SVR model with the strong generalization performance were selected to compare with the PSO-ELM model. The prediction performance of three models was slightly improved with the increase of the input factors, indicating the slight overall improvement. The three models shared the strong generalization and robustness. The meteorological factors were input into the prediction model, according to the order of importance. The meteorological factors ranked the 4th and 5th were relatively less important, where the prediction accuracy was slightly improved with the increase of the input parameters. The PSO-ELM model presented the highest prediction accuracy among the three models. 3) The ELM model performed better applicability in the Yunnan-Guizhou Plateau region, the Sichuan Basin, and the surrounding areas. The three optimization algorithms showed the better applicability in the South China and the YunnanGuizhou Plateau region, with the highest applicability of the PSO-ELM model. The findings can provide an important reference for the crop water demand calculation in nine major agricultural regions in China. [ABSTRACT FROM AUTHOR]

This volume is largely about nontraditional data; this paper is about a nontraditional visualization: classification trees. Using trees with data will be new to many students, so rather than beginning with a computer algorithm that produces optimal trees, we suggest that students first construct their own trees, one node at a time, to explore how they work, and how well. This build‐it‐yourself process is more transparent than using algorithms such as CART; we believe it will help students not only understand the fundamentals of trees, but also better understand tree‐building algorithms when they do encounter them. And because classification is an important task in machine learning, a good foundation in trees can prepare students to better understand that emerging and important field. We also describe a free online tool—Arbor—that students can use to do this, and note some implications for instruction. [ABSTRACT FROM AUTHOR]

The spatial heterogeneity of soil properties has a significant impact on crop growth, making it difficult to adopt site-specific crop management practices. Traditional laboratory-based analyses are costly, and data extrapolation for mapping soil properties using high-resolution imagery becomes a computationally expensive procedure, taking days or weeks to obtain accurate results using a desktop workstation. To overcome these challenges, cloud-based solutions such as Google Earth Engine (GEE) have been used to analyze complex data with machine learning algorithms. In this study, we explored the feasibility of designing and implementing a digital soil mapping approach in the GEE platform using high-resolution reflectance imagery derived from a thermal infrared and multispectral camera Altum (MicaSense, Seattle, WA, USA). We compared a suite of multispectral-derived soil and vegetation indices with in situ measurements of physical-chemical soil properties in agricultural lands in the Peruvian Mantaro Valley. The prediction ability of several machine learning algorithms (CART, XGBoost, and Random Forest) was evaluated using R2, to select the best predicted maps (R2 > 0.80), for ten soil properties, including Lime, Clay, Sand, N, P, K, OM, Al, EC, and pH, using multispectral imagery and derived products such as spectral indices and a digital surface model (DSM). Our results indicate that the predictions based on spectral indices, most notably, SRI, GNDWI, NDWI, and ExG, in combination with CART and RF algorithms are superior to those based on individual spectral bands. Additionally, the DSM improves the model prediction accuracy, especially for K and Al. We demonstrate that high-resolution multispectral imagery processed in the GEE platform has the potential to develop soil properties prediction models essential in establishing adaptive soil monitoring programs for agricultural regions. [ABSTRACT FROM AUTHOR]

This volume is largely about nontraditional data; this paper is about a nontraditional visualization: classification trees. Using trees with data will be new to many students, so rather than beginning with a computer algorithm that produces optimal trees, we suggest that students first construct their own trees, one node at a time, to explore how they work, and how well. This build‐it‐yourself process is more transparent than using algorithms such as CART; we believe it will help students not only understand the fundamentals of trees, but also better understand tree‐building algorithms when they do encounter them. And because classification is an important task in machine learning, a good foundation in trees can prepare students to better understand that emerging and important field. We also describe a free online tool—Arbor—that students can use to do this, and note some implications for instruction. [ABSTRACT FROM AUTHOR]

Introduction: Clinical prediction rule (CPR) using decision tree analysis is able to show the branching of the variables under consideration in a clear, hierarchical manner, including specific reference values, which can be used as classifiers in clinical practice. However, CPRs developed by decision tree analysis for predicting the degree of independent living of patients with thoracic spinal cord injury (SCI) are few. The purpose of this study was to develop a simplified CPR for prognosticating dependent daily living in patients with thoracic SCI. Methods: We extracted data on patients with thoracic SCI from a national multicenter registry database, the Japan Rehabilitation Database (JRD). All patients with thoracic SCI who were hospitalized within 30 days after the injury onset were included. The independent living was categorized in the JRD as follows: independent socially, independent at home, needing care at home, independent at the facility, and needing care at the facility. These categories were used as the objective variables in classification and regression tree (CART) analysis. The CART algorithm was applied to develop the CPR for predicting whether patients with thoracic SCI achieve independent living at hospital discharge. Results: Three hundred ten patients with thoracic SCI were included in the CART analysis. The CART model identified, in a hierarchical order, patient's age, residual function level, and the bathing sub-score of Functional Independence Measure as the top three factors with moderate classification accuracy and area under the curve. Conclusions: We developed a simplified, moderately accurate CPR for predicting whether patients with thoracic SCI achieve independent living at hospital discharge. [ABSTRACT FROM AUTHOR]

In the present study, various statistical and machine learning (ML) techniques were used to understand how device fabrication parameters affect the performance of copper oxide-based resistive switching (RS) devices. In the present case, the data was collected from copper oxide RS devices-based research articles, published between 2008 to 2022. Initially, different patterns present in the data were analyzed by statistical techniques. Then, the classification and regression tree algorithm (CART) and decision tree (DT) ML algorithms were implemented to get the device fabrication guidelines for the continuous and categorical features of copper oxide-based RS devices, respectively. In the next step, the random forest algorithm was found to be suitable for the prediction of continuous-type features as compared to a linear model and artificial neural network (ANN). Moreover, the DT algorithm predicts the performance of categorical-type features very well. The feature importance score was calculated for each continuous and categorical feature by the gradient boosting (GB) algorithm. Finally, the suggested ML guidelines were employed to fabricate the copper oxide-based RS device and demonstrated its non-volatile memory properties. The results of ML algorithms and experimental devices are in good agreement with each other, suggesting the importance of ML techniques for understanding and optimizing memory devices. [ABSTRACT FROM AUTHOR]

