Search Results (1,210)

Background: The accurate classification of brain tumor subtypes from MRI scans is critical for timely diagnosis, yet the manual annotation of large datasets remains prohibitively labor-intensive. Method: We present SSPLNet (Semi-Supervised Pseudo-Labeling Network), a dual-branch deep learning framework that synergizes confidence-guided iterative pseudo-labelling with deep feature fusion to enable robust MRI-based tumor classification in data-constrained clinical environments. SSPLNet integrates a custom convolutional neural network (CNN) and a pretrained ResNet50 model, trained semi-supervised using adaptive confidence thresholds ($\tau = 0.98 \to 0.95 \to 0.90$) to iteratively refine pseudo-labels for unlabelled MRI scans. Feature representations from both branches are fused via a dense network, combining localized texture patterns with hierarchical deep features. Results: SSPLNet achieves state-of-the-art accuracy across labelled–unlabelled data splits ($90:10$ to $10:90$), outperforming supervised baselines in extreme low-label regimes (10:90) by up to 5.34% from Custom CNN and 5.58% from ResNet50. The framework reduces annotation dependence and with 40% unlabeled data maintains 98.17% diagnostic accuracy, demonstrating its viability for scalable deployment in resource-limited healthcare settings. Conclusions: Statistical Evaluation and Robustness Analysis of SSPLNet Performance confirms that SSPLNet’s lower error rate is not due to chance. The bootstrap results also confirm that SSPLNet’s reported accuracy falls well within the 95% CI of the sampling distribution. Full article

The medical imaging domain frequently encounters the dual challenges of annotation scarcity and class imbalance. A critical issue lies in effectively extracting information from limited labeled data while mitigating the dominance of head classes. The existing approaches often overlook in-depth modeling of sample relationships in low-dimensional spaces, while rigid or suboptimal dynamic thresholding strategies in pseudo-label generation are susceptible to noisy label interference, leading to cumulative bias amplification during the early training phases. To address these issues, we propose a semi-supervised medical image classification framework combining labeled data-contrastive learning with class-adaptive pseudo-labeling (CLCP-MT), comprising two key components: the semantic discrimination enhancement (SDE) module and the class-adaptive pseudo-label refinement (CAPR) module. The former incorporates supervised contrastive learning on limited labeled data to fully exploit discriminative information in latent structural spaces, thereby significantly amplifying the value of sparse annotations. The latter dynamically calibrates pseudo-label confidence thresholds according to real-time learning progress across different classes, effectively reducing head-class dominance while enhancing tail-class recognition performance. These synergistic modules collectively achieve breakthroughs in both information utilization efficiency and model robustness, demonstrating superior performance in class-imbalanced scenarios. Extensive experiments on the ISIC2018 skin lesion dataset and Chest X-ray14 thoracic disease dataset validate CLCP-MT’s efficacy. With only 20% labeled and 80% unlabeled data, our framework achieves a 10.38% F1-score improvement on ISIC2018 and a 2.64% AUC increase on Chest X-ray14 compared to the baselines, confirming its effectiveness and superiority under annotation-deficient and class-imbalanced conditions. Full article

In the field of facial expression recognition, facial expression features are highly similar to identity features, making facial expression recognition a major challenge for researchers, due to the high overlap of expressions and identity features in terms of space, structure, and feature expression. Moreover, the existing models lack a decoupling mechanism during extraction, making it difficult to understand the intrinsic meaning of expressions, which in turn affects the accuracy of expression recognition. To separate expression features from identity features, this paper proposes a method called the Contrastive Disentangled Generative Adversarial Network (CD-GAN). In this study, facial representation is defined as a combination of identity and expression, and different encoders are used to extract these features, respectively. Unlike the methods of direct feature extraction, this paper uses semi-supervised contrastive learning and adversarial training to distangle the entanglement of identity and expression features, thereby obtaining a disentangled expression representation. The model in this paper, through the method of de-entanglement, enables the model to learn the differences between expression and identity features, achieving the separation of expression and identity features. The experimental results show that the quantitative and qualitative results of the CD-GAN on field and laboratory datasets are comparable to those of the state-of-the-art methods. Full article

