Ensemble Of Classifiers Research Articles

Skin cancer diagnosis: Leveraging deep hidden features and ensemble classifiers for early detection and classification

ProblemCancer is a deadly disease that requires better diagnostics. Early detection improves skin cancer survival. Due to skin lesion dissimilarity, automated image categorization for skin cancer is problematic, making early diagnosis costly and complicated. ObjectiveThis study proposes a deep hidden feature and ensemble classifier skin cancer detection and classification technique. It handles real-time data streaming prediction and dimensionality issues. MethodsThe research work employs the sand cat swarm optimization with ResNet50 (SCSO-ResNet50) method to separate deep hidden features from known features, ensuring accurate predictions. They utilize an improved harmony search (EHS) approach to optimize features and reduce data dimensionality. Ensemble classifiers, including Naive Bayes, random forest, k-nearest neighbor (k-NN), support vector machine (SVM), and linear regression, are used for early cancer diagnosis. The performance of the proposed methodology is evaluated using the Kaggle skin cancer dataset and the ISIC 2019 dataset, comparing it to state-of-the-art classifiers in terms of accuracy, precision, recall, and F-measure. ResultsIn the second layer of skin cancer classification, the ensemble classifiers, baseline classifier, and CNN outperformed each other, improving prediction accuracy. ConclusionThe proposed methodology improved prediction accuracy compared to state-of-the-art classifiers, as evaluated on benchmark datasets. These findings highlight the potential of the suggested approach in enhancing the early diagnosis of skin cancer.

An ensemble learning approach for resampling forgery detection using Markov process

Resampling is an extremely well-known technique performed for Image forgery detection. It includes the changes in the content of a picture in terms of rotation, stretching/zooming, and shrinking, to frame a forged picture that is a localized forgery in comparison to the original picture. With the wrong intention, resampling forgery has been increased day by day, and its negative impact has been increased in criminology, law enforcement, forensics, research etc. Accordingly, the interest in the algorithm of image resampling forgery detection is significantly developed in image forensics. In this paper, a novel image resampling forgery detection technique has been proposed. In the proposed technique, two types of Markov feature with spatial and Discrete Cosine Transform domains have been extracted to recognize the resampling operation. The spatial domain gives the information for the distribution of the pixels and DCT gives the edge information. Further, these Markov features are consolidated. Due to high dimensionality hard thresholding technique is used for reducing the dimensionality. Then, these Markov features are applied to the set of models of different classifiers. With the utilization of classifiers, weighted majority voting values have been calculated during the ensemble classification. Unlike the other techniques, these weighted voting boundaries have been consequently balanced during the training process until the best accuracy has been obtained. However, it is very difficult to get best accuracy so for getting best accuracy this research needs to do lots of iterations and trained the dataset. For the comparative study very few research has been found for this resampling forgery technique with different interpolation techniques and classifier. Still, comparison has been done with some latest research work. The comparative analysis shows that the proposed ensemble learning-based algorithm provides the best outcomes with the accuracy of 99.12% for bicubic, 98.89% for bilinear, and 98.23% for lanczos3 kernel with considerably less complexity and high speed in comparison to prior techniques which are using single support vector machine for classification. Moreover, the proposed algorithm also detects a very low probability of error of 0.44% and detects the type of interpolation kernel, size of the forgery, and the type of resampling, whether it is up sampling and down sampling, using Graphical User Interface which has not been detected previously with multiple forgery detection.

Deep learning approach for disease detection in lumbosacral spine radiographs using ConvNet

ABSTRACT Lumbosacral exam enables several computer-aided diagnoses (CAD) applications since it provides detailed spine radiographs, specifically of the lumbar, sacral, and coccygeal regions. We developed a deep learning-based CAD system methodology to detect lumbosacral anomalies in this context. For this purpose, we used a heterogeneous dataset that contains frontal and lateral lumbosacral exams. Our classification experiments achieved promising results with pre-trained CNNs: accuracy of 0.82/0.86, kappa of 0.65/0.66, and F1-Score of 0.82/0.83 for frontal and lateral images, respectively. In addition, we developed an ensemble classification that combines frontal and lateral images of the same exam and uses a confidence threshold selection. In this ensemble, we managed to issue alerts of 22.31% with a False Discovery Rate of 2.79%. Our proposal allows specialists to assist in decision-making.

