Ensemble-based Approach Research Articles

Towards Superior Android Ransomware Detection: An Ensemble Machine Learning Perspective

Ransomware remains a pervasive threat to Android devices, with its ability to encrypt critical data and demand ransoms causing significant disruptions to users and organizations alike. This research proposes a novel ensemble-based machine learning approach for the detection of Android ransomware, leveraging the strengths of multiple classifiers to enhance detection accuracy and robustness. Utilizing a comprehensive dataset comprising 203,556 network traffic records across 10 distinct ransomware types and benign traffic, we meticulously preprocess and feature-engineer the data to ensure optimal model performance. The methodology integrates various ensemble classifiers, evaluating each through rigorous cross-validation. Feature importance analysis using Random Forest identifies key indicators of ransomware activity, enabling us to refine our models and focus on the most predictive features. The results demonstrate that the ensemble models, particularly Bagging, achieve near-perfect detection rates, with precision, recall, and F1 scores consistently exceeding 99% for different binary attacks and multi-class classification. Finally, in-depth statistical analysis further validates the superiority of our approach, showcasing significant improvements over traditional machine learning methods. This research sets a new benchmark for Android ransomware detection, offering a robust, scalable, and highly accurate solution that enhances the security and resilience of mobile networks against evolving cyber threats.

Abstract A021: Development of cross-ancestry polygenic risk. scores for breast cancer in women of African ancestry

Abstract Introduction: Polygenic risk scores (PRSs) predict breast cancer (BC) risk and have shown utility for screening in European ancestry women (EUR). However, PRSs developed for non-European ancestry, particularly African American (AA) women, have limited predictive accuracy. Methods: We analyzed data from 17,454 BC cases and 19,093 controls in the African American Breast Cancer Genetics (AABCG) consortium, split into training (70%), tuning (10%), and testing (20%) sets. Genome-wide association analyses for overall BC, ER-positive BC, ER- negative BC and triple-negative BC (TNBC) were performed in the training dataset, controlling for age, genotyping platform, and the top 10 principal components. We built single-ancestry PRS models using forward stepwise selection (FSS), PRSice-2, PLINK C+T, Lassosum2, and LDpred2-auto. These were combined with published EUR 313-SNP models (330-SNP for TNBC) in the tuning set to obtain cross-ancestry models. Genome-wide cross-ancestry PRS methods, including CT-SLEB and PRScsx, were also used. We created an ensemble model by combining different PRS models across subtypes using ensemble-based approaches. All developed PRS models were then evaluated in the independent testing set. Additional validation was performed using the All of Us (AoU) study with 834 BC cases and 29,122 controls from the AA population. Results: The observed-scale SNP-based heritability was estimated at 0.29 (SE: 0.12) for overall BC risk, 0.43 (SE: 0.18) for ER-positive BC, 0.44 (SE: 0.24) for ER-negative BC, and 1.13 (SE: 0.40) for TNBC. The best models showed good discriminating capacity: ensemble-based models for overall (AUC=0.626) and ER-positive BC (AUC=0.626), and combined cross-subtype and cross-ancestry FSS models for ER-negative (AUC=0.647) and TNBC (AUC=0.654). The odds ratio per standard deviation was 1.63 (95% CI: 1.55, 1.71) for the ensemble-based PRS of overall BC risk, with an estimated life risk of 28% for the top 1%. The cross-ancestry model using CT-SLEB combined with the EUR 313-SNP model was validated (AUC=0.61) among AA women in the AoU study. Conclusion: We developed PRSs with improved discriminating ability for BC risk in women with African ancestry. Cross- ancestry and subtype learning enhanced model performance. These findings indicate common variation has a larger role in BC in AA women than previously reported, warranting further validation in external AA populations and clinical evaluation. Citation Format: James L. Li, Haoyu Zhang, Julian C McClellan, Guimin Gao, Kevin Wang, Julie R. Palmer, Olufunmilayo I. Olopade, Christopher A. Haiman, Dezheng Huo. Development of cross-ancestry polygenic risk. scores for breast cancer in women of African ancestry [abstract]. In: Proceedings of the 17th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2024 Sep 21-24; Los Angeles, CA. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2024;33(9 Suppl):Abstract nr A021.