High-resolution remote sensing imagery offers detailed spatial and semantic insights into the Earth’s surface, yet its classification remains hindered by the limited availability of labeled data, primarily due to the substantial expense and time required for manual annotation. To overcome this challenge, we propose a hybrid semi-supervised tri-training framework that integrates traditional classification methods with a lightweight convolutional neural network. By combining heterogeneous learners with complementary strengths, the framework iteratively assigns pseudo-labels to unlabeled samples and collaboratively refines model performance in a co-training manner. Additionally, a landscape-metric-guided relearning module is introduced to incorporate spatial configuration and land cover composition, further enhancing the framework’s representational capacity and classification robustness. Experiments were conducted on four high-resolution multispectral datasets (QuickBird (QB), WorldView-2 (WV-2), GeoEye-1 (GE-1), and ZY-3) covering diverse land-cover types and spatial resolutions. The results demonstrate that the proposed method surpasses state-of-the-art baselines by 1.5–10% while generating more spatially coherent classification maps. Full article

Supervised deep learning methods have been widely utilized in hyperspectral image (HSI) classification tasks. However, acquiring a large number of reliably labeled samples to train deep networks is not always possible in practical HSI applications due to the time-consuming and laborious labeling process. Semi-supervised learning is commonly used in scenarios with insufficient labeled samples. However, semi-supervised models based on a pseudo-label strategy often suffer from error accumulation. To address this issue and improve HSI classification performance with few labeled samples, a semi-supervised deep learning approach is proposed. First, a multi-scale convolutional neural network with accurate discriminative capability is constructed to reduce pseudo-label errors. Then, a new pseudo-label generation strategy based on Dropout is presented, in which feature-level data augmentation is applied by considering multiple predictions of the unlabeled samples to mitigate the error accumulation problem. Finally, the multi-scale CNN and the new pseudo-label strategy are integrated into a unified model to improve HSI classification performance. The experimental results demonstrate that the proposed approach outperforms other semi-supervised methods in the literature on four real HSI datasets with limited labeled samples. Full article

Wildfires pose a regularly increasing threat to ecosystems and critical infrastructure. The severity of this threat is steadily increasing. The growing threat necessitates the development of technologies for rapid and accurate early detection. However, the prevailing fire point detection algorithms, including several deep learning models, are generally constrained by the inherent hard threshold limitations in their decision-making logic. As a result, these methods lack adaptability and robustness in complex and dynamic real-world scenarios. To address this challenge, the present paper proposes an innovative two-stage, semi-supervised anomaly detection framework. The framework initially employs a Transformer-based autoencoder, which serves to transform raw fire-free time-series data derived from satellite imagery into a multidimensional deep anomaly feature vector. Self-supervised learning achieves this transformation by incorporating both reconstruction error and latent space distance. In the subsequent stage, a semi-supervised XGBoost classifier, trained using an iterative pseudo-labeling strategy, learns and constructs an adaptive nonlinear decision boundary in this high-dimensional anomaly feature space to achieve the final fire point judgment. In a thorough validation process involving multiple real-world fire cases in Yunnan Province, China, the framework attained an F1 score of 0.88, signifying a performance enhancement exceeding 30% in comparison to conventional deep learning baseline models that employ fixed thresholds. The experimental results demonstrate that by decoupling feature learning from classification decision-making and introducing an adaptive decision mechanism, this framework provides a more robust and scalable new paradigm for constructing next-generation high-precision, high-efficiency wildfire monitoring and early warning systems. Full article

