Application Of Ensemble Learning Research Articles

Application of Ensemble Learning in CXR Classification for Improving COVID-19 Diagnosis

This study delves into the vital task of classifying chest X-ray (CXR) samples, particularly those related to respiratory ailments, using advanced clinical image analysis and computer-aided radiology techniques. Its primary focus is on developing a classifier to accurately identify COVID-19 cases. Through the application of machine learning and computer vision methodologies, the research aims to enhance the precision of COVID-19 detection. It investigates the effectiveness of Histogram of Oriented Gradients (HOG) feature extraction techniques in conjunction with various classifiers, such as Support Vector Machine (SVM), Decision Tree (DT), Naive Bayes (NB), K-nearest neighbor (KNN), and Tree Bagger (TB), alongside an innovative ensemble learning approach. Results indicate impressive accuracy rates, with KNN, SVM, DT, NB, and TB all surpassing the 90% mark. However, the ensemble learning method emerges as the standout performer. By leveraging HOG features extracted from CXR images, this approach presents a robust solution for COVID-19 diagnosis, offering a powerful tool to address the diagnostic challenges posed by the pandemic.

Application of Ensemble Learning in CXR Classification for Enhancing COVID-19 Diagnosis

This study delves into the vital task of classifying chest X-ray (CXR) samples, particularly those related to respiratory ailments, using advanced clinical image analysis and computer-aided radiology techniques. Its primary focus is on developing a classifier to accurately identify COVID-19 cases. Through the application of machine learning and computer vision methodologies, the research aims to enhance the precision of COVID-19 detection. It investigates the effectiveness of Histogram of Oriented Gradients (HOG) feature extraction techniques in conjunction with various classifiers, such as Support Vector Machine (SVM), Decision Tree (DT), Naive Bayes (NB), K-nearest neighbor (KNN), and Tree Bagger (TB), alongside an innovative ensemble learning approach. Results indicate impressive accuracy rates, with KNN, SVM, DT, NB, and TB all surpassing the 90% mark. However, the ensemble learning method emerges as the standout performer. By leveraging HOG features extracted from CXR images, this approach presents a robust solution for COVID-19 diagnosis, offering a powerful tool to address the diagnostic challenges posed by the pandemic.

Application of Ensemble Learning and Feature Selection Models in Energy Expenditure Estimation of Fitness Tracking Devices

The use of fitness tracking devices to monitor energy expenditure (EE) is becoming increasingly popular among consumers. However, the accuracy of EE estimation still needs to be improved due to the lack of accurate data filtering and more efficient data analysis models. To address this issue, we designed an energy expenditure estimation (EEE) model based on smart tracking devices. This paper proposes an algorithm for data reconstruction called PC-DF-RFECV: firstly, Pearson correlation analysis (PC) is used for initial data screening, then Feature Derivation (DF) is applied to reconstruct new features, and finally, the Recursive Feature Elimination algorithm based on cross-validation (RFECV) is employed to select the new features. Furthermore, the EEE model adopts a weighted average (Wei-Voting) strategy to enhance the robustness of the model by integrating the predictions of multiple base learners (XGBoost, LightGBM, Random Forest). During algorithm optimization, a Bayesian hyperparameter optimization technique is employed to fine-tune the model's hyperparameters. Empirical findings indicate that the EEE model, when applied to the dataset collected from motion tracking devices, attains an score of 0.9985, of 1.033, and of 0.865. These results demonstrate superior performance compared to current state-of-the-art research and conventional algorithms including random forests, gradient boosting, and bagging.