Simple Summary: This study aimed to estimate body weight from various biometric measurements and features such as genotype (share of Suffolk and Polish Merino genotypes), birth weight (BiW), sex, birth type and body weight at 12 months of age (LBW) and some body measurements such as withers height (WH), sacrum height (SH), chest depth (CD), chest width (CW), chest circumference (CC), shoulder width (SW) and rump width (RW). Three hundred and forty-four animals were used in the study. Data mining and machine learning algorithms such as Random Forest Regression, Support Vector Regression and classification and regression tree were used to estimate the body weight from various features. Results show that the random forest procedure may help breeders improve characteristics of great importance. In this way, the breeders can get an elite population and determine which features are essential for estimating the body weight of the herd in Poland. The study's main goal was to compare several data mining and machine learning algorithms to estimate body weight based on body measurements at a different share of Polish Merino in the genotype of crossbreds (share of Suffolk and Polish Merino genotypes). The study estimated the capabilities of CART, support vector regression and random forest regression algorithms. To compare the estimation performances of the evaluated algorithms and determine the best model for estimating body weight, various body measurements and sex and birth type characteristics were assessed. Data from 344 sheep were used to estimate the body weights. The root means square error, standard deviation ratio, Pearson's correlation coefficient, mean absolute percentage error, coefficient of determination and Akaike's information criterion were used to assess the algorithms. A random forest regression algorithm may help breeders obtain a unique Polish Merino Suffolk cross population that would increase meat production. [ABSTRACT FROM AUTHOR]

In this work we propose a new algorithm to train and optimize an ensemble of classifiers. We call this algorithm the Krypteia ensemble, based on an ancient Spartan tradition designed to convert their most promising individuals into future leaders of their society. We show how to adapt this ancient custom to optimize classifiers by generating different variations of the same task, each one offering different hardships according to distinct stochastic variables. This is thus applied to induce diversity in the set of individual weak learners. Then, we use a set of agents designed to select those subjects who excel in their assignments, and whose interaction minimizes excessive redundancies in the resulting population. We also study how different Krypteia ensembles can be stacked together, so that more complex classifiers can be built using the same procedure. Besides, we consider a wide range of different aggregation functions in the decision making phase to find the optimal performance for the different Krypteia ensemble variations tested. Finally, we study how different Krypteia ensembles perform for a wide range of classification datasets and we compare them with other state-of-the-art design techniques of classifier ensembles, obtaining favourable results to our proposal. • We propose a way to train classifier ensembles based on an ancient Spartan costume. • We obtain better results than those achieved using state-of-the-art ensembles. • We study the effects of different parameters of the algorithm using a CART model. [ABSTRACT FROM AUTHOR]

An actual cropland extent product with a high spatial resolution with a precision of up to 60 m is believed to be particularly significant in tackling numerous water security concerns and world food challenges. To advance the development of niche, advanced cropland goods such as crop variety techniques, crop intensities, crop water production, and crop irrigation, it is necessary to examine how cropland products typically span narrow or expansive farmlands. Some of the existing challenges are processing by constructing precision-high resolution cropland-wide items of training and testing data on diverse geographical locations and safe frontiers, computing capacity, and managing vast volumes of geographical data. This analysis includes eight separate Sentinel-2 multi-spectral instruments data from 2018 to 2019 (Short-wave Infrared Imagery (SWIR 2), SWIR 1, Cirrus, the near infrared, red, green, blue, and aerosols) have been used. Pixel-based classification algorithms have been employed, and their precision is measured and scrutinized in this study. The computations and analyses have been conducted on the cloud-based Google Earth Engine computing network. Training and testing data were obtained from the Google Earth Engine map console at a high spatial 10 m resolution for this analysis. The basis of research information for testing the computer algorithms consists of 855 training samples, culminating in a manufacturing field of 200 individual validation samples measuring product accuracy. The Pakistan cropland extent map produced in this study using four state-of-the-art machine learning (ML) approaches, Random Forest, SVM, Naïve Bayes & CART shows an overall validation accuracy of 82%, 89% manufacturer accuracy, and 77% customer accuracy. Among these four machine learning algorithms, the CART algorithm overperformed the other three, with an impressive classification accuracy of 93%. Pakistan's average cropland areas were calculated to be 370,200 m2, and the cropland's scale of goods indicated that sub-national croplands could be measured. The research offers a conceptual change in the development of cropland maps utilizing a remote sensing multi-date. [ABSTRACT FROM AUTHOR]

Background: Standard clinical practice and national guidelines dictate somatic testing of metastatic colorectal cancer (mCRC) tumors to guide appropriate therapy; however, previous studies suggest that not all patients are tested. The objective of this study was to investigate potential differences in testing for mCRC by demographic and clinical factors. Methods: We performed a retrospective review of de‐identified patient data derived from electronic health records (EHRs) of 25,469 patients diagnosed with mCRC between the years 2013 and 2020. Our outcome was a receipt of the following tests: (a) biomarker testing (BRAF, KRAS, NRAS, MMR/MSI) and (b) next‐generation sequencing (NGS). We interrogated our data using the machine‐learning algorithm Classification and Regression Tree (CART), a unique approach to identifying combinations of, rather than individual demographic and clinical characteristics associated with receipt of testing. Results: A total of 25,469 patients were identified with mCRC. Of these, 21,133 (83%) received either biomarker testing only (n = 12,485) or any testing (biomarker + NGS) (n = 8648). The proportion of patients who received any testing increased over calendar time for all age, race, and sex categories. Receipt of any testing was highest (90%) among younger and patients with better performance status, and there was no difference in receipt of any testing by race. The highest percentage of NGS testing was among those with better performance status, <70 years old, commercial or other governmental program payers, and low comorbidity burden; however, those who were Black or Hispanic had a lower prevalence of NGS testing than those who were White. Conclusions and Relevance: Considerable variations exist in somatic biomarker testing across subgroups of the population. Identification of genomic alterations can aid in determining targeted treatment and improving clinical outcomes; therefore, equitable use of these testing strategies, particularly NGS, is necessary. [ABSTRACT FROM AUTHOR]

