Search Results (6,424)

RipenessGAN is a novel Generative Adversarial Network (GAN) designed to generate synthetic images across different ripeness stages of jujubes (green fruit, white ripe fruit, semi-red fruit, and fully red fruit), aiming to provide balanced training data for diverse applications beyond classification accuracy. This study addresses the problem of data imbalance by augmenting each ripeness stage using our proposed Growth Day Embedding mechanism, thereby enhancing the performance of downstream classification models. The core innovation of RipenessGAN lies in its ability to capture continuous temporal transitions among discrete ripeness classes by incorporating fine-grained growth day information (0–56 days) in addition to traditional class labels. The experimental results show that RipenessGAN produces synthetic data with higher visual quality and greater diversity compared to CycleGAN. Furthermore, the classification models trained on the enriched dataset exhibit more consistent and accurate performance. We also conducted comprehensive comparisons of RipenessGAN against CycleGAN and class-conditional diffusion models (DDPM) under strictly controlled and fair experimental settings, carefully matching model architectures, computational resources, training conditions, and evaluation metrics. The results indicate that although diffusion models yield highly realistic images and CycleGAN ensures stable cycle-consistent generation, RipenessGAN provides superior practical benefits in training efficiency, temporal controllability, and adaptability for agricultural applications. This research demonstrates the potential of RipenessGAN to mitigate data imbalance in agriculture and highlights its scalability to other crops. Full article

In today’s digital ecosystem, where millions of users interact with diverse online services and generate vast amounts of textual, transactional, and behavioral data, ensuring the trustworthiness of this information has become a critical challenge. Low-quality data—manifesting as incompleteness, inconsistency, duplication, or noise—not only undermines analytics and machine learning models but also exposes unsuspecting users to unreliable services, compromised authentication mechanisms, and biased decision-making processes. Traditional data quality assessment methods, largely based on manual inspection or rigid rule-based validation, cannot cope with the scale, heterogeneity, and velocity of modern data streams. To address this gap, we propose DQMAF (Data Quality Modeling and Assessment Framework), a generalized machine learning–driven approach that systematically profiles, evaluates, and classifies data quality to protect end-users and enhance the reliability of Internet services. DQMAF introduces an automated profiling mechanism that measures multiple dimensions of data quality—completeness, consistency, accuracy, and structural conformity—and aggregates them into interpretable quality scores. Records are then categorized into high, medium, and low quality, enabling downstream systems to filter or adapt their behavior accordingly. A distinctive strength of DQMAF lies in integrating profiling with supervised machine learning models, producing scalable and reusable quality assessments applicable across domains such as social media, healthcare, IoT, and e-commerce. The framework incorporates modular preprocessing, feature engineering, and classification components using Decision Trees, Random Forest, XGBoost, AdaBoost, and CatBoost to balance performance and interpretability. We validate DQMAF on a publicly available Airbnb dataset, showing its effectiveness in detecting and classifying data issues with high accuracy. The results highlight its scalability and adaptability for real-world big data pipelines, supporting user protection, document and text-based classification, and proactive data governance while improving trust in analytics and AI-driven applications. Full article

The article introduces the Guarantee-Based Bandwidth Traffic Engineering Queue (GB(Bw)-TEQ) and Guarantee-Based Utilization Traffic Engineering Queue (GB(U)-TEQ) models for queue management on router interfaces. These models implement the principles of Traffic Engineering Queues and support both DiffServ and IntServ. Their novelty lies in the ability to provide guarantees either for the bandwidth allocated to a class queue or for its utilization coefficient. Such guarantees stabilize and control the average queue length, positively affecting key Quality of Service (QoS) indicators, particularly average delay and packet loss probability. The unreserved portion of the interface bandwidth is allocated among queues in proportion to their classes. Therefore, the higher-priority queues have lower utilization, while lower-priority queues operate with higher utilization, which is consistent with DiffServ principles. The models are formulated as a mixed-integer linear programming problem with an optimality criterion and a system of constraints. Computational experiments confirmed the operability and efficiency of GB(Bw)-TEQ and GB(U)-TEQ compared to the known analogue CB-TEQ model, which does not provide service-level guarantees. The results demonstrate that the proposed models achieve the stated guarantees and enable differentiated service without blocking the lowest-class queues. These solutions can be applied to automate queue management in IP/MPLS switches and routers as well as in software-defined networks. Full article

