Ensemble Of Classifiers Research Articles

ENSMBL-PASD: Spearheading early autism spectrum disorder detection through advanced genomic computational frameworks utilizing ensemble learning models.

Autism spectrum disorder (ASD) is a complex neurodevelopmental condition influenced by various genetic and environmental factors. Currently, there is no definitive clinical test, such as a blood analysis or brain scan, for early diagnosis. The objective of this study is to develop a computational model that predicts ASD driver genes in the early stages using genomic data, aiming to enhance early diagnosis and intervention. This study utilized a benchmark genomic dataset, which was processed using feature extraction techniques to identify relevant genetic patterns. Several ensemble classification methods, including Extreme Gradient Boosting, Random Forest, Light Gradient Boosting Machine, ExtraTrees, and a stacked ensemble of classifiers, were applied to assess the predictive power of the genomic features. TheEnsemble Model Predictor for Autism Spectrum Disorder (eNSMBL-PASD) model was rigorously validated using multiple performance metrics such as accuracy, sensitivity, specificity, and Mathew's correlation coefficient. The proposed model demonstrated superior performance across various validation techniques. The self-consistency test achieved 100% accuracy, while the independent set and cross-validation tests yielded 91% and 87% accuracy, respectively. These results highlight the model's robustness and reliability in predicting ASD-related genes. The eNSMBL-PASD model provides a promising tool for the early detection of ASD by identifying genetic markers associated with the disorder. In the future, this model has the potential to assist healthcare professionals, particularly doctors and psychologists, in diagnosing and formulating treatment plans for ASD at its earliest stages.

An optimized ensemble grey wolf-based pipeline for monkeypox diagnosis

As the world recovered from the coronavirus, the emergence of the monkeypox virus signaled a potential new pandemic, highlighting the need for faster and more efficient diagnostic methods. This study introduces a hybrid architecture for automatic monkeypox diagnosis by leveraging a modified grey wolf optimization model for effective feature selection and weighting. Additionally, the system uses an ensemble of classifiers, incorporating confusion based voting scheme to combine salient data features. Evaluation on public data sets, at various of training samples percentages, showed that the proposed strategy achieves promising performance. Namely, the system yielded an overall accuracy of 98.91% with testing run time of 5.5 seconds, while using machine classifiers with small number of hyper-parameters. Additional experimental comparison reveals superior performance of the proposed system over literature approaches using various metrics. Statistical analysis also confirmed that the proposed AMDS outperformed other models after running 50 times. Finally, the generalizability of the proposed model is evaluated by testing its performance on external data sets for monkeypox and COVID-19. Our model achieved an overall diagnostic accuracy of 98.00% and 99.00% on external COVID and monkeypox data sets, respectively.

Cyber Espionage in the Age of Artificial Intelligence: A Comparative Study of State-Sponsored Campaign

This study investigates the transformative role of artificial intelligence (AI) in state-sponsored cyber espionage, focusing on its dual use in offensive and defensive operations. Using data from the MITRE ATT&CK Framework, FireEye APT Groups Database, UNSW-NB15 Intrusion Detection Dataset, and the Cyber Conflict Tracker by CFR, this research applied network graph analysis, multi-criteria decision analysis (MCDA), ensemble classification models, and Difference-in-Differences (DiD) analysis. Results revealed that AI-driven offensive techniques, phishing (degree centrality 0.85), and adaptive malware (betweenness centrality 0.81) significantly enhance operational precision and scalability. Defensively, ensemble classification models achieved up to 95.8% accuracy, highlighting AI's efficacy in intrusion detection. AI regulatory frameworks reduced misattribution rates by 20% and escalation incidents by 10%, demonstrating their critical role in mitigating geopolitical risks. The findings impress AI's transformative potential in advancing cyber operations and shaping international policy and governance. By addressing challenges such as attribution, escalation risks, and ethical dilemmas, this study highlights the necessity for stronger global cooperation and regulatory frameworks to navigate the dual-use nature of AI, providing actionable insights for policymakers, cybersecurity professionals, and researchers, emphasizing the urgency of aligning technological advancements with strategies for enhancing global cybersecurity resilience.

