Search Results (1,288)

The photovoltaic field has seen significant development in recent years, with continuously expanding installation capacity and increasing grid integration. However, due to the intermittency of solar energy and meteorological variability, PV output power poses serious challenges to grid security and dispatch reliability. Traditional forecasting methods largely rely on modeling historical power and meteorological data, often neglecting the consideration of cloud movement, which constrains further improvement in prediction accuracy. To enhance prediction accuracy and model interpretability, this paper proposes a dual-branch attention-based PV power prediction model that integrates physical features from ground-based cloud images. Regarding input features, a cloud segmentation model is constructed based on the vision foundation model DINO encoder and an improved U-Net decoder to obtain cloud cover information. Based on deep feature point detection and an attention matching mechanism, cloud motion vectors are calculated to extract cloud motion speed and direction features. For feature processing, feature attention and temporal attention mechanisms are introduced, enabling the model to learn key meteorological factors and critical historical time steps. Structurally, a parallel architecture consisting of a linear branch and a nonlinear branch is adopted. A context-aware fusion module adaptively combines the prediction results from both branches, achieving collaborative modeling of linear trends and nonlinear fluctuations. Comparative experiments were conducted using two years of engineering data. Experimental results demonstrate that the proposed model outperforms the benchmarks across multiple metrics, validating the predictive advantages of the dual-branch structure that integrates physical features under complex weather conditions. Full article

Background/Objectives: Rapid and accurate diagnosis of acute appendicitis is crucial for patient health and management, and the diagnostic process can be prolonged due to varying clinical symptoms and limitations of diagnostic tools. This study aims to shorten the timeframe for these vital processes and increase accuracy by developing a quantum-inspired hybrid model to identify appendicitis types. Methods: The developed model initially selects the two most performing architectures using four convolutional neural networks (CNNs) and two Transformers (ViTs). Feature extraction is then performed from these architectures. Phase-based trigonometric embedding, low-order interactions, and norm-preserving principles are used to generate a Quantum Feature Map (QFM) from these extracted features. The generated feature map is then passed to the Multiple Head Attention (MHA) layer after undergoing Hadamard fusion. At the end of this stage, classification is performed using a multilayer perceptron (MLP) with a ReLU activation function, which allows for the identification of acute appendicitis types. The developed quantum-inspired hybrid model is also compared with six different CNN and ViT architectures recognized in the literature. Results: The proposed quantum-inspired hybrid model outperformed the other models used in the study for acute appendicitis detection. The accuracy achieved in the proposed model was 97.96%. Conclusions: While the performance metrics obtained from the quantum-inspired model will form the basis of deep learning architectures for quantum technologies in the future, it is thought that if 6G technology is used in medical remote interventions, it will form the basis for real-time medical interventions by taking advantage of quantum speed. Full article

Background: Executive functions, notably attention and processing speed, are essential for athletic performance, especially in sports that require quick reactions and decision-making under pressure. The current study aims to assess the impact of the SmartACT program—a psychological intervention that includes acceptance and commitment therapy, hypnosis, and guided imagery—on attentional processes and psychological flexibility in adolescent student-athletes. Methods: This 7-week quasi-experimental controlled study investigated the efficacy of SmartACT in adolescent student-athletes aged 15 to 18. A total of 309 individuals were divided into three groups using convenience sampling: SmartACT (n = 93), MAC (Mindfulness–Acceptance–Commitment, the standardized Gardner & Moore technique; n = 109), and control (n = 107). The d2 test was used to examine attention and visual processing, while the Acceptance and Action Questionnaire—II (AAQ-II) was used to assess psychological flexibility, both before and after the intervention. The data were analyzed using mixed-design repeated-measures ANOVA and paired-samples t-tests. Results: The SmartACT group showed significant improvement on both tests, specifically in the total number of items processed in the d2 test (457.83 to 600.24; p < 0.001), and experiential avoidance, measured by AAQ-II, decreased (18.48 to 12.80; p < 0.001), indicating increased psychological flexibility. Conclusions: The main findings of our study suggest that integrating ACT with hypnosis and imagery may enhance cognitive attentional functions and psychological flexibility in adolescent student-athletes. Full article