Electric micro-mobility modes, such as e-scooters and e-bikes, are increasingly used in urban areas, posing challenges for accurate travel mode detection in mobility studies. Traditional supervised learning approaches require large labeled datasets, which are costly and time-consuming to generate. To address this, we propose xSeCA, a semi-supervised convolutional autoencoder that leverages both labeled and unlabeled trajectory data to detect electric micro-mobility travel modes. The model architecture integrates representation learning and classification in a compact and efficient manner, enabling accurate detection even with limited annotated samples. We evaluate xSeCA on multi-city datasets, including Copenhagen, Tel Aviv, Beijing and San Francisco, and benchmark it against supervised baselines such as XGBoost. Results demonstrate that xSeCA achieves high classification accuracy while exhibiting strong generalization capabilities across different urban contexts. In addition to validating model performance, we examine key travel properties relevant to micro-mobility behavior. This research highlights the benefits of semi-supervised learning for scalable and transferable travel mode detection, offering practical implications for urban planning and smart mobility systems. Full article

Introduction: Stroke remains a major cause of disability worldwide, and precise identification of stroke lesions is essential for prognosis and rehabilitation planning. Machine learning has emerged as a powerful tool for automating stroke lesion segmentation and outcome prediction; however, these tasks are often studied in isolation. The two strategies are inherently interdependent since segmentation provides lesion-based features that directly inform prediction models. Methods: This narrative review synthesises studies published between 2010 and 2024 on the application of machine learning in stroke lesion segmentation and recovery forecasting. A total of 23 relevant studies were reviewed, including 10 focused on lesion segmentation and 13 on recovery prediction. Results: Convolutional Neural Networks (CNNs), including architectures such as U-Net, have improved segmentation accuracy on the Anatomical Tracings of Lesions After Stroke (ATLAS) V2 dataset; however, dataset bias and inconsistent evaluation metrics limit comparability. Integrating imaging-derived lesion characteristics with clinical features improves predictive accuracy at a higher level. Furthermore, semi-supervised and self-supervised methods enhanced performance where annotated datasets are scarce. Discussion: The review highlights the interdependence between segmentation and outcome prediction. Reliable segmentation provides biologically meaningful features that underpin recovery forecasting, while prediction tasks validate the clinical relevance of segmentation outputs. This bidirectional relationship underlines the need for unified pipelines integrating lesion segmentation with outcome prediction. Future research can improve generalisability and foster clinically robust models by advancing semi-supervised and self-supervised learning, bridging the gap between automated image analysis and patient-centred prognosis. Conclusion: Accurate lesion segmentation and outcome prediction should be viewed not as separate goals but as mutually reinforcing components of a single pipeline. Progress in segmentation strengthens recovery forecasting, while predictive modelling emphasises the clinical importance of segmentation outputs. This interdependence provides a pathway for developing more effective, generalisable, and relevant AI-driven stroke care tools. Full article

Illegal waste dumping poses a severe challenge to sustainable urban and regional development, undermining environmental integrity, public health, and the efficient use of resources. This study contributes to sustainability science by proposing a circular data feedback loop that enables dynamic, scalable, and cost-efficient monitoring and prevention of illegal dumping, aligned with the goals of sustainable waste governance. Historical data from the Slovenian illegal dumping register, UAV-based surveys and a newly developed application were used to update, monitor, and validate waste site locations. A comprehensive risk model, developed using machine learning methods, was created for the Municipality of Maribor (Slovenia). The modelling approach combined unsupervised and semi-supervised learning techniques, suitable for a positive-unlabeled (PU) dataset structure, where only confirmed illegal waste dumping sites were labeled. The approach demonstrates the feasibility of a circular data feedback loop integrating updated field data and predictive analytics to support waste management authorities and illegal waste dumping prevention. The fundamental characteristic of the stated approach is that each iteration of the loop improves the prediction of risk areas, providing a high-quality database for conducting targeted UAV overflights and consequently detecting locations of illegally dumped waste (LNOP) risk areas. At the same time, information on risk areas serves as the primary basis for each field detection of new LNOPs. The proposed model outperforms earlier approaches by addressing smaller and less conspicuous dumping events and by enabling systematic, technology-supported detection and prevention planning. Full article

