Search Results (1,357)

As a common brain-computer interface (BCI) paradigm, electroencephalogram (EEG)-based motor imagery provides a critical pathway for both assistive technology to (restoring communication and control) and active rehabilitation (promoting neural plasticity and functional recovery). Domain adaptation has been shown to effectively enhance the decoding performance of motor intentions for target subjects by leveraging labeled data from source subjects. However, EEG data from source subjects often contains extensive personal privacy, and the direct access to source EEG data easily leads to privacy leakage issues. An important research topic is to achieve domain adaptation without directly accessing the source subjects’ raw data. To address this challenge, a privacy-preserving source-free domain adaptation framework, termed Transformer-based SFDA with Class-balanced Multicentric Dynamic Pseudo-labeling (T-CMDP), is proposed for cross-subject motor-imagery EEG classification. This framework consists of three coupled stages. In the source model training stage, a Transformer-based encoder combined with Riemannian manifold-aware feature extraction is employed to learn transferable and discriminative EEG feature representations. In the source-free target adaptation stage, only the pretrained source model is transferred to the target domain and adapted through knowledge distillation and information maximization, without accessing raw source EEG data. In the self-supervised learning stage, class-balanced multicentric prototypes and high-confidence pseudo-label updates are introduced to progressively refine the target-domain decision boundaries. Extensive experiments on three motor-imagery EEG datasets demonstrate that the proposed T-CMDP framework consistently outperforms eleven representative baselines from traditional machine learning, deep learning, and source-free transfer approaches, achieving average accuracies of 56.85%, 76.34%, and 74.49%, respectively. These results indicate that T-CMDP effectively alleviates inter-subject EEG distribution discrepancies and ensures the privacy preserving of source subjects, thereby facilitating more reliable and practical deployment of EEG-based BCI systems. Full article

This study investigates the influence of extraction method and solvent on the UV spectral characteristics of extracts obtained from selected agro-industrial waste materials. Conventional maceration and ultrasound-assisted extraction (UAE) were applied using distilled water and 70% (v/v) ethanol as solvents. The analyzed materials included spent coffee grounds, orange peel, rosehip, milk thistle, eucalyptus leaves, and chili pepper. UV spectrophotometric analysis (190–400 nm) was used to compare the absorption profiles of the obtained extracts and to evaluate the effect of extraction conditions on spectral features. The results showed that both solvent type and extraction technique significantly influenced the intensity and shape of the absorption spectra. Ethanol generally resulted in higher absorbance values and more defined spectral features in the 250–350 nm region, while aqueous extracts exhibited stronger absorption in the lower UV range. Overall, UV spectroscopy proved to be a rapid and effective screening tool for evaluating extraction performance and comparing spectral characteristics of complex plant extracts, supporting the valorization of agro-industrial waste. Total phenolic content (TPC) was additionally determined to support the evaluation of extraction efficiency. Full article

