Boosted Trees Research Articles

A novel method for favorable zone prediction of conventional hydrocarbon accumulations based on RUSBoosted tree machine learning algorithm

The prediction of favorable zone (FZ) is the most important step for conventional hydrocarbon accumulations (CHAs) exploration. Recently, the method of coupling multiple hydrocarbon accumulation (HA) elements is widely used to predict the distribution of FZ in the petroleum exploration field. However, the forming mechanism of CHAs is extremely complicated, which causes difficulty in accurately describing the relationship between multiple HA elements and HA probability (HAP). Hence, it is difficult to predict the distribution of FZ quantitatively and credibly using traditional methods. This study proposes a method for predicting FZ for CHAs based on random undersampling boosted (RUSBoosted) tree machine learning (ML) algorithm. First, the characteristics of data in the petroleum exploration field are clarified, and a suitable ML algorithm is selected. Second, the theory and knowledge of the petroleum exploration field is integrated into the data, a HAP prediction model for CHAs is constructed, and then the method for FZ prediction is proposed. Further, the method is applied to Jin 93 Well Block for predicting FZ of CHAs. Finally, this study discussed the difference in performance among models constructed by the RUSBoosted tree and other five ML algorithms and the difference in training results between the original geological data and preprocessed geological data on the RUSBoosted tree ML algorithm. Results show that, currently, datasets in the petroleum exploration field are small and unbalanced, and the RUSBoosted tree ML algorithm has excellent training results on it. Compared with the original geological data, the performance of the HAP prediction model constructed by preprocessed geological data is improved. On a Jin 93 Well Block dataset, the HAP prediction model constructed by the RUSBoosted tree ML algorithm belongs to a good prediction model, and FZ of CHAs predicted by this HAP prediction model agree well with CHAs discovered areas. The results of this study provide an idea for intelligently predicting the distribution of FZ of CHAs and are of great significance to the development of intelligent petroleum exploration technology.

Interpretable Dynamic Ensemble Selection Approach for the Prediction of Road Traffic Injury Severity: A Case Study of Pakistan’s National Highway N-5

Road traffic accidents are among the top ten major causes of fatalities in the world, taking millions of lives annually. Machine-learning ensemble classifiers have been frequently used for the prediction of traffic injury severity. However, their inability to comprehend complex models due to their “black box” nature may lead to unrealistic traffic safety judgments. First, in this research, we propose three state-of-the-art Dynamic Ensemble Learning (DES) algorithms including Meta-Learning for Dynamic Ensemble Selection (META-DES), K-Nearest Oracle Elimination (KNORAE), and Dynamic Ensemble Selection Performance (DES-P), with Random Forest (RF), Adaptive Boosting (AdaBoost), Classification and Regression Tree (CART), and Binary Logistic Regression (BLR) as the base learners. The DES algorithm automatically chooses the subset of classifiers most likely to perform well for each new test instance to be classified when generating a prediction, making it more efficient and flexible. The META-DES model using RF as the base learner outperforms other models with accuracy (75%), recall (69%), precision (71%), and F1-score (72%). Afterwards, the risk factors are analyzed with SHapley Additive exPlanations (SHAP). The driver’s age, month of the year, day of the week, and vehicle type influence SHAP estimation the most. Young drivers are at a heightened risk of fatal accidents. Weekends and summer months see the most fatal injuries. The proposed novel META-DES-RF algorithm with SHAP for predicting injury severity may be of interest to traffic safety researchers.

The value of CT radiomic in differentiating mycoplasma pneumoniae pneumonia from streptococcus pneumoniae pneumonia with similar consolidation in children under 5 years

