Classification And Regression Tree Method Research Articles

Building semi-supervised decision trees with semi-cart algorithm

AbstractDecision trees are a fundamental statistical learning tool for addressing classification and regression problems through a recursive partitioning approach that effectively accommodates numerical and categorical data [1, 2]. The Classification and regression tree (CART) algorithm underlies modern Boosting methodologies such as Gradient boosting machine (GBM), Extreme gradient boosting (XGBoost), and Light gradient boosting machine (LightGBM). However, the standard CART algorithm may require improvement due to its inability to learn from unlabeled data. This study proposes several modifications to incorporate test data into the training phase. Specifically, we introduce a method based on Graph-based semi-supervised learning called “Distance-based Weighting,” which calculates and removes irrelevant records from the training set to accelerate the training process and improve performance. We present Semi-supervised classification and regression tree (Semi-Cart), a new implementation of CART that constructs a decision tree using weighted training data. We evaluated its performance on thirteen datasets from various domains. Our results demonstrate that Semi-Cart outperforms standard CART methods and contributes to statistical learning.

Object Based Classification in Google Earth Engine Combining SNIC and Machine Learning Methods (Case Study: Lake Köyceğiz)

Köyceğiz Lake is one of our country’s most critical coastal barrier lakes, rich in sulfur, located at the western end of the Mediterranean Region. Köyceğiz Lake, connected to the Mediterranean via the Dalyan Strait, is one of the 7 lakes in the world with this feature. In this study, water change analysis of Köyceğiz Lake was carried out by integrating the Object-Based Image Classification method with CART (Classification and Regression Tree), RF (Random Forest), and SVM (Support Vector Machine) algorithms, which are machine learning algorithms. SNIC (Simple Non-iterative Clustering) segmentation method was used, which allows a detailed analysis at the object level by dividing the image into super pixels. Sentinel 2 Harmonized images of the study area were obtained from the Google Earth Engine (GEE) platform for 2019, 2020, 2021, and 2022,and all calculations were made in GEE. When the classification accuracies of four years were examined, it was seen that the classification accuracies(OA, UA, PA, and Kappa) of the lake water area were above 92%, F-score was above 0.98 for all methods using the object-based classification method obtained by the combination of the SNIC algorithm and CART, RF, and SVM machine learning algorithms. It has been determined that the SVM algorithm has higher evaluation metrics in determining the lake water area than the CART and RF methods.

Using Diverse Data Sources to Impute Missing Air Quality Data Collected in a Resource-Limited Setting

The sustainable operation of ambient air quality monitoring stations in developing countries is not always possible. Intermittent failures and breakdowns at air quality monitoring stations often affect the continuous measurement of data as required. These failures and breakdowns result in missing data. This study aimed to impute NO2, SO2, O3, and PM 10 to produce complete data sets of daily average exposures from 2010 to 2017. Models were built for (a) an individual pollutant at a monitoring station, (b) a combined model for the same pollutant from different stations, and (c) a data set with all the pollutants from all the monitoring stations. This study sought to evaluate the efficacy of the Multiple Imputation by Chain Equations (MICE) algorithm in successfully imputing air quality data that are missing at random. The application of classification and regression trees (CART) analysis using the MICE package in the R statistical programming language was compared with the predictive mean matching (PMM) method. The CART method performed better, with the pooled R-squared statistics of the imputed data ranging from 0.3 to 0.7, compared to a range of 0.02 to 0.25 for PMM. The MICE algorithm successfully resolved the incompleteness of the data. It was concluded that the CART method produced better reliable data than the PMM method. However, in this study, the pooled R2 values were accurate for NO2, but not so much for other pollutants.

County-level socio-environmental factors and obesity prevalence in the United States.