An Ensemble Voting classification Approach for Software defects prediction

An Ensemble Voting classification Approach for Software defects prediction

A novel deep learning-based 1D-CNN-optimized GRU approach for heart disease prediction

Cardiac data modeling remains challenging in emerging nations across Asia and Africa. This research proposes an ensemble classification method leveraging machine learning (ML) to predict cardiac problems, providing physicians with actionable insights for personalized diagnoses and treatments. An ensemble classification method for modelling cardiac temporal data is presented in this research. The minimax scalar transform is applied to first denoise the input data, and then the ENN-smote approach is applied to address the issue of an imbalanced dataset. Secondly, we employ a standard deep learning (DL) methodology. To identify the irregularities in the cardiac data pattern, a gated recurrent unit (GRU) classifier and a one-dimensional convolutional neural network (1D-CNN) are introduced. A typical genetic algorithm (GA) is used to optimize the suggested GRU network in order to pass over the local minima. This aids with 1D-CNN weight training. GA methodically optimizes the model’s GRU parameters. The data processed were finally used by the hybrid 1D-CNN-Optimized GRU network to predict cardiovascular illness. The suggested method attained a training accuracy of over 97% and a test accuracy of over 96% on the dataset. The proposed model’s overall accuracy is 99%. This is completely evaluated against other deep learning algorithms.

Ensembles of deep one-class classifiers for multi-class image classification

Ensembles of deep one-class classifiers for multi-class image classification

Blockchain Assisted Al‐Biruni Earth Radius Optimization with Deep Learning Model for Sustainable Healthcare Disease Detection and

The cybersecurity and sustainability concepts involve safeguarding and analyzing sustainable systems, providing a versatile perspective. In the extensive data landscape of sustainable healthcare systems, ensuring diagnostic and security processes poses challenges. Healthcare disease detection using Blockchain (BC) employs BC technology to boost security and precision. This system securely shares and stores patient records through BC, fostering collaboration among researchers and healthcare providers to improve disease detection accuracy. This study designs a new BC-Assisted Al‐Biruni Earth Radius Optimization with Deep Learning Model for Sustainable Healthcare Disease Detection and Classification (BAERDL-SHDDC) technique. The BAERDL-SHDDC technique presented utilizes BC to securely store patient data and employs DL models to analyze the data for the disease detection process. For disease detection, the BAERDL-SHDDC technique involves a three-stage process namely Al‐Biruni Earth Radius (AER)-based feature selection, ensemble DL classification, and hyperparameter optimization. The hyperparameters of the ensemble DL models with fractals optimizations are optimally selected using an Adadelta optimizer. The stimulation result analysis of the BAERDL-SHDDC approach shows the guaranteeing performance of the BAERDL-SHDDC algorithm over other existing techniques with greater accuracy of 98.45%, 95.22%, and 96.49% under Heart Statlog, Pima Indian Diabetes, and EEG Eyestate databases respectively

A deep neural network-based multi-layer classifier ensembles for intrusion detection in fog-based Internet of Things environments

Intrusion Detection Systems (IDS) are regarded as an efficient security mechanism in the Internet of Things (IoT). IDSs in the IoT face critical challenges, such as a vast amount of data with many features, limited resources, detection of unknown attacks, and many false alarms. To overcome these issues, this paper proposes a novel framework, namely a Multi-Layer Multi-Classification System (MLMCS). The proposed framework consists of four steps: In the first step, the data collected from information sources are pre-processed. The second step divides the feature space into several subspaces to reduce the model's complexity. The third step proposes a multilayer base classifier called a Multi-Layer Classifier System (MLCS) for each feature subspace. Each MLCS is layered to transform a multi-class classification into several binary classifications so that a specific category of attacks has been detected in each layer based on the Group Method of Data Handling (GMDH) neural network. In the fourth step, the results obtained from MLCSs based on the Dempster-Shafer theory are combined to reduce the problems related to overfitting. The simulation results were gained using three datasets, i.e., NSL-KDD, UNSW-NB15, and TON-IoT. They indicated that the proposed method, compared with other methods, improved F1-score by 5.64%, 0.65%, and 0.11%, respectively. Furthermore, the false alarm rate was reduced by 2.66%, 2.52%, and 0.02%. Moreover, the impact of four well-known adversarial attacks on the dataset was investigated. It was observed that the MLMCS method, with an average 5.21% reduction, could perform well against these attacks.

