Search Results (323)

Domain generalization (DG) aims to develop models that perform robustly on unseen target domains, a critical but challenging objective for real-world fault diagnosis. The challenge is further complicated in compound fault diagnosis, where the rigidity of hard labels and the simplicity of label smoothing under-represent inter-class relations and compositional structures, degrading cross-domain robustness. While current domain generalization methods can alleviate these issues, they typically rely on multi-source domain data. However, considering the limitations of equipment operational conditions and data acquisition costs in industrial applications, only one or two independently distributed source datasets are typically available. In this work, an adaptive label refinement network (ALRN) was designed for learning with imperfect labels under source-scarce conditions. Compared to hard labels and label smoothing, ALRN learns richer, more robust soft labels that encode the semantic similarities between fault classes. The model first trains a convolutional neural network (CNN) to obtain initial class probabilities. It then iteratively refines the training labels by computing a weighted average of predictions within each class, using the sample-wise cross-entropy loss as an adaptive weighting factor. Furthermore, a label refinement stability coefficient based on the max-min Kullback–Leibler (KL) divergence ratio across classes is proposed to evaluate label quality and determine when to terminate the refinement iterations. With only one or two source domains for training, ALRN achieves accuracy gains exceeding 22% under unseen operating conditions compared with a conventional CNN baseline. These results validate that the proposed label refinement algorithm can effectively enhance the cross-domain diagnostic performance, providing a novel and practical solution for learning with imperfect supervision in cross-domain compound fault diagnosis. Full article

The scarcity of labeled hyperspectral video samples has motivated existing methods to leverage RGB-pretrained networks; however, many existing methods of hyperspectral object tracking (HOT) select only three representative spectral bands from hyperspectral images, leading to spectral information loss and weakened target discrimination. To address this issue, we propose the Band and Context Refinement Network (BCR-Net) for HOT. Firstly, we design a band importance learning module to partition hyperspectral images into multiple false-color images for pre-trained backbone network. Specifically, each hyperspectral band is expressed as a non-negative linear combination of other bands to form a correlation matrix. This correlation matrix is used to guide an importance ranking of the bands, enabling the grouping of bands into false-color images that supply informative spectral features for the multi-branch tracking framework. Furthermore, to exploit spectral–spatial relationships and contextual information, we design a Contextual Feature Refinement Module, which integrates multi-scale fusion and context-aware optimization to improve feature discrimination. Finally, to adaptively fuse multi-branch features according to band importance, we employ a correlation matrix-guided fusion strategy. Extensive experiments on two public hyperspectral video datasets show that BCR-Net achieves competitive performance compared with existing classical tracking methods. Full article

Medical image segmentation, driven by the intrinsic fractal characteristics of biological patterns, plays a crucial role in medical image analysis. Recently, universal image segmentation, which aims to build models that generalize robustly to unseen anatomical structures and imaging modalities, has emerged as a promising research direction. To achieve this, previous solutions typically follow the in-context learning (ICL) framework, leveraging segmentation priors from a few labeled in-context references to improve prediction performance on out-of-distribution samples. However, these ICL-based methods often overlook the quality of the in-context set and struggle with capturing intricate anatomical details, thus limiting their segmentation accuracy. To address these issues, we propose VG-SAM, which employs a multi-scale in-context retrieval phase and a visual in-context guided segmentation phase. Specifically, inspired by the hierarchical and self-similar properties in fractal structures, we introduce a multi-level feature similarity strategy to select in-context samples that closely match the query image, thereby ensuring the quality of the in-context samples. In the segmentation phase, we propose to generate multi-granularity visual prompts based on the high-quality priors from the selected in-context set. Following this, these visual prompts, along with the semantic guidance signal derived from the in-context set, are seamlessly integrated into an adaptive fusion module, which effectively guides the Segment Anything Model (SAM) with powerful segmentation capabilities to achieve accurate predictions on out-of-distribution query images. Extensive experiments across multiple datasets demonstrate the effectiveness and superiority of our VG-SAM over the state-of-the-art (SOTA) methods. Notably, under the challenging one-shot reference setting, our VG-SAM surpasses SOTA methods by an average of $6.61\%$ in DSC across all datasets. Full article

