Multi-classifier System Research Articles

A Multi-Class ECG Signal Classifier Using a Binarized Depthwise Separable CNN with the Merged Convolution–Pooling Method

Binarized convolutional neural networks (bCNNs) are favored for the design of low-storage, low-power cardiac arrhythmia classifiers owing to their high weight compression rate. However, multi-class classification of ECG signals based on bCNNs is challenging due to the accuracy loss introduced by the binarization operation. In this paper, an effective multi-classifier system is proposed for electrocardiogram (ECG) signals using a binarized depthwise separable convolutional neural network (bDSCNN) with the merged convolution–pooling (MCP) method. The binarized depthwise separable convolution layer is adopted to reduce the increased number of parameters in multi-classification systems. Instead of operating convolution and pooling sequentially as in a traditional convolutional neural network (CNN), the MCP method merges pooling together with convolution layers to reduce the number of computations. To further reduce hardware resources, this work employs blockwise incremental calculation to eliminate redundant storage with computations. In addition, the R peak interval data are integrated with P-QRS-T features to improve the classification accuracy. The proposed bDSCNN model is evaluated on an Intel DE1-SoC field-programmable gate array (FPGA), and the experimental results demonstrate that the proposed system achieves a five-class classification accuracy of 96.61% and a macro-F1 score of 89.08%, along with a dynamic power dissipation of 20 μW for five-category ECG signal classification. The hardware resource usage of BRAM and LUTs plus REGs is reduced by at least 2.94 and 1.74 times, respectively, compared with existing ECG classifiers using bCNN methods.

A multi-classifier system integrated by clinico-histology-genomic analysis for predicting recurrence of papillary renal cell carcinoma

Integrating genomics and histology for cancer prognosis demonstrates promise. Here, we develop a multi-classifier system integrating a lncRNA-based classifier, a deep learning whole-slide-image-based classifier, and a clinicopathological classifier to accurately predict post-surgery localized (stage I–III) papillary renal cell carcinoma (pRCC) recurrence. The multi-classifier system demonstrates significantly higher predictive accuracy for recurrence-free survival (RFS) compared to the three single classifiers alone in the training set and in both validation sets (C-index 0.831-0.858 vs. 0.642-0.777, p < 0.05). The RFS in our multi-classifier-defined high-risk stage I/II and grade 1/2 groups is significantly worse than in the low-risk stage III and grade 3/4 groups (p < 0.05). Our multi-classifier system is a practical and reliable predictor for recurrence of localized pRCC after surgery that can be used with the current staging system to more accurately predict disease course and inform strategies for individualized adjuvant therapy.

A hybrid deep CNN model for brain tumor image multi-classification

The current approach to diagnosing and classifying brain tumors relies on the histological evaluation of biopsy samples, which is invasive, time-consuming, and susceptible to manual errors. These limitations underscore the pressing need for a fully automated, deep-learning-based multi-classification system for brain malignancies. This article aims to leverage a deep convolutional neural network (CNN) to enhance early detection and presents three distinct CNN models designed for different types of classification tasks. The first CNN model achieves an impressive detection accuracy of 99.53% for brain tumors. The second CNN model, with an accuracy of 93.81%, proficiently categorizes brain tumors into five distinct types: normal, glioma, meningioma, pituitary, and metastatic. Furthermore, the third CNN model demonstrates an accuracy of 98.56% in accurately classifying brain tumors into their different grades. To ensure optimal performance, a grid search optimization approach is employed to automatically fine-tune all the relevant hyperparameters of the CNN models. The utilization of large, publicly accessible clinical datasets results in robust and reliable classification outcomes. This article conducts a comprehensive comparison of the proposed models against classical models, such as AlexNet, DenseNet121, ResNet-101, VGG-19, and GoogleNet, reaffirming the superiority of the deep CNN-based approach in advancing the field of brain tumor classification and early detection.