The spread of misinformation during the COVID-19 pandemic raised widespread concerns about public health communication and media reliability. In this study, we focus on these issues as they manifested in Romanian-language media and employ Large Language Models (LLMs) to classify misinformation, with a particular focus on super-narratives—broad thematic categories that capture recurring patterns and ideological framings commonly found in pandemic-related fake news, such as anti-vaccination discourse, conspiracy theories, or geopolitical blame. While some of the categories reflect global trends, others are shaped by the Romanian cultural and political context. We introduce a novel dataset of fake news centered on COVID-19 misinformation in the Romanian geopolitical context, comprising both annotated and unannotated articles. We experimented with multiple LLMs using zero-shot, few-shot, supervised, and semi-supervised learning strategies, achieving the best results with an LLaMA 3.1 8B model and semi-supervised learning, which yielded an F1-score of 78.81%. Experimental evaluations compared this approach to traditional Machine Learning classifiers augmented with morphosyntactic features. Results show that semi-supervised learning substantially improved classification results in both binary and multi-class settings. Our findings highlight the effectiveness of semi-supervised adaptation in low-resource, domain-specific contexts, as well as the necessity of enabling real-time misinformation tracking and enhancing transparency through claim-level explainability and fact-based counterarguments. Full article

Infrared small target detection has long faced significant challenges due to the extremely small size of targets, low contrast, and the scarcity of annotated data. To tackle these issues, we propose a wavelet-recalibrated semi-supervised network (WRSSNet) that integrates synthetic data augmentation, feature reconstruction, and semi-supervised learning, aiming to fully exploit the potential of unlabeled infrared images under limited supervision. We construct a dataset containing 843 visible-light small target images and employ an improved CycleGAN model to convert them into high-quality pseudo-infrared images, effectively expanding the scale of training data for infrared small target detection. In addition, we design a lightweight wavelet-enhanced channel recalibration and fusion (WECRF) module, which integrates wavelet decomposition with both channel and spatial attention mechanisms. This module enables adaptive reweighting and efficient fusion of multi-scale features, highlighting high-frequency details and weak target responses. Extensive experiments on two public infrared small target datasets, NUAA-SIRST and IRSTD-1K, demonstrate that WRSSNet achieves superior detection accuracy and lower false alarm rates compared to several state-of-the-art methods, while maintaining low computational complexity. Full article

Generative models, particularly autoencoders, often function as black boxes, making it challenging for non-expert users to effectively control the generation process and understand how inputs affect outputs. Existing methods for improving interpretability and control frequently require specific model training regimes or labeled data, limiting their applicability. This work introduces a novel approach to enhance the controllability and explainability of generative models, specifically tested on autoencoders with entangled latent spaces. We propose using a semi-supervised contrastive learning setup to learn steering vectors. These vectors, when added to an input’s latent representation, effectively manipulate specific attributes in the generated output without conditional training of the model or attribute classifiers, thus being applicable to pretrained models and avoiding compound classification errors. Furthermore, we leverage these learned steering vectors to interpret and explain the decoding process of a target attribute, allowing for efficient exploration of feature dimension interactions and the construction of an interpretable plot of the generative process, while lowering scalability limitations of perturbation-based Explainable AI (XAI) methods by reducing the search space. Our method provides an efficient pathway to controllable generation, offers an interpretable result of the model’s internal mechanisms, and relates the interpretations to human-understandable explanation questions. Full article