ObjectiveTo investigate the value of CT radiomics in the differentiation of mycoplasma pneumoniae pneumonia (MPP) from streptococcus pneumoniae pneumonia (SPP) with similar CT manifestations in children under 5 years.MethodsA total of 102 children with MPP (n = 52) or SPP (n = 50) with similar consolidation and surrounding halo on CT images in Qilu Hospital and Qilu Children’s Hospital between January 2017 and March 2022 were enrolled in the retrospective study. Radiomic features of the both lesions on plain CT images were extracted including the consolidation part of the pneumonia or both consolidation and surrounding halo area which were respectively delineated at region of interest (ROI) areas on the maximum axial image. The training cohort (n = 71) and the validation cohort (n = 31) were established by stratified random sampling at a ratio of 7:3. By means of variance threshold, the effective radiomics features, SelectKBest and least absolute shrinkage and selection operator (LASSO) regression method were employed for feature selection and combined to calculate the radiomics score (Rad-score). Six classifiers, including k-nearest neighbor (KNN), support vector machine (SVM), extreme gradient boosting (XGBoost), random forest (RF), logistic regression (LR), and decision tree (DT) were used to construct the models based on radiomic features. The diagnostic performance of these models and the radiomic nomogram was estimated and compared using the area under the receiver operating characteristic (ROC) curve (AUC), and the decision curve analysis (DCA) was used to evaluate which model achieved the most net benefit.ResultsRF outperformed other classifiers and was selected as the backbone in the classifier with the consolidation + the surrounding halo was taken as ROI to differentiate MPP from SPP in validation cohort. The AUC value of MPP in validation cohort was 0.822, the sensitivity and specificity were 0.81 and 0.81, respectively.ConclusionThe RF model has the best classification efficiency in the identification of MPP from SPP in children, and the ROI with both consolidation and surrounding halo is most suitable for the delineation.

Design and Implementation of a Self-Learner Smart Home System Using Machine Learning Algorithms

Smart home systems are the integration of technology and services through the network for a better quality of life. Smart homes perform daily housework and activities more easily without user intervention or with remote control of the user. In this study, a machine learning-based smart home system has been developed. The aim of the study is to design a system that can continuously improve itself and learn instead of an ordinary smart home system that can be remotely controlled. The developed machine learning model predicts the routine activities of the users in the home and performs some operations for the user autonomously. The dataset used in the study consists of real data received from the sensors as a result of the daily use. Naive Bayes (NB) (i.e. Gaussian NB, Bernoulli NB, Multinomial NB, and Complement NB), ensemble (i.e. Random Forest, Gradient Tree Boosting and eXtreme Gradient Boosting), linear (i.e. Logistic Regression, Stochastic Gradient Descent, and Passive-Aggressive Classification), and other (i.e. Decision Tree, Support Vector Machine, K Nearest Neighbor, Gaussian Process Classifier (GPC), Multilayer Perceptron) machine learning-based algorithms were utilized. The performance of the proposed smart home system was evaluated using several performance metrics: The best results were obtained from the GPC algorithm (i.e. Precision: 0.97, Recall: 0.98, F1-score: 0.97, Accuracy: 0.97).

Applying hybrid machine learning algorithms to assess customer risk-adjusted revenue in the financial industry

A Peer-to-Peer (P2P) service is a decentralized platform that directly connects individuals, buyers (lenders) and sellers (investors) without the intermediation of a third party. In the P2P lending market, customer cash flows are undeniably linked to their financial risk of default. Thus, forecasting customers’ Risk-Adjusted Revenue (RAR) value is one of the most critical issues in financial decision-making. With the emergence of big data, traditional forecasting methods cannot provide the high predictive power needed for such metrics. We propose a hybrid method by integrating the use of supervised and unsupervised Machine Learning (ML) algorithms to enhance the accuracy of predicting customer-adjusted risk metrics. Using a real P2P dataset from the Lending Club, containing over two million cases, we forecast customers’ risk-adjusted revenue by applying ML algorithms for the first time. These include individual methods such as gradient boosting and decision trees, and hybrid frameworks that group customers using a clustering algorithm (k-Means or Density-Based Spatial Clustering of Applications with Noise (DBSCAN)) prior to implementing the individual methods. We compare the efficiency (processing time and accuracy) of this hybrid approach with the performance of individual regressor-based models to predict RAR. Our results indicate high predictive power for many individual ML algorithms (R2 score over 90%). Further, in most cases, hybrid models outperform the individual ones in both predictive performance and processing time. Finally, the feature importance analysis in the best predictive frameworks helps identify the most influential factors in predicting customers’ RAR in the P2P lending market.

A machine learning analysis of COVID-19 mental health data

In late December 2019, the novel coronavirus (Sars-Cov-2) and the resulting disease COVID-19 were first identified in Wuhan China. The disease slipped through containment measures, with the first known case in the United States being identified on January 20th, 2020. In this paper, we utilize survey data from the Inter-university Consortium for Political and Social Research and apply several statistical and machine learning models and techniques such as Decision Trees, Multinomial Logistic Regression, Naive Bayes, k-Nearest Neighbors, Support Vector Machines, Neural Networks, Random Forests, Gradient Tree Boosting, XGBoost, CatBoost, LightGBM, Synthetic Minority Oversampling, and Chi-Squared Test to analyze the impacts the COVID-19 pandemic has had on the mental health of frontline workers in the United States. Through the interpretation of the many models applied to the mental health survey data, we have concluded that the most important factor in predicting the mental health decline of a frontline worker is the healthcare role the individual is in (Nurse, Emergency Room Staff, Surgeon, etc.), followed by the amount of sleep the individual has had in the last week, the amount of COVID-19 related news an individual has consumed on average in a day, the age of the worker, and the usage of alcohol and cannabis.