In the framework of integrated pest management, plant-based insecticides represent a promising tool for the control of insect pests. Indeed, N-alkylamides extracted from Acmella oleracea (L.) RK Jansen (Asteraceae) have been recently studied for their insecticidal properties. The encapsulation of these substances into stable formulations, like nanoemulsions (NEs), could boost their efficacy and stability. Herein, a N-alkylamide-enriched fraction (AEF) encapsulated into a stable NE was tested against Tuta absoluta (Meyrick) (Lepidoptera: Gelechiidae), a key tomato pest, able to develop resistance towards chemical insecticides. Acmella oleracea was reported to be effective against many target species, but this is the first time that this extract was tested against T. absoluta in terms of toxicity against eggs, ingestion toxicity on larvae and repellence on adults. The AEF, containing 42.8% of spilanthol, was prepared by combining two eco-friendly techniques, namely supercritical CO₂ extraction and wiped-film short path molecular distillation, and then encapsulated into a stable NE. Preliminary tests on the phytotoxicity of the AEF-NEs at 0.25 and 0.5% (w/w) a.i., compared with a control NE solution (i.e., the AEF-free NE) and a negative control (distilled water), showed a negative effect on tomato plants at the highest concentration. On this basis, three concentrations (0.06, 0.125, and 0.25% a.i.) were evaluated against eggs (topical toxicity), larvae of 2nd instar (ingestion and topical toxicity), and adults (ovideterrence) of T. absoluta. The results showed that all adopted AEF-NE concentrations caused a significant inhibition in egg hatching (>20%). The larval survival, at the end of the evaluation (72 h), in ingestion toxicity tests were significantly different in the AEF-NEs at 0.06, 0.12, and 0.25% (56.7, 33.3 and 26.7%, respectively) compared with control NE and distilled water (100% both). Similar results were obtained in the adult emergence in ingestion toxicity comparing AEF-NEs at 0.06, 0.12, and 0.25% (64.7, 50.0 and 75.0%, respectively) with control NE and distilled water (100% both). Finally, a significant ovideterrent effect was shown by the concentrations 0.125 and 0.25% of the AEF-NEs (% of egg laid: 7.5 and 27.4% respectively), compared with distilled water. Overall, the AEF-NE tested showed promising and encouraging effectiveness as ovicidal and larvicidal against T. absoluta. This supports its potential use as an effective alternative to synthetic products for the control of this important pest. Full article

This study focuses on the evaluation of eco-friendly corrosion inhibitors derived from extracts of Rhus typhina L. leaves, collected in August during the summer season, on OLC45 metal surfaces in a 0.5 M H₂SO₄ corrosive environment. The extracts were obtained using the microwave extraction technique and characterized by HPLC. The protective properties of OLC45 coated with LESRT (leaf extract collected in summer from Rhus typhina L.) were examined by potentiostatic and potentiodynamic polarization procedures and electrochemical impedance spectroscopy (EIS) in 0.5 M H₂SO₄. The application of the Langmuir isotherm revealed high values of the adsorption constant and standard free energies (ΔG°_ads), suggesting a possible mixed adsorption process with an increased tendency toward chemisorption. The influence of temperature on the electrochemical behavior of OLC45 samples in H₂SO₄, both in the absence and presence of two extracts derived from Rhus typhina leaves at a concentration of 1000 ppm, was investigated over the temperature range of 293–333 K. A comparison of the two inhibitors’ effectiveness revealed high inhibitory efficiency, up to 91% at 1000 ppm LESRT₁ (methanol/double-distilled water (50%:50%, v/v)) and 92% for LESRT₂ (ethanol/double-distilled water (50%:50%, v/v)) at 1000 ppm LESRT₂. Full article

Photovoltaic (PV) power stations are pivotal for the renewable energy transition, yet their operational efficiency is often compromised by defects such as surface dust accumulation and cracks. Traditional manual inspections are labor-intensive and subjective, while conventional monitoring methods struggle with environmental interference. This study proposes YOLO-MSG, a lightweight framework specifically designed for the automated detection of PV module defects during system operation, including normal panels as well as defective conditions such as dusty and cracked panels. The methodology integrates a Multi-Scale Grouped Convolution (MSGC) module for enhanced feature extraction and a Group-Stem Decoupled Head (GSD-Head) to reduce parameter redundancy. Furthermore, a joint optimization strategy involving LAMP and logits-based knowledge distillation is employed to facilitate edge deployment. Experimental results on a specialized PV defect dataset demonstrate that YOLO-MSG achieves a superior balance between detection accuracy and computational cost. Compared to state-of-the-art models like YOLO11 and YOLOv12, YOLO-MSG significantly reduces GFLOPs and parameter count while maintaining highly competitive mean Average Precision (mAP), with improvements of 1.35% in mAP and 2.37% in mAP50-95 over the baseline models. Specifically, the model achieves an average inference speed of 90.30 FPS on the NVIDIA Jetson AGX platform. These findings confirm the algorithm’s industrial viability, providing a robust and efficient solution for the real-time automated maintenance of photovoltaic infrastructures. Full article

