Search Results (409)

Condition monitoring of rotating machinery is critical for ensuring industrial safety and operational reliability. As a core component of intelligent diagnostic systems, domain adaptation methods have achieved notable progress in mechanical fault diagnosis. However, most existing approaches presume a fully shared label space between source and target domains, limiting their effectiveness under partial domain adaptation scenarios commonly encountered in industrial practice. In addition, they often struggle with classification uncertainty near decision boundaries. To address these challenges, this paper proposes a Selective Adversarial Augmentation Network (SAAN) for cross-domain rolling bearing fault diagnosis with partial label space alignment. The proposed framework designs a multi-level feature extraction module to enhance transferable feature representation and a Balanced Augmentation Selective Adversarial Module (BASAM) to dynamically balance class distributions and selectively filter irrelevant source classes, thereby mitigating negative transfer and achieving fine-grained class alignment. Furthermore, an uncertainty suppression mechanism is put forth to reinforce classifier boundaries by minimizing the impact of ambiguous samples. Comprehensive experiments conducted on public and proprietary bearing datasets demonstrate that SAAN consistently surpasses state-of-the-art benchmarks in diagnostic accuracy and robustness, providing an effective solution for practical applications under class-imbalanced and variable operating conditions. Full article

Digital twins (DTs) are increasingly adopted to enhance the monitoring, management, and planning of urban infrastructure. While DT development for buildings is well established, applications to urban road networks remain limited, particularly in integrating heterogeneous geospatial datasets into semantically rich, multi-scale representations. This study presents a methodology for developing a BIM-based DT of urban roads by integrating geospatial data from Mobile Mapping System (MMS) surveys with semantic information from municipal geodatabases. The approach follows a multi-modal (point clouds, imagery, vector data), multi-scale and multi-level framework, where ‘multi-level’ refers to modeling at different scopes—from a city-wide level, offering a generalized representation of the entire road network, to asset-level detail, capturing parametric BIM elements for individual road segments or specific components such as road sign and road marker, lamp posts and traffic light. MMS-derived LiDAR point clouds allow accurate 3D reconstruction of road surfaces, curbs, and ancillary infrastructure, while municipal geodatabases enrich the model with thematic layers including pavement condition, road classification, and street furniture. The resulting DT framework supports multi-scale visualization, asset management, and predictive maintenance. By combining geometric precision with semantic richness, the proposed methodology delivers an interoperable and scalable framework for sustainable urban road management, providing a foundation for AI-ready applications such as automated defect detection, traffic simulation, and predictive maintenance planning. The resulting DT achieved a geometric accuracy of ±3 cm and integrated more than 45 km of urban road network, enabling multi-scale analyses and AI-ready data fusion. Full article

The classification of ship targets in remote sensing images holds significant application value in fields such as marine monitoring and national defence. Although existing research has yielded considerable achievements in ship classification, current methods struggle to distinguish highly similar ship categories for fine-grained classification tasks due to a lack of targeted design. Specifically, they exhibit the following shortcomings: limited ability to extract locally discriminative features; inadequate fusion of features at high and low levels of representation granularity; and sensitivity of model performance to background noise. To address this issue, this paper proposes a fine-grained classification framework for ship targets in remote sensing images based on Multi-Granularity Attention Network (MA-Net), specifically designed to tackle the aforementioned three major challenges encountered in fine-grained classification tasks for ship targets in remote sensing. This framework first performs multi-level feature extraction through a backbone network, subsequently introducing an Adaptive Local Feature Attention (ALFA) module. This module employs dynamic overlapping region segmentation techniques to assist the network in learning spatial structural combinations, thereby optimising the representation of local features. Secondly, a Dynamic Multi-Granularity Feature Fusion (DMGFF) module is designed to dynamically fuse feature maps of varying representational granularities and select key attribute features. Finally, a Feature-Based Data Augmentation (FBDA) method is developed to effectively highlight target detail features, thereby enhancing feature expression capabilities. On the public FGSC-23 and FGSCR-42 datasets, MA-Net attains top-performing accuracies of 93.12% and 98.40%, surpassing the previous best methods and establishing a new state of the art for fine-grained classification of ship targets in remote sensing images. Full article

With the large-scale integration of renewable energy and power electronic devices, power quality disturbances exhibit strong nonlinearity and complex dynamic behavior. Traditional methods are limited by insufficient feature extraction and cumbersome classification, often failing to meet practical accuracy and robustness requirements. To address this issue, this paper proposes a multi-level ensemble method for power quality disturbance identification. A time–frequency dual-branch feature extraction module was designed, combining residual networks and bidirectional temporal convolutional networks to capture both local discriminative features and long-range temporal dependencies in the time and frequency domains. A cross-attention mechanism was further employed to fuse the time–frequency features, enabling adaptive focus on the most critical information for disturbance classification. The fused features were fed into fully connected layers and a Softmax classifier for multi-class identification. Experimental results demonstrated superior accuracy, robustness, and generalization capability compared with existing methods, validating the effectiveness of the proposed model. Full article

