Search Results (86)

In recent years, data augmentation techniques have become the predominant approach for addressing highly imbalanced classification problems in machine learning. Algorithms such as the Synthetic Minority Over-sampling Technique (SMOTE) and Conditional Tabular Generative Adversarial Network (CTGAN) have proven effective in synthesizing minority class samples. However, these methods often introduce distributional bias and noise, potentially leading to model overfitting, reduced predictive performance, increased computational costs, and elevated cybersecurity risks. To overcome these limitations, we propose a novel architecture, FADEL, which integrates feature-type awareness with a supervised discretization strategy. FADEL introduces a unique feature augmentation ensemble framework that preserves the original data distribution by concurrently processing continuous and discretized features. It dynamically routes these feature sets to their most compatible base models, thereby improving minority class recognition without the need for data-level balancing or augmentation techniques. Experimental results demonstrate that FADEL, solely leveraging feature augmentation without any data augmentation, achieves a recall of 90.8% and a G-mean of 94.5% on the internal test set from Kaohsiung Chang Gung Memorial Hospital in Taiwan. On the external validation set from Kaohsiung Medical University Chung-Ho Memorial Hospital, it maintains a recall of 91.9% and a G-mean of 86.7%. These results outperform conventional ensemble methods trained on CTGAN-balanced datasets, confirming the superior stability, computational efficiency, and cross-institutional generalizability of the FADEL architecture. Altogether, FADEL uses feature augmentation to offer a robust and practical solution to extreme class imbalance, outperforming mainstream data augmentation-based approaches. Full article

Machine predictive maintenance plays a critical role in reducing unplanned downtime, lowering maintenance costs, and improving operational reliability by enabling the early detection and classification of potential failures. Artificial intelligence (AI) enhances these capabilities through advanced algorithms that can analyze complex sensor data with high accuracy and adaptability. This study introduces an explainable AI framework for failure detection and classification using symbolic expressions (SEs) derived from a genetic programming symbolic classifier (GPSC). Due to the imbalanced nature and wide variable ranges in the original dataset, we applied scaling/normalization and oversampling techniques to generate multiple balanced dataset variations. Each variation was used to train the GPSC with five-fold cross-validation, and optimal hyperparameters were selected using a Random Hyperparameter Value Search (RHVS) method. However, as the initial Threshold-Based Voting Ensembles (TBVEs) built from SEs did not achieve a satisfactory performance for all classes, a meta-dataset was developed from the outputs of the obtained SEs. For each class, a meta-dataset was preprocessed, balanced, and used to train a Random Forest Classifier (RFC) with hyperparameter tuning via RandomizedSearchCV. For each class, a TBVE was then constructed from the saved RFC models. The resulting ensemble demonstrated a near-perfect performance for failure detection and classification in most classes (0, 1, 3, and 5), although Classes 2 and 4 achieved a lower performance, which could be attributed to an extremely low number of samples and a hard-to-detect type of failure. Overall, the proposed method presents a robust and explainable AI solution for predictive maintenance, combining symbolic learning with ensemble-based meta-modeling. Full article

High dropout rates remain a significant challenge in Massive Open Online Courses (MOOCs), making early identification of at-risk students crucial. This study introduces a novel approach called In-Session Stacked Ensemble Learning for Dropout Prediction (ISELDP), which predicts student dropout during course sessions by combining multiple base learners—Adaptive Boosting (AdaBoost), Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Gradient Boosting—into a stacked ensemble with a Multi-Layer Perceptron (MLP) serving as the meta-learner. To optimise model performance, hyperparameters were tuned using Grid Search. The proposed method was evaluated under two scenarios using in-session student interaction data, one with imbalanced data and another with balanced data. Results demonstrate that ISELDP achieves an average accuracy of 88%, outperforming individual baseline models with improvements of up to 2% in accuracy and 2.4% in F1-score. Full article

