Search Results (84)

Background: Anemia, a common health disorder affecting populations globally, demands timely and accurate diagnosis for treatment to be effective. The aim of this paper is to detect and classify four types of anemia: hgb, iron-deficiency, folate-deficiency, and B12-deficiency anemia. Methods: This paper proposes an ontology-enhanced machine learning (ML) framework to classify types of anemia from CBC data obtained from Kaggle, which contains 15,300 patient records. It evaluates the effects of classical versus deep classifiers on imbalanced and oversampled training samples. Tests include KNN, SVM, DT, RF, CNN, CNN+SVM, CNN+RF, and XGBoost. Another interesting contribution is the use of ontological reasoning via SPARQL queries to semantically enrich clinical features with categories like “Low Hemoglobin” or “Macrocytic MCV”. These semantic features were then used in both classical (SVM) and deep hybrid models (CNN+SVM). Results: Ontology-enhanced and CNN hybrid models perform competitively when paired with ROS or ADASYN, but their performance degrades significantly on the original dataset. There were tremendous performance gains with ontology-enhanced models in that Onto-CNN+SVM achieved an F1-score (1.00) for all the four types of anemia under ROS sampling, while Onto-SVM exhibited more than 20% improvement in F1-scores for minority categories like folate and B12 when compared to baseline models, except XGBoost. Conclusions: Ontology-driven knowledge coalescence has been shown to improve classification results; however, XGBoost consistently outperformed all other classifiers across all data conditions, making it the most robust and reliable model for clinically relevant decision-support systems in anemia diagnosis. Full article

Agricultural pest detection is critical for crop protection and food security, yet existing methods suffer from low computational efficiency and poor generalization due to imbalanced data distribution, minimal inter-class variations among pest categories, and significant intra-class differences. To address the high computational complexity and inadequate feature representation in traditional convolutional networks, this study proposes MA-YOLO, an agricultural pest detection model based on multi-scale fusion and attention mechanisms. The SDConv module reduces computational costs through depthwise separable convolution and dynamic group convolution while enhancing local feature extraction. The LDSPF module captures multi-scale information via parallel dilated convolutions with spatial attention mechanisms and dual residual connections. The ASCC module improves feature discriminability by establishing an adaptive triple-weight system for global, channel, and spatial semantic responses. The MDF module balances efficiency and multi-scale feature extraction using multi-branch depthwise separable convolution and soft attention-based dynamic weighting. Experimental results demonstrate detection accuracies of 65.4% and 73.9% on the IP102 and Pest24 datasets, respectively, representing improvements of 2% and 1.8% over the original YOLOv11s network. These results establish MA-YOLO as an effective solution for automated agricultural pest monitoring with applications in precision agriculture and crop protection systems. Full article

In industrial scenarios, bearing fault diagnosis often suffers from data scarcity and class imbalance, which significantly hinders the generalization performance of data-driven models. While generative adversarial networks (GANs) have shown promise in data augmentation, their efficacy deteriorates in the presence of multi-category and structurally complex fault distributions. To address these challenges, this paper proposes a novel fault diagnosis framework based on a Multi-Domain Feature Transformer GAN (MDFT-GAN). Specifically, raw vibration signals are transformed into 2D RGB representations via joint time-domain, frequency-domain, and time–frequency-domain mappings, effectively encoding multi-perspective fault signatures. A Transformer-based feature extractor, integrated with Efficient Channel Attention (ECA), is embedded into both the generator and discriminator to capture global dependencies and channel-wise interactions, thereby enhancing the representation quality of synthetic samples. Furthermore, a gradient penalty (GP) term is introduced to stabilize adversarial training and suppress mode collapse. To improve classification performance, an Enhanced Hybrid Visual Transformer (EH-ViT) is constructed by coupling a lightweight convolutional stem with a ViT encoder, enabling robust and discriminative fault identification. Beyond performance metrics, this work also incorporates a Grad-CAM-based interpretability scheme to visualize hierarchical feature activation patterns within the discriminator, providing transparent insight into the model’s decision-making rationale across different fault types. Extensive experiments on the CWRU and Jiangnan University (JNU) bearing datasets validate that the proposed method achieves superior diagnostic accuracy, robustness under limited and imbalanced conditions, and enhanced interpretability compared to existing state-of-the-art approaches. Full article