Novel Ensemble Model Recommendation Approach for the Detection of Dyslexia.

There are a large number of neurological disorders being explored regarding possible management and treatment, with dyslexia being one of the disorders that affect children at the onset of their learning process. Dyslexia is a developmental neurological disorder that prevents children from learning. The disorder has a prevalence of around 10% across the globe, as reported by most of the literature on dyslexia. The early detection and management of dyslexia is one of the primary pursuits among different research. One such domain that leads this pursuit of the early detection and management of dyslexia is artificial intelligence. With so much effort being expended to explore the applicability of artificial intelligence to address the problem of dyslexia detection, in this work, an ensemble model for the early detection of dyslexia is proposed and recommend. The work experimentally considers a pool of ensembles with rigorous validation on a large sized dataset. The final ensemble model recommendation for detection is expressed after evaluating all of the ensemble frameworks based on a number of evaluation parameters. Our experiments reveal that the subspace discriminant ensemble showed superiority for the detection of dyslexia with an accuracy of 90% on five-fold cross validation with the least training time. An accuracy of 90.90% was achieved using boosted trees with a holdout validation of 30%, while with no validation the subspace K-Nearest Neighbor (KNN) outperformed the other ensembles with an accuracy of 99.9%.

Gap Filling Cloudy Sentinel-2 NDVI and NDWI Pixels with Multi-Frequency Denoised C-Band and L-Band Synthetic Aperture Radar (SAR), Texture, and Shallow Learning Techniques

Multispectral imagery provides unprecedented information on Earth system processes: however, data gaps due to clouds and shadows are a major limitation. Normalized-Difference Vegetation Index (NDVI) and Normalized-Difference Water Index (NDWI) are two spectral indexes employed for monitoring vegetation phenology, land-cover change and more. Synthetic Aperture Radar (SAR) with its cloud-penetrating abilities can fill data gaps using coincident imagery. In this study, we evaluated C-band Sentinel-1, L-band Uninhabited Aerial Vehicle SAR (UAVSAR) and texture for gap filling using efficient machine learning regression algorithms across three seasons. Multiple models were evaluated including Support Vector Machine, Random Forest, Gradient Boosted Trees and an ensemble of models. The Gap filling ability of SAR was evaluated with Sentinel-2 imagery from the same date, 3 days and 8 days later than both SAR sensors in September. Sentinel-1 and Sentinel-2 imagery from winter and spring seasons were also evaluated. Because SAR imagery contains noise, we compared two robust de-noising methods and evaluated performance against a refined lee speckle filter. Mean Absolute Error (MAE) rates of the cloud gap-filling model were assessed across different dataset combinations and land covers. The results indicated de-noised Sentinel-1 SAR and UAVSAR with GLCM texture provided the highest predictive abilities with random forest R2 = 0.91 (±0.014), MAE = 0.078 (±0.003) (NDWI) and R2 = 0.868 (±0.015), MAE = 0.094 (±0.003) (NDVI) during September. The highest errors were observed across bare ground and forest, while the lowest errors were on herbaceous and woody wetland. Results on January and June imagery without UAVSAR were less strong at R2 = 0.60 (±0.036), MAE = 0.211 (±0.005) (NDVI), R2 = 0.61 (±0.043), MAE = 0.209 (±0.005) (NDWI) for January and R2 = 0.72 (±0.018), MAE = 0.142 (±0.004) (NDVI), R2 = 0.77 (±0.022), MAE = 0.125 (±0.004) (NDWI) for June. Ultimately, the results suggest de-noised C-band SAR with texture metrics can accurately predict NDVI and NDWI for gap-filling clouds during most seasons. These shallow machine learning models are rapidly trained and applied faster than intensive deep learning or time series methods.