Deep Ensemble Learning using Transfer Learning for Food Classification

Aim: Deep learning models, such as deep convolutional neural networks (CNNs), have undergone extensive scrutiny in the context of food classification because of their exceptional feature extraction capabilities. Background: Similarly, ensemble-based learning approaches have exhibited great potential for achieving effective supervised classification. Objective: We suggest an innovative approach to improve the effectiveness of deep learningbased food classification. Method: Our proposal involves a novel deep learning ensemble framework that draws inspiration from the fusion of deep learning models with ensemble learning based on random subspaces. The random subspaces play a role in diversifying the ensemble system in a straightforward but impactful way. Moreover, to enhance the classification accuracy even more, we explore transfer learning, employing the migration of acquired weights from a single classifier to another (namely, CNNs). This approach expedites the process of learning. Result: Results from experiments conducted using well-established food datasets illustrate that the suggested deep learning ensemble system delivers competitive performance compared to state-of-the-art techniques, as evidenced by its classification accuracy. Conclusion: The amalgamation of deep learning and ensemble learning holds substantial promise for dependable food categorization.

Integration of dual band radio waves and ensemble-based approach for rice moisture content determination and localisation

Maintaining optimal moisture content in grain storage is critical to ensuring adequate supply throughout the year, but it presents a significant challenge. Current moisture measurement methods often necessitate sophisticated and costly equipment. This paper introduces an approach employing real-time rice moisture content determination and detection of spoilage (specifically wet spots) within a storage facility achieved through the utilisation of radio waves operating at 2.4 GHz and 868 MHz, along with an ensemble-based machine learning algorithm. Experimental samples spanning from 12% to 30% moisture levels were collected, then subjected to pre-processing, and subsequently employed to train the Ensemble-based Rice Moisture Content and Localisation (eRMCL) algorithm. The eRMCL produced an effective prediction of both rice moisture content and the localisation of wet spots within the grain storage unit. The results show that compared to support vector machine, random forest, and machine learning methods, the eRMCL algorithm had the best performance metrics, with an accuracy of 94.8% in predicting the moisture content and location of spoilage in storage. The measurement of moisture content and the identification of wet spots in rice storage using the dual frequency wave approach were found to be more accurate than with a single frequency band. Thus, the dual frequency band is a novel method for the determination of the moisture content of stored rice and the localisation of the spoilage area.

Multimodal Religiously Hateful Social Media Memes Classification Based on Textual and Image Data

Multimodal hateful social media meme detection is an important and challenging problem in the vision-language domain. Recent studies show high accuracy for such multimodal tasks due to datasets that provide better joint multimodal embedding to narrow the semantic gap. Religiously hateful meme detection is not extensively explored among published datasets. While there is a need for higher accuracy on religiously hateful memes, deep learning–based models often suffer from inductive bias. This issue is addressed in this work with the following contributions. First, a religiously hateful memes dataset is created and published publicly to advance hateful religious memes detection research. Over 2000 meme images are collected with their corresponding text. The proposed approach compares and fine-tunes VisualBERT pre-trained on the Conceptual Caption (CC) dataset for the downstream classification task. We also extend the dataset with the Facebook hateful memes dataset. We extract visual features using ResNeXT-152 Aggregated Residual Transformations–based Masked Regions with Convolutional Neural Networks (R-CNN) and Bidirectional Encoder Representations from Transformers (BERT) uncased for textual encoding for the early fusion model. We use the primary evaluation metric of an Area Under the Operator Characters Curve (AUROC) to measure model separability. Results show that the proposed approach has a higher AUROC score of 78%, proving the model’s higher separability performance and an accuracy of 70%. It shows comparatively superior performance considering dataset size and against ensemble-based machine learning approaches.