Application of ensemble learning in adaptive surface modeling of soil total potassium content in complex landform areas

Application of ensemble learning in adaptive surface modeling of soil total potassium content in complex landform areas

Application of ensemble learning in predicting shallow foundation settlement in cohesionless soil

ABSTRACT Due to significant uncertainties associated with soil, it is challenging to anticipate settlement accurately for shallow footings on cohesionless soil. To produce more precise predictive settlement models, four ensemble learning models have been created in this study: Bagging, Random Forest (RF), Adaptive Boosting (AdaBoost), and Extreme Gradient Boosting (XGBoost). The models are created utilizing a sizable database based on standard penetration tests (SPT). A variety of evaluation criteria, including R 2, RMSE, and MAE, were employed to rate the performance of the models. The analysis results showed that Bagging and XGBoost models demonstrate excellent performance with R 2 values of 0.901 and 0.915, respectively, surpassing other models studied here as well as other models from the literature. Consequently, Bagging and XGBoost can be effective methods for predicting settlement in shallow foundations on cohesionless soil.

Predicting the equilibrium solubility of CO2 in alcohols, ketones, and glycol ethers: Application of ensemble learning and deep learning approaches

In the present work, the solubility of CO2 in solutions comprising various physical solvents (Methanol, Ethanol, Propylene Glycol, n-Pentanol, n-Butanol, n-Propanol, Ethylene Glycol, 2-Butanone, 2-Methoxyethanol, 2-Ethoxyethanol, and Acetone) was modeled using machine learning approaches. In this regard, ensemble learning and deep learning approaches including Bagging Regressor with support vector regression (SVR) as the based estimator (Bagging_SVR), Adaptive Boosting Regressor with Decision Tree as the based estimator (ADA_DT), Decision Tree (DT), and Convolutional Neural Network (CNN) were developed. To develop the models, a broad set of CO2 solubility data (810 experimental data points for 11 alcohol, ketone, and glycol ether solvents) was acquired over various operating temperatures (283.15-373.15 K) and pressures (0.0142-57.38 MPa). In addition, the pressure, temperature, critical properties, and acentric factor of physical solvents were considered as the inputs to the machine learning approaches. To evaluate models’ performance, different graphical and statistical analyzes were conducted. The results revealed that the CNN model is more accurate than other proposed models. Root mean square error (RMSE) and determination coefficient (R2) values for CNN model were obtained as 0.016027 and 0.9943, respectively. Based on the sensitivity analysis, the dissolution of CO2 in physical solvents was highly affected by acentric factors as well as critical temperature and critical pressure. The use of leverage method showed that the used experimental data have high reliability and the CNN model also displayed high credit. Results of this study provide accurate models to estimate the solubility of CO2 in solutions containing physical solvents, which is more straightforward and user-friendly compared to thermodynamic methods with difficult calculations and procedures.

Application of Ensemble Learning Using Weight Voting Protocol in the Prediction of Pile Bearing Capacity

Accurate prediction of pile bearing capacity is an important part of foundation engineering. Notably, the determination of pile bearing capacity through an in situ load test is costly and time-consuming. Therefore, this study focused on developing a machine learning algorithm, namely, Ensemble Learning (EL), using weight voting protocol of three base machine learning algorithms, gradient boosting (GB), random forest (RF), and classic linear regression (LR), to predict the bearing capacity of the pile. Data includes 108 pile load tests under different conditions used for model training and testing. Performance evaluation indicators such as R-square (R2), root mean square error (RMSE), and MAE (mean absolute error) were used to evaluate the performance of models showing the efficiency of predicting pile bearing capacity with outstanding performance compared to other models. The results also showed that the EL model with a weight combination of w 1 = 0.482, w 2 = 0.338, and w 3 = 0.18 corresponding to the models GB, RF, and LR gave the best performance and achieved the best balance on all data sets. In addition, the global sensitivity analysis technique was used to detect the most important input features in determining the bearing capacity of the pile. This study provides an effective tool to predict pile load capacity with expert performance.