To investigate high-risk sociodemographic and environmental determinants of health (SEDH) potentially associated with adult obesity in counties in the United States using machine-learning techniques. We performed a cross-sectional analysis of county-level adult obesity prevalence (body mass index ≥30 kg/m2) in the United States using data from the Diabetes Surveillance System 2017. We harvested 49 county-level SEDH factors that were used in a classification and regression trees (CART) model to identify county-level clusters. The CART model was validated using a 'hold-out' set of counties and variable importance was evaluated using Random Forest. Overall, we analysed 2752 counties in the United States, identifying a national median (interquartile range) obesity prevalence of 34.1% (30.2%, 37.7%). The CART method identified 11 clusters with a 60.8% relative increase in prevalence across the spectrum. Additionally, seven key SEDH variables were identified by CART to guide the categorization of clusters, including Physically Inactive (%), Diabetes (%), Severe Housing Problems (%), Food Insecurity (%), Uninsured (%), Population over 65 years (%) and Non-Hispanic Black (%). There is significant county-level geographical variation in obesity prevalence in the United States, which can in part be explained by complex SEDH factors. The use of machine-learning techniques to analyse these factors can provide valuable insights into the importance of these upstream determinants of obesity and, therefore, aid in the development of geo-specific strategic interventions and optimize resource allocation to help battle the obesity pandemic.

APPLICATION OF BAGGING CART IN THE CLASSIFICATION OF ON-TIME GRADUATION OF STUDENTS IN THE STATISTICS STUDY PROGRAM OF TANJUNGPURA UNIVERSITY

The timeliness of graduation is used as the success of students in pursuing education which can be seen from the time taken and measured by the predicate of graduation obtained. The characteristics of students who tend to graduate not or on time can be analyzed using classification techniques. Classification and Regression Tree (CART) is one of the classification tree methods. There is a weakness in CART, which is less stable in predicting a single classification tree. The weaknesses in CART can be improved by using Ensemble methods, one of which is Bootstrap Aggregating (Bagging) which can reduce classification errors and increase accuracy in a single classification model. This study aims to classify and determine the accuracy of Bagging CART in the case of the accuracy of student graduation classification. The number of samples used is 140 data on the graduation status of Untan Statistics Study Program students from Period I of the 2017/2018 academic year to Period II of the 2022/2023 academic year. The variables used are the timeliness of graduation which is categorized into two namely Not and On Time, Gender, Semester 1 GPA, Semester 2 GPA, Semester 3 GPA, Semester 4 GPA, Region of Origin Domicile, High School Accreditation, Entry Path, Scholarship, and first TUTEP. A good classification can be seen from the accuracy value. The CART method obtained an accuracy value of 70%. While using the CART Bagging method obtained an accuracy value of 85.71%. Based on the accuracy value obtained, the application of the CART Bagging method can increase accuracy and correct classification errors on a single CART classification tree by 15.71% by resampling 25 times.

Comparison of Error Rate Prediction Methods in Classification Modeling with Classification and Regression Tree (CART) Methods for Balanced Data

CART (Classification and Regression Tree) is one of the classification algorithms in the decision tree method. The model formed in CART is a tree consisting of root nodes, internal nodes, and terminal nodes. After the model is formed, it is necessary to calculate the accuracy of the model. The aims is to see the performance of the model. The accuracy of this model can be done by calculating the predicted error rate in the model. The error rate prediction method works by dividing the data into training data and testing data. There are three methods in the error rate prediction method, such as Leave One Out Cross Validation (LOOCV), Hold Out (HO), and K-Fold Cross Validation. These methods have different performance in dividing data into training data and testing data, so there are advantages and disadvantages to each method. Therefore, a comparison was made for the three error rate prediction methods with the aim of determining the appropriate method for the CART algorithm. This comparison was made by considering several factors, for instance variations in the mean, number of variables, and correlations in normal distributed random data. The results of the comparison will be observed using a boxplot by looking at the median error rate and the lowest variance. The results of this study indicate that the K-Fold Cross Validation has the median error rate and the lowest variance, so the most suitable error prediction method used for the CART method is the K-Fold Cross Validation method.