An unbalanced classification dataset is one with skewed class proportions. An example of an unbalanced classification issue is one in which the distribution of instances across the known classes is biased or distorted. The distribution can range from a little bias to a severe imbalance, with one example in the minority class for hundreds, thousands, or millions in the dominant class or classes. This work proposes the OKC classifier, which is a hybrid of the One-Class SVM, k-Nearest Neighbours, and CART algorithms. The success of most classification algorithms is heavily influenced by certain qualities of the datasets on which they are trained, such as imbalances in class distribution, class overlapping, and lack of density. On imbalanced datasets, the proposed method may accomplish classification without resampling. This method is compared against a few well-known classification algorithms, as well as datasets with varying degrees of class imbalance and overlap. The experimental results reveal that the proposed method outperforms various well-established classification algorithms. [ABSTRACT FROM AUTHOR]

Amazonas is a mountain region in Peru with high cloud cover, so using optical data in the analysis of surface changes of water bodies (such as the Burlan and Pomacochas lakes in Peru) is difficult, on the other hand, SAR images are suitable for the extraction of water bodies and delineation of contours. Therefore, in this research, to determine the surface changes of Burlan and Pomacochas lakes, we used Sentinel-1 A/B products to analyse the dynamics from 2014 to 2020, in addition to evaluating the procedure we performed a photogrammetric flight and compared the shapes and geometric attributes from each lake. For this, in Google Earth Engine (GEE), we processed 517 SAR images for each lake using the following algorithms: a classification and regression tree (CART), Random Forest (RF) and support vector machine (SVM).) 2021-02-10, then; the same value was validated by comparing the area and perimeter values obtained from a photogrammetric flight, and the classification of a SAR image of the same date. During the first months of the year, there were slight increases in the area and perimeter of each lake, influenced by the increase in rainfall in the area. CART and Random Forest obtained better results for image classification, and for regression analysis, Support Vector Regression (SVR) and Random Forest Regression (RFR) were a better fit to the data (higher R2), for Burlan and Pomacochas lakes, respectively. The shape of the lakes obtained by classification was similar to that of the photogrammetric flight. For 2021-02-10, for Burlan Lake, all 3 classifiers had area values between 42.48 and 43.53, RFR 44.47 and RPAS 45.63 hectares. For Pomacohas Lake, the 3 classifiers had area values between 414.23 and 434.89, SVR 411.89 and RPAS 429.09 hectares. Ultimately, we seek to provide a rapid methodology to classify SAR images into two categories and thus obtain the shape of water bodies and analyze their changes over short periods. A methodological scheme is also provided to perform a regression analysis in GC using five methods that can be replicated in different thematic areas. [ABSTRACT FROM AUTHOR]

We propose a tree‐based algorithm (μCART) for classification and regression problems in the context of functional data analysis, which allows to leverage measure learning and multiple splitting rules at the node level, with the objective of reducing error while retaining the interpretability of a tree. For each internal node, our main contribution is the idea of learning a weighted functional L2 space by means of constrained convex optimization, which is then used to extract multiple weighted integral features from the functional predictors, in order to determine the binary split. The approach is designed to manage multiple functional predictors and/or responses, by defining suitable splitting rules and loss functions that can depend on the specific problem and can also be combined with additional scalar and categorical predictors, as the tree is grown with the original greedy CART algorithm. We focus on the case of scalar‐valued functional predictors defined on unidimensional domains and illustrate the effectiveness of our method in both classification and regression tasks, through a simulation study and four real‐world applications. [ABSTRACT FROM AUTHOR]

With the development of urbanization, the hourly PM2.5 concentration in the air is constantly changing. In order to improve the accuracy of PM2.5 prediction, a prediction model based on the Classification and Regression Tree (CART) and Broad Learning System (BLS) was constructed. Firstly, the CART algorithm was used to segment the dataset in a hierarchical way to obtain a subset with similar characteristics. Secondly, the BLS model was trained by using the data of each subset, and the validation error of each model was minimized by adjusting the window number of the mapping layer in the BLS network. Finally, for each leaf in the tree, the global BLS model and the local BLS model on the path from the root node to the leaf node are compared, and the model with the smallest error is selected. The data collected in this paper come from the Chine Meteorological Historical Data website. We selected historical data from the Huaita monitoring station in Xuzhou city for experimental analysis, which included air pollutant content and meteorological data. Experimental results show that the prediction effect of the CART–BLS model is better than that of RF, V-SVR, and seasonal BLS models. [ABSTRACT FROM AUTHOR]

Sexual harassment and its negative consequences continue to affect a large percentage of higher education students in the US. Previous research has identified a limited number of harassment risk factors, and has generally not examined them in combination. In this study, an expanded set of individual, relationship, and community-level risk factors were examined using hurdle models and classification and regression tree (CART) analyses to identify key risk factors for peer and faculty/staff sexual harassment. Secondary data analysis was conducted using data from a sample of 9,285 students from 18 two-year and four-year schools in Minnesota. CART analyses indicated that, for peer sexual harassment, being younger; consuming alcohol more than once a month; attending a four-year school; being transgender, genderqueer, self-identified, or a cisgender woman; and having experienced bullying were the most important risk factors for peer harassment on campus. For faculty/staff harassment, being gay, lesbian, bisexual, questioning, or having a self-identified sexual orientation was the most important risk factor. These and other risk factors were significant in the hurdle models. More research is needed to understand why these factors are associated with harassment. Limitations and implications for prevention programming at higher education institutions are discussed. [ABSTRACT FROM AUTHOR]