A Deep Learning Framework for Classification of Immature White Blood Cells in Acute Myeloid Leukemia Using Convolutional Autoencoder and Transfer-Learning Ensemble

Acute myeloid leukemia (AML) is a type of acute leukemia that affects myeloid cells. It is characterized by uncontrolled proliferation of immature WBCs causing an accumulation of immature WBCs in the bone marrow and peripheral circulation. AML is an aggressive cancer that can be life-threatening if not treated promptly, therefore, early detection is crucial. Identification of immature WBCs and their subtypes is the first step towards AML diagnosis. Microscopic blood smear image analysis is commonly used to diagnose AML as it is less expensive non-invasive diagnostic tool compared to bone marrow biopsy and immunophenotype. Nonetheless, classifying immature WBCs presents challenges due to their high similarity and minimal interclass variation, especially for intermediate stages of myelopoiesis which make is susceptible to misclassification. The current diagnostic methods of AML are based on manual identification of immature WBCs using peripheral blood smear. These methos are time-consuming, prone to errors, and subject to inter-observer variation. Therefore, this study aims to develop a computer-aided diagnostic framework to accurately identify immature WBCs and classify them into various subtypes. The proposed framework consists of two main components: a binary classification system to classify cells into mature versus immature cells and a multiclassification system to further classify immature cells into four subtypes including myeloblast, monoblast, and promyelocytes. The proposed framework was designed to undergo four distinct phases: the first phase involves preprocessing, which includes data augmentation techniques aimed at addressing the imbalance distribution of WBCs. Augmentation encompasses geometric transformation and generation of synthetic images using convolutional Autoencoder (CAE). Feature extraction phase involves using image embedding and transfer-learning. Image embedding representation was obtained using CAE and then utilized by two pre-trained models: VGG19 and Resnet50. Classification phase was carried out using weighted ensemble of the VGG19 and Resnet50 with the optimal weights determined through Grid search. The validation phase evaluated the model performance using overall accuracy, precision, and sensitivity. The area under the ROC curve (AUC) was used to assess model discrimination ability. The proposed framework demonstrated excellent results, achieving an average accuracy of 99.5%, a sensitivity of 97.97%, and a precision of 94.12%. The model exhibited an excellent discriminatory capability, with an AUC of 99.9%. Furthermore, the proposed framework outperformed previous methods, showcasing improved performance. Key word: Acute myeloid leukemia, peripheral blood smear, immature white blood cells, deep learning, feature extraction, computer-aided diagnosis.

A multi-classifier system for automatic fingerprint classification using transfer learning and majority voting

A multi-classifier system for automatic fingerprint classification using transfer learning and majority voting

Spatio-temporal modelling with multi-gradient features and elongated quinary pattern descriptor for dynamic facial expression recognition

We propose a new spatio-temporal modelling approach for Dynamic Facial Expression Recognition (DFER). We first convert the domain of the spatial images in the sequence to the gradient of magnitude and angle images at different orientations. Robust gradient components are developed to deal with difficult types of illuminations, such as darkness, by forming the eight edge responses of the Gaussian mask. To describe the dynamic Facial Expression (FE) changes we extend the Elongated Quinary Pattern (EQP) descriptor to encode separately the anisotropic structure of the uniform patterns from Three Orthogonal Planes (TOP) of each gradient sequence. Then each encoded sequence is divided into a stack of block volumes in the XY, XT and YT planes. For each plane, the co-occurrence of histogram features are calculated from each block volume and concatenated together. Simple three-dimensional histogram features are generated by concatenating the histogram features of all planes. A Multi Classifier System (MCS) based on a multi-class Support Vector Machine (SVM) is adopted to combine all scores for the encoded sequences. The proposed approach is evaluated with the challenging MMI and Oulu-CASIA databases with different set-ups and advantage has been shown in terms of generalisation to different databases, together with robustness against difficult pose variations and illumination changes. In terms of Recognition Accuracy (RA), a comparison is established with DFER methods in the literature. A high recognition rate of 79.23% is attained in the case of six classes when applied to the MMI database which surpasses all the state-of-the-art results.