Skin Cancer Classification using Ensemble Classification Model with Improved Deep Joint Segmentation

Skin Cancer Classification using Ensemble Classification Model with Improved Deep Joint Segmentation

Skin cancer classification using ensemble classification model with improved deep joint segmentation

Skin cancer classification using ensemble classification model with improved deep joint segmentation

Learning‐Based Progression Detection of Alzheimer’s Disease Using 3D MRI Images

Alzheimer’s disease (AD) is an irreversible brain disease. In addition to the functional deterioration of memory and cognition, patients with severe conditions lose their self‐care ability. Patients exhibiting symptoms are often attributed to aging and thus lack proper medical care. If it can be diagnosed early, the doctor can provide adequate treatments to mitigate the symptoms. Magnetic resonance imaging (MRI) can reflect the characteristics of different human tissues and organs, and is a common tool implemented in clinical examinations. In this study, we tested learning‐based approaches to detect disease progression in AD patients using MRI. Specifically, each patient is categorized as one of the following four classes: cognitive normal, early mild cognitive impairment, late mild cognitive impairment, and AD. To extract 3D information in MRI, we proposed a 3D convolutional neural network structure based on ResNet3D‐18. We designed various multiclass classification frameworks. Moreover, we implemented ensemble classification combining these frameworks. Experiments demonstrated great potential for learning‐based approaches on the Alzheimer’s Disease Neuroimaging Initiative dataset. The ensemble approach performed the best with an accuracy of 0.950, which is competitive with neurologists in diagnosing AD progression in clinical practice. With precise detection, patients can understand their conditions early and seek proper treatments.

Fast and reliable uncertainty quantification with neural network ensembles for industrial image classification

Fast and reliable uncertainty quantification with neural network ensembles for industrial image classification

Distinguishing Among Causes of Death for Patients with Kidney Failure on Hemodialysis.

Patients treated with maintenance hemodialysis (HD) are at high risk of death from a variety of causes. To identify markers (i.e., risk phenotypes) that distinguish among causes of death, we used dialysis electronic health record data for a cohort of adults treated with maintenance in-center HD who died between 2003-2016. Patients were linked to the United States Renal Data System (USRDS) Files. We classified USRDS-reported causes of death into five categories: Sudden Cardiac Death (SCD), non-SCD Cardiovascular Death, Infection, Others, and Unknown. A sub-cohort was linked to the National Death Index (NDI) with similar categories defined. We used ensemble classification trees to discriminate among causes using demographics, vital signs, laboratory measures, health service utilization, and comorbidity claims from 30 days prior to death. The area under the receiver operating curves (AUCs) were all between 0.59-0.70, suggesting minimal ability to distinguish among causes using clinical risk markers. We then created nested case-control populations for each cause of death and used ridge logistic regression to evaluate clinical risk markers that associate with distinct causes. Model coefficients were similar and highly correlated across different cause of death models (i.e., 0.87 - 0.94). This suggests that most clinical risk markers are shared across causes without distinct risk phenotypes. We conclude that different causes of death may share similar clinical risk markers in the setting of kidney failure or that the causes of death attributed on USRDS or NDI forms are not precise.