Retraction: Analysis and Prediction of Epilepsy Using Heart Rate by Application of Ensemble Learning and Linear Regression (J. Phys.: Conf. Ser. 1916 012213)

This article (and all articles in the proceedings volume relating to the same conference) has been retracted by IOP Publishing following an extensive investigation in line with the COPE guidelines. This investigation has uncovered evidence of systematic manipulation of the publication process and considerable citation manipulation.IOP Publishing respectfully requests that readers consider all work within this volume potentially unreliable, as the volume has not been through a credible peer review process.IOP Publishing regrets that our usual quality checks did not identify these issues before publication, and have since put additional measures in place to try to prevent these issues from reoccurring. IOP Publishing wishes to credit anonymous whistleblowers and the Problematic Paper Screener [1] for bringing some of the above issues to our attention, prompting us to investigate further.[1] Cabanac G, Labbé C and Magazinov A 2021 arXiv:2107.06751v1 Retraction published: 23 February 2022

Analysis and Prediction of Epilepsy Using Heart Rate by Application of Ensemble Learning and Linear Regression

In the existing methods the epilepsy was analysed using the PPG, EEG, ECG. The output obtained from the two different signals were analysed and found that the signal obtained while using ECG wearable sensor was more accurate and reliable when compared to the result obtained while using PPG. The main drawback while using EEG signal is the placement of wet scalp electrodes. Hence heart rate is used to analyse epilepsy in the proposed methodin order to obtain accurate and reliable result. In this method analysing the heart rate signal of the patient and epilepsy death rate prediction are two main goals of the project. The biomedical sensors and wearable sensors currently available in the market was studied. Sensors like EEG, ECG, PPG characteristics, and their working were studied completely. In this paper, we have not used any biomedical sensors or wearable sensors. For the heart rate signal, the dataset from the “fitbase” website was collected. Heart rate data collection per minute average heartbeat of the person. heart rate signal data length was 12,000 But only 90 samples were used for ensemble averaging. Not only the heart rate of the signal the epilepsy was also focussed. The epilepsy death rate data from the Statista. Epilepsy data contains year and death for future prediction; a linear regression algorithm was used.

Application of Ensemble Learning in EEG Signal Analysis of Fatigue Driving

Fatigue detection has now become an important direction of fatigue driving research. As a reliable physiological signal, EEG signals can be used to detect fatigue driving. This passage uses the idea of ensemble learning to establish an ensemble learning classification model of Bagged Tree, RSM Discrimination and RUSBoosted Tree, and uses the fatigue driving experiment data as the object to divide the fatigue driving object into normal state and fatigue state, using Pearson Correlation Coefficient method build a functional brain network. Six methods of Betweenness Centrality, Edge Betweenness Centrality, Clustering Coefficient, Degree, Local Efficiency, and Rich Club Coefficient are used to process and analyze six kinds of EEG signal characteristics, and then bring them into different in the ensemble learning model, the EEG signal characteristics and the ensemble learning model are matched and selected to improve the accuracy and stability of the detection model. By simulating 24 subjects, the results show that the accuracy and robustness of RSM Discrimination ensemble learning model and Degree method are the best, with an average accuracy rate of 90.35% and a standard deviation of 0.081.

Novel application of multi-model ensemble learning for fault diagnosis in refrigeration systems

Despite the importance of fault diagnosis in refrigeration systems, the performance and improvement of most existing diagnostic models are limited by their reliance on a single method. This study proposes a novel application of ensemble learning that incorporates several intelligent ensemble members into an integrated model by means of majority voting. The ensemble members include k-nearest neighbour (KNN), support vector machine (SVM), decision tree (DT), random forest (RF) and logistic regression (LR). ASHRAE fault data were employed to establish the model. In addition, this study explores the integration of different subsets of ensemble members and revealed that the optimum subset combination comprised KNN, DT, and RF. Although the accuracy of this model was slightly lower than the model with all five ensemble members, it realised a substantial reduction in runtime. Compared to an SVM optimization model, the integrated model realised higher accuracy and reduced training time, without requiring parameter optimization. This achievement merits note as ensemble learning is traditionally associated high time-costs. Further investigation revealed that both the diversity and high accuracy of ensemble members are required to obtain an effective integrated model. These observations demonstrate the proposed model offers a promising alternative solution for fault diagnosis in refrigeration systems.