Large-scale quantification of groundwater recharge threshold conditions using machine learning classifications: An attempt over the Australian continent

The large-scale quantification of groundwater recharge threshold conditions is a bottleneck in the field of research, considering that groundwater recharge processes can be quite complex and affected by different factors in different regions. Traditional statistical approaches have either focused on local to regional scales or are limited to a single factor such as rainfall, resulting in a lack of a comprehensive understanding of groundwater recharge mechanisms on large scales. Considering that finding a threshold to instantly determine whether the groundwater is in the state of recharge or discharge is a classification task involving multiple factors, machine learning techniques with self-learning capabilities, efficient processing of big data, and mining relationships between multiple factors is, thus, applied to this study. In this study, three traditional machine learning classification techniques are explored; Classification and Regression Tree (CART), Random Forest (RF), and Logistical Regression (LR), to quantify specific threshold values for each condition (including rainfall, evaporation, soil moisture, runoff and vegetation) since they are more interpretable compared to advanced machine learning techniques such as neural networks. Using the Australian continent as an example, CART is the fastest method and provides an average classification accuracy (76%) at almost the same levels compared to RF (77–78%) and LR (79–80%). Meanwhile, CART is the only method to rank the importance of conditions while providing a specific threshold for each condition. When inferring the groundwater recharge mechanism through threshold conditions, the CART method suggests that a primary (the most important) threshold condition is sufficient for most parts of the Australian continent, e.g., rainfall as the primary threshold condition in northern Australia indicates a direct recharge mechanism. Only the coastal areas of southeastern and southwestern Australia are dominated by multiple threshold conditions, showing the complex groundwater recharge mechanism. Overall, the significance of this work is to provide the spatial maps of threshold conditions that mainly control groundwater recharge and their specific threshold values, which are crucial for managers to carry out a good plan over a large area. More importantly, this study demonstrates the potential of traditional machine learning methods to reveal groundwater recharge mechanisms, which may help further refine the development of groundwater models in the future.

Evaluation of surface reflectance bandpass adjustment techniques

There is an increasing number of on-orbit earth observation sensors in the solar domain (visible to middle infrared). While most the sensors are designed with apparent analogous bandpasses, they often exhibit differences in terms of Relative Spectral Response (RSR). Although the differences are well characterized, there is a need for techniques to adjust for the effect of these differences on surface reflectance after accounting for calibration, directional, and atmospheric effects. This research evaluated eight bandpass adjustment techniques using synthetic and actual remote sensing observations on seven widely used sensors. The scope of the study is global.The eight evaluated techniques were: a) spectral band adjustment factor technique (SBAF, i.e., one-coefficient regression), b) linear fit technique (i.e., two-coefficient regression), c) three Adaptive SBAF techniques (ASBAF), which are defined according to three different cost functions and apply a target-dependent SBAF, d) two artificial neural network approaches using (i) a single band (ANN-1B) and (ii) all bands (ANN-NB) as inputs, and e) a Classification and Regression Tree method (CART) using all bands as inputs. All these techniques require a calibration phase, which was carried out separately using three hyperspectral data sets: (i) USGS spectral measurements, (ii) simulated reflectance by the ProSail radiative transfer model, and (iii) real-world Hyperion observations. The full data set is publically available.The evaluation using the three hyperspectral data sets alone showed that the techniques with a single band as input (SBAF, LIN, and ANN-1B) generated higher uncertainty than the techniques with all bands as input (ASBAF, ANN-N, CART). The ASBAF techniques performed well with a few differences among the three ASBAF variants. The ANN-N was the technique that performed the best. The evaluation based on actual remote sensing data sets (Landsat-8 and Sentinel-2 data were used) suggested that all techniques reduced the deviation between the two data sets. Nonetheless, the deviation between the two data sets caused by factors other than RSR differences did not permit a clearcut comparison of the techniques. Some recommendations regarding the techniques to select for a particular application are provided.Finally, this research introduces the concept of RSR difference index (RDI) to quantify the spectral differences between two spectral bands.