The rapid expansion of Edge and Industrial Internet of Things (IIoT) systems has intensified the risk and complexity of cyberattacks. Detecting advanced intrusions in these heterogeneous and high-dimensional environments remains challenging. As the IIoT becomes integral to critical infrastructure, ensuring security is crucial to prevent disruptions and data breaches. Traditional IDS approaches often fall short against evolving threats, highlighting the need for intelligent and adaptive solutions. While deep learning (DL) offers strong capabilities for pattern recognition, single-model architectures often lack robustness. Thus, hybrid and optimized DL models are increasingly necessary to improve detection performance and address data imbalance and noise. In this study, we propose an optimized hybrid DL framework that combines a transformer, generative adversarial network (GAN), and autoencoder (AE) components, referred to as Transformer–GAN–AE, for robust intrusion detection in Edge and IIoT environments. To enhance the training and convergence of the GAN component, we integrate an improved chimp optimization algorithm (IChOA) for hyperparameter tuning and feature refinement. The proposed method is evaluated using three recent and comprehensive benchmark datasets, WUSTL-IIoT-2021, EdgeIIoTset, and TON_IoT, widely recognized as standard testbeds for IIoT intrusion detection research. Extensive experiments are conducted to assess the model’s performance compared to several state-of-the-art techniques, including standard GAN, convolutional neural network (CNN), deep belief network (DBN), time-series transformer (TST), bidirectional encoder representations from transformers (BERT), and extreme gradient boosting (XGBoost). Evaluation metrics include accuracy, recall, AUC, and run time. Results demonstrate that the proposed Transformer–GAN–AE framework outperforms all baseline methods, achieving a best accuracy of 98.92%, along with superior recall and AUC values. The integration of IChOA enhances GAN stability and accelerates training by optimizing hyperparameters. Together with the transformer for temporal feature extraction and the AE for denoising, the hybrid architecture effectively addresses complex, imbalanced intrusion data. The proposed optimized Transformer–GAN–AE model demonstrates high accuracy and robustness, offering a scalable solution for real-world Edge and IIoT intrusion detection. Full article

Landslides are among the most destructive geological hazards, necessitating precise landslide susceptibility mapping (LSM) for effective risk management. This study focuses on the northeastern region of Leshan City and investigates the influence of various non-landslide sampling strategies and machine learning (ML) models on LSM performance. Ten landslide conditioning factors, selected by SHAP analysis, and six models were utilized: Convolutional neural networks (CNNs), Long Short-Term Memory (LSTM), CNN-LSTM, CNN-LSTM with an attention mechanism (AM), Random Forest (RF), and eXtreme Gradient Boosting combined with Logistic Regression (XGBoost-LR). Three non-landslide sampling strategies were designed, with the certainty factor-based approach demonstrating superior performance by effectively capturing geological and physical characteristics, applying spatial constraints to exclude high-risk zones, and achieving improved mean squared error (MSE) and area under the curve (AUC) values. The results reveal that traditional ML models struggle with complex nonlinear relationships and imbalanced datasets, often leading to high false positive rates. In contrast, deep learning (DL) models—particularly CNN-LSTM-AM—achieved the best performance, with an AUC of 0.9044 and enhanced balance in accuracy, precision, recall, and Kappa. These improvements are attributed to the model’s ability to extract static spatial features (via CNNs), capture dynamic temporal patterns (via LSTM), and emphasize key features through the attention mechanism. This integrated architecture enhances the capacity to process heterogeneous data and extract landslide-relevant features. Overall, optimizing non-landslide sampling strategies, incorporating comprehensive geophysical information, enforcing spatial constraints, and enhancing feature extraction capabilities are essential for improving the accuracy and reliability of LSM. Full article