Obstructive sleep apnoea (OSA) is a complex health condition associated with significant health risks and diminished quality of life. Despite continuous positive airway pressure (CPAP) being the gold standard treatment for years, its poor adherence is well documented. With the emergence of drug-induced sleep endoscopy (DISE) and phenotypic approach to OSA, traditional surgical and non-surgical treatment pathways have been improved to allow personalised treatment and minimising suboptimal treatment to patients demonstrating various upper airway obstruction of OSA endotypes. Sedation protocol propofol, midazolam and dexmedetomidine have been suggested. The VOTE classification for documenting DISE findings have been proposed to unify results across studies. DISE plays an invaluable role in offering insights on treatment successes for positive airway pressure (PAP) therapy, mandibular advancement device (MAD) therapy, positional therapy, and surgical interventions including palatal surgeries, tongue base surgeries, upper airway stimulation (UAS) surgery and maxillomandibular advancement (MMA). This review aims at consolidating current evidence on DISE protocols, indications, and treatment implications to improve therapeutic success in OSA management. Full article

Water quality is an essential part of maintaining a healthy environment for fish farming. The quality of the water is related to a few of the chemical and biological characteristics of water. The conventional evaluation methods of the water quality are often time-consuming and may overlook complex interdependencies among multiple indicators. This study has proposed a robust machine learning framework for aquaculture water quality classification by integrating the Honey Badger Algorithm (HBA) with the XGBoost classifier. The framework enhances classification accuracy and incorporates explainability through SHAP and DiCE, thereby providing both predictive performance and transparency for practical water quality management. For reliability, the dataset has been randomly shuffled, and a custom 5-fold cross-validation strategy has been applied. Later, through the metaheuristic-based HBA, feature selections and hyperparameter tuning have been performed to improve and increase the prediction accuracy. The highest accuracy of 98.45% has been achieved by a particular fold, whereas the average accuracy is 98.05% across all folds, indicating the model’s stability. SHAP analysis reveals Ammonia, Nitrite, DO, Turbidity, BOD, Temperature, pH, and CO₂ as the topmost water quality indicators. Finally, the DiCE analysis has analyzed that Temperature, Turbidity, DO, BOD, CO₂, pH, Ammonia, and Nitrite are more influential parameters of water quality. Full article

Background and objectives: Pain is a prevalent and often underestimated issue in children with cerebral palsy (CP). When left untreated, pain can result in secondary complications such as reduced mobility and mental health challenges, which negatively impact social activity, participation, and overall quality of life. This review explores the complex mechanisms underlying pain in CP, highlights contributing factors, and places particular emphasis on diagnostic challenges and multimodal pain management strategies. Methods: Three scientific databases and, additionally, guideline repositories (2015–2025) were searched, yielding 1335 records. Following a two-step deduplication process, 850 unique items remained. Eighty-five full texts were assessed, of which 49 studies were included. These comprised one randomised controlled trial, 16 non-randomised studies, 12 systematic reviews, 8 non-systematic reviews, and 12 guidelines or consensus statements. Methodological quality was appraised with AMSTAR-2 where applicable, and Oxford levels of evidence were assigned to all studies. Results: Study quality was variable: 25% were systematic reviews, with only one randomised controlled trial. This literature identifies overlapping nociceptive, neuropathic, and nociplastic mechanisms of pain development. Classification remains inconsistent, though the International Classification of Diseases provides a useful framework. Only five assessment tools have been validated for this population. Interventions were reported in 45% of studies, predominantly pharmacological (27%) and physiotherapeutic (23%). Evidence gaps remain substantial. Conclusions: This review highlights the complexity of pain in children and adolescents with cerebral palsy and the need for a biopsychosocial approach to assessment and management. Evidence supports individualised, multimodal strategies integrating physical therapies, contextual supports, and, where appropriate, medical or surgical interventions. Clinical implementation remains inconsistent due to limited high-quality evidence, inadequate assessment tools, and poor interdisciplinary integration. Full article