Detection of Water Hyacinth (Eichhornia crassipes) in Lake Tana, Ethiopia, Using Machine Learning Algorithms

Lake Tana is Ethiopia’s largest lake and is infested with invasive water hyacinth (E. crassipes), which endangers the lake’s biodiversity and habitat. Using appropriate remote sensing detection methods and determining the seasonal distribution of the weed is important for decision-making, water resource management, and environmental protection. As the demand for the reliable estimation of E. crassipes mapping from satellite data grows, comparing the performance of different machine learning algorithms could help in identifying the most effective method for E. crassipes detection in the lake. Therefore, this study aimed to examine the ability of random forest (RF), support vector machine (SVM), and classification and regression tree (CART) machine learning algorithms to detect E. crassipes and estimating seasonal spatial coverage of the weed on the Google Earth Engine (GEE) platform using Landsat 8 and Sentinel 2 images. Cloud-masked monthly median composite Landsat 8 and Sentinel 2 data from October 2021 and 2022, January 2022 and 2023, March 2022, and June 2022 were used to represent autumn, winter, spring, and summer, respectively. Four spectral indices were derived and used in combination with spectral bands to improve the E. crassipes detection accuracy. All methods achieved greater than 95% and 90% overall accuracy when using Sentinel 2 and Landsat 8 images, respectively. Using both data sets, all methods achieved a greater than 93% F1 score for E. crassipes detection. Though the difference in performance between the methods was small, the RF was the most accurate, while the SVM and CART methods had the same accuracy. The maximum E. crassipes coverage area was observed in autumn (22.4 km2), while the minimum (2.2 km2) was observed in summer. Based on Sentinel 2 data, the E. crassipes area coverage decreased significantly by 62.5% from winter to spring and increased significantly by 81.7% from summer to autumn. The findings suggested that the RF classifier was the most accurate E. crassipes detection algorithm, and autumn was an appropriate season for E. crassipes detection in Lake Tana.

Implementation Of The Data Mining Cart Algorithm In The Characteristic Pattern Of New Student Admissions

University of Harapan Medan is one of the private universities in North Sumatra which has an Informatics Engineering Study Program with Good Accreditation. With better accreditation, the number of students who register is also increasing. At the admission of new students, the committee has a huge pile of data, making it difficult in the process of whether the student passed or did not pass. Therefore, in this study, we will implement data mining with the CART (Classification And Regression Tree) algorithm. Data mining is a technique to determine the characteristic pattern of a variable or data criteria with a large amount. In the CART method, the data is first converted into testing data, which will then be used to form a classification tree by calculating the value of information gain, Gini index and goodness of split. From the results obtained, it will be re-determined terminal nodes, marking class labels and finally pruning the classification tree which produces a decision tree. In this study, the number of testing data was 75 with 3 criteria, namely the average value of report cards, CAT test scores, and interview scores. The results of testing data testing using RapisMiner 5.3 software produce 23 number of characteristic pattern rules, where node 1 is the CAT test score, level 1 branch node is the interview score criteria and level 2 branch node is the average report card value.

An evaluation model based on procedural behaviors for predicting MOOC learning performance: students’ online learning behavior analytics and algorithms construction

PurposeThe purpose of this study is to set up an evaluation model to predict massive open online courses (MOOC) learning performance by analyzing MOOC learners’ online learning behaviors, and comparing three algorithms – multiple linear regression (MLR), multilayer perceptron (MLP) and classification and regression tree (CART).Design/methodology/approachThrough literature review and analysis of data correlation in the original database, a framework of online learning behavior indicators containing 26 behaviors was constructed. The degree of correlation with the final learning performance was analyzed based on learners’ system interaction behavior, resource interaction behavior, social interaction behavior and independent learning behavior. A total of 12 behaviors highly correlated to learning performance were extracted as major indicators, and the MLR method, MLP method and CART method were used as typical algorithms to evaluate learners’ MOOC learning performance.FindingsThe behavioral indicator framework constructed in this study can effectively analyze learners’ learning, and the evaluation model constructed using the MLP method (89.91%) and CART method (90.29%) can better achieve the prediction of MOOC learners’ learning performance than using MLR method (83.64%).Originality/valueThis study explores the patterns and characteristics among different learning behaviors and constructs an effective prediction model for MOOC learners’ learning performance, which can help teachers understand learners’ learning status, locate learners with learning difficulties promptly and provide targeted instructional interventions at the right time to improve teaching quality.

