Search Results (8,311)

With the rapid advancement of Generative Adversarial Networks (GANs), diffusion models, and other deep generative techniques, AI-generated images have achieved unprecedented levels of visual realism, posing severe challenges to the authenticity, security, and credibility of digital content. This paper proposes a novel hybrid transformer model that integrates spatial and frequency domains. It leverages CLIP to extract semantic inconsistencies in the image’s spatial domain while employing wavelet transforms to capture multi-scale frequency anomalies in AI-generated images. After cross-domain feature fusion, global modeling is performed within the Swin-Transformer architecture, enabling robust authenticity detection of AI-generated images. Extensive experiments demonstrate that our detector maintains high accuracy across diverse datasets. Full article

With the integration of high-proportion renewable energy, the operation modes of the power system are becoming increasingly complex and diverse. The typical operation modes selected with manual experience cannot comprehensively represent system operating characteristics. To more accurately analyze system operating characteristics, an analysis method for power system operation modes based on autoencoder clustering is proposed. Compared to other clustering methods, the autoencoder clustering method can adapt to data of different types and structures, extract features and perform clustering in a reduced-dimensional space, and suppress noise in the data to a certain extent. First, multi-dimensional analysis metrics for power system operation modes are proposed. The metrics are used to evaluate system characteristics such as cleanliness, security, flexibility, and adequacy. The evaluation metrics for clustering are designed based on the metrics. Second, an operation mode analysis framework is constructed. The framework uses an autoencoder to extract implicit coupling relationships between system operation variables. The encoded feature vectors are used for clustering, which helps to find the internal similarities of the operation modes. Regulation resources such as pumped hydro storage are also considered in the framework. Finally, the proposed method is tested on the IEEE 39-node system. In the test, the comparison of clustering evaluation metrics and operation mode analysis errors shows that the proposed method has the best clustering performance and operation mode analysis effect compared to other clustering methods. The results prove that the proposed method can effectively extract the inner correlations and coupling relations of high-dimensional operating vectors, form consistent operation mode clusters, select typical operation modes, and accurately assess the characteristics and risks of the power system with high-proportion renewable energy integration. This paper helps to build a stronger power system that can integrate a higher proportion of renewable energy, replace fossil fuel generation, and contribute to a higher level of sustainable development. Full article

Unmanned aerial vehicles (UAVs) are now widely used in various applications, including agriculture, urban traffic management, and search and rescue operations. However, several challenges arise, including the small size of objects occupying only a sparse number of pixels in images, complex backgrounds in aerial footage, and limited computational resources onboard. To address these issues, this paper proposes an improved UAV-based small object detection algorithm, YOLO11s-UAV, specifically designed for aerial imagery. Firstly, we introduce a novel FPN, called Content-Aware Reassembly and Interaction Feature Pyramid Network (CARIFPN), which significantly enhances small object feature detection while reducing redundant network structures. Secondly, we apply a new downsampling convolution for small object feature extraction, called Space-to-Depth for Dilation-wise Residual Convolution (S2DResConv), in the model’s backbone. This module effectively eliminates information loss caused by pooling operations and facilitates the capture of multi-scale context. Finally, we integrate a simple, parameter-free attention module (SimAM) with C3k2 to form Flexible SimAM (FlexSimAM), which is applied throughout the entire model. This improved module not only reduces the model’s complexity but also enables efficient enhancement of small object features in complex scenarios. Experimental results demonstrate that on the VisDrone-DET2019 dataset, our model improves mAP@0.5 by 7.8% on the validation set (reaching 46.0%) and by 5.9% on the test set (increasing to 37.3%) compared to the baseline YOLO11s, while reducing model parameters by 55.3%. Similarly, it achieves a 7.2% improvement on the TinyPerson dataset and a 3.0% increase on UAVDT-DET. Deployment on the NVIDIA Jetson Orin NX SUPER platform shows that our model achieves 33 FPS, which is 21.4% lower than YOLO11s, confirming its feasibility for real-time onboard UAV applications. Full article