Short-term traffic prediction is vital for intelligent transportation systems, enabling adaptive congestion control, real-time signal management, and dynamic route planning for autonomous vehicles (AVs). This study introduces a custom Transformer-based deep learning framework for joint forecasting of traffic flow and vehicle speed, leveraging handcrafted positional encoding and stacked multi-head attention layers to model multivariate traffic patterns. Evaluated against baselines including Long Short-Term Memory (LSTM), Support Vector Machine (SVM), Random Tree, and Random Forest on the Next-Generation Simulation (NGSIM) dataset, the model achieves 94.2% accuracy (Root Mean Squared Error (RMSE) 0.16) for flow and 92.1% accuracy for speed, outperforming traditional and deep learning approaches. A hybrid evaluation metric, integrating RMSE and threshold-based accuracy tailored to AV operational needs, enhances its practical relevance. With its parallel processing capability, this framework offers a scalable, real-time solution, advancing AV ecosystems and smart mobility infrastructure. Full article

Fused Deposition Modeling (FDM) is a widely used additive manufacturing technique that enables the fabrication of components using polymeric and composite materials; however, the mechanical performance of printed parts is jointly influenced by multiple printing parameters, which complicates the control and prediction of their mechanical properties. In this study, an attention-enhanced multi-modal convolutional neural network (ATT-MM-CNN) is developed to predict the tensile performance of carbon fiber reinforced polylactic acid (PLA-CF) composites manufactured by FDM. Four key printing parameters, layer thickness, nozzle temperature, material flow rate, and printing speed, are systematically investigated, resulting in 256 parameter combinations and corresponding tensile test data for constructing a multi-modal dataset. By integrating multi-modal feature representations and incorporating an attention mechanism, the proposed model effectively learns the nonlinear relationships between printing parameters and mechanical performance under multi-parameter conditions. The results show that all evaluation metrics, including accuracy, precision, recall, and F1-score, exceed 0.95, and the prediction accuracy is improved by at least 17.3% compared with baseline models. These findings demonstrate that the proposed ATT-MM-CNN provides an effective and reliable framework for tensile property prediction and process-parameter optimization of FDM-printed composite structures. Full article

This study discusses the issue of designing reverse curves, i.e. a geometric system consisting of two circular arcs (usually with different radii), directed in opposite directions and directly connected to each other. The design is performed in an appropriate local Cartesian coordinate system. The origin of this system is located at the point of intersection of adjacent main directions of the route. Unlike other geometric situations, reverse curves have three main directions, which significantly complicate the design process. The initial values of the radii of the reverse arcs must correspond to the existing system of main directions. The introduction of transition curves causes these radii to decrease; their values are determined iteratively. A set of formulas for creating a geometric system of reverse curves is presented. These formulas were used in the calculation example. A graph of the horizontal curvature of the track axis and a method for determining the possible train speed, both without the use of cant on an arc and with the use of cant, are shown. The presented procedure is universal and can be applied to other geometric situations involving the design of reverse curves. It is also necessary to emphasize the practical usefulness of the discussed method not only in the design process, but also to pay attention to the cognitive value of the article. Full article

Background: This study examines whether participation in STEAM-based educational activities is associated with improvements in executive functions (EFs) and cognitive skills in children with Attention Deficit Hyperactivity Disorder (ADHD). Methods: A total of 60 children diagnosed with ADHD (mean age = 8 years) participated, with 30 following a traditional educational approach and 30 engaged in STEAM-based activities. Executive functions and cognitive abilities were assessed using standardized instruments (BRIEF, WISC-V, CARAS-R), and data were analyzed with IBM SPSS Statistics 25. Results: Children in the STEAM group outperformed the control group across several domains, showing statistically significant gains in inhibition, planning and organization, verbal comprehension, visuospatial skills, processing speed, total IQ, efficiency, and the Impulsivity Control Index (ICI). Conclusions: These findings suggest that STEAM-based educational experiences may support neurodevelopmental growth and enhance cognitive and executive functioning in children with ADHD, although causal inferences cannot be drawn due to the cross-sectional design. Full article