Determination of Factors Affecting Vitamin D Levels in Women at Risk Using Classification and Regression Tree Analysis

BACKGROUND: The influence of the factors on Vitamin D as a health indicator in premenopausal and menopausal women is a significant subject to be investigated. AIM: The study uses the potential of classification and regression trees (CART) as a data mining method for medical type samples. METHODS: The data set is built by records of 84 indoor working women at the age of 45 to 67 years from five Bulgarian companies. The data are obtained through laboratory tests of serum concentrations of 25-OH-Vitamin D and a questionnaire, created for the study. Statistical data processing is made by descriptive statistics and the CART method. RESULTS: The results show Vitamin D deficiency in 69% of the studied women at risk from Stara Zagora. For the target variable – Vitamin D (the quantity of 25-OH-Vitamin D), a regression CART tree was built. The calculated percentages of normalized importance for each independent variable reveal that the most important predictors, affecting Vitamin D, are body mass index (100%), alcohol (84.2%), education (70.3%), coffee (70.2%), Са_Vit D (69.8%), and sports frequency (42.4%), while the other variables have much less importance. CONCLUSION: The application of the CART method makes it possible to study the distribution and importance of the factors influencing the state of vitamin D. The presence of such a high percentage of women at risk requires a comprehensive approach, including educational programs and strict application of guidelines for vitamin D supplementation to prevent the effects of hypovitaminosis.

Parcel-Level Flood and Drought Detection for Insurance Using Sentinel-2A, Sentinel-1 SAR GRD and Mobile Images

Floods and droughts cause catastrophic damage in paddy fields, and farmers need to be compensated for their loss. Mobile applications have allowed farmers to claim losses by providing mobile photos and polygons of their land plots drawn on satellite base maps. This paper studies diverse methods to verify those claims at a parcel level by employing (i) Normalized Difference Vegetation Index (NDVI) and (ii) Normalized Difference Water Index (NDWI) on Sentinel-2A images, (iii) Classification and Regression Tree (CART) on Sentinel-1 SAR GRD images, and (iv) a convolutional neural network (CNN) on mobile photos. To address the disturbance from clouds, we study the combination of multi-modal methods—NDVI+CNN and NDWI+CNN—that allow 86.21% and 83.79% accuracy in flood detection and 73.40% and 81.91% in drought detection, respectively. The SAR-based method outperforms the other methods in terms of accuracy in flood (98.77%) and drought (99.44%) detection, data acquisition, parcel coverage, cloud disturbance, and observing the area proportion of disasters in the field. The experiments conclude that the method of CART on SAR images is the most reliable to verify farmers’ claims for compensation. In addition, the CNN-based method’s performance on mobile photos is adequate, providing an alternative for the CART method in the case of data unavailability while using SAR images.

KLASIFIKASI KEMISKINAN DI PROVINSI BENGKULU MENGGUNAKAN METODE POHON KLASIFIKASI GABUNGAN

Poverty is a global problem that is of concern to the world. It can be seen from the SDGs declaration, which makes poverty a top priority. Good poverty management will help solve other world problems such as hunger, health, welfare, education, and sanitation. To achieve the goal of handling poverty quickly and maximally, an analysis that can identify poor households correctly can be designed so that a targeted program can be designed according to the characteristics of households classified as poor households. One of the statistical methods used to see these characteristics is a classification tree such as the Classification and Regression Tree (CART). The weakness of the cart method if there is an unbalanced dataset type can be overcome by the SMOTE method. In addition to the CART method, classification will be carried out using Random Forest and Xgboost. The results show that the random forest CART model has the highest AUC value in balanced data. It is indicated that this method is better than the others. Based on random forest, variables that determine the most determined poor households are number of household members, last diploma of the head of the home, and floor area of the house.