Recent advances in time-series anomaly detection have leveraged artificial intelligence (AI) to improve detection performance. In industrial control systems (ICSs), however, acquiring training data is challenging due to operational constraints and the difficulty of system shutdowns. To address this, many countries are developing ICS simulators and testbeds to generate training data. This study uses a publicly available ICS testbed dataset as a benchmark for the discriminator in a Semi-Supervised Generative Adversarial Network (SGAN). The goal is to generate large volumes of synthetic time-series data through adversarial training between generator and discriminator networks, thereby mitigating data scarcity in ICS anomaly detection. Comparative experiments were conducted using this synthetic data to evaluate its impact on existing detection models. Using the HAI 22.04 dataset from the National Security Research Institute, this study performed feature engineering and preprocessing to identify correlations and remove irregularities. Various models, including One-Class SVM, VAE, CNN-GRU-Autoencoder, and CNN-LSTM-Autoencoder, were trained and tested on the dataset. A synthetic dataset was then generated via SGAN and validated using PCA and t-SNE. The results show that applying SGAN-generated data to time-series anomaly detection yielded significant performance improvements in F1 score. Additional validation using the SWaT dataset from the National University of Singapore confirmed similar gains. These findings indicate that synthetic data generated by SGANs can effectively enhance semi-supervised learning for anomaly detection, classification, and prediction in data-constrained environments such as medical, industrial, transportation, and environmental systems. Full article

Retinal vessel segmentation is crucial for analyzing medical images, where symmetry in vascular structures plays a fundamental role in diagnostic accuracy. In recent years, the rapid advancements in deep learning have provided robust tools for predicting detailed images. However, within many scenarios of medical image analysis, the task of data annotation remains costly and challenging to acquire. By leveraging symmetry-aware semi-supervised learning frameworks, our approach requires only a small portion of annotated data to achieve remarkable segmentation outcomes, significantly diminishing the costs associated with data labeling. At present, most semi-supervised approaches rely on pseudo-label update strategies. Nonetheless, while these methods generate high-quality pseudo-label images, they inevitably contain minor prediction errors in a few pixels, which can accumulate during iterative training, ultimately impacting learner performance. To address these challenges, we propose an enhanced semi-supervised vessel semantic segmentation approach that employs a symmetry-preserving pixel-level filtering strategy. This method retains highly reliable pixels in pseudo labels while eliminating those with low reliability, ensuring spatial symmetry coherence without altering the intrinsic spatial information of the images. The filtering strategy integrates various techniques, including probability-based filtering, edge detection, image filtering, mathematical morphology methods, and adaptive thresholding strategies. Each technique plays a unique role in refining the pseudo labels. Extensive experimental results demonstrate the superiority of our proposed method, showing that each filtering strategy contributes to enhancing learner performance through symmetry-constrained optimization. Full article

The aviation industry prioritizes safety and has embraced innovative approaches for both reactive and proactive safety measures. Machine learning (ML) has emerged as a useful tool for aviation safety. This systematic literature review explores ML applications for safety within the aviation industry over the past 25 years. Through a comprehensive search on Scopus and backward reference searches via Google Scholar, 87 of the most relevant papers were identified. The investigation focused on the application context, ML techniques employed, data sources, and the implications of contextual nuances for safety analysis outcomes. ML techniques have been effective for post-accident analysis, predictive, and real-time incident detection across diverse aviation scenarios. Supervised, unsupervised, and semi-supervised learning methods, including neural networks, decision trees, support vector machines, and deep learning models, have all been applied for analyzing accidents, identifying patterns, and forecasting potential incidents. Notably, data sources such as the Aviation Safety Reporting System (ASRS) and the National Transportation Safety Board (NTSB) datasets were the most used. Transparency, fairness, and bias mitigation emerge as critical factors that shape the credibility and acceptance of ML-based safety research in aviation. The review revealed seven recommended future research directions: (1) interpretable AI; (2) real-time prediction; (3) hybrid models; (4) handling of unbalanced datasets; (5) privacy and data security; (6) human–machine interface for safety professionals; (7) regulatory implications. These directions provide a blueprint for further ML-based aviation safety research. This review underscores the role of ML applications in shaping aviation safety practices, thereby enhancing safety for all stakeholders. It serves as a constructive and cautionary guide for researchers, practitioners, and decision-makers, emphasizing the value of ML when used appropriately to transform aviation safety to be more data-driven and proactive. Full article