Financial news has a significant impact on investor sentiment and short-term stock price trends. While many studies have applied natural language processing (NLP) techniques to financial forecasting, most have focused on single tasks or English corpora, with limited research in non-English language contexts such as Taiwan. This study develops a joint framework to perform sentiment classification and short-term stock price prediction using Chinese financial news from Taiwan’s top 50 listed companies. Five types of word embeddings—one-hot, TF-IDF, CBOW, skip-gram, and BERT—are systematically compared across 17 traditional, deep, and Transformer models, as well as a large language model (LLaMA3) fully fine-tuned on the Chinese financial texts. To ensure annotation quality, sentiment labels were manually assigned by annotators with finance backgrounds and validated through a double-checking process. Experimental results show that a CNN using skip-gram embeddings achieves the strongest performance among deep learning models, while LLaMA3 yields the highest overall F1-score for sentiment classification. For regression, LSTM consistently provides the most reliable predictive power across different volatility groups, with Bayesian Linear Regression remaining competitive for low-volatility firms. LLaMA3 is the only Transformer-based model to achieve a positive $R^2$ under high-volatility conditions. Furthermore, forecasting accuracy is higher for the five-day horizon than for the fifteen-day horizon, underscoring the increasing difficulty of medium-term forecasting. These findings confirm that financial news provides valuable predictive signals for emerging markets and that short-term sentiment-informed forecasts enhance real-time investment decisions. Full article

More than one billion end-of-life tyres (EOLTs) are produced worldwide every year, and this is continuously increasing and has become an issue in sustainable development. This review discusses recent developments in the management of EOLTs and focuses on pyrolysis, which produces valuable tyre-derived products (TDPs) like steel, gas, oil, and char. This review focuses on recovered carbon black (rCB), a refined char with great potential as a sustainable alternative to commercial carbon black (CB). The review introduces a novel classification system for CB, virgin carbon black (vCB), recovered carbon black (rCB), and sustainable carbon black (sCB) to guide the transition toward environmentally friendly materials. It also examines how rCB enhances polymer properties for addressing price volatility and reducing carbon footprint. Additionally, a SWOT analysis evaluates the strengths (cost-effectiveness, reduced environmental impact), weaknesses (quality consistency), opportunities (emerging markets, circular economy integration), and threats (competition from virgin materials) of using rCB as a polymer reinforcement. By positioning rCB as a key material, this review outlines pathways for addressing the EOLT crisis and advancing a circular economy. Full article

Accurate diagnosis of myocardial infarction (MI) holds significant clinical importance for public health systems. Deep learning-based ECG, classification and localization methods can automatically extract features, thereby overcoming the dependence on manual feature extraction in traditional methods. However, these methods still face challenges such as insufficient utilization of dynamic information in cardiac cycles, inadequate ability to capture both global and local features, and data imbalance. To address these issues, this paper proposes a ResNet-Transformer cascaded network (RTCN) to process time frequency features of ECG signals generated by the S-transform. First, the S-transform is applied to adaptively extract global time frequency features from the time frequency domain of ECG signals. Its scalable Gaussian window and high phase resolution can effectively capture the dynamic changes in cardiac cycles that traditional methods often fail to extract. Then, we develop an architecture that combines the Transformer attention mechanism with ResNet to extract multi-scale local features and global temporal dependencies collaboratively. This compensates for the existing deep learning models’ insufficient ability to capture both global and local features simultaneously. To address the data imbalance problem, the Denoising Diffusion Probabilistic Model (DDPM) is applied to synthesize high-quality ECG samples for minority classes, increasing the inter-patient accuracy from 61.66% to 68.39%. Gradient-weighted Class Activation Mapping (Grad-CAM) visualization confirms that the model’s attention areas are highly consistent with pathological features, verifying its clinical interpretability. Full article