Coffee yield variation in the field can be learned to obtain useful information for coffee management. Machine learning algorithms were evaluated to determine Arabica coffee yield. The Classification and Regression Tree (CART) rpart1SE algorithm used for classification and regression provided crucial nutrient thresholds to obtain high yield and minimise yield variability, by increasing vigour in well-nourished plants, with fertiliser management in the field. The use of the random forest model enabled to detect the most important variables for predicting coffee yield, as well as to identify how the nutritional status of the plants, such as Mg, Fe and Ca contents can be balanced to maximise yield. Variables related to the coffee nutritional status were more important than remote sensing variables for estimating coffee yield in the field. Despite the better accuracy of the random forest model (rf) to predict coffee yield when compared to the rpart1SE model, the particularity of each machine learning algorithm modelling was used in terms of the benefits of the results of each methodology synergistically in favour of wisely defining the best strategy and tactics for the crop management. In general, Mg leaf content was the most important variable for yield class prediction in both the 2005 and 2006 harvests by the rf model. The CART algorithm defined Mg leaf content threshold <3.615 g kg−1 in 6/15/2005 for yield classification in the first node and this threshold obtained is consistent with the available literature associated with high coffee yields between 3.6 and 4.0 g kg−1. • Machine learning with big data enabled to predict coffee yield variation in the field. • Random forest and rpart1SE modelling provided insights for crop yield management. • Leaf mineral nutrition must be considered for coffee yield management in the field. [ABSTRACT FROM AUTHOR]

Accurate identification of maize plantation distribution and timely examination of key spatial-temporal drivers is a practice that can support agricultural production estimates and development decisions. Previous studies have rarely used efficient cloud processing methods to extract crop distribution, and meteorological and socioeconomic factors were often considered independently in driving force analysis. In this paper, we extract the spatial distribution of maize using classification and regression tree (CART) and random forest (RF) algorithms based on the Google Earth Engine (GEE) platform. Combining remote sensing, meteorological and statistical data, the spatio-temporal variation characteristics of maize plantation proportion (MPP) at the county scale were analyzed using trend analysis, kernel density estimation, and standard deviation ellipse analysis, and the driving forces of MPP spatio-temporal variation were explored using partial correlation analysis and geodetectors. Our empirical results in Heilongjiang province, China showed that (1) the CART algorithm achieved higher classification accuracy than the RF algorithm; (2) MPP showed an upward trend in more than 75% of counties, especially in high-latitude regions; (3) the main climatic factor affecting the inter-annual fluctuation of MPP was relative humidity; (4) the impact of socioeconomic factors on MPP spatial distribution was significantly larger than meteorological factors, the temperature was the most important meteorological factor, and the number of rural households was the most important socioeconomic factor affecting MPP spatial distribution. The interaction between different factors was greater than a single factor alone; (5) the correlation between meteorological factors and MPP differed across different latitudinal regions and landforms. This research provides a key reference for the optimal adjustment of crop cultivation distribution and agricultural development planning and policy. [ABSTRACT FROM AUTHOR]

To overcome the difficulties in interpreting fetal heart rate (FHR), several tools based on the autonomic nervous system and heart rate variability (HRV) have been developed. The objective of this study was to use FHR and HRV parameters for the prediction of fetal hypoxia. It was an experimental study in the instrumented fetal sheep. Repeated umbilical cord occlusions were performed to achieve severe acidosis. Hemodynamic parameters, ECG, and blood gases were analyzed. The variables used were heart rate baseline, HRV analysis (RMSSD, SDNN, LF, HF, HFnu, Fetal Stress Index (FSI), ...), and morphological analysis of decelerations. The gold standard used to classify hypoxia was the fetal arterial pH (pH < 7.10). Different multivariable statistical methods (logistic regression and decision trees) were applied for the detection of acidosis. 21 lambs were instrumented. A total of 130 pairs of FHR/fetal pH analysis were obtained of which 29 in the acidosis group and 101 in the non-acidosis group. After logistic regression model with bootstrap resampling and stepwise backward selection, only one variable was selected, FSI. The AUC of FSI alone in this model was 0.81 with a sensitivity of 0.66, specificity of 0.88, PPV of 0.61, and NPV of 0.90 considering a threshold of 68. Decision trees with CHAID and CART algorithms showed a sensitivity of 0.48 and 0.59, respectively, and a specificity of 0.94 for both. All employed methods identified HRV variables as the most predictive of acidosis. The primary variables selected automatically were those from the HRV. Supporting the use of FHRV measures for the screening of fetal acidosis during labour is interesting. [ABSTRACT FROM AUTHOR]

We introduce causal interaction tree (CIT) algorithms for finding subgroups of individuals with heterogeneous treatment effects in observational data. The CIT algorithms are extensions of the classification and regression tree algorithm that use splitting criteria based on subgroup‐specific treatment effect estimators appropriate for observational data. We describe inverse probability weighting, g‐formula, and doubly robust estimators of subgroup‐specific treatment effects, derive their asymptotic properties, and use them to construct splitting criteria for the CIT algorithms. We study the performance of the algorithms in simulations and implement them to analyze data from an observational study that evaluated the effectiveness of right heart catheterization for critically ill patients. [ABSTRACT FROM AUTHOR]