3D object feature extraction and classification using 3D MF-DFA

In this study, we propose a three-dimensional (3D) object recognition method using multifractal properties. The proposed method is based on a 3D multifractal detrended fluctuation analysis (MF-DFA) using the voxel data of an object. We propose a 3D MF-DFA by extending a conventional MF-DFA, which is widely adopted for analyzing the time series. In the current study, the data processed by the model were changed from the time-series data in the original MF-DFA into the voxels of 3D objects. Thus, the steps in the original model were extended to a 3D processing structure. To voxelize the scatter point data, we apply a modified Allen–Cahn (AC) equation with the Neumann boundary condition to generate the object volume. Various 3D models after voxelization are used for the 3D MF-DFA to calculate the generalized Hurst exponents. The calculated generalized Hurst exponents of different categories show different distributions and are used as the training feature input vector into a multi-classification system, i.e., one-versus-one support vector machines (OvO-SVMs). The computational results show that the proposed method can effectively extract the features of an object. Metrics such as the accuracy, precision, and recall are utilized to measure the efficiency and robustness. When compared with state-of-art algorithms, our empirical tests show that the proposed 3D MF-DFA-OvO-SVM system is superior to most of the methods in terms of classification accuracy. In addition, we also confirm that our proposed model is applicable to object detection in 3D space. An efficient method may be useful for autonomous driving, robot cruises, and AR-based intelligent user interfaces.

Hypoglycaemia prediction using information fusion and classifiers consensus

The recommendation that there must be a balance between insulin, food, and exercise to keep diabetes under control provides an opportunity for developing mobile applications for self-management of the disease. Real predictions can improve the quality of patients’ lives by avoiding unwanted events, namely, hypoglycaemia. We proposed a hypoglycaemia prediction approach combining information fusion and classifiers consensus to predict the risk of hypoglycaemia in a 24-h window. First, we train a multi-classifiers system from different sources of different patients. After using data from a unique patient, we performed the prediction of the risk of hypoglycaemia and evaluate the consensus decision of the single models resulting from the learning process. The predictions were performed for 54 patients from the University of California Irvine diabetes dataset. The results from classifiers consensus decision provide very promising results, which are acceptable considering that we used sparse data and data from self-monitoring blood glucose. Our approach shows that with a 24-h window is possible to catch appropriate patterns associated with the risk of hypoglycaemia and proposed a solution that can improve the hypoglycaemia prediction with a higher specificity, i.e. less false alarms, when compared with similar literature.

Towards autonomous cross-pollination: Portable multi-classification system for in situ growth monitoring of tomato flowers

A fundamental step towards an autonomous cross-pollination process for tomato plants involves classifying tomato flowers in line with their maturity. This paper is concerned with the development of a novel, portable, and deep learning enabled multi-classification system for classifying maturity levels of tomato flowers. The multi-class classification is powered by individual tomato flower images. As a dataset with individual tomato flowers is currently unavailable commercially, a dataset with more than 2000 images was created ensuring diversity among maturity levels and several other factors. A Convolutional Neural Network (CNN) was trained and tested with this dataset to be integrated with a feasible technology to institute portability in the system. Given the common use of smartphones, an Android based mobile application was developed to enable portable access to the neural network. A user would be able to capture or insert a tomato flower image and receive the predicted level of maturity using the mobile application. Rigorous testing show that the portable system generates comprehensive predictions reflecting the 75% classification accuracy possessed by the neural network. This paper also highlights the introductory work leading to the above-mentioned initiatives, culminated with future work paving the way towards autonomous tomato flower cross-pollination.

A novel framework based on the multi-label classification for dynamic selection of classifiers.

Multi-classifier systems (MCSs) are some kind of predictive models that classify instances by combining the output of an ensemble of classifiers given in a pool. With the aim of enhancing the performance of MCSs, dynamic selection (DS) techniques have been introduced and applied to MCSs. Dealing with each test sample classification, DS methods seek to perform the task of classifier selection so that only the most competent classifiers are selected. The principal subject regarding DS techniques is how the competence of classifiers corresponding to every new test sample classification task can be estimated. In traditional dynamic selection methods, for classifying an unknown test sample x, first, a local region of data thatis similar to x is detected. Then, those classifiers that efficiently classify the data in the local region are also selected so as to perform the classification task for x. Therefore, the main effort of these methods is focused on one of the two following tasks: (i) to provide a measure for identifying a local region, or (ii) to provide a criterion for measuring the efficiency of classifiers in the local region (competence measure). This paper proposes a new version of dynamic selection techniques that does not follow the aforementioned approach. Our proposed method uses a multi-label classifier in the training phase to determine the appropriate set of classifiers directly (without applying any criterion such as a competence measure). In the generalization phase, the suggested method is employed efficiently so as to predict the appropriate set of classifiers for classifying the test sample x. It is remarkable that the suggested multi-label-based framework is the first method that uses multi-label classification concepts for dynamic classifier selection. Unlike the existing meta-learning methods for dynamic ensemble selection in the literature, our proposed method is very simple to implement and does not need meta-features. As the experimental results indicate, the suggested technique produces a good performance in terms of both classification accuracy and simplicity which is fairly comparable with that of the benchmark DS techniques. The results of conducting the Quade non-parametric statistical test corroborate the clear dominance of the proposed method over the other benchmark methods.