The reduction in disaster risk in urban regions due to natural hazards (e.g., earthquakes, landslides, floods, and tropical cyclones) is primarily a development matter that must be treated within the scope of a broader urban development framework. Natural hazard assessment is one of the turning points in mitigating disaster risk, which typically contributes to stronger urban resilience and more sustainable urban development. Regarding this challenge, our research proposes a new approach in the signal processing chain and feature extraction from microtremor data that focuses mainly on the Horizontal-to-Vertical Spectral Ratio (HVSR) so as to assess liquefaction potential as a natural hazard using AI. The key raw seismic features of site amplification and resonance are extracted from the data via bandpass filtering, Fourier Transformation (FT), the calculation of the HVSR, and smoothing through the use of moving averages. The main novelty is the integration of machine learning, particularly stacked ensemble learning, for liquefaction potential classification from imbalanced seismic datasets. For this approach, several models are used to consider class imbalance, enhancing classification performance and offering better insight into liquefaction risk based on microtremor data. Then, the paper proposes a liquefaction detection method based on deep learning with an autoencoder and stacked classifiers. The autoencoder compresses data into the latent space, underlining the liquefaction features classified by the multi-layer perceptron (MLP) classifier and eXtreme Gradient Boosting (XGB) classifier, and the meta-model combines these outputs to put special emphasis on rare liquefaction events. This proposed methodology improved the detection of an imbalanced dataset, although challenges remain in both interpretability and computational complexity. We created a synthetic dataset of 1000 samples using realistic feature ranges that mimic the Rif data region to test model performance and conduct sensitivity analysis. Key seismic and geotechnical variables were included, confirming the amplification factor (Af) and seismic vulnerability index ($K_g$) as dominant predictors and supporting model generalizability in data-scarce regions. Our proposed method for liquefaction potential classification achieves 100% classification accuracy, 100% precision, and 100% recall, providing a new baseline. Compared to existing models such as XGB and MLP, the proposed model performs better in all metrics. This new approach could become a critical component in assessing liquefaction hazard, contributing to disaster mitigation and urban planning. Full article

The application of deep learning in side-channel analysis faces critical challenges arising from dispersed public datasets—i.e., datasets collected from heterogeneous sources and platforms with varying formats, labeling schemes, and sampling settings—and insufficient sample distribution uniformity, characterized by imbalanced class distributions and long-tailed label samples. This paper presents a systematic analysis of symmetric cryptographic AES side-channel leakage datasets, examining how these issues impact the performance of deep learning-based side-channel analysis (DL-SCA) models. We analyze over 10 widely used datasets, including DPA Contest and ASCAD, and highlight key inconsistencies via visualization, statistical metrics, and model performance evaluations. For instance, the DPA_v4 dataset exhibits extreme label imbalance with a long-tailed distribution, while the ASCAD datasets demonstrate missing leakage features. Experiments conducted using CNN and Transformer models show that such imbalances lead to high accuracy for a few labels (e.g., label 14 in DPA_v4) but also extremely poor accuracy (<0.5%) for others, severely degrading generalization. We propose targeted improvements through enhanced data collection protocols, training strategies, and feature alignment techniques. Our findings emphasize that constructing balanced datasets covering the full key space is vital to achieving robust and generalizable DL-SCA performance. This work contributes both empirical insights and methodological guidance for standardizing the design of side-channel datasets. Full article

AI-oriented quality inspection in manufacturing often faces highly imbalanced data, as defective products are rare, and there are limited possibilities for data augmentation. This paper presents a systematic comparison between Deep Transfer Learning (DTL) and Contrastive Learning (CL) under such challenging conditions, addressing a critical gap in the industrial machine learning literature. We focus on a galvanized steel coil quality classification task with acceptable vs. defective classes, where the vast majority of samples (>95%) are acceptable. We implement a DTL approach using strategically fine-tuned YOLOv8 models pre-trained on large-scale datasets, and a CL approach using a Siamese network with multi-reference design to learn robust similarity metrics for one-shot classification. Experiments employ k-fold cross-validation and a held-out gold-standard test set of coil images, with statistical validation through bootstrap resampling. Results demonstrate that DTL significantly outperforms CL, achieving higher overall accuracy (81.7% vs. 61.6%), F1-score (79.2% vs. 62.1%), and precision (91.3% vs. 61.0%) on the challenging test set. Computational analysis reveals that DTL requires 40% less training time and 25% fewer parameters while maintaining superior generalization capabilities. We provide concrete guidance on when to select DTL over CL based on dataset characteristics, demonstrating that DTL is particularly advantageous when data augmentation is constrained by domain-specific spatial patterns. Additionally, we introduce a novel adaptive inspection framework that integrates human-in-the-loop feedback with domain adaptation techniques for continuous model improvement in production environments. Our comprehensive comparative analysis offers empirically validated insights into performance trade-offs between these approaches under extreme class imbalance, providing valuable direction for practitioners implementing industrial quality inspection systems with limited, skewed datasets. Full article