3D protein structures determine proteins' biological functions. The 3D structure of the protein backbone can be approximated using the prototypes of local protein conformations. Sets of these prototypes are called structural alphabets (SAs). Amongst several approaches to the prediction of 3D structures from amino acid sequences, one approach is based on the prediction of SA prototypes for a given amino acid sequence. Protein Blocks (PBs) is the most known SA, and it is composed of 16 prototypes of five consecutive amino acids which were identified as optimal prototypes considering the ability to correctly approximate the local structure and the prediction accuracy of prototypes from an amino acid sequence. We developed models for PBs prediction from sequence information using different data mining approaches and machine learning algorithms. Besides the amino acid sequences, the results of the following tools were used to train the models: the Spider3 predictor of protein structure properties, several predictors of the protein's intrinsically disordered regions, and a tool for finding repeats in amino acid sequences. The highest accuracy of the constructed models is 80%, which is a significant improvement compared to the previous best available prediction, whose accuracy was 61%. Analyzing the models constructed by applying different algorithms, it was noticed that the significance of input attributes differs among the models constructed by algorithms. Using the information about amino acids belonging to intrinsically disordered regions and repeats improves the precision of prediction for some PBs using the CART classification algorithm, while this is not the case with the C5.0 classification algorithm. Improved prediction approaches can have interesting applications in protein structural model approaches or computational protein design. [Display omitted] • Protein Blocks can be used to predict local structure from protein sequence. • Data mining approaches are used for building models for Protein Blocks prediction. • Protein structure predictors can increase precision for Protein Blocks. • Repeats in amino acid sequence can increase precision for Protein Blocks. • Best developed Protein Blocks prediction model has an accuracy of 80%. [ABSTRACT FROM AUTHOR]

Objectives: Traffic congestion detection is one of the key points and difficulties of urban traffic management. The existing congestion detection methods are based on road sections, which is not conducive to the extraction of spatiotemporal evolution information of congestion. Moreover, most of the detection only involves the degree of congestion but lacks the congestion type identification. With the classification and regression tree (CART) algorithm, this paper proposes a method for the classification and detection of traffic congestion points, which takes the road section point as the detection unit. In the practical application of this method, congestion points and their categories can be detected in real time according to the average running speed on the road section. Methods: Firstly, the road section is divided at a specific interval and mapped to be road section points. According to the abnormal rules and patterns of spatiotemporal road conditions, the spatiotemporal evolution patterns of four congestion types are analyzed with road section points as units. Secondly, the spatial and temporal sequence of road conditions of road section points is extracted on the basis of the road condition detection of road sections, and the spatial and temporal sequence of road conditions is classified and labeled according to different congestion types. Thirdly, four speed indexes are selected to constitute the attribute set of samples, and the speed of each road section point at each period is extracted according to the attribute set, which forms the dataset of decision tree learning. Finally, with the CART algorithm, the optimal model is obtained by the training with cross-validation to achieve the best generalization ability. Results: This paper proposes a classification and detection method of traffic congestion points based on CART. On one hand, congestion point detection is added to refine the basic unit of congestion detection, and on the other hand, congestion point type detection is also involved. Classification and detection of congestion points is helpful to improve the efficiency of traffic management. Conclusions: The proposed method is compared with the support vector machine classification model, and the experimental results show that the method in this paper has higher accuracy, higher recall rate, and better classification and detection timeliness. [ABSTRACT FROM AUTHOR]

With the systematization, informatization, and intelligence of the management and operation of communication enterprises, the amount of audit content and business data is increasing. The traditional audit work is mainly offline audit, the task is heavy and temporary, there are few auditors, and there is a lack of unified data mart and analysis model support. In order to solve many problems in traditional auditing, this paper realizes the interface of data dictionary attributes through effective domain management of multisystem data, so as to achieve the purpose of system support and effective management to improve data quality. Furthermore, the platform is extensible, which can gradually expand the data coverage and support more management fields and business systems. A method of obtaining continuous attribute clustering center points by K-means algorithm and using triangular fuzzy numbers to fuzzify process continuous data is proposed. At the same time, a visual fuzzy decision-making system based on Fuzzy ID3 and Min-Ambiguity algorithm was designed. Adding the C4.5 and CART algorithms implemented in the Weka open source data mining software, through experimental analysis, the differences in the classification accuracy and the number of rules generated by the four decision tree algorithms are compared. The experiment found that the Fuzzy ID3 algorithm has a high accuracy rate on each dataset and the number of rules is large. The number of rules generated by the CART algorithm is the least because of the model characteristics of its binary tree and the characteristics of using the Gini index as the criterion for the selection of splitting attributes. Comparing Fuzzy ID3 and Min-Ambiguity fuzzy decision tree algorithms, it is found that the overall performance of the former is better than that of the latter, and the effect of authenticity on the two algorithms is analyzed experimentally. This paper constructs the internal audit flowchart in the big data environment and studies the optimization of the internal audit process in the big data environment. We evaluate traditional internal audit processes using process optimization theory. The internal audit process in this paper refers to the internal audit process under the risk-oriented model that is widely used at this stage. The optimization research on the internal audit process in this paper is mainly aimed at the internal audit process of general enterprises with a certain level of informatization, at a large scale, and certain foundation and requirements for the analysis and use of data. The optimization of internal audit process is feasible in research and practical application and has universal applicability and reference value. [ABSTRACT FROM AUTHOR]

In order to overcome the problems existing in traditional financial risk evaluation methods, such as high generalization error and fitting degree with actual value, this paper designs a financial risk evaluation method of blockchain digital currency based on CART algorithm. After screening and ranking the financial risk indicators of blockchain digital currency, the financial risk level of blockchain digital currency is determined by combining CART algorithm. Finally, by calculating the covariance matrix of the financial risk decision matrix, the positive ideal solution and the negative ideal solution of the financial risk are found, and then the final evaluation result is obtained by combining the progress of the financial risk. Experimental results show that the minimum generalization error of this method is only 0.021, the fitting degree of the obtained results and the actual risk can reach 98.0%, and the maximum risk accuracy can reach 0.978. [ABSTRACT FROM AUTHOR]

Day‐ahead forecasting for campus‐level load is important for better energy management, but especially difficult to be accurate, compared to large‐scale loads such as cities or regions. This is because irregular and unpredictable behavior of individual loads in small‐scale loads cannot be fully smoothed out and thus pose a negative impact on forecasting accuracy. This paper presents an online refinement strategy for day‐ahead forecasting using intraday data for a campus‐level load, focusing on self‐adapting correction of forecasting considering load pattern. First, according to the load pattern forecasted by Classification and Regression Trees (CART) one day ahead, the correction parameter group is assigned to the correction model. If the correction conditions are met, the forecasting results for the rest of the day will be updated. After all‐day load data is achieved, the actual load pattern can be identified and used to train CART model. To confirm the effectiveness of the proposed strategy, the model is evaluated by two datasets, a real‐life dataset of an industrial park in Shanghai China and a public dataset of an institute campus in Delhi, India. The results demonstrate that the proposed strategy can improve short‐term forecasting accuracy. [ABSTRACT FROM AUTHOR]