Multivariate time series anomaly detection is a critical technique for industrial intelligent monitoring. However, existing methods often suffer from prohibitively high training costs and slow convergence, making them ill-suited for industrial scenarios that require frequent model retraining due to dynamic operating conditions. To this end, an efficient two-stage spatio-temporal attention detection framework, TSA-Net, is proposed. This framework adopts a two-branch architecture utilizing a structurally reparameterized temporal convolutional network (RepVGG-TCN) and a graph attention network (GAT). Crucially, the RepVGG design enhances feature extraction capability during training through a multi-branch structure while collapsing into a compact single-branch architecture for deployment, thereby optimizing structural complexity. At the core of TSA-Net is a cascading feedback mechanism, where preliminary predictions from the first stage serve as guidance signals to augment the input for the second stage, enabling coarse-to-fine iterative refinement. Furthermore, an adaptive gating mechanism dynamically fuses spatio-temporal features, improving the model’s adaptability. Extensive experiments with ten state-of-the-art algorithms on three benchmark datasets demonstrate that TSA-Net achieves significant optimization. Specifically, it improves the F1 score by approximately 7% while reducing the training time by up to 99% compared to complex Transformer-based models, offering a rapid-deployment solution for high-dimensional anomaly detection. Full article

Chronic ultraviolet (UV) exposure disrupts dermal collagen homeostasis and accelerates skin aging. This study evaluated the protective effects of black ginseng extract (BGE) against UV-induced photoaging in human dermal fibroblasts. BGE restored collagen-related markers, including COL5A1 and COL7A1, improved fibroblast proliferative capacity, and reduced senescence-associated changes under UV stress. Data-independent acquisition (DIA) proteomics identified broad pathway modulation by BGE, involving extracellular matrix remodeling, chromatin organization, and stress-response processes. To validate genome maintenance-related signals highlighted by proteomics, qPCR showed that BGE increased telomere/replication-associated genes compared with the UV group, including POT1 (2.29-fold) and ORC1 (6.70-fold). In addition, comet assay imaging indicated reduced UV-associated DNA damage features following BGE treatment. Overall, these findings indicate that BGE mitigates UV-induced photoaging phenotypes in fibroblasts, with collagen-related recovery and multi-level protective responses, supporting its potential as a natural bioactive ingredient for anti-photoaging skincare applications. Full article

Introduction: Resting-state EEG (rsEEG) is a scalable window onto trait-like “executive readiness,” but findings have been fragmented by task impurity on the executive-function (EF) side and heterogeneous EEG pipelines. This review synthesizes rsEEG features that reliably track EF in healthy samples across development and aging and evaluates moderators such as cognitive reserve. Materials and methods: Following PRISMA 2020, we defined PECOS-based eligibility (human participants; eyes-closed/eyes-open rsEEG; spectral, aperiodic, connectivity, topology, microstate, and LRTC features; behavioral EF outcomes) and searched MEDLINE/PubMed, Embase, PsycINFO, Web of Science, Scopus, and IEEE Xplore from inception to 30 August 2025. Two reviewers were screened/double-extracted; the risk of bias in non-randomized studies was assessed using the ROBINS-I tool. Sixty-three studies met criteria (plus citation tracking), spanning from childhood to old age. Results: Across domains, tempo, noise, and wiring jointly explained EF differences. Faster individual/peak alpha frequency (IAF/PAF) related most consistently to manipulation-heavy working may and interference control/vigilance in aging; alpha power was less informative once periodic and aperiodic components were separated. Aperiodic 1/f parameters (slope/offset) indexed domain-general efficiency (processing speed, executive composites) with education-dependent sign flips in later life. Connectivity/topology outperformed local power: efficient, small-world-like alpha networks predicted faster, more consistent decisions and higher WM accuracy, whereas globally heightened alpha/gamma synchrony—and rigid high-beta organization—were behaviorally sluggish. Within-frontal beta/gamma coherence supported span maintenance/sequencing, but excessive fronto-posterior theta coherence selectively undermined WM manipulation/updating. A higher frontal theta/beta ratio forecasts riskier, less adaptive choices and poorer reversal learning for decision policy. Age and reserve consistently moderated effects (e.g., child frontal theta supportive for WM; older-adult slow power often detrimental; stronger EO ↔ EC connectivity modulation and faster alpha with higher reserve). Boundary conditions were common: low-load tasks and homogeneous young samples usually yielded nulls. Conclusions: RsEEG does not diagnose EF independently; single-band metrics or simple ratios lack specificity and can be confounded by age/reserve. Instead, a multi-feature signature—faster alpha pace, steeper 1/f slope with appropriate offset, efficient/flexible alpha-band topology with limited global over-synchrony (especially avoiding long-range theta lock), and supportive within-frontal fast-band coherence—best captures individual differences in executive speed, interference control, stability, and WM manipulation. For reproducible applications, recordings should include ≥5–6 min eyes-closed (plus eyes-open), ≥32 channels, vigilant artifact/drowsiness control, periodic–aperiodic decomposition, lag-insensitive connectivity, and graph metrics; analyses must separate speed from accuracy and distinguish WM maintenance vs. manipulation. Clinical translation should prioritize stratification and monitoring (not diagnosis), interpreted through the lenses of development, aging, and cognitive reserve. Full article