Currently, the increasing number of Internet of Things devices makes spectrum resource shortage prominent. Spectrum sensing technology can effectively solve this problem by conducting real-time monitoring of the spectrum. However, in practical applications, it is difficult to obtain a large number of labeled samples, which leads to the neural network model not being fully trained and affects the performance. Moreover, the existing few-shot methods focus on capturing spatial features, ignoring the representation forms of features at different scales, thus reducing the diversity of features. To address the above issues, this paper proposes a few-shot spectrum sensing method based on multi-scale global feature. To enhance the feature diversity, this method employs a multi-scale feature extractor to extract features at multiple scales. This improves the model’s ability to distinguish signals and avoids overfitting of the network. In addition, to make full use of the frequency features at different scales, a learnable weight feature reinforcer is constructed to enhance the frequency features. The simulation results show that, when SNR is under 0∼10 dB, the recognition accuracy of the network under different task modes all reaches above 81%, which is better than the existing methods. It realizes the accurate spectrum sensing under the few-shot conditions. Full article

Traditional federated learning frameworks face significant challenges posed by non-independent and identically distributed (non-IID) data in the healthcare domain, particularly in multi-institutional collaborative gout staging prediction. Differences in patient population characteristics, distributions of clinical indicators, and proportions of disease stages across hospitals lead to inefficient model training, increased category prediction bias, and heightened risks of privacy leakage. In the context of gout staging prediction, these issues result in decreased classification accuracy and recall, especially when dealing with minority classes. To address these challenges, this paper proposes FedCG-WGAN, a federated learning method based on conditional gradient penalization in Wasserstein GAN (CG-WGAN). By incorporating conditional information from gout staging labels and optimizing the gradient penalty mechanism, this method generates high-quality synthetic medical data, effectively mitigating the non-IID problem among clients. Building upon the synthetic data, a federated architecture is further introduced, which replaces traditional parameter aggregation with synthetic data sharing. This enables each client to design personalized prediction models tailored to their local data characteristics, thereby preserving the privacy of original data and avoiding the risk of information leakage caused by reverse engineering of model parameters. Experimental results on a real-world dataset comprising 51,127 medical records demonstrate that the proposed FedCG-WGAN significantly outperforms baseline models, achieving up to a 7.1% improvement in accuracy. Furthermore, by maintaining the composite quality score of the generated data between 0.85 and 0.88, the method achieves a favorable balance between privacy preservation and model utility. Full article

The limited availability of pixel-level annotated medical images complicates training supervised segmentation models, as these models require large datasets. To deal with this issue, SemiSeg-CAW, a semi-supervised segmentation framework that leverages class-level information and an adaptive multi-loss function, is proposed to reduce dependency on extensive annotations. The model combines segmentation and classification tasks in a multitask architecture that includes segmentation, classification, weight generation, and ClassElevateSeg modules. In this framework, the ClassElevateSeg module is initially pre-trained and then fine-tuned jointly with the main model to produce auxiliary feature maps that support the main model, while the adaptive weighting strategy computes a dynamic combination of classification and segmentation losses using trainable weights. The proposed approach enables effective use of both labeled and unlabeled images with class-level information by compensating for the shortage of pixel-level labels. Experimental evaluation on two public ultrasound datasets demonstrates that SemiSeg-CAW consistently outperforms fully supervised segmentation models when trained with equal or fewer labeled samples. The results suggest that incorporating class-level information with adaptive loss weighting provides an effective strategy for semi-supervised medical image segmentation and can improve the segmentation performance in situations with limited annotations. Full article

As the core refrigeration equipment in cooling systems, the operational state of chiller units is crucial for ship support, equipment cooling, and mission stability. However, because of their sensitivity and the complexity of operating environments, obtaining large volumes of complete, fault-labeled data is difficult in practical engineering appli-cations. This limitation makes it challenging for traditional data-driven approaches to deliver accurate fault diagnoses. Furthermore, data collected from different devices or under varying operating conditions often differ significantly in both feature dimensions and distributions, i.e., data heterogeneity, which further complicates model transfer. To address these challenges, this study proposes a deep transfer learning–based fault di-agnosis method designed to leverage abundant knowledge from the source domain while adaptively learning features of the target domain. Given the persistent difficulties in collecting sufficient high-quality labeled fault data, traditional data-driven models continue to face restricted diagnostic performance on target equipment. At the same time, data heterogeneity across devices or operating conditions intensifies the challenge of cross-domain knowledge transfer. To overcome these issues, this study develops a heterogeneous transfer learning method that integrates a dual-channel autoencoder, domain adversarial training, and pseudo-label self-training. This combination enables precise small-sample knowledge transfer from the source to the target domain. Specifi-cally, the dual-channel autoencoder is first applied to align heterogeneous feature di-mensions. Then, a Gradient Reversal Layer (GRL) and a domain discriminator are in-troduced to extract domain-invariant features. In parallel, high-confidence pseu-do-labeled samples from the target domain are incorporated into joint training to im-prove generalization and robustness. Experimental results confirm that the method achieves high fault diagnosis accuracy in typical industrial application scenarios, ena-bling effective identification of common faults in various types of chiller units under conventional operating conditions, the proposed method achieves higher accuracy and F1-scores in multi-class fault diagnosis tasks compared with both traditional approaches and existing transfer learning methods. These findings provide a novel perspective for advancing the intelligent operation and maintenance of chiller units. Full article