Simple Summary: The purpose of this study is to predict the risk of metastatic lymph nodes related to oral tongue squamous cell carcinoma (OTSCC) and tumor grading through the combination of clinical data with radiomics metrics extracted from computed tomography (CT) images. We aimed to develop a supportive approach in the management of lymphatic cervical areas, with particular attention given to the early stages (T1−T2). Specifically, we evaluated the effectiveness of the radiomics and clinical features in the study of OTSCC and in the prediction of occult laterocervical metastatic lymph nodes. We concluded that radiomics features and clinical parameters have an important role in identifying tumor grading and metastatic lymph nodes. Machine learning approaches can be used as an easy-to-use tool to stratify patients with early-stage OTSCC, based on the identification of metastatic and non-metastatic lymph nodes Objective: To predict the risk of metastatic lymph nodes and the tumor grading related to oral tongue squamous cell carcinoma (OTSCC) through the combination of clinical data with radiomics metrics by computed tomography, and to develop a supportive approach in the management of the lymphatic cervical areas, with particular attention to the early stages (T1−T2). Between March 2016 and February 2020, patients with histologically confirmed OTSCC, treated by partial glossectomy and ipsilateral laterocervical lymphadenectomy and subjected to computed tomography (CT) before surgery, were identified by two centers: 81 patients (49 female and 32 male) with 58 years as the median age (range 19–86 years). Univariate analysis with non-parametric tests and multivariate analysis with machine learning approaches were used. Clinical, hematological parameters and radiological features extracted by CT were considered individually and in combination. All clinical parameters showed statistically significant differences (p < 0.05) for the Kruskal−Wallis test when discriminating both the tumor grading and the metastatic lymph nodes. DOI, PLR, SII, and SIRI showed an accuracy of 0.70 (ROC analysis) when identifying the tumor grading, while an accuracy ≥ 0.78 was shown by DOI, NLR, PLR, SII, and SIRI when discriminating metastatic lymph nodes. In the context of the analysis of radiomics metrics, the original_glszm_HighGrayLevelZoneEmphasis feature was selected for identifying the tumor grading (accuracy of 0.70), while the wavelet_HHH_glrlm_LowGrayLevelRunEmphasis predictor was selected for determining metastatic lymph nodes (accuracy of 0.96). Remarkable findings were also obtained when classifying patients with a machine learning approach. Radiomics features alone can predict tumor grading with an accuracy of 0.76 using a logistic regression model, while an accuracy of 0.82 can be obtained by running a CART algorithm through a combination of three clinical parameters (SIRI, DOI, and PLR) with a radiomics feature (wavelet_LLL_glszm_SizeZoneNonUniformityNormalized). In the context of predicting metastatic lymph nodes, an accuracy of 0.94 was obtained using 15 radiomics features in a logistic regression model, while both CART and CIDT achieved an asymptotic accuracy value of 1.00 using only one radiomics feature. Radiomics features and clinical parameters have an important role in identifying tumor grading and metastatic lymph nodes. Machine learning approaches can be used as an easy-to-use tool to stratify patients with early-stage OTSCC, based on the identification of metastatic and non-metastatic lymph nodes. [ABSTRACT FROM AUTHOR]

Black and odorous water bodies represent a topic of significant interest in the field of water pollution prevention and control. Remote sensing technology is increasingly exploited for the monitoring of black and odorous water bodies because of its high efficiency and large-scale monitoring potential. In the present study, the Sentinel-2A imagery data were combined with data obtained by measuring spectral properties of black and odorous water bodies to produce a classification and regression tree (CART) model-based improved remote sensing recognition method for such water bodies. This method transforms the traditional single-feature empirical threshold segmentation algorithm to a multi-feature fuzzy decision-tree classification algorithm. The results reveal overall accuracy values of 84.78%, 92.85%, and 72.23% for the CART decision-tree algorithm, the confidence zone classification, and the fuzzy zone node classification, respectively. The method proposed in the present study enables the highly precise extraction of features representing black and odorous water bodies from satellite imagery. The characterization of confidence and fuzzy zones minimizes the need for field inspections, and it enhances the efficiency of diverse applications including engineering. [ABSTRACT FROM AUTHOR]

The development of an accurate nitrogen oxide (NO x) prediction model is difficult because of multiple parameters, strong coupling, and long delay time of selective catalytic reduction (SCR) systems. In this study, a modeling scheme based on combined feature selection, the JAYA optimization algorithm, and deep neural network (DNN) was developed. First, historical operating data preprocessing, including eliminating outlier points and normalization, was completed. Next, a combined feature selection algorithm based on classification and regression tree, random forest, extreme gradient boosting, and maximal information coefficient (MIC) was developed to select critical input variables. Subsequently, the delay time of the input variables was calculated based on the MIC and JAYA algorithm, and the modeling data were reconstructed. Finally, the real-time dynamic prediction of the SCR outlet NO x concentration was realized based on the DNN model. Experimental results based on operation data of 1000 MW ultra-supercritical boiler revealed that the prediction errors of the established models were less than 5%. Thus, could accurately predict the NO x emission concentration at the outlet of SCR system. • A combined feature selection algorithm based on CART, RF, XGBoost, and MIC is developed. • A JAYA-based method for calculating delay time between NOx emission and input variables is developed. • A real-time dynamic prediction model of the SCR outlet NOx concentration is developed. • Case study on NOx emissions at a 1000 MW coal-fired power plant. • The proposed model outperformed other comparable models. [ABSTRACT FROM AUTHOR]