The Mega-Sub Controlled Structure System (MSCSS) represents an innovative category of seismic-resistant super high-rise building structural systems, and exploring its damage mechanisms and identification methods is crucial. Nonetheless, the prevailing methodologies for establishing criteria for structural damage are deficient in providing a lucid and comprehensible representation of the actual damage sustained by edifices during seismic events. To address these challenges, the present study develops a finite element model of the MSCSS, conducts nonlinear time-history analyses to assess the MSCSS’s response to prolonged seismic motion records, and evaluates its damage progression. Moreover, considering the genuine damage conditions experienced by the MSCSS, damage working scenarios under seismic forces were formulated to delineate the damage patterns. A convolutional neural network recognition framework based on stacking ensemble learning is proposed for extracting damage features from the temporal response of structural systems and achieving damage classification. This framework accounts for the temporal and spatial interrelations among sensors distributed at disparate locations within the structure and addresses the issue of data imbalance arising from a limited quantity of damaged samples. The research results indicate that the proposed method achieves an accuracy of over 98% in dealing with damage in imbalanced datasets, while also demonstrating remarkable robustness. Full article

Aiming at the limitations of existing multisensor fault diagnosis methods for rolling bearings in real industrial scenarios, this paper proposes an innovative intuitionistic fuzzy weighted least squares twin support higher-order tensor machine (IFW-LSTSHTM) model, which realizes a breakthrough in the noise robustness, adaptability to the working conditions, and the class imbalance processing capability. First, the multimodal feature tensor is constructed: the fourier synchro-squeezed transform is used to convert the multisensor time-domain signals into time–frequency images, and then the tensor is reconstructed to retain the three-dimensional structural information of the sensor coupling relationship and time–frequency features. The nonlinear feature mapping strategy combined with Tucker decomposition effectively maintains the high-order correlation of the feature tensor. Second, the adaptive sample-weighting mechanism is developed: an intuitionistic fuzzy membership score assignment scheme with global–local information fusion is proposed. At the global level, the class contribution is assessed based on the relative position of the samples to the classification boundary; at the local level, the topological structural features of the sample distribution are captured by K-nearest neighbor analysis; this mechanism significantly improves the recognition of noisy samples and the handling of class-imbalanced data. Finally, a dual hyperplane classifier is constructed in tensor space: a structural risk regularization term is introduced to enhance the model generalization ability and a dynamic penalty factor is set to set adaptive weights for different categories. A linear equation system solving strategy is adopted: the nonparallel hyperplane optimization is converted into matrix operations to improve the computational efficiency. The extensive experimental results on the two rolling bearing datasets have verified that the proposed method outperforms existing solutions in diagnostic accuracy and stability. Full article

Imbalanced data are a non-trivial problem in deep learning. The high variability in the number of samples composing each category might force learning procedures to become biased towards classes with major cardinality and disregard classes with low instances. To overcome such limitations, common strategies involve data balancing using resampling techniques. The cardinality of overnumbered categories is often lowered by sample deletion, thus reducing the data space where the model can learn from. This paper introduces a new approach based on data balancing without sample deletion, allowing for biasing reduction in instance localization and classification tasks. The method is a multi-stage pipeline starting with data cleaning and data filtering steps and ending with the actual data balancing process, during which overnumbered samples are not deleted but divided into multiple sub-classes. In this way, the model can learn from balanced data distribution in which some classes have a high correlation factor. To evaluate the effectiveness of the method in real-life scenarios, a case study in the field of precision agriculture has been developed, motivated by the fact that the publicly available datasets for pest classification often reflect the real-world imbalanced distribution of pests, making the task challenging. Two models for the localization and recognition of pests belonging to several species are also indicated. The obtained results show the method’s validity as the performance both in the detection and classification tasks outperforms the state-of-the-art methods. The general nature of the conceived balancing technique may make the approach useful in other application fields. Full article