Predicting Financial Manipulation Using an Ensemble-based Approach

Predicting Financial Manipulation Using an Ensemble-based Approach

Exploring ensemble-based approaches for granular suicide risk assessment: a comprehensive framework in therapeutic informatics

Exploring ensemble-based approaches for granular suicide risk assessment: a comprehensive framework in therapeutic informatics

Ensemble-based deep learning model for welding defect detection and classification

This study introduces an ensemble-based deep learning approach for monitoring and detecting submerged arc weld defects in weld beads and adjacent zones during Non-Destructive Testing (NDT). The methodology utilizes an open-source image dataset to categorize submerged arc weld conditions into three defect types: cracks, lack of penetration and porosity, and ideal welds (no defects). To enhance image analysis, we employ preprocessing and feature extraction in both spatial and frequency domains using segmentation techniques like grey level difference method (GLDM), grey level co-occurrence matrix (GLCM), discrete wavelet transform (DWT), Fast Fourier Transform (FFT), and texture analysis. Following image preparation, the preprocessed data undergoes training and testing in our proposed ensemble-based deep learning model. The model's performance is thoroughly assessed using key metrics such as precision, recall, F1 score, receiver operating characteristics (ROC) curve, and a confusion matrix, resulting in an impressive accuracy rate of 93.12% for detecting and classifying weld faults. In comparing our model to state-of-the-art techniques in existing literature, our ensemble-based deep learning approach consistently demonstrates a high fault detection and classification performance in the face of a simplistic MLP-based core architecture, ratifying the robustness of our feature ensemble approach. The study concludes that this model has significant potential for integration into current inspection systems, offering an efficient and robust solution for real-time condition monitoring of welds along weldment joints.

An experimental review of the ensemble-based data stream classification algorithms in non-stationary environments

Data streams are sequences of fast-growing and high-speed data points that typically suffer from the infinite length, large volume, and specifically unstable data distribution. Ensemble learning as a prevalent classification approach is widely used in data stream mining studies. Besides the impressive performance of ensemble learning algorithms in providing a collection of diverse and accurate classifiers, they are specifically efficient in handling non-stationary data streams. Due to the component-based nature and the chance of dynamic updates for the components of the ensemble, this category is appropriate for dynamically learning the changing concepts of the data. Several review research have been conducted on the challenges of non-stationary data streams so far. None of the available surveys are dedicated to examine the effect of ensemble learning models on concept drift handling. This paper aims to provide a thorough theoretical and experimental review of the most significant ensemble-based data stream classification approaches in confronting with various types of concept drifts. In this comprehensive experimental analysis, 21 state-of-the-art ensemble algorithms are tested on 30 synthetic datasets under various types and volumes of concept drifts. This experimental analysis involves analyzing the classification accuracy, kappa score and running time of the algorithms, along with performing various statistical tests. In addition to conducting experimental analysis, a comprehensive investigation is carried out on the most significant challenges posed by non-stationary data streams, which provides the reader with valuable insights.

A Survey on Cyberbullying Predictive Model using Deep Learning Techniques

Cyberbullying, a pervasive issue in the current digital age, has prompted the need for advanced predictive models to identify and mitigate online harassment. This survey paper explores the landscape of cyberbullying severity level prediction using an ensemble-based deep learning approach for multimodal datasets. Delving into the realm of deep learning techniques and investigating their efficacy in discerning subtle patterns indicative of cyberbullying behaviour, the survey encompasses a comprehensive review of existing ensemble methodologies, highlighting their strengths and weaknesses in cyberbullying prediction. Diverse datasets, model architectures, and evaluation metrics employed in relevant studies are analysed, aiming to provide a thorough understanding of the current technological status. Additionally, difficulties and potential avenues for upcoming studies are discussed, fostering advancements in the development of robust predictive models to combat cyberbullying effectively. Researchers, practitioners, and policymakers looking for insights on the changing field of cyberbullying prevention using ensemble-based deep-learning methodologies will find this survey to be a valuable resource.