Outlier detection is extensively adopted in machine learning applications to identify rare but significant objects in a data distribution that deviate from the majority of objects. However, none of the existing outlier definitions use the available contextual label information in a dataset to improve the identification of outliers, though it could improve the performance of data analysis. In this study, we propose a novel definition for outliers considering the available contextual label information along with a method to remove outliers based on the proposed definition to improve classification performance and granulation purity. The experimental results on eight public datasets show that the removal of outliers using the novel method highly improves the classification accuracy with Support Vector Machine, k-Nearest Neighbors, and Classification and Regression Tree algorithms while identifying 100% pure subclasses of the labeled major classes. This method is beneficial in identifying the outliers automatically when the data contains classification information about a specific application instead of outlierness information. • Outlier removal approach to improve the performance of the remaining data. • Define outliers using the available contextual label information. • Identify outliers which reduce the purity of data granules within a dataset. • Confirm 100% purity of the granules (clusters) after the outlier removal. [ABSTRACT FROM AUTHOR]

Purpose: We sought to exploit the heterogeneity afforded by patient-derived tumor xenografts (PDX) to first, optimize and identify robust radiomic features to predict response to therapy in subtype-matched triple negative breast cancer (TNBC) PDX, and second, to implement PDX-optimized image features in a TNBC co-clinical study to predict response to therapy using machine learning (ML) algorithms. Methods: TNBC patients and subtype-matched PDX were recruited into a co-clinical FDG-PET imaging trial to predict response to therapy. One hundred thirty-one imaging features were extracted from PDX and human-segmented tumors. Robust image features were identified based on reproducibility, cross-correlation, and volume independence. A rank importance of predictors using ReliefF was used to identify predictive radiomic features in the preclinical PDX trial in conjunction with ML algorithms: classification and regression tree (CART), Naïve Bayes (NB), and support vector machines (SVM). The top four PDX-optimized image features, defined as radiomic signatures (RadSig), from each task were then used to predict or assess response to therapy. Performance of RadSig in predicting/assessing response was compared to SUVmean, SUVmax, and lean body mass-normalized SULpeak measures. Results: Sixty-four out of 131 preclinical imaging features were identified as robust. NB-RadSig performed highest in predicting and assessing response to therapy in the preclinical PDX trial. In the clinical study, the performance of SVM-RadSig and NB-RadSig to predict and assess response was practically identical and superior to SUVmean, SUVmax, and SULpeak measures. Conclusions: We optimized robust FDG-PET radiomic signatures (RadSig) to predict and assess response to therapy in the context of a co-clinical imaging trial. [ABSTRACT FROM AUTHOR]

This paper is intended to apply data mining techniques for real Iraqi biochemical dataset to discover hidden patterns within tests relationships. It is worth noting that preprocessing steps take remarkable efforts to handle this type of data, since it is pure data set with so many null values reaching a ratio of 94.8%, then it becomes 0% after achieving these steps. However, in order to apply Classification And Regression Tree (CART) algorithm, several tests were assumed as classes, because of the dataset was unlabeled. Which then enabled discovery of patterns of tests relationships, that consequently, extends its impact on patients‟ health, since it will assist in determining test values by performing only relevant tests. Therefore decreases the number of tests for patients. [ABSTRACT FROM AUTHOR]

These days, telecommunications is very much needed in all areas of life. This condition has made the competition among the company is extremely tense. One strategic way to protect the company is to retain existing customers. The retention program as a scheme to retain customers must be implemented precisely and efficiently so that the company can maintain as many customers as possible. In this case, customer churn prediction holds an essential role. However, the existence of imbalanced data can increase prediction errors and create problems. Hence, in order to overcome the issue, this study combined the Synthetic Minority Oversampling Technique - Nominal Continuous (SMOTE-NC) with Classification and Regression Trees (CART). SMOTE-NC was applied to balance classes on training data, while CART formed a classification tree from those balanced data. Then, this classification tree created by CART algorithm had become the basis for predicting customer churn. The data used in this study are from https://community.ibm.com/, where the variables are related to customer demographics, customer contracts, usage history, and customer status of one of the telecom companies. Based on the analysis of these data, SMOTE-NC and CART combination succeeded in reducing errors in predicting customer churn, which also led recall value to increase by approximately 19%. Moreover, the accuracy generated from this combination method was still in a pretty good range of over 75%. Therefore, this study proposes an excellent way to improve the performance of churn prediction, especially in the telecommunications industry. [ABSTRACT FROM AUTHOR]

We propose to extend CART for bivariate marked point processes to provide a segmentation of the space into homogeneous areas for interaction between marks. While usual CART tree considers marginal distribution of the response variable at each node, the proposed algorithm, SpatCART, takes into account the spatial location of the observations in the splitting criterion. We introduce a dissimilarity index based on Ripley's intertype K-function quantifying the interaction between two populations. This index used for the growing step of the CART strategy, leads to a heterogeneity function consistent with the original CART algorithm. Therefore the new variant is a way to explore spatial data as a bivariate marked point process using binary classification trees. The proposed procedure is implemented in an R package, and illustrated on simulated examples. SpatCART is finally applied to a tropical forest example. [ABSTRACT FROM AUTHOR]

Nonintrusive industrial load identification can accurately acquire the operation data of each load in the plant, which is the benefit of intelligent power management. The identification method of the industrial load is complicated and difficult to be realized due to the difficulty in collecting transient data for modeling, and high-precision measuring equipment is required. Aiming at this situation, the article proposes a nonintrusive industrial load identification method using a random forest algorithm and steady-state waveform. Firstly, by monitoring the change of the industrial load power state, when the load changes and becomes stable, the steady-state waveform is extracted. Due to different electrical characteristics of industrial loads, the current waveform of loads is different to some extent. We can construct characteristic data for each industrial load to construct its own current steady-state waveform. Then, using the high-dimensional data of the steady-state waveform as the sample data, the bootstrap sampling method and the CART algorithm in the random forest algorithm are used to generate multiple decision trees. Finally, the industrial load types are identified by voting multiple decision trees. The actual operating load data of a factory are used as the sample data in the simulation, and the effectiveness and rapidity of the proposed identification algorithm are verified by the combined load method simulation comparison. The simulation results show that the accuracy of the proposed identification algorithm is more than 99%, the identification time is 3.36 s, which is much higher than that of other methods, and the operation time is less than that of other methods. Therefore, the proposed identification algorithm can effectively realize the nonintrusive industrial load identification. [ABSTRACT FROM AUTHOR]