Traditional node classification is typically conducted in a closed-world setting, where all labels are known during training, enabling graph neural network methods to achieve high performance. However, in real-world scenarios, the constant emergence of new categories and updates to existing labels can result in some nodes no longer fitting into any known category, rendering closed-world classification methods inadequate. Thus, open-world classification becomes essential for graph data. Due to the inherent diversity of graph data in the open-world setting, it is common for the number of nodes with different labels to be imbalanced, yet current models are ineffective at handling such imbalance. Additionally, when there are too many or too few nodes from unseen classes, classification performance typically declines. Motivated by these observations, we propose a solution to address the challenges of open-world node classification and introduce a model named OWNC. This model incorporates a dual-embedding interaction training framework and a generator–discriminator architecture. The dual-embedding interaction training framework reduces label loss and enhances the distinction between known and unseen samples, while the generator–discriminator structure enhances the model’s ability to identify nodes from unseen classes. Experimental results on three benchmark datasets demonstrate the superior performance of our model compared to various baseline algorithms, while ablation studies validate the underlying mechanisms and robustness of our approach. Full article

With the rapid advancement of network technologies, cyberthreats have become increasingly sophisticated, posing significant challenges to traditional intrusion detection systems. Conventional machine learning and deep learning approaches frequently experience performance degradation when confronted with imbalanced datasets and novel attack vectors. To address these limitations, this study proposes a deep learning-based intrusion detection framework that employs feature fusion through incremental transfer learning between source and target domains. The proposed architecture integrates convolutional neural networks (CNNs) with an attention mechanism to extract and aggregate salient features, thereby enhancing the model’s discriminative capacity between normal traffic and various network attack categories. Experimental results demonstrate that the proposed model achieves a detection accuracy of 94.21% even when trained on only 33% of the available data, outperforming conventional models. These findings underscore the effectiveness of the proposed feature fusion strategy via transfer learning in improving detection capabilities within dynamic and evolving cyberthreat environments. Full article

Emotion classification in natural language processing (NLP) has recently witnessed significant advancements. However, class imbalance in emotion datasets remains a critical challenge, as dominant emotion categories tend to overshadow less frequent ones, leading to biased model predictions. Traditional techniques, such as undersampling and oversampling, offer partial solutions. More recently, synthetic data generation using large language models (LLMs) has emerged as a promising strategy for augmenting minority classes and improving model robustness. In this study, we investigate the impact of synthetic data augmentation on German-language emotion classification. Using an imbalanced dataset, we systematically evaluate multiple balancing strategies, including undersampling overrepresented classes and generating synthetic data for underrepresented emotions using a GPT-4–based model in a few-shot prompting setting. Beyond enhancing model performance, we conduct a detailed linguistic analysis of the synthetic samples, examining their lexical diversity, syntactic structures, and semantic coherence to determine their contribution to overall model generalization. Our results demonstrate that integrating synthetic data significantly improves classification performance, particularly for minority emotion categories, while maintaining overall model stability. However, our linguistic evaluation reveals that synthetic examples exhibit reduced lexical diversity and simplified syntactic structures, which may introduce limitations in certain real-world applications. These findings highlight both the potential and the challenges of synthetic data augmentation in emotion classification. By providing a comprehensive evaluation of balancing techniques and the linguistic properties of generated text, this study contributes to the ongoing discourse on improving NLP models for underrepresented linguistic phenomena. Full article