Cattle behavior constitutes important phenotypic information reflecting animals’ health status, activity level, and welfare condition, and is therefore of considerable significance for automated monitoring and precision management in smart livestock farming. However, under complex barn conditions, cattle behavior recognition is easily affected by factors such as illumination variation, partial occlusion, background interference, and individual differences, thereby reducing recognition stability and generalization capability. To address these challenges, this study proposes a pose-driven method for cattle behavior recognition in complex barn environments. First, a 16-keypoint annotation scheme suitable for describing bovine posture, termed cow16, was constructed. Based on this scheme, OpenPose was employed to extract heatmaps (HMs) and part affinity fields (PAFs), which were then used to build an intermediate HM/PAF posture representation. Subsequently, this representation was taken as the input to a lightweight convolutional neural network for classifying three behavioral categories: stand, walk, and lying. On this basis, class-imbalance correction during training and a multi-random-seed logits ensemble strategy during inference were further introduced. In addition, knowledge distillation was adopted to transfer knowledge from a high-performance teacher model to a lightweight student model. Experimental results demonstrate that training-stage class-imbalance correction and inference-stage multi-random-seed logits ensembling exhibit strong complementarity; when combined, the AB configuration improves the test-set Macro-F1 by 3.83 percentage points. Moreover, the distilled student model still achieves competitive recognition performance while maintaining 1× inference cost, indicating a favorable trade-off between accuracy and efficiency. This study provides a useful reference for deployment-oriented cattle behavior recognition in smart farming scenarios and offers a lightweight technical basis for subsequent practical applications. Full article

Hexavalent chromium, a widespread heavy metal, induces apoptosis via the mitochondrial pathway through Bax (pro-apoptotic) and Bcl2 (anti-apoptotic) proteins. Hypericum perforatum, rich in antioxidants, can neutralise free radicals. This study investigated the effects of CrVI on the pancreas and the protective role of Hypericum perforatum. Five groups of animals were used: control, Cr (CrVI for 3 months), CrH (CrVI + 2.5% Hypericum perforatum extract made from flowers, for 3 months), Cr2 (CrVI for 3 months + distilled water for 1 month), and CrH2 (CrVI for 3 months + Hypericum perforatum extract for 1 month). Samples were collected for histological analysis, gene expression (qRT-PCR), and blood glucose level analysis. CrVI exposure (Cr, Cr2) caused pancreatic damage: oedema, reduced islet size, endocrine cell vacuolisation, and endothelial swelling. Lesions were milder in CrH, while CrH2 resembled the control group. The Bax/Bcl2 ratio increased under CrVI (highest in Cr2), indicating apoptosis, but decreased toward control values in CrH and CrH2. Blood glucose levels confirmed these findings. CrVI proved toxic to the endocrine pancreas, inducing structural and molecular alterations that impaired carbohydrate metabolism. Administration of Hypericum perforatum extract reduced these effects, confirming its antioxidant action and potential as a protective agent against CrVI-induced oxidative stress. Full article

Recent automated search methods have improved lower bounds for several Ramsey numbers, but the strongest gains often depend on structured seeding and cell-specific heuristic discovery. This leaves open a more fundamental question: Can a useful search structure be transferred across related Ramsey cells rather than rediscovered independently for each target instance? This work proposes a teacher–student framework for transferable structural search in Ramsey graph construction, inspired by the structure-distillation logic of Physics Structure-Informed Neural Networks (Ψ-NNs). The framework builds compressed structural representations from teacher witnesses and search traces, extracts reusable motifs and relations, and reconstructs transfer candidates. These are refined by balanced search and, for weak R(3, s) cells, by exact small-cell supervision. The framework is evaluated as a proof of concept across five Ramsey cells under transfer, matched-compute, search, ablation, and interpretability settings, including a proportional shift-scaling baseline and a greedy triangle-closing baseline that probe the structure-validity frontier from complementary directions. Supplementary experiments cover seed robustness, budget sensitivity, transfer-neighborhood variation, structural-resolution changes, stronger exact supervision, cross-r teacher pooling, single-teacher configurations, and scaling behavior across graph sizes. The results show that the portfolio version of the framework is the strongest balanced transfer method in the current study, while a structure-dominant oracle achieves stronger witness-shape agreement but worse Ramsey-valid construction. These findings reveal a clear structure-validity frontier and suggest that transferable Ramsey search should be evaluated by how well structural priors survive the validity constraints of new cells. Full article