Two-stage consumer credit risk modelling using heterogeneous ensemble learning

Modelling consumer credit risk is a crucial task for banks and non-bank financial institutions to support decision-making on granting loans. To model the overall credit risk of a consumer loan in terms of expected loss (EL), three key credit risk parameters must be estimated: probability of default (PD), loss given default (LGD) and exposure at default (EAD). Research to date has tended to model these parameters separately. Moreover, a neglected area in the field of LGD/EAD modelling is the application of ensemble learning, which by benefitting from diverse base learners reduces the over-fitting problem and enables modelling diverse risk profiles of defaulted loans. To overcome these problems, this paper proposes a two-stage credit risk model that integrates (1) class-imbalanced ensemble learning for predicting PD (credit scoring), and (2) an EAD prediction using a regression ensemble. Furthermore, multi-objective evolutionary feature selection is used to minimize both the misclassification cost (root mean squared error) of the PD and EAD models and the number of attributes necessary for modelling. For this task, we propose a misclassification cost metric suitable for consumer loans with fixed exposure because it combines opportunity cost and LGD. We show that the proposed credit risk model is not only more effective than single-stage credit risk models but also outperforms state-of-the-art methods used to model credit risk in terms of prediction and economic performance.

A competitive ensemble pruning approach based on cross-validation technique

Ensemble pruning is crucial for the consideration of both efficiency and predictive accuracy of an ensemble system. This paper proposes a new Competitive technique for Ensemble Pruning based on Cross-Validation (CEPCV). The data to be learnt by neural computing models are mostly drifting with time and environment, therefore a dynamic ensemble pruning method is indispensable for practical applications, while the proposed CEPCV method is just the kind of dynamic ensemble pruning method, which can realize on-line ensemble pruning and take full advantage of potentially valuable information. The algorithm naturally inherits the predominance of cross-validation technique, which implies that those networks regarded as winners in selective competitions and chosen into the pruned ensemble have the “strongest” generalization capability. It is essentially based on the strategy of “divide and rule, collect the wisdom”, and might alleviate the local minima problem of many conventional ensemble pruning approaches only at the cost of a little greater computational cost, which is acceptable to most applications of ensemble learning. The comparative experiments among the four ensemble pruning algorithms, including: CEPCV and the state-of-the-art Directed Hill Climbing Ensemble Pruning (DHCEP) algorithm and two baseline methods, i.e. BSM, which chooses the Best Single Model in the initial ensemble based on their performances on the pruning set, and ALL, which reserves all network members of the initial ensemble, on ten benchmark classification tasks, demonstrate the effectiveness and validity of CEPCV.

앙상블 학습을 이용한 DRAM 모듈 출하 품질보증 검사 불량 예측

The DRAM module is an important part of servers, workstations and personal computer. Its malfunction causes a lot of damage on customer system. Therefore, customers demand the highest quality products. The company applies DRAM module Outgoing Quality Assurance Inspection(OQA) to secures the highest quality. It is the key process to decides shipment of products through sample inspection method with customer oriented tests. High fraction of defectives entering to OQA causes inevitable high quality cost. This article proposes the application of ensemble learning to classify the lot status to minimize the ratio of wrong decision in OQA, observing a potential in reducing the wrong decision.

Improved customer choice predictions using ensemble methods

In this paper various ensemble learning methods from machine learning and statistics are considered and applied to the customer choice modeling problem. The application of ensemble learning usually improves the prediction quality of flexible models like decision trees and thus leads to improved predictions. We give experimental results for two real-life marketing datasets using decision trees, ensemble versions of decision trees and the logistic regression model, which is a standard approach for this problem. The ensemble models are found to improve upon individual decision trees and outperform logistic regression. Next, an additive decomposition of the prediction error of a model is considered known as the bias/variance decomposition. A model with a high bias lacks the flexibility to fit the data well. A high variance indicates that a model is instable with respect to different datasets. Decision trees have a high variance component and a low bias component in the prediction error, whereas logistic regression has a high bias component and a low variance component. It is shown that ensemble methods aim at minimizing the variance component in the prediction error while leaving the bias component unaltered. Bias/variance decompositions for all models for both customer choice datasets are given to illustrate these concepts.