Background and Objective: Using echocardiogram data for cardiovascular disease (CVD) can lead to difficulties due to imbalanced datasets, leading to biased predictions. Machine learning models can enhance prognosis accuracy, but their effectiveness is influenced by optimal feature selection and robust classification techniques. This study introduces an event-based self-similarity approach to enhance automatic feature selection approach for imbalanced echocardiogram data. Critical features correlated with disease progression were identified by leveraging self-similarity patterns. This study used an echocardiogram dataset, visual presentations of high-frequency sound wave signals, and data of patients with heart disease who are treated using three treatment methods: catheter ablation, ventricular defibrillator, and drug control—over the course of three years. Methods: The dataset was classified into nine categories and Recursive Feature Elimination (RFE) was applied to identify the most relevant features, reducing model complexity while maintaining diagnostic accuracy. Machine learning classification models, including XGBoost and CATBoost, were trained and evaluated. Results: Both models achieved comparable accuracy values, 84.3% and 88.4%, respectively, under different normalization techniques. To further optimize performance, the models were combined into a voting ensemble, improving feature selection and predictive accuracy. Four essential features—age, aorta (AO), left ventricular (LV), and left atrium (LA)—were identified as critical for prognosis and were found in Random Forest (RF)-voting ensemble classifier. The results underscore the importance of feature selection techniques in handling imbalanced datasets, improving classification robustness, and reducing bias in automated prognosis systems. Conclusions: Our findings highlight the potential of machine learning-driven echocardiogram analysis to enhance patient care by providing accurate, data-driven assessments. Full article

Hierarchical classification, which organizes items into structured categories and subcategories, has emerged as a powerful solution for handling large and complex datasets. However, traditional flat classification approaches often overlook the hierarchical dependencies between classes, leading to suboptimal predictions and limited interpretability. This paper addresses these challenges by proposing a novel integration of tree-based models with hierarchical-aware split criteria through adjusted entropy calculations. The proposed method calculates entropy at multiple hierarchical levels, ensuring that the model respects the taxonomic structure during training. This approach aligns statistical optimization with class semantic relationships, enabling more accurate and coherent predictions. Experiments conducted on real-world datasets structured according to the GS1 Global Product Classification (GPC) system demonstrate the effectiveness of our method. The proposed model was applied using tree-based ensemble methods combined with the newly developed hierarchy-aware metric Penalized Information Gain (PIG). PIG was implemented with level-wise entropy adjustments, assigning greater weight to higher hierarchical levels to maintain the taxonomic structure. The model was trained and evaluated on two real-world datasets based on the GS1 Global Product Classification (GPC) system. The final dataset included approximately 30,000 product descriptions spanning four hierarchical levels. An 80-20 train–test split was used, with model hyperparameters optimized through 5-fold cross-validation and Bayesian search. The experimental results showed a 12.7% improvement in classification accuracy at the lowest hierarchy level compared to traditional flat classification methods, with significant gains in datasets featuring highly imbalanced class distributions and deep hierarchies. The proposed approach also increased the F1 score by 12.6%. Despite these promising results, challenges remain in scaling the model for very large datasets and handling classes with limited training samples. Future research will focus on integrating neural networks with hierarchy-aware metrics, enhancing data augmentation to address class imbalance, and developing real-time classification systems for practical use in industries such as retail, logistics, and healthcare. Full article

Predicting traffic speed is an important issue, especially in urban regions. Precise long-term forecasts would enable individuals to conserve time and financial resources while diminishing air pollution. Despite extensive research on this subject, to our knowledge, no publications investigate or tackle the issue of imbalanced datasets in traffic speed prediction. Traffic speed data are often biased toward high numbers because low traffic speeds are infrequent. The temporal aspect of traffic carries two important factors for low-speed value. The daily population movement, captured by the time of day, and the weather data, recorded by month, are both considered in this study. Hour-wise Pattern Organization and Month-wise Pattern Organization techniques were devised, which organize the speed data using these two factors as a metric with a view to providing a superior representation of data characteristics that are in the minority. In addition to these two methods, a Speed-wise Pattern Organization strategy is proposed, which arranges train and test samples by setting boundaries on speed while taking the volatile nature of traffic into consideration. We evaluated these strategies using four popular model types: long short-term memory (LSTM), gated recurrent unit networks (GRUs), bi-directional LSTM, and convolutional neural networks (CNNs). GRU had the best performance, achieving a MAPE (Mean Absolute Percentage Error) of 13.51%, whereas LSTM demonstrated the lowest performance, with a MAPE of 13.74%. We validated their robustness through our studies and observed improvements in model accuracy across all categories. While the average improvement was approximately 4%, our methodologies demonstrated superior performance in low-traffic speed scenarios, augmenting model prediction accuracy by 11.2%. The presented methodologies in this study are applied in the pre-processing steps, allowing their application with various models and additional pre-processing procedures to attain comparable performance improvements. Full article