A multi-classifier system to identify and subtype congenital adrenal hyperplasia based on circulating steroid hormones

A multi-classifier system to identify and subtype congenital adrenal hyperplasia based on circulating steroid hormones

A comparison of advanced semi-quantitative amyloid PET analysis methods

PurposeTo date, there is no consensus on how to semi-quantitatively assess brain amyloid PET. Some approaches use late acquisition alone (e.g., ELBA, based on radiomic features), others integrate the early scan (e.g., TDr, which targets the area of maximum perfusion) and structural imaging (e.g., WMR, that compares kinetic behaviour of white and grey matter, or SI based on the kinetic characteristics of the grey matter alone). In this study SUVr, ELBA, TDr, WMR, and SI were compared. The latter — the most complete one — provided the reference measure for amyloid burden allowing to assess the efficacy and feasibility in clinical setting of the other approaches.MethodsWe used data from 85 patients (aged 44–87) who underwent dual time-point PET/MRI acquisitions. The correlations with SI were computed and the methods compared with the visual assessment. Assuming SUVr, ELBA, TDr, and WMR to be independent measures, we linearly combined them to obtain more robust indices. Finally, we investigated possible associations between each quantifier and age in amyloid-negative patients.ResultsEach quantifier exhibited excellent agreement with visual assessment and strong correlation with SI (average AUC = 0.99, ρ = 0.91). Exceptions to this were observed for subcortical regions with ELBA and WMR (ρELBA = 0.44, ρWMR = 0.70). The linear combinations showed better performances than the individual methods. Significant associations were observed between TDr, WMR, SI, and age in amyloid-negative patients (p < 0.05).ConclusionAmong the other methods, TDr came closest to the reference with less implementation complexity. Moreover, this study suggests that combining independent approaches gives better results than the individual procedure, so efforts should focus on multi-classifier systems for amyloid PET. Finally, the ability of techniques integrating blood perfusion to depict age-related variations in amyloid load in amyloid-negative subjects demonstrates the goodness of the estimate.

A Multiclassifier System to Identify and Subtype Congenital Adrenal Hyperplasia Based on Circulating Steroid Hormones.

ContextMeasurement of plasma steroids is necessary for diagnosis of congenital adrenal hyperplasia (CAH). We sought to establish an efficient strategy for detection and subtyping of CAH with a machine-learning algorithm.MethodsClinical phenotype and genetic testing were used to provide CAH diagnosis and subtype. We profiled 13 major steroid hormones by liquid chromatography-tandem mass spectrometry. A multiclassifier system was established to distinguish 11β-hydroxylase deficiency (11βOHD), 17α-hydroxylase/17,20-lyase deficiency (17OHD), and 21α-hydroxylase deficiency (21OHD) in a discovery cohort (n = 226). It was then validated in an independent cohort (n = 111) and finally applied in a perspective cohort of 256 patients. The diagnostic performance on the basis of area under receiver operating characteristic curves (AUCs) was evaluated.ResultsA cascade logistic regression model, we named the “Steroidogenesis Score”, was able to discriminate the 3 most common CAH subtypes: 11βOHD, 17OHD, and 21OHD. In the perspective application cohort, the steroidogenesis score had a high diagnostic accuracy for all 3 subtypes, 11βOHD (AUC, 0.994; 95% CI, 0.983-1.000), 17OHD (AUC, 0.993; 95% CI, 0.985-1.000), and 21OHD (AUC, 0.979; 95% CI, 0.964-0.994). For nonclassic 21OHD patients, the tool presented with significantly higher sensitivity compared with measurement of basal 17α-hydroxyprogesterone (17OHP) (0.973 vs 0.840, P = 0.005) and was not inferior to measurement of basal vs stimulated 17OHP (0.973 vs 0.947, P = 0.681).ConclusionsThe steroidogenesis score was biochemically interpretable and showed high accuracy in identifying CAH patients, especially for nonclassic 21OHD patients, thus offering a standardized approach to diagnose and subtype CAH.