Machine Learning and Rules Induction in Support of Analog Amplifier Design

The aim of the paper is to present a two-step method for facilitating the design of analog amplifiers taking into account the bottom–top approach and utilizing machine learning techniques. The X-chart and a framework describing the specificity of analog circuit design using machine learning are introduced. The possibility of libraries with open machine learning models to support the designer is also discussed. The proposed method is verified for a three-stage amplifier design. In the first step, the stage type is predicted with 89.74% accuracy as the applied learner is a Decision Tree machine learning algorithm. Moreover, two induction rule algorithms are used for predictive logic generation. In the second step, some typical parameters for a given stage are predicted considering four learners: Decision Tree, Random Forest, Gradient Boosted Trees, and Support Vector Machine. The most suitable is found to be Support Vector Machine, which is characterized with the smallest obtained errors.

Predicting the Risk of Overweight and Obesity in Madrid—A Binary Classification Approach with Evolutionary Feature Selection

In this paper, we experimented with a set of machine-learning classifiers for predicting the risk of a person being overweight or obese, taking into account his/her dietary habits and socioeconomic information. We investigate with ten different machine-learning algorithms combined with four feature-selection strategies (two evolutionary feature-selection methods, one feature selection from the literature, and no feature selection). We tackle the problem under a binary classification approach with evolutionary feature selection. In particular, we use a genetic algorithm to select the set of variables (features) that optimize the accuracy of the classifiers. As an additional contribution, we designed a variant of the Stud GA, a particular structure of the selection operator of individuals where a reduced set of elitist solutions dominate the process. The genetic algorithm uses a direct binary encoding, allowing a more efficient evaluation of the individuals. We use a dataset with information from more than 1170 people in the Spanish Region of Madrid. Both evolutionary and classical feature-selection methods were successfully applied to Gradient Boosting and Decision Tree algorithms, reaching values up to 79% and increasing the average accuracy by two points, respectively.

Enhancing drugs bioavailability using nanomedicine approach: Predicting solubility of Tolmetin in supercritical solvent via advanced computational techniques

Preparation of nanodrug has been a subject of great interest in pharmaceutical manufacturing due to the inherent high solubility of drug nanoparticles in aqueous media. For the solid dosage oral formulations, the size of drug particles plays fundamental role in the solubility values of drug in aqueous media due to the enhanced surface energy associated with the nanoparticles. To develop the drug production at nanoscale, the solubility of drugs in the solvents must be determined prior to the operational processing. In this study, the solubility of Tolmetin (an anti-inflammatory drug) in supercritical carbon dioxide (SC-CO2) is modeled and analyzed using tree-based models. Temperature and pressure are the two features of the input, and the solubility of the Tolmetin is the target output of this modeling.The studied models are CART (Regression Tree), Extra Tree (ET), and Gradient Tree Boosting (GBRT). Their hyper-parameters were optimized based on multiple statistical criteria and three final models was obtained. CART, ET, and GBRT models had error values of 9.79E-08, 5.53E-08, and 1.24E-08 based on MSE parameter. Based on this fact and other metrics, we finally introduced the Gradient Tree Boosting (GBRT) model as the strongest and most accurate model developed in this research compared to other two models. The developed machine learning models for the solubility prediction, indicated that these models are robust enough to be considered for prediction of drug solubility in supercritical solvents.

Feasibility Study of Constructing a Screening Tool for Adolescent Diabetes Detection Applying Machine Learning Methods.

Prediabetes and diabetes are becoming alarmingly prevalent among adolescents over the past decade. However, an effective screening tool that can assess diabetes risks smoothly is still in its infancy. In order to contribute to such significant gaps, this research proposes a machine learning-based predictive model to detect adolescent diabetes. The model applies supervised machine learning and a novel feature selection method to the National Health and Nutritional Examination Survey datasets after an exhaustive search to select reliable and accurate data. The best model achieved an area under the curve (AUC) score of 71%. This research proves that a screening tool based on supervised machine learning models can assist in the automated detection of youth diabetes. It also identifies some critical predictors to such detection using Lasso Regression, Random Forest Importance and Gradient Boosted Tree Importance feature selection methods. The most contributing features to Youth diabetes detection are physical characteristics (e.g., waist, leg length, gender), dietary information (e.g., water, protein, sodium) and demographics. These predictors can be further utilised in other areas of medical research, such as electronic medical history.

A Performance Comparison of Classification Algorithms for Rose Plants.