With the continuous evolution of social media, users are increasingly inclined to express their personal emotions on digital platforms by integrating information presented in multiple modalities. Within this context, research on image–text sentiment analysis has garnered significant attention. Prior research efforts have made notable progress by leveraging shared emotional concepts across visual and textual modalities. However, existing cross-modal sentiment analysis methods face two key challenges: Previous approaches often focus excessively on fusion, resulting in learned features that may not achieve emotional alignment; traditional fusion strategies are not optimized for sentiment tasks, leading to insufficient robustness in final sentiment discrimination. To address the aforementioned issues, this paper proposes a Dual-path Interaction Network with Multi-level Consistency Learning (DINMCL). It employs a multi-level feature representation module to decouple the global and local features of both text and image. These decoupled features are then fed into the Global Congruity Learning (GCL) and Local Crossing-Congruity Learning (LCL) modules, respectively. GCL models global semantic associations using Crossing Prompter, while LCL captures local consistency in fine-grained emotional cues across modalities through cross-modal attention mechanisms and adaptive prompt injection. Finally, a CLIP-based adaptive fusion layer integrates the multi-modal representations in a sentiment-oriented manner. Experiments on the MVSA_Single, MVSA_Multiple, and TumEmo datasets with baseline models such as CTMWA and CLMLF demonstrate that DINMCL significantly outperforms mainstream models in sentiment classification accuracy and F1-score and exhibits strong robustness when handling samples containing highly noisy symbols. Full article

This study systematically reviews and re-evaluates the international competitiveness and economic sustainability of China’s solar photovoltaic (PV) industry. Based on the PRISMA protocol, it integrates both qualitative and quantitative evidence from 70 core English-language publications published between 2000 and 2025. An analytical framework is developed that combines keyword co-occurrence analysis, thematic clustering, and mechanism pathway mapping. The study identifies three key thematic domains: policy governance mechanisms, economic feasibility and cost structures, and the coupling between technological innovation and environmental performance. The findings reveal a transition in China’s PV development pathway—from early policy-driven expansion to the co-evolution of institutional adaptation and market mechanisms—highlighting the dynamic tension among multi-level variables. Four institutional dimensions and associated variable chains are proposed, uncovering long-term contradictions such as the reliance on subsidies versus structural efficiency and the strategic mismatch between national industrial strategies and global decarbonization goals. The study suggests that future research should prioritize system modeling, feedback mechanism identification, and the theoretical expansion of multi-level governance frameworks. In doing so, this review provides a reusable variable classification framework for analyzing green industrial transformation and offers policy insights for emerging economies engaged in global climate governance. Full article

High-precision land cover classification is fundamental to environmental monitoring, urban planning, and sustainable land-use management. With the growing availability of multimodal remote sensing data, combining spectral and structural information has become an effective strategy for improving classification performance in complex high-resolution scenes. However, most existing methods predominantly rely on shallow feature concatenation, which fails to capture long-range dependencies and cross-modal interactions that are critical for distinguishing fine-grained land cover categories. This study proposes a multi-level cross-modal attention fusion network, Cross-Modal Cross-Attention UNet (CMCAUNet), which integrates a Cross-Modal Cross-Attention Fusion (CMCA) module and a Skip-Connection Attention Gate (SCAG) module. The CMCA module progressively enhances multimodal feature representations throughout the encoder, while the SCAG module leverages high-level semantics to refine spatial details during decoding and improve boundary delineation. Together, these modules enable more effective integration of spectral–textural and structural information. Experiments conducted on the ISPRS Vaihingen and Potsdam datasets demonstrate the effectiveness of the proposed approach. CMCAUNet achieves an mean Intersection over Union (mIoU) ratio of 81.49% and 84.76%, with Overall Accuracy (OA) of 90.74% and 90.28%, respectively. The model also shows superior performance in small object classification, with targets like “Car,” achieving 90.85% and 96.98% OA for the “Car” category. Ablation studies further confirm that the combination of CMCA and SCAG modules significantly improves feature discriminability and leads to more accurate and detailed land cover maps. Full article