Ensemble models based on CNN and LSTM for dropout prediction in MOOC

Massive Open Online Courses (MOOCs) have gained a lot of popularity recently. Despite the large number of students enrolled in these courses, a large percentage drop out. Due to this, predicting student dropout has taken on fundamental importance in this area. Predicting dropout early allows course organizers and educators to intervene and provide targeted support to at-risk students. They can offer additional resources, personalized assistance, or interventions tailored to address specific challenges faced by students, increasing their chances of successful course completion.This study first pre-processes the dataset to create a thirty-day correlation matrix for each learner, enabling early dropout prediction by the end of the first week. Then, six new models have been proposed using ensemble classification techniques with Convolutional Neural Network (CNN) and Long-Short Term Memory (LSTM). CNN is used for automatic feature extraction, while LSTM considers the time series aspect of the data to improve early prediction performance.As ensemble classifiers can reduce the variance of prediction errors, using ensemble classifiers in addition to neural networks can enhance accuracy and F1 score without overfitting. The application of these techniques results in more accurate week-by-week dropout prediction.The experimental results on the KDD Cup 2015 dataset (representing XuetangX, a MOOC platform in China with 39 courses, 79,186 students, and 120,542 registered students, with 8,157,277 records collected over 30 days) show that all Bagging models improve performance of their base models. In one of the proposed models (Bagging LSTM-LSTM), at the end of the fifth week, the accuracy reached 94%, and the average accuracy reached 91%. Also, precision and recall reached an average of 92%, and F1 score reached 98%, which shows a significant improvement compared to previous researches.

Classifying Mountain Vegetation Types Using Object-Oriented Machine Learning Methods Based on Different Feature Combinations

Mountainous vegetation type classification plays a fundamental role in resource investigation in forested areas, making it necessary to accurately identify mountain vegetation types. However, Mountainous vegetation growth is readily affected by terrain and climate, which often makes interpretation difficult. This study utilizes Sentinel-2A images and object-oriented machine learning methods to map vegetation types in the complex mountainous region of Jiuzhaigou County, China, incorporating multiple auxiliary features. The results showed that the inclusion of different features improved the accuracy of mountain vegetation type classification, with terrain features, vegetation indices, and spectral features providing significant benefits. After feature selection, the accuracy of mountain vegetation type classification was further improved. The random forest recursive feature elimination (RF_RFE) algorithm outperformed the RliefF algorithm in recognizing mountain vegetation types. Extreme learning machine (ELM), random forest (RF), rotation forest (ROF), and ROF_ELM algorithms all achieved good classification performance, with an overall accuracy greater than 84.62%. Comparing the mountain vegetation type distribution maps obtained using different classifiers, we found that classification algorithms with the same base classifier ensemble exhibited similar performance. Overall, the ROF algorithm performed the best, achieving an overall accuracy of 89.68%, an average accuracy of 88.48%, and a Kappa coefficient of 0.879.

An Efficient Multi-modal Facial Gesture-based Ensemble Classification and Reaction to Sound Framework for Large Video Sequences

Machine learning-based feature extraction and classification models play a vital role in evaluating and detecting patterns in multivariate facial expressions. Most conventional feature extraction and multi-modal pattern detection models are independent of filters for multi-class classification problems. In traditional multi-modal facial feature extraction models, it is difficult to detect the dependent correlated feature sets and use ensemble classification processes. This study used advanced feature filtering, feature extraction measures, and ensemble multi-class expression prediction to optimize the efficiency of feature classification. A filter-based multi-feature ranking-based voting framework was implemented on different multiple-based classifiers. Experimental results were evaluated on different multi-modal facial features for the automatic emotions listener using a speech synthesis library. The evaluation results showed that the proposed model had better feature classification, feature selection, prediction, and runtime than traditional approaches on heterogeneous facial databases.

Retracted: Ensemble Classification Approach for Sarcasm Detection.

[This retracts the article DOI: 10.1155/2021/9731519.].