Short-Term Residential Load Forecasting (STRLF) is a core task in smart grid dispatching and energy management, and its accuracy directly affects the economy and stability of power systems. Current mainstream methods still have limitations in addressing issues such as complex temporal patterns, strong stochasticity of load data, and insufficient model interpretability. To this end, this paper proposes an explainable and efficient forecasting framework named KAN+Transformer, which integrates Kolmogorov–Arnold Networks (KAN) with Transformers. The framework achieves performance breakthroughs through three innovative designs: constructing a Reversible Mixture of KAN Experts (RMoK) layer, which optimizes expert weight allocation using a load-balancing loss to enhance feature extraction capability while preserving model interpretability; designing an attention-guided cascading mechanism to dynamically fuse the local temporal patterns extracted by KAN with the global dependencies captured by the Transformer; and introducing a multi-objective loss function to explicitly model the periodicity and trend characteristics of load data. Experiments on four power benchmark datasets show that KAN+Transformer significantly outperforms advanced models such as Autoformer and Informer; ablation studies confirm that the KAN module and the specialized loss function bring accuracy improvements of 7.2% and 4.8%, respectively; visualization analysis further verifies the model’s decision-making interpretability through weight-feature correlation, providing a new paradigm for high-precision and explainable load forecasting in smart grids. Collectively, the results demonstrate our model’s superior capability in representing complex residential load dynamics and capturing both transient and stable consumption behaviors. By enabling more accurate, interpretable, and computationally efficient short-term load forecasting, the proposed KAN+Transformer framework provides effective support for demand-side management, renewable energy integration, and intelligent grid operation. As such, it contributes to improving energy utilization efficiency and enhancing the sustainability and resilience of modern power systems. Full article

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

Accurate building footprint is a fundamental element of large-scale base maps, which serve as critical inputs for urban planning, infrastructure development, environmental monitoring, and disaster management. While building footprint extraction and geometric regularization have been widely studied, their combined application for automated, large-scale basemap generation using very-high-resolution satellite imagery has received limited attention. To address this gap, this study proposes an integrated framework that leverages deep learning and geometric regularization to efficiently extract and refine building footprints for large-scale base maps. The framework first enhances spectral, spatial, and textural features of very-high-resolution satellite imagery through pan-sharpening, NDVI computation, GLCM-based texture analysis, and PCA. A Mask R-CNN model is then trained on multi-band imagery to segment building footprints, followed by geometric regularization to simplify and align polygons along dominant structural orientations. Object-based evaluation on ground-truth buildings demonstrates high performance, with 97.6% precision, 91.6% recall, and a 94.5% F1-score. The proposed systematic framework substantially reduces production time compared to manual stereo-plotting, requiring less than an hour per 5.29 km² map sheet in operational production, representing a more than 35-fold efficiency gain. While minor geometric inaccuracies and merged adjacent buildings persist, the methodology offers a robust, scalable, and efficient approach to support large-scale base map production. Full article