One of the key roles of Botanists is to be able to recognize flowers. This role has become highly challenging given that the number of discovered flower types are nearing half a million. To support Botanists, Information Technology offers promising solutions. Specifically, machine learning techniques are intrinsically appealing due to being precise enough as required. To this aim, two observations on flower leaves are relevant and leverage flower identification: one, flower plants exhibit unique features in their leaves thus allow distinction of their co-located flowers; two, leaves have a much longer life than flowers thus preserve identity properties longer. This paper proposes the use of machine learning-based identification of rose types by leveraging the features from their leaves. For this purpose, the performance of Naive Bayes, Generalized Linear Model, Multilayer Perceptron, Decision Tree, Random Forest, Gradient Boosted Trees, and Support Vector Machine has been analyzed. This study optimizes the RF model by investigating and tuning its various parameters such as the number of trees, the depth of trees, and splitting criteria. The best results are achieved with gain ratio because it takes more distinct values to avoid the problems associated with Information Gain. Optimizing the number of trees and the depth of trees of RF yield better accuracy than other models. Extensive experiments are performed to analyze the results of ensemble algorithms by using the voting method for each instance. Results suggest that the performance of ensemble classifiers is superior to that of individual models.

Machine learning for wildfire classification: Exploring blackbox, eXplainable, symbolic, and SMOTE methods

Whether triggered by natural or human-made events, wildfires are considered one of the most traumatic events to our community and environment. Thus, properly predicting wildfires continues to be an active area of research. This work showcases a statistical overview of the problem of wildfires and then presents a dense data-driven (D3) approach that leverages a variety of machine learning (ML) techniques, namely, blackbox and eXplainable ML (i.e., deep learning (DL), decision tree (DT), Stochastic Gradient Descent (SGD), Extreme Gradient Boosted Trees (ExGBT), Logistic regression (LR)), and symbolic ML via genetic algorithms (GA) to classify and predict wildfire breakouts. This approach was developed and validated using two databases comprising more than 1.04 million geo-referenced wildfires that burned over 359,000 ​km2 (88.7 million acres) between 1992 and 2015 in North America and Europe. Despite the complex nature of wildfire formation and the interdependency of its governing factors, the findings of this D3 analysis show the feasibility of utilizing ML in preciously classifying the expected size of wildfires and predicting the possibility of the breakout of wildfires.

Concentration-Temporal Multilevel Calibration of Low-Cost PM2.5 Sensors

Ambient aerosols have a significant impact on plant species mortality, air pollution, and climate change. It is critical to monitor the concentrations of aerosols, especially particulate matter with an aerodynamic diameter ≤ 2.5 μm (PM2.5), which has a direct relationship with human respiratory diseases. Recently, low-cost PM2.5 sensors have been deployed to provide a denser monitoring coverage than that of government-built monitoring supersites, which only give a macro perspective of air quality. To increase the measurement accuracy, low-cost sensors need to be calibrated. In current practice, regression techniques are used to calibrate sensors. This paper proposes a concentration-temporal multilevel calibration method to cope with the varying regression relation in different concentration and temporal domains. The performance of our method is evaluated with real field data from a supersite sensor and a low-cost sensor deployed in Puli, Taiwan. The experimental results show that our calibration method significantly outperforms linear regression in terms of R2, Root Mean Square Error, and Normalized Mean Error. Moreover, our method compares favorably with a machine learning calibration method based on gradient regression tree boosting.

An Anomaly Detection Model for Oil and Gas Pipelines Using Machine Learning

Detection of minor leaks in oil or gas pipelines is a critical and persistent problem in the oil and gas industry. Many organisations have long relied on fixed hardware or manual assessments to monitor leaks. With rapid industrialisation and technological advancements, innovative engineering technologies that are cost-effective, faster, and easier to implement are essential. Herein, machine learning-based anomaly detection models are proposed to solve the problem of oil and gas pipeline leakage. Five machine learning algorithms, namely, random forest, support vector machine, k-nearest neighbour, gradient boosting, and decision tree, were used to develop detection models for pipeline leaks. The support vector machine algorithm, with an accuracy of 97.4%, overperformed the other algorithms in detecting pipeline leakage and thus proved its efficiency as an accurate model for detecting leakage in oil and gas pipelines.