A Metadata-Assisted Cascading Ensemble Classification Framework for Automatic Annotation of Open IoT Data

Public Internet of Things (IoT) platforms, such as Thingspeak, significantly increased the availability of open IoT data and enabled faster and cheaper development of novel IoT applications by reducing or even eliminating the need for deploying their own IoT sensors and platforms. However, open IoT data is often heterogeneous, sparse, fuzzy, and lacks accurate description (which we refer to as IoT metadata). These limitations make open IoT data challenging to integrate and use, and prevent the efficient development of IoT applications. In fact, while several sensor data description models have been proposed and standardized, open IoT data currently lack or include only partial metadata description. Therefore, novel techniques for automatically annotating open IoT data are needed to fully unleash the power of open IoT. This paper proposes a novel Metadata-Assisted Cascading Ensemble classification framework (MACE) for the automatic annotation of IoT data. MACE is capable of sequentially combining standalone classifiers, enabling it to cope with heterogeneous IoT data and different domains of information (e.g. numerical and textual), which have not been considered previously. MACE incorporates a novel ensemble approach for automatically selecting, sorting, filtering, and assembling classifiers in a way that improves annotation performance. The paper presents extensive experimental evaluations of MACE using public IoT datasets. Results demonstrate that the MACE framework significantly outperforms existing solutions for open IoT data by as much as 10% in classification accuracy.

Hybrid Multi-Label Classification Model for Medical Applications Based on Adaptive Synthetic Data and Ensemble Learning.

In recent years, both machine learning and computer vision have seen growth in the use of multi-label categorization. SMOTE is now being utilized in existing research for data balance, and SMOTE does not consider that nearby examples may be from different classes when producing synthetic samples. As a result, there can be more class overlap and more noise. To avoid this problem, this work presented an innovative technique called Adaptive Synthetic Data-Based Multi-label Classification (ASDMLC). Adaptive Synthetic (ADASYN) sampling is a sampling strategy for learning from unbalanced data sets. ADASYN weights minority class instances by learning difficulty. For hard-to-learn minority class cases, synthetic data are created. Their numerical variables are normalized with the help of the Min-Max technique to standardize the magnitude of each variable's impact on the outcomes. The values of the attribute in this work are changed to a new range, from 0 to 1, using the normalization approach. To raise the accuracy of multi-label classification, Velocity-Equalized Particle Swarm Optimization (VPSO) is utilized for feature selection. In the proposed approach, to overcome the premature convergence problem, standard PSO has been improved by equalizing the velocity with each dimension of the problem. To expose the inherent label dependencies, the multi-label classification ensemble of Adaptive Neuro-Fuzzy Inference System (ANFIS), Probabilistic Neural Network (PNN), and Clustering-Based Decision tree methods will be processed based on an averaging method. The following criteria, including precision, recall, accuracy, and error rate, are used to assess performance. The suggested model's multi-label classification accuracy is 90.88%, better than previous techniques, which is PCT, HOMER, and ML-Forest is 65.57%, 70.66%, and 82.29%, respectively.

New Classifier Ensemble and Fuzzy Community Detection Methods Using POP Choquet-like Integrals

Among various data analysis methods, classifier ensemble (data classification) and community network detection (data clustering) have aroused the interest of many scholars. The maximum operator, as the fusion function, was always used to fuse the results of the base algorithms in the classifier ensemble and the membership degree of nodes to classes in the fuzzy community. It is vital to use generalized fusion functions in ensemble and community applications. Since the Pseudo overlap function and the Choquet-like integrals are two new fusion functions, they can be combined as a more generalized fusion function. Along this line, this paper presents new classifier ensemble and fuzzy community detection methods using a pseudo overlap pair (POP) Choquet-like integral (expressed as a fraction). First, the pseudo overlap function pair is proposed to replace the product operator of the Choquet integral. Then, the POP Choquet-like integrals are defined to perform the combinatorial step of ensembles of classifiers and to generalize the GN modularity for the fuzzy community network. Finally, two new algorithms are designed for experiments, and some computational experiments with other algorithms show the importance of POP Choquet-like integrals. All of the experimental results show that our algorithms are practical.

Deep learning pipeline for quality filtering of MRSI spectra.