Research on extracting building from airborne point clouds is abundant, yet discussions regarding scenarios where vegetation and building structures are closely intertwined with similar height in rural areas remain relatively scarce. This thesis adopts a region representative of typical rural building features in China as an experimental site to conduct research on building classification procedures from airborne point clouds. Firstly, the multi-level grid size is dynamically determined through slope analysis to creatively segment and recognize terrain type, then differentiated filtering parameters are applied to various terrains to fully extract ground points, providing a ground reference for building classification. Secondly, the selection of building Region of Interest is conducted by multiple geometric feature differences between building and other objects based on watershed segmentation results, which eliminates interference from non-building points, significantly reducing redundant and unnecessary mathematical computation. Finally, refined building classification is achieved based on multiple morphological differences between buildings and other objects. The experimental results show that the precision, recall, and F1 of both datasets exceeded 93.37%, 97.05%, and 95.17%, respectively. The average precision, recall, and F1 reached 94.02%, 97.20%, and 95.58%, respectively. This method demonstrates successful building classification in rural areas, showing strong adaptability and practicality for the extraction of various building data. Full article

The emerging paradigm of “fusion of lifeforms” represents a transformative shift from conventional human–machine interfaces toward deeply integrated symbiotic systems, where biological and artificial components co-adapt structurally, energetically, informationally, and cognitively. This review systematically classifies multi-level perception systems within fusion of lifeforms into four functional categories: sensory and functional restoration, beyond-natural sensing, endogenous state sensing, and cognitive enhancement. We survey recent advances in neuroprosthetics, sensory augmentation, closed-loop physiological monitoring, and brain–computer interfaces, highlighting the transition from substitution to fusion. Despite significant progress, critical challenges remain, including multi-source heterogeneous integration, bandwidth and latency limitations, power and thermal constraints, biocompatibility, and system-level safety. We propose future directions such as layered in-body communication networks, sustainable energy strategies, advanced biointerfaces, and robust safety frameworks. Ethical considerations regarding self-identity, neural privacy, and legal responsibility are also discussed. This work aims to provide a comprehensive reference and roadmap for the development of next-generation fusion of lifeforms, ultimately steering human–machine integration from episodic functional repair toward sustained, multi-level symbiosis between biological and artificial systems. Full article

With the acceleration of digital transformation, open-source software has become a fundamental component of modern smart grids and other critical infrastructures. However, the complex dependency structures of open-source ecosystems and the continuous emergence of vulnerabilities pose substantial challenges to software supply chain security. In power information networks and cyber–physical control systems, vulnerabilities in open-source components integrated into Supervisory Control and Data Acquisition (SCADA), Energy Management System (EMS), and Distribution Management System (DMS) platforms and distributed energy controllers may propagate along the supply chain, threatening system security and operational stability. In such application scenarios, large language models (LLMs) often suffer from limited semantic accuracy when handling domain-specific security terminology, as well as deployment inefficiencies that hinder their practical adoption in critical infrastructure environments. To address these issues, this paper proposes KD-SecBERT, a domain-specific semantic bidirectional encoder optimized through multi-level knowledge distillation for open-source software supply chain security in smart grid applications. The proposed framework constructs a hierarchical multi-teacher ensemble that integrates general language understanding, cybersecurity-domain knowledge, and code semantic analysis, together with a lightweight student architecture based on depthwise separable convolutions and multi-head self-attention. In addition, a dynamic, multi-dimensional distillation strategy is introduced to jointly perform layer-wise representation alignment, ensemble knowledge fusion, and task-oriented optimization under a progressive curriculum learning scheme. Extensive experiments conducted on a multi-source dataset comprising National Vulnerability Database (NVD) and Common Vulnerabilities and Exposures (CVE) entries, security-related GitHub code, and Open Web Application Security Project (OWASP) test cases show that KD-SecBERT achieves an accuracy of 91.3%, a recall of 90.6%, and an F1-score of 89.2% on vulnerability classification tasks, indicating strong robustness in recognizing both common and low-frequency security semantics. These results demonstrate that KD-SecBERT provides an effective and practical solution for semantic analysis and software supply chain risk assessment in smart grids and other critical-infrastructure environments. Full article

Extreme environments such as low pressure, high temperature, and intense radiation pose severe challenges for humidity sensors, causing conventional hygroscopic materials to exhibit sluggish responses, drift, and instability. In response, recent research has adopted multi-level strategies involving material modification, structural engineering, and packaging optimization to enhance the adaptability of humidity-sensitive materials in extreme environments. This review examines humidity sensing from an environmental perspective, integrating sensing mechanisms, material classifications, and application scenarios. The performance, advantages, and limitations of six major categories of humidity-sensitive materials, including carbon-based, metal oxides, conductive and insulating polymers, two-dimensional (2D) materials, and composites, are systematically summarized under extreme conditions. Finally, emerging development trends are discussed, highlighting a shift from material-driven to system-driven approaches. Future progress will rely on multidisciplinary integration, including interface engineering, multiscale structural design, and intelligent algorithms, to achieve higher accuracy, stability, and durability in extreme-environment humidity sensing. Full article