Developing a multi-classifier system to classify OSM tags based on centrality parameters

Misclassification of features is a major source of uncertainty in OpenStreetMap (OSM). This study is an automated data-enrichment study whose primary goal is predicting road classes based on multi-classifier systems (MCSs). In this regard, fourteen parameters (thirteen centrality parameters and length) that were assumed to have the highest impact on the classes of the features were calculated for the features. Choosing Tehran, Iran, as the test case, no ground truth was available; therefore, the tags assigned by the Iranian identified experts were fed to several classifiers including random forest, decision tree, support vector machine (SVM), Artificial Neural Network (ANN), and naïve Bayes. Using the five-fold cross-validation method, the overall accuracy of the classifiers was 93.55%, 90.19%, 88.50%, 83.06%, and 25.06%, respectively. Using Gini importance showed that closeness, eccentricity, and length were the most important parameters affecting the classification. To further enhance the accuracy, MCSs were used to fuse the results. The employed methods were weighted majority voting, naïve Bayes, Dempster-Shaffer, decision template, and behavior knowledge space (BKS). Experimenting different fusion methods with different combinations of the input classifiers led to enhanced results, in which BKS being fed with the combination of SVM and random forest scored the highest with an accuracy of 97.19%. Also, the methodology was tested on two other major cities of Iran, namely Mashhad and Karaj, and the BKS fusion method resulted in the accuracy of 93.18% and 87.86%, respectively.

Information fusion and multi-classifier system for miner fatigue recognition in plateau environments based on electrocardiography and electromyography signals

Background and objectiveHuman factors are important contributors to accidents, especially human error induced by fatigue. In this study, field tests and analyses were conducted on physiological indexes extracted from electrocardiography (ECG) and electromyography (EMG) signals in miners working under the extreme conditions of a plateau environment. To provide insights into models for fatigue classification and recognition based on machine learning, multi-modal feature information fusion and miner fatigue identification based on ECG and EMG signals as physiological indicators were studied. MethodsFifty-five miners were randomly selected as field test subjects, and characteristic signals were extracted from 110 groups of ECG and EMG signals as the basic signals for fatigue analysis. We conducted principal component analysis (PCA) and grey relational analysis (GRA) on the measurement indicators. Support vector machine (SVM), random forest (RF) and extreme gradient boosting (XG-Boost) machine learning models were used for fatigue classification based on multi-modal information fusion. The area under the receiver operating characteristic (ROC) curve and the confusion matrix were used to evaluate the performance of the recognition models. ResultsThe ECG and EMG signals showed obvious changes with fatigue. The results of fatigue model identification showed that PCA feature fusion was superior to GRA feature fusion for all three machine learning approaches, and XG-Boost achieved the best performance, with a recognition accuracy of 89.47%, a sensitivity and specificity of 100%, and an AUC of 0.90. The SVM model also showed good recognition performance (89.47% accuracy, AUC=0.89). The worst performance was that of the RF model, with a recognition accuracy of only 78.95%. ConclusionsThis study shows that the physiological indexes of ECG and EMG exhibit obvious, regular changes with fatigue and that it is feasible to use SVM, RF and XG-Boost models for miner fatigue identification. The PCA fusion technique can improve the identification accuracy more than the GRA method. XG-Boost classification yields the best accuracy and robustness. This study can serve as a reference for clinical research on the identification of human fatigue at high altitudes and for the clinical study of acute mountain sickness and human acclimatization to high altitudes.

Developing a preliminary cost estimation model for tall buildings based on machine learning

ABSTRACT The last half-century has witnessed an astronomical rise in the number of tall building projects in urban centers globally. These projects however frequently experience delays and total abandonment due to economic reasons. This study presents the application of Machine Learning techniques in the systematic development of a model to estimate the preliminary cost of tall building projects. The techniques considered include Multi-Linear Regression Analysis (MLRA), k-Nearest Neighbors (KNN), Artificial Neural Networks (ANN), Support Vector Machines (SVM), and Multi Classifier Systems. Twelve models were developed and compared using standard performance metrics. The results revealed that the best performing model was based on a Multi Classifier System using KNN as the combining classifier, with a Correlation Coefficient (R2) of 0.81, Root Mean Squared Error (RMSE) of 6.09, and Mean Absolute Percentage Error (MAPE) of 80.95%. This research showed the potential of modern digital technologies such as machine learning to solve problems of the construction industry. The procedure described in this study is of significant value to research and practice in the development of preliminary cost estimation models. The developed model can function as a decision support tool in the preliminary cost estimation stage of tall building projects.