With the rise of novel 3D magnetic resonance spectroscopy imaging (MRSI) acquisition protocols in clinical practice, which are capable of capturing a large number of spectra from a subject's brain, there is a need for an automated preprocessing pipeline that filters out bad-quality spectra and identifies contaminated but salvageable spectra prior to the metabolite quantification step. This work introduces such a pipeline based on an ensemble of deep-learning classifiers. The dataset consists of 36,338 spectra from one healthy subject and five brain tumor patients, acquired with an EPSI variant, which implemented a novel type of spectral editing named SLOtboom-Weng (SLOW) editing on a 7T MR scanner. The spectra were labeled manually by an expert into four classes of spectral quality as follows: (i) noise, (ii) spectra greatly influenced by lipid-related artifacts (deemed not to contain clinical information), (iii) spectra containing metabolic information slightly contaminated by lipid signals, and (iv) good-quality spectra. The AI model consists of three pairs of networks, each comprising a convolutional autoencoder and a multilayer perceptron network. In the classification step, the encoding half of the autoencoder is kept as a dimensionality reduction tool, while the fully connected layers are added to its output. Each of the three pairs of networks is trained on different representations of spectra (real, imaginary, or both), aiming at robust decision-making. The final class is assigned via a majority voting scheme. The F1 scores obtained on the test dataset for the four previously defined classes are 0.96, 0.93, 0.82, and 0.90, respectively. The arguably lower value of 0.82 was reached for the least represented class of spectra mildly influenced by lipids. Not only does the proposed model minimise the required user interaction, but it also greatly reduces the computation time at the metabolite quantification step (by selecting a subset of spectra worth quantifying) and enforces the display of only clinically relevant information.

Discovering NDM-1 inhibitors using molecular substructure embeddings representations.

NDM-1 (New-Delhi-Metallo-β-lactamase-1) is an enzyme developed by bacteria that is implicated in bacteria resistance to almost all known antibiotics. In this study, we deliver a new, curated NDM-1 bioactivities database, along with a set of unifying rules for managing different activity properties and inconsistencies. We define the activity classification problem in terms of Multiple Instance Learning, employing embeddings corresponding to molecular substructures and present an ensemble ranking and classification framework, relaying on a k-fold Cross Validation method employing a per fold hyper-parameter optimization procedure, showing promising generalization ability. The MIL paradigm displayed an improvement up to 45.7 %, in terms of Balanced Accuracy, in comparison to the classical Machine Learning paradigm. Moreover, we investigate different compact molecular representations, based on atomic or bi-atomic substructures. Finally, we scanned the Drugbank for strongly active compounds and we present the top-15 ranked compounds.

An adaptive selective ensemble algorithm for fault classification

With the aim of improving the classification performance of a single extreme learning machine (ELM) for fault diagnosis, an adaptive selective ensemble classification algorithm is proposed based on the idea of ensemble learning. The proposed algorithm achieves better classification performance than a single model and the selected ELM subnetworks are selected adaptively and the ensemble weights of selected ELM subnetworks are calculated adaptively, which avoids the complex process of manually selecting subnetworks and calculating ensemble weights. First, a regularized error weight adjustment ELM is constructed by introducing regularization parameters and error weight adjustment matrix to a standard ELM, where the error weight adjustment matrix is obtained by the method of adaptive Gaussian kernel density estimation. Then, discrepancy subnetworks are constructed using six different activation functionsand the ensemble weights of subnetworks are obtained adaptively according to the normalized ratio of mean and variance of subnetwork F-scores to achieve the ensemble of subnetworks. Finally, the adaptive selective ensemble classification algorithm is validated using the UCI dataset and experimental acoustic emission signals of gearbox faults. The results show that the adaptive selective ensemble method can improve the stability and accuracy of classification algorithms and the achieved classification accuracy for experimental acoustic emission was 0.9773.

Prediction System for Covid-19 Upcoming Cases Using Ensemble Classification

An epidemic of the novel destructive Coronavirus has been spreading rapidly around the world since 2019 and has caused a great number of deaths. Providing patients with appropriate and most timely care is crucial to combating COVID-19 spread. Testing for the disease must be done quickly and accurately. Therefore, this paper developed an ensemble classification-based country-wise COVID-19 upcoming cases prediction model. This ensemble classification and prediction model shows the upcoming month's Corona virus cases, including newly confirmed cases, recovered cases, and deaths. This analysis is carried out based on these three cases occurring in different countries on sequential dates. The proposed model uses three famous classifiers, namely ANN, Gaussian Process and SVM which have different learning characteristics and architectures at the first stage. In the second stage, they combine their predictions with average calculations. Training and assessment of the proposed model were conducted using 75065 observations comprised of 61 features from John Hopkins University in Maryland. For data preparation, the envisioned work clusters the dataset based on world countries affected by COVID-19 separately. As a result, this set of clusters fetched data once again based on death, newly confirmed, and recovered cases. The experimental result shows the proposed ensemble model provides better performance when compared with previous classification algorithms.