Personalized federated learning (PFL) faces significant challenges in resource-constrained edge environments, where strict communication budgets and severe system heterogeneity must be jointly addressed. Although one-shot federated learning reduces communication overhead, existing methods typically impose unified model architectures or rely on coarse manual selection strategies, limiting their adaptability to highly heterogeneous data distributions and restricting personalized representation capability. To overcome these limitations, we propose Personalized Federated Zero-shot Knowledge Distillation (pFedZKD), a data-free one-shot federated learning framework designed for structurally heterogeneous scenarios. The framework follows a decouple-and-reconstruct collaborative paradigm. On the client side (decoupling stage), we introduce Particle Swarm Optimization-based Federated Neural Architecture Search (PSO-FedNAS), a gradient-free neural architecture search method that enables each client to autonomously discover a customized convolutional architecture aligned with its local data distribution, eliminating the need for architectural consistency across clients. On the server side (reconstruction stage), to address parameter-space incompatibility caused by structural heterogeneity, we develop an architecture-agnostic multi-teacher zero-shot knowledge distillation mechanism (Multi-ZSKD). This method synthesizes pseudo-samples in latent space to extract semantic consensus from heterogeneous client models and transfers the aggregated knowledge to a unified global student model without accessing real data. The entire collaborative process is completed within a single communication round, substantially reducing communication cost while enhancing privacy preservation. Extensive experiments on MNIST, FashionMNIST, SVHN, and CIFAR-10 under heterogeneous data settings demonstrate that pFedZKD consistently achieves superior personalization accuracy, global generalization performance, and communication efficiency compared with state-of-the-art PFL methods. Full article

In natural agricultural environments, plant disease monitoring faces significant challenges, including a highly uneven (long-tail) distribution of disease species, tiny scales of early-stage lesions, and complex, variable backgrounds. These factors hinder the ability of existing lightweight models to balance detection accuracy and computational efficiency. To address these issues, this paper proposes a detection scheme driven by the synergy of data distribution reshaping and model architecture optimization. At the data level, we propose the CALM-Aug augmentation strategy. Based on the statistical distribution characteristics of disease categories, this strategy utilizes object-level copy-paste logic to specifically compensate for the feature shortcomings of rare disease samples. It introduces a teacher-guided screening mechanism and employs accept–reject sampling to ensure the pathological consistency of the augmented samples, thereby alleviating the model’s inductive bias toward head categories. At the model architecture level, using YOLOv11 as the baseline, the YOLO11-ARL model adapted to agricultural scenarios is constructed. It enhances sensitivity to early point-like disease spots through Efficient Multi-Scale Convolutional Pyramids and lightweight decoupled detection heads. Furthermore, a Layer-wise Adaptive Feature-guided Distillation Pruning (LAFDP) algorithm is utilized to extract a lightweight version, YOLO11-ARL-PD, achieving a significant reduction in parameters and computational cost. Experimental results on the PlantDoc dataset show that the final model achieves a precision of 89.0% and an mAP@0.5 of 85.3%. Compared to the baseline model YOLOv11n, YOLO11-ARL-PD improves precision and average precision by 7.7 and 2.6 percentage points, respectively, while reducing parameters by 51.93% and weights by 46.15%. Cross-dataset tests prove the good generalization performance of the proposed method. This study indicates that, under lightweight constraints, jointly optimizing the training distribution and model architecture is an effective way to improve plant disease monitoring and to support the edge deployment of smart crop-protection systems. All resources for CALM-Aug are available at wyz-2004/CALM-Aug on GitHub. Full article