An ensemble-based approach for effective distributed denial of service attack detection in software defined networking

<p>Software defined networking (SDN) is a network framework that aims to redefine network characteristics through the programmability of network components, faster and larger network monitoring, centralized network operation, and effective detection of fraudulent traffic and special malfunctions. However, SDN networks are vulnerable to security threats that can cause complete network failure. To address this issue, in this paper, machine learning techniques are suggested for the swift detection of attacks. Various methods for detecting distributed denial of service (DDoS) attacks are evaluated, and the study identifies the most precise method for categorizing such attacks within a SDN network. The results indicate that the proposed system achieves high accuracy in detecting DDoS attacks, with ensemble learning achieving 99% accuracy. This indicates a remarkable improvement percentage in comparison to the approaches of decision tree (DT), k-nearest neighbors (KNN), and support vector machine (SVM).</p>

Prenatal and childhood air pollution exposure, cellular immune biomarkers, and brain connectivity in early adolescents

IntroductionAmbient air pollution is a neurotoxicant with hypothesized immune-related mechanisms. Adolescent brain structural and functional connectivity may be especially vulnerable to ambient pollution due to the refinement of large-scale brain networks during this period, which vary by sex and have important implications for cognitive, behavioral, and emotional functioning. In the current study we explored associations between air pollutants, immune markers, and structural and functional connectivity in early adolescence by leveraging cross-sectional sex-stratified data from the Adolescent Brain Cognitive Development℠ Study®. MethodsPollutant concentrations of fine particulate matter, nitrogen dioxide, and ozone were assigned to each child's primary residential address during the prenatal period and childhood (9-10 years-old) using an ensemble-based modeling approach. Data collected at 11-13 years-old included resting-state functional connectivity of the default mode, frontoparietal, and salience networks and limbic regions of interest, intracellular directional and isotropic diffusion of available white matter tracts, and markers of cellular immune activation. Using partial least squares correlation, a multivariate data-driven method that identifies important variables within latent dimensions, we investigated associations between 1) pollutants and structural and functional connectivity, 2) pollutants and immune markers, and 3) immune markers and structural and functional connectivity, in each sex separately. ResultsAir pollution exposure was related to white matter intracellular directional and isotropic diffusion at ages 11–13 years, but the direction of associations varied by sex. There were no associations between pollutants and resting-state functional connectivity at ages 11–13 years. Childhood exposure to nitrogen dioxide was negatively correlated with white blood cell count in males. Immune biomarkers were positively correlated with white matter intracellular directional diffusion in females and both white matter intracellular directional and isotropic diffusion in males. Lastly, there was a reliable negative correlation between lymphocyte-to-monocyte ratio and default mode network resting-state functional connectivity in females, as well as a compromised immune marker profile associated with lower resting-state functional connectivity between the salience network and the left hippocampus in males. In post-hoc exploratory analyses, we found that the PLSC-identified white matter tracts and resting-state networks related to processing speed and cognitive control performance from the NIH Toolbox. ConclusionsWe identified novel links between childhood nitrogen dioxide and cellular immune activation in males, and brain network connectivity and immune markers in both sexes. Future research should explore the potentially mediating role of immune activity in how pollutants affect neurological outcomes as well as the potential consequences of immune-related patterns of brain connectivity in service of improved brain health for all.

A multistage framework for respiratory disease detection and assessing severity in chest X-ray images

Chest Radiography is a non-invasive imaging modality for diagnosing and managing chronic lung disorders, encompassing conditions such as pneumonia, tuberculosis, and COVID-19. While it is crucial for disease localization and severity assessment, existing computer-aided diagnosis (CAD) systems primarily focus on classification tasks, often overlooking these aspects. Additionally, prevalent approaches rely on class activation or saliency maps, providing only a rough localization. This research endeavors to address these limitations by proposing a comprehensive multi-stage framework. Initially, the framework identifies relevant lung areas by filtering out extraneous regions. Subsequently, an advanced fuzzy-based ensemble approach is employed to categorize images into specific classes. In the final stage, the framework identifies infected areas and quantifies the extent of infection in COVID-19 cases, assigning severity scores ranging from 0 to 3 based on the infection’s severity. Specifically, COVID-19 images are classified into distinct severity levels, such as mild, moderate, severe, and critical, determined by the modified RALE scoring system. The study utilizes publicly available datasets, surpassing previous state-of-the-art works. Incorporating lung segmentation into the proposed ensemble-based classification approach enhances the overall classification process. This solution can be a valuable alternative for clinicians and radiologists, serving as a secondary reader for chest X-rays, reducing reporting turnaround times, aiding clinical decision-making, and alleviating the workload on hospital staff.