Combined Tri-Classifiers for IoT Botnet Detection with Tuned Training Weights

Although IoT sectors seem more popular and pervasively, they struggle with hazards. The botnet is one of the largest security dangers associated with IoT. It enables malicious software to administer and attack private network equipment collectively without the owners’ knowledge. Although many studies have used ML to detect botnets, these are either not very effective or only work with specific types of botnets or devices. As a result, the detection model for deep learning ideas is the focus of this research. It entails three key processes: (a) preprocessing, (b) feature extraction, and (c) classification. The input data are initially preprocessed using an improved data normalization approach. The preprocessed data are used to extract a number of features, including Tanimoto coefficient features, improved differential holoentropy-based features, Pearson r correlation-based features, and others. The detection process will be completed by an ensemble classification model that randomly shuffles models like the Deep Belief Network (DBN) model, Bidirectional Gated Recurrent Unit (Bi-GRU), and Long Short-Term Memory (LSTM). Bi-GRU, DBN, and LSTM will be averaged to provide the ensemble results. Bi-GRU is trained using the Self Improved Blue Monkey Optimization (SIBMO) Algorithm by selecting the optimal weights, which increases the detection accuracy. The overall performance of the suggested work is then evaluated in relation to other existing models using various methodologies. In comparison to existing methods, the created ensemble classifier [Formula: see text] SIBMO scheme obtains the highest accuracy (93%) at a learning percentage of 90%.

Sequential ensemble learning for next item recommendation

Predicting the next item that users may engage in is a key task of recommender systems, and many methods have been proposed to deal with this task from different aspects. Theoretically, the proper ensemble of multiple different methods (a.k.a. base models) can make more accurate and stable recommendations. However, most of the existing ensemble methods rely on static aggregation strategies, which fail to capture base models’ dynamic predictive abilities for each user over time. In addition, most of the existing diversity measures used in regression or classification ensemble methods rely on a distance metric of base models’ outputs, which makes it intractably apply for next-item recommendation whose base models output sequential ranking lists.To solve the above problems, we propose a Sequential Ensemble Method, named SEM, to aggregate different base models for next-item recommendation. We assume users’ concentration and base models’ expertise can be inferred from users’ sequential behaviors and base models’ prediction results. Therefore, we propose to explicitly model base models’ dynamic predictive abilities on different users over time based on users’ concentration and base models’ expertise. In addition, we propose a new diversity measure for sequential ranking ensemble, which can perform diversity-based learning over time for better performance of next-item recommendation. Extensive experiments on six real-world data sets show that our method consistently outperforms state-of-the-art methods.

An ensemble-based Machine learning technique for dyslexia detection during a visual continuous performance task

BackgroundDyslexia is a neurological disorder which affects the learning of individuals suffering from it, especially children. It causes reading and writing difficulties, leading to anger, frustration, poor self-esteem, and other negative emotions. Early diagnosis of dyslexia can be extremely useful for dyslexic children since their learning requirements can be correctly handled. MethodThis study aimed to propose an efficient method for dyslexia detection via evoked-related potentials (ERPs) during a Visual Continuous Performance Task (VCPT). To this end, after extracting the latency and amplitude of the event-related potential components and a statistical analysis between the two groups, the number of data dimensions is reduced by the KS-test and principal component analysis (PCA). This method used the ensemble learning classification technique to classify the normal and dyslexic groups, including five classifiers, namely a Support Vector Machine (SVM), Decision Tree, Linear Discriminant Analysis (LDA), K-nearest Neighbors (KNN), and Naive Bayesian. Moreover, we have used an 8-fold cross-validation method to assess how generalized the process is and, more importantly, to have a well-performed control on overfitting. ResultsAccording to this approach, the overall average classification accuracy is 87.5%, and the sensitivity and specificity are 81.2% and 93.7%, respectively. ConclusionThe suggested technique can improve children's education before they start school and have any skills in writing and reading. The most discriminative electrodes were found in the left hemisphere, which can be related to the Wernicke and Broca areas that have an essential role in the brain's reading, writing, and language-related functions.