The Digital Elevation Model (DEM) is widely used in fields such as geoscience and environmental management. However, the existing DEMs struggle to meet the current requirements for timeliness and accuracy, especially in forested areas where vegetation cover can lead to overestimation of elevation. To address this issue, this paper proposes a PolInSAR and Spaceborne LiDAR Regression/Classification Network (PSLRC-Net) for refining external DEMs. Additionally, a forest/non-forest classification labeling method for spaceborne LiDAR footprints is introduced to provide labeled data for the classification branch during the training phase. PSLRC-Net adopts a multi-task learning framework and uses an expert selection mechanism based on a gating network to provide targeted support for the regression and classification branches. The regression branch consists of two task towers, and their outputs are weighted and fused by the output of the classification branch. This approach directs the regression branch to focus on the feature differences between forested and non-forested areas, resulting in more accurate elevation predictions. The network was trained on SAOCOM data from two sites, and the fitting results are evaluated for accuracy using an airborne LiDAR-derived DEM. Compared to different DEM datasets, the RMSE decreased by 51.7–64.6% and 51.9–63.7% at the two sites, while the MAE decreased by 55.5–66.8% and 55.5–68.6%. The experimental results confirm the validity of the model and demonstrate the potential of spaceborne LiDAR fusion with spaceborne PolInSAR to improve DEM accuracy. Full article

Background/Objectives: In Japan, well-balanced meals composed of staple grains, protein-rich main dishes, and vegetable sides are recommended. However, issues such as infrequent breakfast consumption and poor vegetable intake persist. Obesity and non-communicable disease (NCD) rates from age 40 have also begun rising. Therefore, we investigated the structural associations between healthy diets and weight control for NCD prevention, including the potential associations with rice consumption and eating out/home meal replacement use in middle-aged Japanese individuals. Methods: This study was a cross-sectional survey based on data from 577 respondents to the 2016 Hyogo Diet Survey, Hyogo Prefecture, Japan, aged 40–59 years. A healthy diet was defined as including at least two well-balanced meals daily, eating breakfast regularly, and eating five or more vegetable dishes daily. A hypothetical model included factors associated with healthy diets and maintaining a healthy weight (energy, salt, fat, and sugar intake; using nutritional fact labels; and regular exercise), and the frequencies of rice consumption and eating out/home-meal replacement. A simultaneous multi-population analysis by sex was performed. Results: Simultaneous multi-population analysis showed acceptable goodness-of-fit. Maintaining appropriate weight and eating rice were positively associated with healthy diet scores in both sexes. However, for men, using home meal replacements was negatively associated. Conclusions: Among middle-aged Japanese in Hyogo Prefecture, weight control for NCD prevention and rice consumption were linked to healthy diets. In men, using home meal replacements was associated with worse diet quality. Full article

Rice, as one of the world’s four major staple crops, is frequently threatened by pests and diseases during its growth. With the rapid expansion of agricultural information data, the effective management and utilization of such data have become crucial for the development of agricultural informatization. Named entity recognition technology offers precise support for the early prevention and control of crop pests and diseases. However, entity recognition for rice pests and diseases faces challenges such as structural complexity and prevalent nesting issues. Inspired by biological visual mechanisms, we propose a deep learning model capable of extracting multi-granularity features. Text representations are encoded using BERT, and the model enhances its ability to capture nested boundary information through multi-granularity convolutional neural networks (CNNs). Finally, sequence modeling and labeling are performed using a bidirectional long short-term memory network (BiLSTM) combined with a conditional random field (CRF). Experimental results demonstrate that the proposed model effectively identifies entities related to rice diseases and pests, achieving an F1 score of 91.74% on a self-constructed dataset. Full article