The integration of machine vision systems with programmable logic controllers (PLCs) is increasingly crucial for automated quality assurance in Industry 4.0 environments. This paper presents an applied case study of vision–PLC integration, focusing on real-time synchronization, deterministic communication, and practical industrial deployment. The proposed platform combines a Cognex In-Sight 2802C smart camera (Cognex Corporation, Natick, MA, USA) with an Allen-Bradley Compact GuardLogix PLC through Ethernet/IP implicit cyclic exchange. Three representative case studies were investigated: 3D-printed prototypes with controlled defects, automotive electrical connectors inspected using Cognex ViDi supervised learning tools, and fiber optic tubes evaluated via a custom fixture-based heuristic method. Across all scenarios, detection accuracy exceeded 95%, while PLC-level triple verification reduced false classifications by 28% compared to camera-only operation. The work highlights the benefits of PLC-driven inspection, including robustness, real-time performance, and dynamic tolerance adjustment via HMI interfaces. At the same time, several limitations were identified, including sensitivity to lighting variations, limited dataset size, and challenges in scaling to full production environments. These findings demonstrate a replicable integration framework that supports intelligent manufacturing. Future research will focus on hybrid AI–PLC architectures, extended validation on industrial production lines, and predictive maintenance enabled by edge computing. Full article

The continuously evolving cyber threat landscape necessitates not only resilient defense mechanisms but also the sustained capacity development of security personnel. However, conventional training pipelines are predominantly dependent on static real-world datasets, which fail to adequately reflect the diversity and dynamics of emerging attack tactics. To address these limitations, this study employs a Wasserstein GAN with Gradient Penalty (WGAN-GP) to synthesize realistic network traffic that preserves both temporal and statistical characteristics. Using the CIC-IDS-2017 dataset, which encompasses diverse attack scenarios including brute-force, Heartbleed, botnet, DoS/DDoS, web, and infiltration attacks, two training methodologies are proposed. The first trains a single conditional WGAN-GP on the entire dataset to capture the global distribution. The second employs multiple generators tailored to individual attack types, while sharing a discriminator pretrained on the complete traffic set, thereby ensuring consistent decision boundaries across classes. The quality of the generated traffic was evaluated using a Train on Synthetic, Test on Real (TSTR) protocol with LSTM and Random Forest classifiers, along with distribution similarity measures in the embedding space. The proposed approach achieved a classification accuracy of 97.88% and a Fréchet Inception Distance (FID) score of 3.05, surpassing baseline methods by more than one percentage point. These results demonstrate that the proposed synthetic traffic generation strategy provides advantages in scalability, diversity, and privacy, thereby enriching cyber range training scenarios and supporting the development of adaptive intrusion detection systems that generalize more effectively to evolving threats. Full article

Reverse logistics (RL) plays a crucial role in promoting circularity and sustainability in supply chains, particularly in the face of increasing waste generation and growing environmental demands. In recent years, machine learning (ML) has emerged as a strategic tool to enhance processes, decision-making, and outcomes in RL. This article presents a systematic review of ML applications in reverse logistics, highlighting trends, challenges, and research opportunities. The analysis covers 52 articles retrieved from the Scopus and Web of Science databases, following the PRISMA protocol. The results show that the most frequently employed techniques are supervised models, followed by unsupervised methods and, to a lesser extent, reinforcement learning. The main ML applications in RL focus on return and waste generation forecasting, process optimization, classification, pricing, reliability assessments, and consumer behavior analysis. The studies examined predominantly use traditional evaluation metrics, such as MAPE and F1-score, while few consider multidimensional indicators encompassing long-term social or environmental impacts. Key challenges identified include data scarcity and quality, inherent uncertainties in reverse supply chains, and the high computational cost of models. This article also points to research gaps concerning metadata standardization, the absence of public benchmarks, model explainability, and the integration of ML with simulations and digital twins, indicating pathways toward more robust, transparent, and sustainable RL. Full article