Amidst global economic fluctuations and escalating geopolitical risks, gold futures, as a pivotal safe-haven asset, demonstrate price dynamics that directly impact investor decision-making and risk mitigation effectiveness. Traditional forecasting models face significant limitations in capturing long-term trends, addressing abrupt volatility, and mitigating multi-source noise within complex market environments characterized by nonlinear interactions and extreme events. Current research predominantly focuses on single-model approaches (e.g., ARIMA or standalone neural networks), inadequately addressing the synergistic effects of multimodal market signals (e.g., cross-market index linkages, exchange rate fluctuations, and policy shifts) and lacking the systematic validation of model robustness under extreme events. Furthermore, feature selection often relies on empirical assumptions, failing to uncover non-explicit correlations between market factors and gold futures prices. A review of the global literature reveals three critical gaps: (1) the insufficient integration of temporal dependency and global attention mechanisms, leading to imbalanced predictions of long-term trends and short-term volatility; (2) the neglect of dynamic coupling effects among cross-market risk factors, such as energy ETF-metal market spillovers; and (3) the absence of hybrid architectures tailored for high-frequency noise environments, limiting predictive utility for decision support. This study proposes a three-stage LSTM–Transformer–XGBoost fusion framework. Firstly, XGBoost-based feature importance ranking identifies six key drivers from thirty-six candidate indicators: the NASDAQ Index, S&P 500 closing price, silver futures, USD/CNY exchange rate, China’s 1-year Treasury yield, and Guotai Zhongzheng Coal ETF. Second, a dual-channel deep learning architecture integrates LSTM for long-term temporal memory and Transformer with multi-head self-attention to decode implicit relationships in unstructured signals (e.g., market sentiment and climate policies). Third, rolling-window forecasting is conducted using daily gold futures prices from the Shanghai Futures Exchange (2015–2025). Key innovations include the following: (1) a bidirectional LSTM–Transformer interaction architecture employing cross-attention mechanisms to dynamically couple global market context with local temporal features, surpassing traditional linear combinations; (2) a Dynamic Hierarchical Partition Framework (DHPF) that stratifies data into four dimensions (price trends, volatility, external correlations, and event shocks) to address multi-driver complexity; (3) a dual-loop adaptive mechanism enabling endogenous parameter updates and exogenous environmental perception to minimize prediction error volatility. This research proposes innovative cross-modal fusion frameworks for gold futures forecasting, providing financial institutions with robust quantitative tools to enhance asset allocation optimization and strengthen risk hedging strategies. It also provides an interpretable hybrid framework for derivative pricing intelligence. Future applications could leverage high-frequency data sharing and cross-market risk contagion models to enhance China’s influence in global gold pricing governance. Full article