To address the challenges of sensor installation limitations, severe background noise interference, and low model deployment efficiency in rolling bearing fault diagnosis in industrial environments, this paper proposes a lightweight, progressive fusion and knowledge-distillation diagnostic framework that integrates vibration and sound signals. First, considering the differences in physical characteristics between vibration and sound signals, a feature-extraction network for heterogeneous modality perception is designed: the vibration branch employs a large-kernel one-dimensional convolutional neural network, while the sound branch uses a small-kernel stacked two-dimensional convolutional neural network, with depthwise separable convolutions introduced for lightweight modification. Second, an attention-gated progressive feedback fusion strategy is proposed. Learnable gating units are used to filter the confidence of the fused features, feeding them back to the original input as residuals, effectively suppressing noise accumulation and improving fusion quality. Finally, a cross-architecture knowledge-distillation scheme is constructed, transferring the fault feature-discrimination ability from the deep heterogeneous fusion network (teacher network GAF-Net) to the lightweight LightGBM (student network Distilled-LGB). Combined with a normal sample statistical feature alignment mechanism, the student model can independently complete end-to-end fault diagnosis only with online-extractable handcrafted features, achieving microsecond-level pure model inference speed while ensuring diagnostic accuracy, fully meeting industrial edge deployment requirements. Experiments on a self-built industrial dataset and the public UOEMD-VAFCVS dataset show that GAF-Net achieves 97.89% (A → B) and 96.72% (15 Hz → 30 Hz) accuracy. Distilled-LGB achieves 21 ms inference time and 4.2 MB model size with <1% accuracy loss, demonstrating noise robustness, cross-condition generalization, and edge deployment capability. Full article

To improve detection accuracy for color-sensitive and small-target defects in steel cord ply, this paper introduces an improved YOLOv8s algorithm using multi-teacher stepwise hierarchical knowledge distillation for better adaptation across production lines. The improvements include: replacing the initial backbone convolutional layer with RGBV grouped convolution to enhance color feature extraction; substituting the SPPF module with SPPFCSPC-LSKA to improve multi-scale perception; and optimizing bounding box accuracy with the WIoU loss function. The multi-teacher distillation approach first transfers color feature learning using an RGBV-only teacher, then multi-scale feature learning with an SPPFCSPC-LSKA-only teacher. Experimental results show the improved model achieved 90.4% precision, 92.0% recall, 91.2% F1-score, and 97.2% mAP@0.5, surpassing the baseline YOLOv8s by 1.9, 2.2, 2.1, and 3.4 percentage points, respectively. The proposed model also achieves an inference time of 3.9 ms, representing a 1.0 ms reduction compared to the baseline. On a smaller dataset from another production line, single-teacher distillation increased precision, recall, F1-score, and mAP@0.5 to 84.6%, 82.0%, 83.3%, and 88.8%, respectively, albeit with an increase in inference time. The multi-teacher strategy further increased metrics to 97.5% precision, 88.8% recall, 92.9% F1-score, and 94.3% mAP@0.5, providing additional gains over single-teacher distillation while maintaining the same parameter count of 11.127 M and achieving a faster inference time of 4.1 ms on the target production line. Full article