Evolving a Multi-Classifier System for Multi-Pitch Estimation of Piano Music and Beyond: An Application of Cartesian Genetic Programming

This paper presents a new method with a set of desirable properties for multi-pitch estimation of piano recordings. We propose a framework based on a set of classifiers to analyze audio input and to identify piano notes present in a given audio signal. Our system’s classifiers are evolved using Cartesian genetic programming: we take advantage of Cartesian genetic programming to evolve a set of mathematical functions that act as independent classifiers for piano notes. Two significant improvements are described: the use of a harmonic mask for better fitness values and a data augmentation process for improving the training stage. The proposed approach achieves competitive results using F-measure metrics when compared to state-of-the-art algorithms. Then, we go beyond piano and show how it can be directly applied to other musical instruments, achieving even better results. Our system’s architecture is also described to show the feasibility of its parallelization and its implementation as a real-time system. Our methodology is also a white-box optimization approach that allows for clear analysis of the solutions found and for researchers to learn and test improvements based on the new findings.

Multi-Layer Selector(MLS): Dynamic selection based on filtering some competence measures

Multi-Classifier Systems (MCSs) have been widely studied as committee methods for increasing accuracy in pattern recognition. Recently, dynamic selection (DS) techniques have attracted undivided attention as effective types of MCSs in application. In DS techniques, the selection process is accomplished in two steps including measurement and selection. Normally, most DS methods in the literature have tried to focus on approaches adopted based on only one of the two options that are to offer a new measurement or a new selection method. On the other hand, some other papers have proposed frameworks in which both options were applied in combination with each other making use of previously existing measurement methods. For the first time, the idea of combining DS methods via multi-layer selectors is offered in this paper. In specific, two main tasks are performed in each layer of the multi-layer selector. First, the competence-level of classifiers are calculated. Then, the classifiers with high competence-level are passed to the next layer, and this way, best classifiers will be passed to the output in the last layer. During this procedure, some competence criteria are combined to measure the competence-level of classifiers. Furthermore, this paper introduces a novel taxonomy for dynamic selection methods and a new technique, called Probability Based (PB) method, to find the competence level of classifier. Experimental results show that the suggested framework improves the classification accuracy when compared against current state-of-the-art dynamic ensemble selection techniques. The Quade non-parametric statistical test confirms the capability of our proposed method to deal with classification problems.

An intelligent work order classification model for government service based on multi-label neural network

The classification of work orders for livelihood service play an important role in the e-government system, which goal is to push these work orders to the corresponding processing department. Although many studies have realized the classification of work orders automatically, these work orders are either related to many subjects or related to many departments. Therefore, the problem of work order classification is not a single label classification problem, but a multi-label classification problem. In view of the continuous development of deep neural networks, the goal of this paper is to modify a MultilabelMarginLoss function and design a MultilabelCrossEntropyLoss function to realize the multi-classification system of work orders, which can push the work orders to the related departments(one or more departments) automatically according to their appeal contents (consisting of short texts). We perform deep neural network for text classification including TextCNN, TextRCNN, TextRNN, TextRNN_Att, FastText and DPCNN on the real government hotline data set and compare the performances of these models. The results reveal that TextCNN and TextRCNN have a more stable performance on different loss functions, especially on the MultilabelCrossEntropyLoss function.

A hierarchical fusion framework to integrate homogeneous and heterogeneous classifiers for medical decision-making

Classifier diversity and fusion architecture are two critical characteristics stressed in homogeneous and heterogeneous ensemble learning methods and they are equally important for building a successful multi-classifier system. In this study, we introduced a two-level framework, namely hierarchical fusion of homogeneous and heterogeneous multi-classifiers (HF2HM), to integrate the diversified classification models produced by feeding heterogeneous classifiers with homogeneous random-projected training datasets. The proposed hierarchical fusion scheme was comprehensively validated using fifteen public UCI datasets and three clinical datasets. The experimental results demonstrated the superiority of the proposed HF2HM framework over the base classifiers and the state-of-the-art benchmark ensemble methods, verifying it as a potential tool to assist in medical decision making in practical clinical settings.