Cuneiform Text Dialect Identification Using Machine Learning Algorithms and Natural Language Processing (NLP)

Due to a lack of resources and the tokenization issue, it is challenging to identify the languages inscribed in cuneiform symbols. Sumerian and six dialects of the Akkadian language-Old Babylonian, Middle Babylonian Peripheral, Standard Babylonian, Neo-Babylonian, Late Babylonian, and Neo-Assyrian-are among the seven languages and dialects written in cuneiform that need to be identified. This problem is addressed by the Cuneiform Language Identification task in VarDial 2019. This paper presents ten machine learning algorithms derived from four types of machine learning that were used (supervised, ensemble, instance-based, and Artificial Neural Network) learnings. The Support Vector Machine (SVM), Na Bayes (NB), Logistic Regression (LR), and Decision Tree (DT) algorithms within supervised learning, the K-Nearest Neighbors algorithm (KNN) within instance- based learning, the Random Forest (RF), Adaptive Boosting (Adaboost), Extreme Gradient Boosting (XGBoost), and Gradient Boosting (GB) algorithms within ensemble learning. Also, one of the natural language processing algorithms, n-gram, is used to identify the cuneiform dialect. The best result belongs to an ensemble of Random Forest classifiers working on character-level features with a macro averaged F1 score of 96%, and the best outcome for the n-grams algorithm is 0.82% of di-gram.

Class-specific feature selection for enhancing explainability in ensemble classification models

AbstractFeature selection techniques aim at finding a relevant subset of features that perform equally or better than the original set of features at explaining the behavior of data. Typically, features are extracted from feature ranking or subset selection techniques, and the performance is measured by classification or regression tasks. However, while selected features may not have equal importance for the task, they do have equal importance for each class. The fundamental idea of the class-specific concept resides in the understanding that the significance of each feature can vary from one class to another. This contrasts with the traditional class-independent approach, which evaluates the importance of attributes collectively for all classes. For example, in tumor prediction scenarios, each type of tumor (class) may be associated with a distinct subset of relevant features. These features possess significant discriminatory power, enabling the differentiation of one tumor type from others (classes). This class-specific perspective offers a more effective approach to classification tasks by recognizing and leveraging the unique characteristics of each class. A novel deep one-versus-each strategy is introduced, which offers advantages from the point of view of explainability (feature selection) and decomposability (classification). In addition, the class-specific relevance matrix is presented, from which some more sophisticated classification schemes can be derived, such as the three-layer class-specific scheme. These schemes have the great advantage to combine independent classification units (e.g., neural networks) that use a reduced number of features to target each class. The potential for further advancements in this area is wide and will open new horizons for exploring novel research directions in interdisciplinary fields, particularly in complex, multiclass hyperdimensional contexts (e.g., in genomics).

Machine and Deep Learning Models for Hypoxemia Severity Triage in CBRNE Emergencies.

This study develops machine learning (ML) models to predict hypoxemia severity during emergency triage, particularly in Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE) scenarios, using physiological data from medical-grade sensors. Tree-based models (TBMs) such as XGBoost, LightGBM, CatBoost, Random Forests (RFs), Voting Classifier ensembles, and sequential models (LSTM, GRU) were trained on the MIMIC-III and IV datasets. A preprocessing pipeline addressed missing data, class imbalances, and synthetic data flagged with masks. Models were evaluated using a 5-min prediction window with minute-level interpolations for timely interventions. TBMs outperformed sequential models in speed, interpretability, and reliability, making them better suited for real-time decision-making. Feature importance analysis identified six key physiological variables from the enhanced NEWS2+ score and emphasized the value of mask and score features for transparency. Voting Classifier ensembles showed slight metric gains but did not outperform individually optimized models, facing a precision-sensitivity tradeoff and slightly lower F1-scores for key severity levels. TBMs were effective for real-time hypoxemia prediction, while sequential models, though better at temporal handling, were computationally costly. This study highlights ML's potential to improve triage systems and reduce alarm fatigue, with future plans to incorporate multi-hospital datasets for broader applicability.