To address the tradeoff between environmental robustness and fine-grained accuracy in single-sensor human behavior recognition, this paper proposes a non-contact system fusing 77 GHz SIFT (mmWave) radar and a 40 kHz ultrasonic array. The system leverages radar’s long-range penetration and low-visibility adaptability, paired with ultrasound’s centimeter-level short-range precision and electromagnetic clutter immunity. A synchronized data acquisition platform ensures multi-modal signal consistency, while wavelet transform (for radar) and STFT (for ultrasound) extract complementary time–frequency features. The proposed Attention-CNN-BiLSTM architecture integrates local spatial feature extraction, bidirectional temporal dependency modeling, and salient cue enhancement. Experimental results on 1600 synchronized sequences (four behaviors: standing, sitting, walking, falling) show a 98.6% mean class accuracy with subject-wise generalization, outperforming single-sensor baselines and traditional deep learning models. As a privacy-preserving, lighting-agnostic solution, it offers promising applications in smart homes, healthcare monitoring, and intelligent surveillance, providing a robust technical foundation for contactless behavior recognition. Full article

Student employment is an increasingly common feature of higher education, yet psychological research on students who combine paid work and study remains conceptually and methodologically fragmented. This scoping review mapped the extent, range, and nature of empirical evidence on working students’ psychological experiences, summarized key psychosocial correlates, and identified gaps for future research. Consistent with PRISMA-ScR guidance, we searched EBSCOhost, Scopus, and Web of Science using tailored Boolean title-field strategies without year limits, screened records against eligibility criteria, and charted and thematically synthesized extracted data. Forty-two peer-reviewed English-language studies were included. Evidence clustered into six recurrent domains, such as work–study interface processes, resources and supports, health, stress and recovery, academic engagement and performance, career development and employability, and identity and social relations. The literature was predominantly quantitative and cross-sectional, with comparatively few intervention studies. Findings suggest that psychological outcomes are frequently examined through, and may be more closely contingent on, the quality of the work–study interface and contextual supports than on employment intensity alone, highlighting the potential value of interventions and institutional/employer practices that enhance role fit, flexibility, and supportive climates, alongside more longitudinal and multi-level research. Full article

This paper proposes a multi-behavior and sequence-aware recommendation method that effectively integrates diverse user–item interaction behaviors and their sequential dependencies to enhance recommendation accuracy. Unlike existing studies that treat different user–item interactions independently, our approach integrates diverse behaviors and their natural sequential dependencies to better capture user preferences and alleviate data sparsity caused by single-behavior modeling. Different from the traditional single-behavior models, our approach constructs a multi-behavior heterogeneous graph and defines multiple meta-path patterns to capture implicit relationships between users and items. By generating subgraph instances, we extract fine-grained interaction patterns and employ a LightGCN with residual connections to learn user representations under different behavioral sequences. Furthermore, an attention mechanism is introduced to fuse features across subgraphs, enabling more expressive preference modeling. Experimental results on two real-world datasets, Taobao and Tmall, demonstrate that our method outperforms state-of-the-art single- and multi-behavior recommendation models, achieving up to 10.0% and 11.1% improvements in HR@10 and NDCG@10 on Taobao and 9.0% and 10.6% on Tmall, respectively. These results confirm the effectiveness of leveraging both multi-behavior information and sequence dependencies in capturing deeper user preferences for more accurate recommendations. Full article