Highly effective end-to-end single-to-multichannel feature fusion and ensemble classification to decode emotional secretes from small-scale spontaneous facial micro-expressions

Facial Micro-Expression (ME) is one of the pre-dominating non-verbal clues to demystify the true emotional states that people try to conceal cautiously. But emotion recognition from spontaneous ME images limits the high accuracy due to short duration and low intensity, lack of sufficient samples and consistencies among publicly available ME datasets. In this study, we have proposed two highly effective, lightweight, and generalized single-channel DLRRF-MER, and multi-channel DLH-3C-FUSION fusion models inspired by deep dense convolutional models and texture-based feature descriptors Local Binary Pattern (LBP) and Histogram of Oriented Gradients (HOG) to recognize ME from apex frame by constructing a composite dataset from five publicly available ME datasets CASME, CASMEII, CAS(ME)2, SAMM and MMEW. Pre-training has been done on a new composition of five facial macro expressions datasets CK+, MUGFE, OuluCasia, SFEW, and RAF-DB. The proposed models are fine-tuned on the target ME dataset rigorously with Stratified 5-Fold and 10-Fold, Leave-One-Subject-Out, and Leave-One-Dataset-Out(LODO) cross-validations(CV). In all evaluations, our proposed algorithms show remarkable improvement in effectiveness which surpasses the state-of-the-art accuracies and results in higher generalization capacity.

Early Detection of Lung Cancer Using Small RNAs

IntroductionLung cancer remains the deadliest cancer in the world, and lung cancer survival is heavily dependent on tumor stage at the time of detection. Low-dose computed tomography screening can reduce mortality; however, annual screening is limited by low adherence in the United States of America and still not broadly implemented in Europe. As a result, less than 10% of lung cancers are detected through existing programs. Thus, there is a great need for additional screening tests, such as a blood test, that could be deployed in the primary care setting. MethodsWe prospectively recruited 1384 individuals meeting the National Lung Screening Trial demographic eligibility criteria for lung cancer and collected stabilized whole blood to enable the pipetting-free collection of material, thus minimizing preanalytical noise. Ultra-deep small RNA sequencing (20 million reads per sample) was performed with the addition of a method to remove highly abundant erythroid RNAs, and thus open bandwidth for the detection of less abundant species originating from the plasma or the immune cellular compartment. We used 100 random data splits to train and evaluate an ensemble of logistic regression classifiers using small RNA expression of 943 individuals, discovered an 18-small RNA feature consensus signature (miLung), and validated this signature in an independent cohort (441 individuals). Blood cell sorting and tumor tissue sequencing were performed to deconvolve small RNAs into their source of origin. ResultsWe generated diagnostic models and report a median receiver-operating characteristic area under the curve of 0.86 (95% confidence interval [CI]: 0.84–0.86) in the discovery cohort and generalized performance of 0.83 in the validation cohort. Diagnostic performance increased in a stage-dependent manner ranging from 0.73 (95% CI: 0.71–0.76) for stage I to 0.90 (95% CI: 0.89–0.90) for stage IV in the discovery cohort and from 0.76 to 0.86 in the validation cohort. We identified a tumor-shed, plasma-bound ribosomal RNA fragment of the L1 stalk as a dominant predictor of lung cancer. The fragment is decreased after surgery with curative intent. In additional experiments, results of dried blood spot collection and sequencing revealed that small RNA analysis could potentially be conducted through home sampling. ConclusionsThese data suggest the potential of a small RNA-based blood test as a viable alternative to low-dose computed tomography screening for early detection of smoking-associated lung cancer.

Disease Diagnosis Based on Improved Gray Wolf Optimization (IGWO) and Ensemble Classification.

This paper introduces a simple strategy for diagnosing disease, which is called improved gray wolf optimization (IGWO) and ensemble classification. The proposed strategy consists of two sequential phases, which are; (i) Feature Selection Phase (FSP) and (ii) Ensemble Classification Phase (ECP). During the former, the most effective features for diagnosing disease are selected, while during the latter, the actual diagnosis takes place depending on voting of five different classifiers. The main contribution of this paper is a suggested modification for the traditional Gray Wolf Optimization (GWO), which is called Improved Gray Wolf Optimization (IGWO). As an optimization technique, the proposed IGWO is employed in the FSP for selecting the effective features. For evaluating, IGWO has been implemented using recent feature selection techniques as well as the proposed method. To accomplish the classification phase; ensemble classification has been used which uses several classification techniques such as; Naïve Bayes (NB), Support Vector Machines (SVM), Deep Neural Network (DNN), Decision Tree (DT), and K-Nearest Neighbors (KNN). Ensemble classification integrate several classifiers for improving prediction performance. Experimental results have shown that employing IGWO promotes the performance of the diagnosing strategy of different diseases in terms of precision, recall, and accuracy.