Klasifikasi Sekolah dalam Penerimaan Mahasiswa Baru Vokasi IPB Jalur USMI Menggunakan Metode CART

The selection of new student admissions for the IPB vocational school consists of several routes, one of which is the USMI route. In order to improve its performance, it is necessary to evaluate the USMI new student admission system. Previously, research with the same objective had been carried out using the clustering method. The study resulted in three clusters in which schools were differentiated based on commitment and quality. This study aims to create a classification model of the clusters obtained using the CART method. Classification and Regression Tree (CART) is a nonparametric classification technique that produces a single decision tree. The CART method can involve mixed-type data. The classification model generated from the 2019 data yields an accuracy of 98.52%. However, the results of 2019 model evaluation with the 2020 data are still not good enough to predict with an accuracy of 57.22%, so the 2020 data is re-clustered and produces three clusters. Furthermore, the classification model was remade with 2020 data, resulting in an accuracy of 97.47%. However, the results of the 2020 model evaluation with the 2021 data are still not good enough to predict with an accuracy of 44.34%, so the clustering in the previous year cannot be used for predictions of the following year's data. The grouping of schools for USMI applicants needs to be done by grouping schools every year.

Performance Analysis of Bandung City Traffic Flow Classification with Machine Learning and Kriging Interpolation

This research focuses on making classification maps using the Classification And Regression Trees (CART), Random Forest and Ordinary Kriging methods. The dataset used is data from the Area Traffic Control System (ATCS) of the Bandung City Transportation Agency and the Google Maps application in April 2022. After the dataset is obtained, then the data pre-processing process will be carried out then the CART and Random Forest classification learning models will be made, after the CART and Random Forest classification learning is complete. From the CART and Random Forest classification models, traffic congestion classification map will then be made using the ArcMap application with the Ordinary Kriging interpolation method. The results of the comparison of classification maps made with Ordinary Kriging interpolation with the Gaussian Model semivariogram in both methods, namely CART and Random Forest. With the CART method has an accuracy of up to 88% while the classification map made with the Random Forest method has an accuracy of up to 90%. This proves that in this study the Random Forest method is far superior in building classification maps compared to the CART method

Models to predict prognosis in older patients with heart failure complicated by pre-frailty and frailty: a pilot prospective cohort study.

There are no clinical prediction models to predict the prognosis of pre-frailty or frailty in patients with heart failure. We aimed to develop prediction models for the prognosis of pre-frailty and frailty in older patients with heart failure using the classification and regression tree (CART) method; we then tested the predictive accuracies of the developed models. Patients with pre-frailty or frailty at admission were divided into improved and non-improved groups. The CART method was used to establish two models: A, which predicted the presence or absence of pre-frailty improvement during hospitalisation; and B, which predicted the presence or absence of frailty improvement during hospitalisation. Patients with heart failure complicated by pre-frailty (n=28) or frailty (n=156) were included. In model A, the accuracy of predicting pre-frailty improvement was high; the best predictor was single-leg standing time at admission, followed by left ventricular ejection fraction at admission. In model B, the accuracy of predicting frailty improvement was moderate; the best predictor was hand grip strength at admission, followed by estimated glomerular filtration rate at admission, haemoglobin level at admission, and change in single-leg standing time during hospitalisation. The areas under the receiver operating characteristic curves of the CART models were 0.96 and 0.84 in models A and B, respectively. Although conditions at admission may predict the improvement of pre-frailty and frailty during hospitalisation, cardiac rehabilitation that improves single-leg standing time may help to improve frailty, particularly when conditions at admission are poor.