Recently, there has been significant progress in the area of semantic classification of water bodies at global scales with deep learning. For the key purposes of water inventory and change detection, advanced deep learning classifiers such as UNets and Vision Transformers have been shown to be both accurate and flexible when applied to large-scale, or even global, satellite image datasets from optical (e.g., Sentinel-2) and radar sensors (e.g., Sentinel-1). Most of this work is conducted with optical sensors, which usually have better image quality, but their obvious limitation is cloud cover, which is why radar imagery is an important complementary dataset. However, radar imagery is generally more sensitive to soil moisture than optical data. Furthermore, topography and wind-ripple effects can alter the reflected intensity of radar waves, which can induce errors in water classification models that fundamentally rely on the fact that water is darker than the surrounding landscape. In this paper, we develop a solution to the use of Sentinel-1 radar images for the semantic classification of water bodies that uses style transfer with multi-modal and multi-temporal image fusion. Instead of developing new semantic classification models that work directly on Sentinel-1 images, we develop a global style transfer model that produces synthetic Sentinel-2 images from Sentinel-1 input. The resulting synthetic Sentinel-2 imagery can then be classified with existing models. This has the advantage of obviating the need for large volumes of manually labeled Sentinel-1 water masks. Next, we show that fusing an 8-year cloud-free composite of the near-infrared band 8 of Sentinel-2 to the input Sentinel-1 image improves the classification performance. Style transfer models were trained and validated with global scale data covering the years 2017 to 2024, and include every month of the year. When tested against a global independent benchmark, S1S2-Water, the semantic classifications produced from our synthetic imagery show a marked improvement with the use of image fusion. When we use only Sentinel-1 data, we find an overall IoU (Intersection over Union) score of 0.70, but when we add image fusion, the overall IoU score rises to 0.93. Full article

Introducing deep learning methods into the quality inspection of production lines can reduce labor and improve efficiency, with great potential for the development of manufacturing systems. However, in specific closed production-line environments, robust and high-quality 3D fixed-area quality inspection is a common and challenging problem due to improper assembly, high data resolution, pose perturbation, and other reasons. In this article, we propose a robust 3D fixed-area quality inspection framework for production lines consisting of two steps: recursive segmentation and one-class classification. First, a Focal Segmentation Module (FSM) is proposed to gradually focus on the areas to be inspected by recursively segmenting the downsampled low-resolution point cloud, thereby ensuring efficient high-resolution segmentation. Moreover, Local Reference Frame (LRF)-based rotation-invariant local feature extraction is introduced to improve the robustness of the proposed method to pose variations. Second, a uniquely designed Semi-Nested Point Cloud Autoencoder (SN-PAE) is proposed to improve data imbalance and hard-to-classify samples. Particularly, we first introduce rotation-invariant feature extraction to a point cloud autoencoder to learn descriptive latent variables, then measure the latent variables using a semi-nested Latent Autoencoding Module (LAM). This avoids unreliable chamfer distance measurement and makes SN-PAE a more robust measurement method. In addition, we implement a set of experiments using solder joints as an example. Compared with PointNet++, the memory usage of recursive segmentation is reduced by 92%, and the time cost is reduced by 97.5%. The recall of SN-PAE on unaligned samples exceeds that of competitors by nearly 30% in the classification stage. The results demonstrate the feasibility and effectiveness of the proposed framework. Full article

In recent years, the powerful feature extraction capabilities of deep learning have attracted widespread attention in the field of bearing fault diagnosis. To address the limitations of single-modal and single-channel feature extraction methods, which often result in incomplete information representation and difficulty in obtaining high-quality fault features, this paper proposes a dual-channel parallel multimodal feature fusion model for bearing fault diagnosis. In this method, the one-dimensional vibration signals are first transformed into two-dimensional time-frequency representations using continuous wavelet transform (CWT). Subsequently, both the one-dimensional vibration signals and the two-dimensional time-frequency representations are fed simultaneously into the dual-branch parallel model. Within this architecture, the first branch employs a combination of a one-dimensional convolutional neural network (1DCNN) and a bidirectional gated recurrent unit (BiGRU) to extract temporal features from the one-dimensional vibration signals. The second branch utilizes a dilated convolutional to capture spatial time–frequency information from the CWT-derived two-dimensional time–frequency representations. The features extracted by both branches were are input into the feature fusion layer. Furthermore, to leverage fault features more comprehensively, a channel attention mechanism is embedded after the feature fusion layer. This enables the network to focus more effectively on salient features across channels while suppressing interference from redundant features, thereby enhancing the performance and accuracy of the dual-branch network. Finally, the fused fault features are passed to a softmax classifier for fault classification. Experimental results demonstrate that the proposed method achieved an average accuracy of 99.50% on the Case Western Reserve University (CWRU) bearing dataset and 97.33% on the Southeast University (SEU) bearing dataset. These results confirm that the suggested model effectively improves fault diagnosis accuracy and exhibits strong generalization capability. Full article