The Internet plays a vital role in the exchange of information in society. Maintaining the security and robustness of the Internet anomaly detection in Border Gateway Protocol (BGP) traffic is very important so that stable routing services can be ensured. The existing solutions are based on the classical machine learning (ML) models, which need to be advanced. In this study, a revolutionary technique that utilizes the Extreme Learning Machine (ELM) to enhance the detection of anomalies in the dynamic environment of the Border Gateway Protocol (BGP), particularly when faced with highly imbalanced class distributions, was used. The combination of imbalanced class distribution and BGP’s dynamic nature often leads to the suboptimal performance of classifiers. Our proposed solution aims to address this imbalance issue by dividing the dominant classes into multiple sub-classes. This division is achieved through optimal partitioning (OP), which involves segmenting the samples from the majority class into different segments to approximate the size of the minority class. As a result, diversified classes are created to train the ELM classifier. In order to assess the effectiveness of the proposed (OP-ELM) model, the RIPE and BCNET datasets were utilized. These trace files were processed using MATLAB to extract and organize the necessary features, thereby generating suitable datasets for analysis, which are referred to as Dataset-1 and Dataset-2. The experimental findings exhibit noteworthy improvements in performance when contrasted with prior methodologies, thereby highlighting the efficacy of our innovative approach in tackling the obstacles associated with anomaly detection in BGP networks. Full article

With the rapid growth of digital computing, communication, and storage devices applied in various real-world scenarios, more and more data have been collected and stored to drive the development of machine learning techniques. It is also noted that the data that emerge in real-world applications tend to become more complex. In this study, we regard a complex data type, i.e., multi-label data, acquired with a time constraint in a dynamic online scenario. Under such conditions, constructing a learning model has to face two challenges: it requires dynamically adapting the variances in label correlations and imbalanced data distributions and it requires more labeling consumptions. To solve these two issues, we propose a novel online multi-label active learning (OMAL) algorithm that considers simultaneously adopting uncertainty (using the average entropy of prediction probabilities) and diversity (using the average cosine distance between feature vectors) as an active query strategy. Specifically, to focus on label correlations, we use a classifier chain (CC) as the multi-label learning model and design a label co-occurrence ranking strategy to arrange label sequence in CC. To adapt the naturally imbalanced distribution of the multi-label data, we select weight extreme learning machine (WELM) as the basic binary-class classifier in CC. The experimental results on ten benchmark multi-label datasets that were transformed into streams show that our proposed method is superior to several popular static multi-label active learning algorithms in terms of both the Macro-F1 and Micro-F1 metrics, indicating its specifical adaptions in the dynamic data stream environment. Full article

Landslides frequently occur in the Xinjiang Uygur Autonomous Region of China due to its complex geological environment, posing serious risks to human safety and economic stability. Existing studies widely use machine learning models for landslide susceptibility prediction. However, they often fail to capture the threshold and interaction effects among environmental factors, limiting their ability to accurately identify high-risk zones. To address this gap, this study employed a gradient boosting decision tree (GBDT) model to identify critical thresholds and interaction effects among disaster-causing factors, while mapping the spatial distribution of landslide susceptibility based on 20 covariates. The performance of this model was compared with that of a support vector machine and deep neural network models. Results showed that the GBDT model achieved superior performance, with the highest AUC and recall values among the tested models. After applying clustering algorithms for non-landslide sample selection, the GBDT model maintained a high recall value of 0.963, demonstrating its robustness against imbalanced datasets. The GBDT model identified that 8.86% of Xinjiang’s total area exhibits extremely high or high landslide susceptibility, mainly concentrated in the Tianshan and Altai mountain ranges. Lithology, precipitation, profile curvature, the Modified Normalized Difference Water Index (MNDWI), and vertical deformation were identified as the primary contributing factors. Threshold effects were observed in the relationships between these factors and landslide susceptibility. The probability of landslide occurrence increased sharply when precipitation exceeded 2500 mm, vertical deformation was greater than 0 mm a⁻¹, or the MNDWI values were extreme (<−0.4, >0.2). Additionally, this study confirmed bivariate interaction effects. Most interactions between factors exhibited positive effects, suggesting that combining two factors enhances classification performance compared with using each factor independently. This finding highlights the intricate and interdependent nature of these factors in landslide susceptibility. These findings emphasize the necessity of incorporating threshold and interaction effects in landslide susceptibility assessments, offering practical insights for disaster prevention and mitigation. Full article