Insulation pull rods used in gas-insulated switchgear (GIS) inevitably contain the micro defects generated during production. The intelligent identification method, which requires large datasets with a balanced distribution of defect types, is regarded as the prevailing way to avoid insulation faults. However, the number of defective pull rods is limited, and the occurrence of different types of defects is highly imbalanced in actual production, leading to poor recognition performance. Thus, this work proposes a data preprocessing method for the insulation pull rod defect feature dataset. In this work, the YOLOv5s algorithm is used to detect defects in insulation pull rod images, creating a dataset with five defect categories. Two preprocessing methods for impurities and bubbles are introduced, including copy–paste within images and bounding box corrections for hair-like impurities. The results show that these two methods can specifically enhance small-sized defect targets while maintaining the detection performance for other types of targets. In contrast, the proposed method integrates copy–paste within images with Mosaic data augmentation and corrects bounding boxes for hair-like impurities significantly improving the model’s performance. Full article

Multiclass classification in machine learning often faces significant challenges due to unbalanced datasets. This situation leads to biased predictions and reduced model performance. This research addresses this issue by proposing a novel approach that combines convolutional neural networks (CNNs) with class weights and early-stopping techniques. The motivation behind this study stems from the need to improve model performance, especially for minority classes, which are often neglected in existing methodologies. Although various strategies such as resampling, ensemble methods, and data augmentation have been explored, they frequently have limitations based on the characteristics of the data and the specific model type. Our approach focuses on optimizing the loss function via class weights to give greater importance to minority classes. Therefore, it reduces bias and improves overall accuracy. Furthermore, we implement early stopping to avoid overfitting and improve generalization by continuously monitoring the validation performance during training. This study contributes to the body of knowledge by demonstrating the effectiveness of this combined technique in improving multiclass classification in unbalanced scenarios. The proposed model is tested for oil palm leaves analysis to identify deficiencies in nitrogen (N), boron (B), magnesium (Mg), and potassium (K). The CNN model with three layers and a SoftMax activation function was trained for 200 epochs each. The analysis compared three scenarios: training with the imbalanced dataset, training with class weights, and training with class weights and early stopping. The results showed that applying class weights significantly improved the classification accuracy, with a trade-off in other class predictions. This indicates that, while class weight has a positive overall impact, further strategies are necessary to improve model performance across all categories in this study. Full article

Background: Breast cancer screening through mammography interpretation is crucial for early detection and improved patient outcomes. However, the manual classification of mammograms using the BIRADS (Breast Imaging-Reporting and Data System) remains challenging due to subtle imaging features, inter-reader variability, and increasing radiologist workload. Traditional computer-aided detection systems often struggle with complex feature extraction and contextual understanding of mammographic abnormalities. To address these limitations, this study proposes MammoViT, a novel hybrid deep learning framework that leverages both ResNet50’s hierarchical feature extraction capabilities and Vision Transformer’s ability to capture long-range dependencies in images. Methods: We implemented a multi-stage approach utilizing a pre-trained ResNet50 model for initial feature extraction from mammogram images. To address the significant class imbalance in our four-class BIRADS dataset, we applied SMOTE (Synthetic Minority Over-sampling Technique) to generate synthetic samples for minority classes. The extracted feature arrays were transformed into non-overlapping patches with positional encodings for Vision Transformer processing. The Vision Transformer employs multi-head self-attention mechanisms to capture both local and global relationships between image patches, with each attention head learning different aspects of spatial dependencies. The model was optimized using Keras Tuner and trained using 5-fold cross-validation with early stopping to prevent overfitting. Results: MammoViT achieved 97.4% accuracy in classifying mammogram images across different BIRADS categories. The model’s effectiveness was validated through comprehensive evaluation metrics, including a classification report, confusion matrix, probability distribution, and comparison with existing studies. Conclusions: MammoViT effectively combines ResNet50 and Vision Transformer architectures while addressing the challenge of imbalanced medical imaging datasets. The high accuracy and robust performance demonstrate its potential as a reliable tool for supporting clinical decision-making in breast cancer screening. Full article