In disaster emergency response, spatial location information embedded within social media texts holds substantial value for the rapid localization of affected areas and the implementation of precise rescue operations. Existing research predominantly employs natural language processing and deep learning technologies for geographic information extraction; however, two critical limitations persist: first, insufficient integration of textual semantic features for disaster relevance determination, resulting in inadequate correlation between extracted results and actual disaster locations; second, absence of mechanisms for identifying affected sites in multi-location contexts, thereby compromising decision support efficacy. Addressing these challenges, this study proposes a hierarchical disaster location information extraction framework that integrates semantic understanding. The framework operates through a three-tier hierarchy: data-level adversarial augmentation, semantic-level dynamic parsing, and parameter-level scale optimization. It achieves three core functionalities: (1) precise determination of disaster relevance for geographic location information; (2) identification of affected areas in multi-location contexts; (3) establishment of a logarithmic scaling relationship between LLM parameter scale and optimal prompt sample size. Full article

Remote sensing image captioning (RSIC) aims to generate natural language descriptions for the given remote sensing image, which requires a comprehensive and in-depth understanding of image content and summarizes it with sentences. Most RSIC methods have successful vision feature extraction, but the representation of spatial features or fusion features fails to fully consider cross-modal differences between remote sensing images and texts, resulting in unsatisfactory performance. Thus, we propose a novel cross-modal spatial–semantic alignment (CSSA) framework for an RSIC task, which consists of a multi-branch cross-modal contrastive learning (MCCL) mechanism and a dynamic geometry Transformer (DG-former) module. Specifically, compared to discrete text, remote sensing images present a noisy property, interfering with the extraction of valid vision features. Therefore, we present an MCCL mechanism to learn consistent representation between image and text, achieving cross-modal semantic alignment. In addition, most objects are scattered in remote sensing images and exhibit a sparsity property due to the overhead view. However, the Transformer structure mines the objects’ relationships without considering the geometry information of the objects, leading to suboptimal capture of the spatial structure. To address this, a DG-former is designed to realize spatial alignment by introducing geometry information. We conduct experiments on three publicly available datasets (Sydney-Captions, UCM-Captions and RSICD), and the superior results demonstrate its effectiveness. Full article

Soil organic matter (SOM) is a key indicator of arable land quality and the global carbon cycle; accurate regional-scale SOM estimation is vitally significant for sustainable agricultural development and climate change research. This study evaluates a multisource data-fusion approach for improving cropland SOM prediction in Yucheng City, Shandong Province, China. We applied a Local Energy Weighted Discrete Wavelet Transform (LEW-DWT) to fuse multi-temporal Landsat 8 imagery (2014–2023). Quantitative analysis (e.g., Information Entropy and Average Gradient) demonstrated that LEW-DWT effectively preserved high-frequency spatial details and texture features of fragmented croplands better than traditional DWT and simple splicing methods. These were combined with 41 environmental predictors to construct composite Ev–Tn–Mm features (environmental variables, temporal NDVI features, and multi-temporal multispectral information). Random Forest (RF) and Convolutional Neural Network (CNN) models were trained and compared to assess the contribution of the fused data to SOM mapping. Key findings are: (1) Comparative analysis showed that the LEW-DWT fusion strategy achieved the lowest spectral distortion and highest spatial fidelity. Using the fused multitemporal dataset, the CNN attained the highest predictive performance for SOM (R² = 0.49). (2) Using the Ev–Tn–Mm features, the CNN achieved R² = 0.62, outperforming the RF model (R² = 0.53). Despite the limited sample size, the optimized shallow CNN architecture effectively extracted local spatial features while mitigating overfitting. (3) Variable importance analysis based on the RF model reveals that mean soil moisture is the primary single variable influencing the SOM, (relative importance 15.22%), with the NDVI phase among time-series features (1.80%) and the SWIR1 band among fused multispectral bands (1.38%). (4) By category, soil moisture-related variables contributed 45.84% of total importance, followed by climatic factors. The proposed multisource fusion framework offers a practical solution for regional SOM digital monitoring and can support precision agriculture and soil carbon management. Full article