Meta-Analysis of the Response of the Productivity of Different Crops to Parameters and Processes in Soil Nitrogen Cycle under Biochar Addition

Biochar addition has been proposed to influence soil nitrogen (N) cycle and improve crop productivity. However, a comprehensive understanding of the impact of soil N cycle on the productivity of different crops under biochar addition remains elusive. Thus, a meta-analysis of 93 peer-reviewed field experiments was undertaken to investigate these outcomes of biochar addition. Results show that biochar addition significantly enhances crop productivity by 13.0%. The productivities of legumes, maize, and wheat were significantly increased by 21.2%, 14.3%, and 8.00% following biochar addition in the fields, respectively. However, the improvement in rice productivity is the lowest (3.36%), insignificant following biochar addition. The aggregated boosted tree, and partial least squares path analyses, indicated that the changes in the soil N pool (i.e., TN, NO3−-N, and NH4+-N) and plant N uptake were the most critical factors in increasing crop productivity under biochar addition. Although biochar addition had no significant enhancement on rice productivity, enhancing field rice nitrogen uptake and modest application of nitrogen fertilizers greatly improved rice productivity. The amount of soil NH4+-N was vital to improving legume productivity rather than biological N2 fixation when biochar was applied. Increases in NH4+-N content and decreasing NO3−-N content were favorable to improving maize productivity under biochar addition. In contrast, biochar additions did not significantly regulate the parameters and processes of soil N cycle to enhance wheat productivity. Overall, the productivity of different types of crops is greatly influenced by soil N cycle under biochar addition.

Identification of pharming in communication networks using ensemble learning

Pharming scams are carried out by exploiting the DNS as the main weapon while phishing attacks employ spoofed websites that appear to be legitimate to internet users. Phishing makes use of baits such as fake links but pharming leverages and negotiates on the DNS server to move and redirect internet users to a fake and simulated website.Having seen several challenges through pharming resulting into vulnerable websites, personal emails and accounts on social media, the usage and reliability on internet calls for caution. Against this backdrop, this work aims at enhancing pharming detection strategies by adopting machine learning classification algorithms. To further obtain the best classification results, an ensemble learning approach was adopted. The algorithms used include K-Nearest Neighbors (KNN), Decision Tree, Random Forest, Gaussian Naive Bayes, Logistic Regression, Support Vector Machine, Adaptive Boosting, Gradient Boosting, and Extra Trees Classifier. During the testing process, the classifiers were tested against four popular metrics: accuracy, recall, precision, F1 score, and Log loss. The results demonstrate the performance of all algorithms used, as well as their relationships. The ensemble model that included Logistic Regression, K-Nearest Neighbors, Decision Tree, Support Vector Machine, Gradient Boosting Classifier, AdaBoost Classifier, Extra Trees Classifier, and Random Forest produced the best results after evaluating them on the two datasets. Random Forest Classifiers showed a better performance of the classifiers, with mean accuracies of 0.932 and 0.939, respectively for each of the datasets when compared to 0.476 and 0.519 obtained for Naive Bayes.

Anomaly detection model based on gradient boosting and decision tree for IoT environments security

Anomaly detection model based on gradient boosting and decision tree for IoT environments security

Real-time internet of medical things framework for early detection of Covid-19.

The Covid-19 pandemic is a deadly epidemic and continues to affect all world. This situation dragged the countries into a global crisis and caused the collapse of some health systems. Therefore, many technologies are needed to slow down the spread of the Covid-19 epidemic and produce solutions. In this context, some developments have been made with artificial intelligence, machine learning and deep learning support systems in order to alleviate the burden on the health system. In this study, a new Internet of Medical Things (IoMT) framework is proposed for the detection and early prevention of Covid-19 infection. In the proposed IoMT framework, a Covid-19 scenario consisting of various numbers of sensors is created in the Riverbed Modeler simulation software. The health data produced in this scenario are analyzed in real time with Apache Spark technology, and disease prediction is made. In order to provide more accurate results for Covid-19 disease prediction, Random Forest and Gradient Boosted Tree (GBT) Ensemble Learning classifiers, which are formed by Decision Tree classifiers, are compared for the performance evaluation. In addition, throughput, end-to-end delay results and Apache Spark data processing performance of heterogeneous nodes with different priorities are analyzed in the Covid-19 scenario. The MongoDB NoSQL database is used in the IoMT framework to store big health data produced in real time and use it in subsequent processes. The proposed IoMT framework experimental results show that the GBTs classifier has the best performance with 95.70% training, 95.30% test accuracy and 0.970 area under the curve (AUC) values. Moreover, the promising real-time performances of wireless body area network (WBAN) simulation scenario and Apache Spark show that they can be used for the early detection of Covid-19 disease.