FNNet: a secure ensemble-based approach for fake news detection using blockchain

FNNet: a secure ensemble-based approach for fake news detection using blockchain

Enhancing flood verification using Signal Detection Theory (SDT) and IoT Sensors: A spatial scale evaluation

Inundation mapping by flood simulation is subject to uncertainties which spatial accuracy assessment could not be processed as normal mapping does. This paper presents a comprehensive study on the spatial accuracy of flood verification using Internet of Things (IoT) sensors in several flood-prone regions in Taiwan, including Changhua, Yunlin, Chiayi, Tainan, Kaohsiung, and Pingtung, during three storm events in 2021. The study adopts Signal Detection Theory (SDT) and proposes an ensemble-based approach that combines multiple evaluation metrics to enhance the accuracy and reliability of flood verification in these regions. The study examines the inundation availabilities between flood observation from IoT sensors and flood simulation. A range of spatial scales varies from 100 m to 1000 m and also administrative divisions are considered including neighborhood-level and village-level scales. The results show that increasing the spatial scale generally leads to higher True Positives, indicating improved flood detection, but it also results in increased False Positives, indicating more misclassification of non-flooded points. The findings reveal that the optimal spatial scale for all cities/counties is 450 m which indicates the averaged spatial accuracy of the flood simulation. However, there is notable variation in the optimal spatial scale across different regions. The ensemble approach demonstrates high consistency in determining the optimal spatial scale, as eight out of ten metrics consistently identify the same value. Additionally, the study compares flood verification across administrative divisions in Taiwan, finding that the village-level spatial scale performs best in Changhua and Yunlin counties, while the neighborhood-level scale is preferred in Tainan, Kaohsiung, and Pingtung. This research provides a valuable framework to estimate inundation mapping accuracy under flood verification using IoT sensors in the specified region of Taiwan and highlights the importance of considering local conditions and administrative divisions in determining the optimal spatial scale. These findings can contribute to the improvement of flood detection and monitoring systems in the area with IoT flood sensors.

Multi-modal lifelog data fusion for improved human activity recognition: A hybrid approach

The rapid growth of lifelog data, collected through smartphones and wearable devices, has driven the need for better Human Activity Recognition (HAR) solutions. However, lifelog data is complex and challenging to analyze due to its diverse sources of information. In response, we introduce an innovative hybrid data fusion framework for HAR. This framework comprises three key elements: a hybrid fusion mechanism, an attention-based classifier, and an ensemble-based recognition approach. Our hybrid fusion mechanism expertly combines the advantages of late and intermediate fusion, enhancing classification performance and improving the network’s ability to learn connections between different data modalities. Additionally, our solution incorporates an attention-based classifier and an ensemble approach, ensuring robust and consistent performance in real-world scenarios. We evaluated our method across multiple public lifelog datasets, demonstrating that our hybrid fusion approach consistently surpasses existing fusion strategies in HAR, promising significant advancements in activity recognition.

Distinguishing the Uterine Artery, the Ureter, and Nerves in Laparoscopic Surgical Images Using Ensembles of Binary Semantic Segmentation Networks.

Performing a minimally invasive surgery comes with a significant advantage regarding rehabilitating the patient after the operation. But it also causes difficulties, mainly for the surgeon or expert who performs the surgical intervention, since only visual information is available and they cannot use their tactile senses during keyhole surgeries. This is the case with laparoscopic hysterectomy since some organs are also difficult to distinguish based on visual information, making laparoscope-based hysterectomy challenging. In this paper, we propose a solution based on semantic segmentation, which can create pixel-accurate predictions of surgical images and differentiate the uterine arteries, ureters, and nerves. We trained three binary semantic segmentation models based on the U-Net architecture with the EfficientNet-b3 encoder; then, we developed two ensemble techniques that enhanced the segmentation performance. Our pixel-wise ensemble examines the segmentation map of the binary networks on the lowest level of pixels. The other algorithm developed is a region-based ensemble technique that takes this examination to a higher level and makes the ensemble based on every connected component detected by the binary segmentation networks. We also introduced and trained a classic multi-class semantic segmentation model as a reference and compared it to the ensemble-based approaches. We used 586 manually annotated images from 38 surgical videos for this research and published this dataset.