Sparse matrix–vector multiplication (SpMV) is a fundamental kernel in high-performance computing (HPC) whose efficiency depends heavily on the storage format across central processing unit (CPU) and graphics processing unit (GPU) platforms. Conventional supervised approaches often use execution time as training labels, but our experiments on 1786 matrices reveal two issues: labels are unstable across runs due to execution-time variability, and single-label assignment overlooks cases where multiple formats perform similarly well. We propose a dynamic labeling strategy that assigns a single label when the fastest format shows clear superiority, and multiple labels when performance differences are small, thereby reducing label noise. We further extend feature analysis to multi-dimensional structural descriptors and apply clustering to refine label distributions and enhance prediction robustness. Experiments demonstrate 99.2% accuracy in hardware (CPU/GPU) selection and up to 98.95% accuracy in format prediction, with up to 10% robustness gains over traditional methods. Under cost-aware, end-to-end evaluation that accounts for feature extraction, prediction, conversion, and kernel execution, CPUs achieve speedups up to 3.15× and GPUs up to 1.94× over a CSR baseline. Cross-round evaluations confirm stability and generalization, providing a reliable path toward automated, cross-platform SpMV optimization. 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

Predictive maintenance (PdM) is essential for reducing equipment downtime and enhancing operational efficiency. However, PdM datasets frequently suffer from significant class imbalance and are often limited to single-label classification, which fails to reflect the complexity of real-world industrial systems where multiple failure modes can occur simultaneously. As the main contribution, we propose the Balanced Hoeffding Tree Forest (BHTF)—a novel multi-label classification framework that combines oversampling and undersampling strategies to effectively mitigate data imbalance. BHTF leverages the binary relevance method to decompose the multi-label problem into multiple binary tasks and utilizes an ensemble of Hoeffding Trees to ensure scalability and adaptability to streaming data. In particular, BHTF unifies three learning paradigms—multi-label learning (MLL), ensemble learning (EL), and incremental learning (IL)—providing a comprehensive and scalable approach for predictive maintenance applications. The key contribution of the proposed method is that it incorporates a hybrid data preprocessing strategy, introducing a novel undersampling technique, named Proximity-Driven Undersampling (PDU), and combining it with the Synthetic Minority Oversampling Technique (SMOTE) to effectively deal with the class imbalance issue in highly skewed datasets. Experimental results on the benchmark AI4I 2020 dataset showed that BHTF achieved an average classification accuracy of 97.44%, outperformed by a margin of the state-of-the-art methods (88.94%) with an improvement of 11% on average. These findings highlight the potential of BHTF as a robust artificial intelligence-based solution for complex fault detection in manufacturing predictive maintenance applications. Full article

Weakly supervised semantic segmentation (WSSS) aims to learn pixel-level semantic concepts from image-level class labels. Due to the simplicity and efficiency of the training pipeline, end-to-end WSSS has received significant attention from the research community. However, the coarse nature of pseudo-label regions remains one of the primary bottlenecks limiting the performance of such methods. To address this issue, we propose class-guided enhanced pseudo-labeling (CEP), a method designed to generate high-quality pseudo-labels for end-to-end WSSS frameworks. Our approach leverages pretrained foundation models, such as contrastive language-image pre-training (CLIP) and segment anything model (SAM), to enhance pseudo-label quality. Specifically, following the pseudo-label generation pipeline, we introduce two key components: a Skip-CAM module and a pseudo-label refinement module. The Skip-CAM module enriches feature representations by introducing skip connections from multiple blocks of CLIP, thereby improving the quality of localization maps. The refinement module then utilizes SAM to refine and correct the pseudo-labels based on the initial class-specific regions derived from the localization maps. Experimental results demonstrate that our method surpasses the state-of-the-art end-to-end approaches as well as many multi-stage competitors. Full article

Black fungus cultivation in bagged form requires frequent inspection of mycelial growth, a process that is labor-intensive and susceptible to subjective judgment. In addition, timely detection of contamination in low-light and high-humidity environments remains a significant challenge. To address these issues, this paper proposed an intelligent agriculture system for black fungus cultivation, with emphasis on practical deployment under real farming conditions. The system integrates a private 5G network with a YOLOv8-based deep learning model for real-time object detection and growth monitoring. Continuous image acquisition and data feedback are achieved through a multi-parameter environmental sensing module and an autonomous ground vehicle (AGV) equipped with IP cameras. To improve model robustness, more than 42,000 labeled training images were generated through data augmentation, and a modified C2f network architecture was employed. Experimental results show that the model achieved a detection accuracy of 93.7% with an average confidence score of 0.96 under live testing conditions. The deployed 5G network provided a downlink throughput of 645.2 Mbps and an uplink throughput of 147.5 Mbps, ensuring sufficient bandwidth and low latency for real-time inference and transmission. Field trials conducted over five cultivation batches demonstrated improvements in disease detection, reductions in labor requirements, and an increase in the average yield success rate to 80%. These findings indicate that the proposed method offers a scalable and practical solution for precision agriculture, integrating next-generation communication technologies with deep learning to enhance cultivation management. Full article