Mapping of the loose sediments of glacial and periglacial formations in areas with boreal vegetation using remote sensing

The southeastern Fennoscandian Shield is a specific region dominated by glacial and periglacial originated Quaternary deposits. In dense boreal vegetation zones, direct remote decoding of Quaternary sediments is impossible. Our aim is to assess the efficiency of machine learning algorithms for identification of types of Quaternary deposits based on spectral data of vegetation cover and digital elevation model data. A comparative analysis of two classification methods, discriminant analysis (DA) and classification and regression trees (CARTs), was performed. Two models, DA and CART, were constructed based on a set of spectral variables. They included principal components and spectral indices, such as the normalized difference vegetation index, the normalized difference moisture index, and the clay minerals ratio. When the absolute height and the topographic position index (DA+ and CART+ models) are added to a set of independent variables, the classification of Quaternary sediments becomes more accurate. The nonparametric CART method was shown to be more accurate in differentiating loose deposits. The correctness of the CART+ model for the reference sample of observation points was as high as 90.5%. According to the trained data, mapping of Quaternary deposits was carried out. Kappa analysis showed that the agreement with the map of Quaternary deposits for the CART+ and DA+ models was 0.5 and 0.44, respectively. For the DA and CART models, the agreement was much lower. It is noted that the sets of spectral data for the vegetation cover more clearly show the grain-size composition of loose sediments. To make the classification of Quaternary deposits more correct, morphometric indicators were added. Furthermore, the CART+ method was used to estimate the maximum height of glaciolacustrine sediments (117.5 m), which corresponds to the maximum absolute mark of the periglacial reservoir.

Dependence of Body Mass Index on Some Dietary Habits: An Application of Classification and Regression Tree

The purpose of this study was to determine the influence of some eating habits on body mass index (BMI) using a regression model created via the classification and regression tree method (CART). The study was conducted using a questionnaire specially developed for the study, evaluated for reliability and validity. In addition to demographics (age and sex), the questions concern the timing of the meals and the type of food consumed. The data contains records for 533 people (322 women and 211 men) aged 18 to 65 years. The survey was conducted in the period 2019-2021 in Stara Zagora, Bulgaria. Data were processed using descriptive statistics, and regression and classification data mining method CART. A CART model with a dependent variable BMI and predictors Sex, Age, Breakfast type, Breakfast time, Lunchtime, Lunch type, Dinner time, Dinner type have been created. The obtained model is statistically significant at a significance level of P<0.0001 and a coefficient of determination R2 = 0.495. The normalized importance of the factors that affect the BMI is as follows: Sex (100%), Age (61.4%), Lunch type (26. 0%), Lunchtime (18.8%), Dinner time (13.9%), and Breakfast type (13.2%). Women have a lower BMI than men. BMI increases with age. The CART method allows to make a classification by the predictors used and gives opportunities for a more in-depth analysis of the reasons for the increase in BMI. The level of influence of diet and eating habits (type of food, time of consumption) on BMI was determined.

A Hybrid Water Balance Machine Learning Model to Estimate Inter-Annual Rainfall-Runoff.

Watershed climatic diversity poses a hard problem when it comes to finding suitable models to estimate inter-annual rainfall runoff (IARR). In this work, a hybrid model (dubbed MR-CART) is proposed, based on a combination of MR (multiple regression) and CART (classification and regression tree) machine-learning methods, applied to an IARR predicted data series obtained from a set of non-parametric and empirical water balance models in five climatic floors of northern Algeria between 1960 and 2020. A comparative analysis showed that the Yang, Sharif, and Zhang’s models were reliable for estimating input data of the hybrid model in all climatic classes. In addition, Schreiber’s model was more efficient in very humid, humid, and semi-humid areas. A set of performance and distribution statistical tests were applied to the estimated IARR data series to show the reliability and dynamicity of each model in all study areas. The results showed that our hybrid model provided the best performance and data distribution, where the R2Adj and p-values obtained in each case were between (0.793, 0.989), and (0.773, 0.939), respectively. The MR model showed good data distribution compared to the CART method, where p-values obtained by signtest and WSR test were (0.773, 0.705), and (0.326, 0.335), respectively.