Revolutionizing healthcare: a comparative insight into deep learning’s role in medical imaging

Recently, Deep Learning (DL) models have shown promising accuracy in analysis of medical images. Alzeheimer Disease (AD), a prevalent form of dementia, uses Magnetic Resonance Imaging (MRI) scans, which is then analysed via DL models. To address the model computational constraints, Cloud Computing (CC) is integrated to operate with the DL models. Recent articles on DL-based MRI have not discussed datasets specific to different diseases, which makes it difficult to build the specific DL model. Thus, the article systematically explores a tutorial approach, where we first discuss a classification taxonomy of medical imaging datasets. Next, we present a case-study on AD MRI classification using the DL methods. We analyse three distinct models-Convolutional Neural Networks (CNN), Visual Geometry Group 16 (VGG-16), and an ensemble approach-for classification and predictive outcomes. In addition, we designed a novel framework that offers insight into how various layers interact with the dataset. Our architecture comprises an input layer, a cloud-based layer responsible for preprocessing and model execution, and a diagnostic layer that issues alerts after successful classification and prediction. According to our simulations, CNN outperformed other models with a test accuracy of 99.285%, followed by VGG-16 with 85.113%, while the ensemble model lagged with a disappointing test accuracy of 79.192%. Our cloud Computing framework serves as an efficient mechanism for medical image processing while safeguarding patient confidentiality and data privacy.

Early identification of potentially low performing community health workers using an ensemble classification model

PurposeCommunity health workers (CHWs) are vital to addressing public health system limitations in developing countries. However, effective identification and support of underperforming CHWs remains a challenge. This study develops a predictive model to proactively identify underperforming CHWs, facilitating targeted interventions for improved CHW programmes.Design/methodology/approachWe developed a predictive model to identify underperforming CHWs in Uttar Pradesh, India. Data from 140,101 CHWs over a 12-month period was used to build, test and validate the model. Classification techniques, ensemble modeling and a model tuning algorithm were employed for accuracy optimization and early identification.FindingsLogistic regression, decision trees and random forests yielded the best performance. While ensemble models offered no significant performance improvements over the base models, the model tuning algorithm effectively increased prediction accuracy by 19 percentage points. This enabled early identification of poor-performing CHWs and high-risk CHW clusters early in the year.Practical implicationsThe developed model has significant potential to improve CHW programmes. It enables targeted support, feedback and resource allocation, leading to enhanced CHW performance, motivation and healthcare outcomes in the communities they serve. The model can provide personalised feedback to help CHWs overcome challenges and dynamic clustering facilitates proactive identification and tailored support for those at risk of underperformance.Originality/valueThis study is the first attempt to use predictive modelling to identify underperforming CHWs, advancing the nascent field of CHW performance analytics. It underscores the effectiveness of digital technologies and data in improving CHW programmes.

Ensembles of neural network classifiers in the problem of analyzing telemetry information data of a small spacecraft

Ensembles of neural network classifiers in the problem of analyzing telemetry information data of a small spacecraft

Ensemble and Non-Ensemble Machine Learning-Based Classification of Liver Cirrhosis Stages

Cirrhosis is a chronic liver condition characterized by gradual scarring of the tissue in the liver, which then leads to one of the more serious health problems. Early diagnosis and detection of this condition are critical to managing the patient's situation and planning his treatment. Machine learning is a computer science field in which many complex issues have otherwise been successfully resolved, especially in medicine. This work focuses on constructing an artificial intelligence system, assisted by machine learning algorithms, to help professionals diagnose liver cirrhosis at its early stage. In this paper, four different models have been constructed with the aid of clinical parameters of patients and machine learning techniques: Random Forest, KNN, histogram-based Gradient Boosting, and Soft Voting. Two Feature selection methods (Chi-Square and mutual information) have been combined to select the most relevant features in the dataset. Then non-ensemble and ensemble methods are used to detect the condition. The random forest model achieved the highest score among other model with 97.4 % accuracy with a 10-fold Cross-validation method.