Acquired brain injury (ABI) often results in cognitive and motor impairments that can compromise driving ability, an essential aspect of independence and social participation. This study utilized a custom-designed driving simulator to compare driving performance between individuals with ABI and controls, and to examine the relationship between cognitive performance and driving behavior within the control group. All participants completed a series of standardized driving simulation tasks of varying complexity. The control group also completed a neuropsychological battery that assessed attention, processing speed, executive function, and visuospatial abilities. Simulator data were analyzed using generalized linear mixed models to evaluate group differences and, for the control group, cognitive predictors of performance. Results showed that individuals with ABI performed comparably to controls in basic operational tasks but demonstrated reduced performance in cognitively demanding scenarios requiring sustained attention, visuospatial monitoring, and adaptive control, such as rural driving, vehicle following, and parking. In the control group, strong associations were found between simulator outcomes and measures of attention, processing speed, and spatial orientation. The findings support the use of simulator-based assessment as an objective tool sensitive to post-injury impairments and highlight its links to cognitive domains relevant to driving. Full article

The growing need for self-powered Internet of Things networks has raised interest in converting abundant waste into reliable energy harvesters despite long-standing material and technology challenges. As demand for environmentally friendly self-powered IoT devices continues to rise, attention toward green waste as an eco-friendly energy source has strengthened. However, its direct utilisation in high-performance energy harvesters remains a significant challenge. Driven by the growing need for renewable sources, the triboelectric nanogenerator has emerged as an innovative technology for converting mechanical energy into electricity. In this work, the design, fabrication, and characterisation of a rotating triboelectric energy harvester as a prototype device employing date seed waste as the tribopositive layer are presented. The date seeds particles, measuring 1.2 to 2 mm, were pulverised using a grinder, mixed with epoxy resin, and subsequently applied to the grating-disc structure. The coated surface was machined on a lathe to provide a smooth surface facing. The performance of the prototype was evaluated through a series of experiments to examine the effects of rotational speed, the number of grating-disc structures, the epoxy mixing process, and the prototype’s influence on the primary system, as well as to determine the optimal power output. An increase in rotational speed (RPM) enhanced power generation. Furthermore, increasing the number of gratings and pre-mixing of epoxy with the biomaterial resulted in enhanced output power. Additionally, with 10 gratings, operating at 1500 rpm, and a 24 h pre-mixing method, the harvester achieved maximum voltage and power outputs of 129 volts and 1183 μW at 7 MΩ. Full article

Hyperspectral image (HSI) and light detection and ranging (LiDAR) data offer complementary spectral and structural information; however, the integration of these high-dimensional, heterogeneous modalities poses significant challenges. We propose a Global–Local Mamba dual-modality fusion framework (GL-Mamba) for HSI–LiDAR classification. Each sensor’s input is decomposed into low- and high-frequency sub-bands: lightweight 3D/2D CNNs process low-frequency spectral–spatial structures, while compact transformers handle high-frequency details. The outputs are aggregated using a global–local Mamba block, a state-space sequence model that retains local context while capturing long-range dependencies with linear complexity. A cross-attention module aligns spectral and elevation features, yielding a lightweight, efficient architecture that preserves fine textures and coarse structures. Experiments on Trento, Augsburg, and Houston2013 datasets show that GL-Mamba outperforms eight leading baselines in accuracy and kappa coefficient, while maintaining high inference speed due to its dual-frequency design. These results highlight the practicality and accuracy of our model for multimodal remote-sensing applications. Full article