As autonomous driving technology advances, the deployment of autonomous vehicles in urban environments is rapidly increasing. Lens flare—an often overlooked optical artifact in object detection research—can lead to increased false positives or missed detections, particularly in the challenging conditions inherent to autonomous driving. Current mitigation methods are often ill-suited for real-time implementation. This work proposes a solution to alleviate the adverse effects of lens flare by utilizing a lightweight lens flare perception network, eliminating the need for additional hardware or complex image pre-processing. Specifically, we propose a reference-free model utilizing a ResNet18 backbone integrated with a lightweight Multi-Layer Perceptron (MLP) to extract and leverage lens flare information. This model is developed via a teacher–student framework, which was distilled from an end-to-end reference-based model optimized using the Learned Perceptual Image Patch Similarity (LPIPS) metric. Our experiments demonstrate that incorporating lens flare information significantly enhances the performance of the baseline object detection network, outperforming previous mitigation methods by a substantial margin. The proposed method can be seamlessly integrated into existing object detectors and requires only an efficient training process, facilitating its deployment in practical autonomous driving tasks. Full article

Rakı, a traditional distilled beverage produced from grapes, holds significant economic importance in Türkiye; however, comprehensive consumer-focused sensory research remains limited. This study aims to determine the aroma profile, sensory characteristics, and consumer preferences of commercial rakı to guide producers in aligning product characteristics with consumer expectations. Nine commercial rakı samples were evaluated. The aroma composition was analyzed using SBSE-GC-MS. Sensory attributes were assessed by a trained panel through descriptive analysis (DA) and by 100 consumers utilizing the Check-All-That-Apply (CATA) method alongside a liking test. Eighty-one aroma compounds were identified, predominantly the phenylpropanoids trans-anethole and estragole, with monoterpenes and sesquiterpenes dominating the secondary profile. Integrating instrumental data with DA evaluations suggests that anethole and sesquiterpenes likely contribute to the attributes related to visual coating, body, creamy, mastic, persistency, and complexity. Consumer profiling revealed two distinct preference groups. Older, frequent consumers preferred complex, high-alcohol profiles with trigeminal harshness and visual glass coating, whereas younger, casual consumers preferred smoother rakı with a traditional white appearance, reacting negatively to “boiled aniseed” flavors and the yellowish tint of oak-aged versions. The CATA technique effectively distinguished these profiles. To enhance overall product quality, producers should eliminate “boiled” defects and adjust sensory profiles: complex products for experienced consumers and visually traditional, smooth profiles for younger consumers. According to current knowledge, this is the first study to employ the CATA method alongside consumer profiling and preference mapping in the sensory evaluation of rakı. Full article

The aim of this study was to comprehensively characterize lavender pellets produced from post-distillation residues and evaluate their multifunctional valorization potential. Physicochemical properties, including moisture, ash, heating value, organic matter, total and organic carbon, macro- and micronutrients, potentially toxic heavy metals, polyphenols, microbiological safety, and nutritive composition, were assessed. The pellets demonstrated an energy content comparable to other agricultural residues, with a higher heating value of 18,900 kJ/kg and a lower heating value of 16,603 kJ/kg. High organic matter (87%) and a slightly acidic pH support soil moisture retention, while favorable macronutrient levels enhance their suitability as a soil amendment. Water-based extractions (infusion and decoction) achieved higher yields (15.60–21.66%) than ethanol (13.04%) and more effectively recovered bioactive polyphenols, particularly rosmarinic and chlorogenic acids. Low moisture and water activity ensured storage stability and minimal microbial growth, which was confirmed by microbiological safety tests. Nutritionally, pellets contained moderate protein (9.38%), high cellulose (33.38%), and low fat (2.18%), with total amino acids of 8.91 g/100 g and 36.7% essential amino acids, along with a favorable fatty acid profile rich in polyunsaturated fractions. Overall, these findings highlight lavender pellets as a sustainable resource for energy, soil improvement, bioactive compound recovery, and complementary animal feed within circular economy frameworks. However, future research should focus on investigating whether residual compounds remain in lavender residues that could exert antifeedant or phytotoxic effects. Additionally, the potential for the sequential valorization of lavender residues should be explored, initially through the extraction of bioactive phenols, followed by pellet production for use as fuel or soil amendments. This approach would enable multiple cascading uses and maximize their contribution to comprehensive circular economy strategies. Full article