The implementation of comprehensive security measures is a critical factor in the rapid growth of industrial control networks. Federated Learning has emerged as a viable solution for safeguarding privacy in machine learning. The effectiveness of pattern detection in models is diminished as a result of the difficulty in extracting attack information from extremely large datasets and obtaining an adequate number of examples for specific types of attacks. A robust Federated Learning method, CGFL, is introduced in this study to resolve the challenges presented by data distribution discrepancies and client class imbalance. By employing a data generation strategy to generate balanced datasets for each client, CGFL enhances the global model. It employs a data generator that integrates artificially generated data with the existing data from local clients by employing label correction and data generation techniques. The geometric median aggregation technique was implemented to enhance the security of the aggregation process. The model was simulated and evaluated using the CIC-IDS2017 dataset, NSL-KDD dataset, and CSE-CIC-IDS2018 dataset. The experimental results indicate that CGFL does an effective job of enhancing the accuracy of ICS attack detection in Federated Learning under imbalanced sample conditions. Full article

Solar photovoltaic (SPV) arrays play a pivotal role in advancing clean and sustainable energy systems, with a worldwide total installed capacity of 1.6 terawatts and annual investments reaching USD 480 billion in 2023. However, climate disaster effects, particularly extremely hot weather events, can compromise the performance and resilience of SPV panels through thermal deterioration and degradation, which may lead to lessened operational life and potential failure. These heatwave-related consequences highlight the need for timely inspection and precise anomaly diagnosis of SPV panels to ensure optimal energy production. This case study focuses on intelligent remote inspection by employing aerial radiometric infrared thermography within a predictive maintenance framework to enhance diagnostic monitoring and early scrutiny capabilities for SPV power plant sites. The proposed methodology leverages pre-trained deep learning (DL) algorithms, enabling a deep transfer learning approach, to test the effectiveness of multiclass classification (or diagnosis) of various thermal anomalies of the SPV panel. This case study adopted a highly imbalanced 6-class thermographic radiometric dataset (floating-point temperature numerical values in degrees Celsius) for training and validating the pre-trained DL predictive classification models and comparing them with a customized convolutional neural network (CNN) ensembled model. The performance metrics demonstrate that among selected pre-trained DL models, the MobileNetV2 exhibits the highest F1 score (0.998) and accuracy (0.998), followed by InceptionV3 and VGG16, which recorded an F1 score of 0.997 and an accuracy of 0.998 in performing the smart inspection of 6-class thermal anomalies, whereas the customized CNN ensembled model achieved both a perfect F1 score (1.000) and accuracy (1.000). Furthermore, to create trust in the intelligent inspection system, we investigated the pre-trained DL predictive classification models using perceptive explainability to display the most discriminative data features, and mathematical-structure-based interpretability to portray multiclass feature clustering. Full article

In the field of ensemble learning, bagging and stacking are two widely used ensemble strategies. Bagging enhances model robustness through repeated sampling and weighted averaging of homogeneous classifiers, while stacking improves classification performance by integrating multiple models using meta-learning strategies, taking advantage of the diversity of heterogeneous classifiers. However, the fixed weight distribution strategy in traditional bagging methods often has limitations when handling complex or imbalanced datasets. This paper combines the concept of heterogeneous classifier integration in stacking with the weighted averaging strategy of bagging, proposing a new adaptive weight distribution approach to enhance bagging’s performance in heterogeneous ensemble settings. Specifically, we propose three weight generation functions with “high at both ends, low in the middle” curve shapes and demonstrate the superiority of this strategy over fixed weight methods on two datasets. Additionally, we design a specialized neural network, and by training it adequately, validate the rationality of the proposed adaptive weight distribution strategy, further improving the model’s robustness. The above methods are collectively called func-bagging. Experimental results show that func-bagging has an average 1.810% improvement in extreme performance compared to the base classifier, and is superior to stacking and bagging methods. It also has better dataset adaptability and interpretability than stacking and bagging. Therefore, func-bagging is particularly effective in scenarios with class imbalance and is applicable to classification tasks with imbalanced classes, such as anomaly detection. Full article