Objective. Several discriminating techniques have been proposed to discriminate between β-thalassemia trait (βTT) and iron deficiency anemia (IDA). These discrimination techniques are essential clinically, but they are challenging and typically difficult. This study is the first application of the Bayesian tree-based method for differential diagnosis of βTT from IDA. Method. This cross-sectional study included 907 patients with ages over 18 years old and a mean (±SD) age of 25 ± 16.1 with either βTT or IDA. Hematological parameters were measured using a Sysmex KX-21 automated hematology analyzer. Bayesian Logit Treed (BLTREED) and Classification and Regression Trees (CART) were implemented to discriminate βTT from IDA based on the hematological parameters. Results. This study proposes an automatic detection model of beta-thalassemia carriers based on a Bayesian tree-based method. The BLTREED model and CART showed that mean corpuscular volume (MCV) was the main predictor in diagnostic discrimination. According to the test dataset, CART indicated higher sensitivity and negative predictive value than BLTREED for differential diagnosis of βTT from IDA. However, the CART algorithm had a high false-positive rate. Overall, the BLTREED model showed better performance concerning the area under the curve (AUC). Conclusions. The BLTREED model showed excellent diagnostic accuracy for differentiating βTT from IDA. In addition, understanding tree-based methods are easy and do not need statistical experience. Thus, it can help physicians in making the right clinical decision. So, the proposed model could support medical decisions in the differential diagnosis of βTT from IDA to avoid much more expensive, time-consuming laboratory tests, especially in countries with limited recourses or poor health services. [ABSTRACT FROM AUTHOR]

A tree model with low time complexity can support the application of artificial intelligence to industrial systems. Variable selection based tree learning algorithms are more time efficient than existing Classification and Regression Tree (CART) algorithms. To our best knowledge, there is no attempt to deal with categorical input variable in variable selection based multi-output tree learning. Also, in the case of multi-output regression tree, a conventional variable selection based algorithm is not suitable to large datasets. We propose a mutual information-based multi-output tree learning algorithm that consists of variable selection and split optimization. The proposed method discretizes each variable based on k-means into 2–4 clusters and selects the variable for splitting based on the discretized variables using mutual information. This variable selection component has relatively low time complexity and can be applied regardless of output dimension and types. The proposed split optimization component is more efficient than an exhaustive search. The performance of the proposed tree learning algorithm is similar to or better than that of a multi-output version of CART algorithm on a specific dataset. In addition, with a large dataset, the time complexity of the proposed algorithm is significantly reduced compared to a CART algorithm. [ABSTRACT FROM AUTHOR]

Stream waters play a crucial role in catering to the world's needs with the required quality of water. Due to the discharges of wastewater from the various point and nonpoint sources, most of the watersheds are contaminated easily. The Upper Green River watershed in Kentucky, USA, is one such watershed that is contaminated over the years due to the runoff from rural areas and agricultural lands and combined sewer overflows (CSOs) from urban areas. Monitoring and characterizing the water quality status of streams in such watersheds has become of great importance, with multivariate statistical techniques such as regression, factor analysis, cluster analysis, and artificial intelligence methods such as artificial neural networks (ANNs). The water quality parameters, namely, fecal coliform (FC), turbidity, pH, and conductivity have been predicted quantitatively using ANNs to understand the water quality status of streams in the Upper Green River watershed elsewhere. In this study, a novel attempt has been made to predict the status of the quality of the Green River water with the predictive capabilities of a few decision tree (DT) algorithms such as classification and regression tree (CART) model, multivariate adaptive regression splines (MARS) model, random forest (RF) model, and extreme learning machine (ELM) model. The RF model's performance is better in predicting FC, turbidity, and pH than CART models in training and testing phases. Relatively, MARS and ELM models did better in testing though the performance is poorer in training. For example, we obtain the RMSE values of 2206, 2532, 1533, and 1969 using RF, CART, MARS, and ELM for FC in testing. A good correlation has been observed between conductivity and temperature, precipitation, and land‐use factors for the MARS model. Overall, DT models are helpful in understanding, interpreting the outcomes, and visualizing the results compared with the other models. Practitioner points: The prediction of stream water quality parameters using decision trees is explored.The climate and land use parameters are used as input parameters to the modeling.The DT models of CART, MARS, RF, and ANNs such as ELM are explored to predict stream water quality.The RF model shows stable results compared with CART, MARS, and ELM for the data explored.Apart from the R2 value, RMSE and MAE indicate the effectiveness of DTs in prediction. [ABSTRACT FROM AUTHOR]

Purpose: To develop an algorithm for the diagnosis of Behçet's disease (BD) uveitis based on ocular findings. Methods: Following an initial survey among uveitis experts, we collected multi-center retrospective data on 211 patients with BD uveitis and 207 patients with other uveitides, and identified ocular findings with a high diagnostic odds ratio (DOR). Subsequently, we collected multi-center prospective data on 127 patients with BD uveitis and 322 controls and developed a diagnostic algorithm using Classification and Regression Tree (CART) analysis and expert opinion. Results: We identified 10 items with DOR >5. The items that provided the highest accuracy in CART analysis included superficial retinal infiltrate, signs of occlusive retinal vasculitis, and diffuse retinal capillary leakage as well as the absence of granulomatous anterior uveitis or choroiditis in patients with vitritis. Conclusion: This study provides a diagnostic tree for BD uveitis that needs to be validated in future studies. [ABSTRACT FROM AUTHOR]