Background: The COVID-19 pandemic has put other infectious diseases, especially in children, into a new perspective. Our study focuses on two important viral infections: COVID-19 and influenza, which often present with similar clinical symptoms. Taking into consideration that the pathophysiology and systemic impact of the two viruses are distinct, which can lead to measurable differences in laboratory values, this study aimed to analyze laboratory features that differentiate between COVID-19 and influenza virus infections in pediatric patients. Methods: We statistically analyzed the routinely available laboratory data of 98 patients with influenza virus and 78 patients with COVID-19. Afterwards, the classification and regression tree (CART) method was performed to identify specific clinical scenarios, based on multilevel interactions of different features that could assist clinicians in evidence-based differentiation. Results: Significant differences between the two groups were observed in ALT, eosinophils, hemoglobin, and creatinine. Influenza-infected infants presented significantly higher leukocyte, neutrophil, and basophil counts compared to infants infected with COVID-19. Regarding children (over 12 months), significantly lower levels of ALT and eosinophil counts were observed in those with influenza compared to those with COVID-19. Furthermore, the CART decision tree model identified distinct profiles based on a combination of features such as age, leukocytes, lymphocytes, platelets, and neutrophils. Conclusions: After further refinement and application, such machine learning-based, evidence-driven models, considering the large scale of clinical and laboratory variables, might help to improve, support, and sustain healthcare practices. The differential decision tree may contribute to enhanced clinical risk assessment and decision making. Full article

Facial expression recognition (FER) is crucial for affective computing and human–computer interaction; however, it is still difficult to achieve under various conditions in the real world, such as lighting, occlusion, and pose. This work presents a lightweight hybrid network, SE-Hybrid + Face-ViT, which merges convolutional and transformer architectures through multi-level feature fusion and adaptive channel attention. The network includes a convolutional stream to capture the fine-grained texture of the image and a retrained Face-ViT branch to provide the high-level semantic context. Squeeze-and-Excitation (SE) modules adjust the channel responses at different levels, thus allowing the network to focus on the emotion-salient cues and suppress the redundant features. The proposed architecture, trained and tested on the large-scale AffectNet benchmark, achieved 70.45% accuracy and 68.11% macro-F1, thereby outperforming the latest state-of-the-art models such as TBEM-Transformer, FT-CSAT, and HFE-Net by around 2–3%. Grad-CAM-based visualization of the model confirmed accurate attention to the most significant facial areas, resulting in better recognition of subtle expressions such as fear and contempt. The findings indicate that SE-Hybrid + Face-ViT is a computationally efficient yet highly discriminative FER strategy that successfully addresses the issue of how to preserve details while globally reasoning with contextual information locally. Full article

This paper proposes a solution to the challenge of low accuracy in fine-grained vehicle classification, which arises from minimal intra-class feature variations. It introduces TS-Net, a multi-scale convolutional progressive fine-grained vehicle recognition network. TS-Net utilizes a jigsaw puzzle generator to create multi-level fine-grained images, facilitating progressive learning from fine to coarse granularity. The network integrates multi-attention modules to localize regions of interest and optimizes feature extraction using a split-transform-fuse strategy with multi-scale convolutions. This approach enables cross-granularity feature learning, resulting in improved fine-grained vehicle classification. Experiments on the Stanford Cars dataset show that TS-Net achieves a vehicle identification accuracy of 95.68%. Ablation studies confirm the effectiveness of the progressive training strategy and highlight the synergistic contributions of each module in addressing the issue of low accuracy. Full article

In today’s fast-paced world, the escalating workloads faced by individuals have rendered fatigue a pressing concern that cannot be overlooked. Fatigue not only signals the need for individuals to take a break but also has far-reaching implications for both individuals and society across various domains, including health, safety, productivity, and the economy. While numerous prior studies have explored fatigue monitoring, many of them have been conducted within controlled experimental settings. These experiments typically require subjects to engage in specific tasks over extended periods to induce profound fatigue. However, there has been a limited focus on assessing daily fatigue in natural, real-world environments. To address this gap, this study introduces a daily fatigue monitoring system. We have developed a wearable device capable of capturing subjects’ ECG signals in their everyday lives. We recruited 12 subjects to participate in a 14-day fatigue monitoring experiment. Leveraging the acquired ECG data, we propose machine learning models based on manually extracted features as well as a deep learning model called C-BL to classify subjects’ fatigue levels into three categories: normal, slight fatigue, and fatigued. Our results demonstrate that the proposed end-to-end deep learning model outperforms other approaches with an accuracy rate of 83.3%, establishing its reliability for daily fatigue monitoring. Full article