Stroke often results in lasting cognitive impairments that severely reduce independence and quality of life. Traditional neuropsychological assessments rely on mean scores that provide an average estimate of overall cognitive function but neglect the fluctuations in performance. The variability in performance can be captured as inconsistency, i.e., fluctuations across multiple trials within a single task or as dispersion, i.e., fluctuations across multiple tasks. While inconsistency has been extensively studied, the impact of post-stroke cognitive impairment on cognitive dispersion is unknown. In this study, ninety-five stroke survivors (41 cognitively impaired and 54 cognitively normal) completed a neuropsychological battery that captured performance across five cognitive domains: executive function, attention, memory, language, and processing speed. We compared the stroke groups on across- and within-domain cognitive dispersion. Cognitively impaired stroke individuals showed elevated dispersion within executive function compared to cognitively normal individuals. The two groups did not differ on any other within-domain or across-domain cognitive dispersion. Post-stroke cognitive impairment increased variability within executive functioning. Incorporating cognitive dispersion into routine post-stroke assessment can advance clinical practice by identifying subtle cognitive instability, anticipate supportive needs, and tailor rehabilitation plans for improving stroke care. Full article

In recent years, with changes in dietary structure, beef has become the third most consumed meat in China after pork and chicken, with its consumption increasing by approximately 50%. The quality and commercial value of beef vary considerably across different muscles. However, due to the high similarity in the appearance of beef cuts and strong background interference, traditional image features are often insufficient for accurate classification. In this study, an improved convolutional neural network based on YOLOv11 was proposed. Four beef muscles were categorized: sirloin (longissimus dorsi), fillet/tenderloin (psoas major), oyster blade (infraspinatus), and ribeye (longissimus thoracis). A dataset comprising 3598 images was established to support model training and validation. We divided the dataset into training, testing, and validation sets in a 6:2:2 ratio. To enhance model performance, wavelet convolution (WTConv) was employed to effectively expand the receptive field and improve image understanding, while a large separable kernel attention (LSKA) module was introduced to strengthen local feature representation and reduce background interference. Comparative experiments were conducted with other deep learning models as well as ablation tests to validate the proposed model’s effectiveness. Experimental results demonstrated that the proposed model achieved a classification accuracy of 98.50%, with Macro-Precision and Macro-Recall reaching 97.38% and 97.38%, respectively, and a detection speed of 147.66 FPS. These findings confirm the potential of the YOLOv11n-cls model for accurate beef classification and its practical application in intelligent meat recognition and processing within the Chinese beef industry. Full article

Maritime UAV operations face challenges in real-time ship detection. Complex ocean backgrounds, drastic scale variations, and prevalent distant small targets create difficulties. We propose MCB-RT-DETR, a real-time detection transformer enhanced by multi-component boosting. This method builds upon the RT-DETR architecture. It significantly improves detection under wave interference, lighting changes, and scale differences. Key innovations address these challenges. An Orthogonal Channel Attention (Ortho) mechanism preserves high-frequency edge details in the backbone network. Receptive Field Attention Convolution (RFAConv) enhances robustness against background clutter. A Small Object Detail Enhancement Pyramid (SOD-EPN) strengthens small-target representation. SOD-EPN combines SPDConv with multi-scale CSP-OmniKernel transformations. The neck network integrates ultra-lightweight DySample upsampling. This enables content-aware sampling for precise multi-scale localization. The method maintains high computational efficiency. Experiments on the SeaDronesSee dataset show significant improvements. MCB-RT-DETR achieves 82.9% mAP@0.5 and 49.7% mAP@0.5:0.95. These correspond to improvements of 4.5% and 3.4% relative to the baseline model. Inference speed maintains 50 FPS for real-time processing. The outstanding performance in cross-dataset tests further validates the algorithm’s strong generalization capability on DIOR remote sensing images and VisDrone2019 aerial scenes. The method provides a reliable visual perception solution for autonomous maritime UAV operations. Full article