Hybrid Approach with Membership-Density Based Oversampling for handling multi-class imbalance in Internet Traffic Identification with overlapping and noise

Internet Traffic identification is a crucial method for monitoring Internet application activities and is essential for Internet management and security. Internet traffic data typically displays imbalanced distributions. The uneven distribution of instances in each class indicates the class imbalance problem. This problem can cause a decrease in classification performance because the classifier assumes the dataset has a balanced class distribution. Internet Traffic Identification dataset is often accompanied by overlapping and noise. The hybrid approach to handling class imbalances involving data-level and ensemble-based approaches is usually chosen to overcome this problem. Data-level with oversampling using SMOTE is the choice because of its ability to synthesize new samples for minority classes. However, SMOTE-generated samples tend to be noisy and overlap with the majority of samples. This research proposes the application of a Hybrid Approach with Membership-density-based Oversampling to tackle this challenge. This research emphasizes the importance of applying membership degrees in determining samples that will group samples into safe, overlapping, and noisy areas. Then, top samples will be selected based on density ratio, stability, and score for safe and overlapping safe areas. The study findings that the proposed method effectively addresses multi-class imbalances in six Internet Traffic Identification datasets, yielding slightly improved average accuracy, FbMeasur, and class balance accuracy results compared to other testing methods, though the difference is not statistically significant. The noise and overlapping scenes experiments demonstrate that the average accuracy obtained is superior, showing a considerable difference compared to all test methods.

District-Level Forecast of Achieving Trachoma Elimination as a Public Health Problem By 2030: An Ensemble Modelling Approach.

Assessing the feasibility of 2030 as a target date for global elimination of trachoma, and identification of districts that may require enhanced treatment to meet World Health Organization (WHO) elimination criteria by this date are key challenges in operational planning for trachoma programmes. Here we address these challenges by prospectively evaluating forecasting models of trachomatous inflammation-follicular (TF) prevalence, leveraging ensemble-based approaches. Seven candidate probabilistic models were developed to forecast district-wise TF prevalence in 11 760 districts, trained using district-level data on the population prevalence of TF in children aged 1-9 years from 2004 to 2022. Geographical location, history of mass drug administration treatment, and previously measured prevalence data were included in these models as key predictors. The best-performing models were included in an ensemble, using weights derived from their relative likelihood scores. To incorporate the inherent stochasticity of disease transmission and challenges of population-level surveillance, we forecasted probability distributions for the TF prevalence in each geographic district, rather than predicting a single value. Based on our probabilistic forecasts, 1.46% (95% confidence interval [CI]: 1.43-1.48%) of all districts in trachoma-endemic countries, equivalent to 172 districts, will exceed the 5% TF control threshold in 2030 with the current interventions. Global elimination of trachoma as a public health problem by 2030 may require enhanced intervention and/or surveillance of high-risk districts.

Countering DDoS threats: leveraging ensemble methods for detection and mitigation

Cloud computing is the modern concept of distributing numerous services through the Internet, such as web applications, databases, and programmers that operate on several servers. As Cloud computing technologies evolve, increasing susceptibility to attack may result from service outages during data storage and transmission. The most common sort of assault against Cloud settings is distributed denial-of-service (DDoS). Several approaches for detecting and mitigating these attacks have been offered, however they are ineffective. In this research, we propose a method for detecting and mitigating DDoS attacks in their early phases, considering top-layer advances at the application layer and the TCP handshake mechanism. This study employs a variety of ensemble-based machine learning approaches to classify incoming data as legitimate or malicious to respond to DDoS attacks at the application layer. Furthermore, the double TCP connection concept is used to prevent DDoS. Experiments show that the stacked voting system detects DDOS attacks with the best F-score of 99.9%.