X-ray-based non-destructive testing technology plays a crucial role in the quality monitoring of aluminum alloy wheel hubs. Due to the characteristics of the casting process, wheel hub images often exhibit low contrast and a discrete distribution of defect edges. Existing methods often face problems such as poor feature extraction capability, low efficiency of cross-scale information fusion, and susceptibility to interference from complex backgrounds when detecting such defects. Therefore, this study proposes an innovative detection framework for defects in aluminum alloy wheel hubs. The model employs data preprocessing to enhance the quality of original images; integrates an asymmetric pinwheel-shaped convolution (PConv) with an efficient receptive field, enabling efficient focus on the edge feature information of discrete defects; innovatively constructs a Mamba-based two-stage feature pyramid network (MFDPN), which improves the network’s defect localization capability in complex scenarios via a secondary focusing-diffusion mechanism; and incorporates a channel and spatial attention block (CASAB), strengthening the model’s ability to resist interference from complex backgrounds. On our self-built wheel hub defect dataset, the proposed model outperforms the baseline by 7.2% in mAP50 and 5% in Recall at 39 FPS inference speed, thus validating its high practical utility for automated aluminum alloy wheel hub defect detection. Full article

Background/Objective: Neuroimmune and metabolic dysregulation have been increasingly implicated in the cognitive heterogeneity of autism spectrum disorder (ASD). However, it remains unclear whether anti-inflammatory diets engage distinct biological and cognitive pathways in autistic and neurotypical children. This study examined whether a 12-week anti-inflammatory dietary protocol produces group-specific neuroimmune–metabolic signatures and cognitive responses in autistic children, neurotypical children receiving the same diet, and untreated neurotypical controls. Methods: Twenty-two children (11 with ASD, six a on neurotypical diet [NT-diet], and five neurotypical controls [NT-control]) completed pre–post assessments of plasma IFN-γ, CXCL1, RANTES (CCL5), trimethylamine-N-oxide (TMAO), and an extensive ENI-2/WISC-IV neuropsychological battery. Linear mixed-effects models were used to test the Time × Group effects on biomarkers and cognitive domains, adjusting for age, sex, and baseline TMAO. Bayesian estimation quantified individual changes (posterior means, 95% credible intervals, and posterior probabilities). Immune–cognitive coupling was explored using Δ–Δ correlation matrices, network metrics (node strength, degree centrality), exploratory mediation models, and responder (≥0.5 SD domain improvement) versus non-responder analyses. Results: In ASD, the diet induced robust reductions in IFN-γ, RANTES, CXCL1, and TMAO, with decisive Bayesian evidence for IFN-γ and RANTES suppression (posterior P(δ < 0) > 0.99). These shifts were selectively associated with gains in verbal learning, semantic fluency, verbal reasoning, attention, and visuoconstructive abilities, whereas working memory and executive flexibility changes were heterogeneous, revealing executive vulnerability in individuals with smaller TMAO reductions. NT-diet children showed modest but consistent improvements in visuospatial processing, attention, and processing speed, with minimal biomarker changes; NT controls remained biologically and cognitively stable. Network analyses in ASD revealed a dense chemokine-anchored architecture with CXCL1 and RANTES as central hubs linking biomarker reductions to improvements in fluency, memory, attention, and executive flexibility. ΔTMAO predicted changes in executive flexibility only in ASD (explaining >50% of the variance), functioning as a metabolic node of executive susceptibility. Responders displayed larger coordinated decreases in all biomarkers and broader cognitive gains compared to non-responders. Conclusions: A structured anti-inflammatory diet elicits an ASD-specific, coordinated neuroimmune–metabolic response in which suppression of CXCL1 and RANTES and modulation of TMAO are tightly coupled with selective improvements in verbal, attentional, and executive domains. Neurotypical children exhibit modest metabolism-linked cognitive benefits and minimal immune modulation. These findings support a precision-nutrition framework in ASD, emphasizing baseline immunometabolic profiling and network-level biomarkers (CXCL1, RANTES, TMAO) to stratify responders and design combinatorial interventions targeting neuroimmune–metabolic pathways. Full article