Search Results (8,698)

Accurate detection and counting of wheat spikes are crucial for yield estimation and variety selection in precision agriculture. However, challenges such as complex field environments, morphological variations, and small target sizes hinder the performance of existing models in real-world applications. This study proposes FEWheat-YOLO, a lightweight and efficient detection framework optimized for deployment on agricultural edge devices. The architecture integrates four key modules: (1) FEMANet, a mixed aggregation feature enhancement network with Efficient Multi-scale Attention (EMA) for improved small-target representation; (2) BiAFA-FPN, a bidirectional asymmetric feature pyramid network for efficient multi-scale feature fusion; (3) ADown, an adaptive downsampling module that preserves structural details during resolution reduction; and (4) GSCDHead, a grouped shared convolution detection head for reduced parameters and computational cost. Evaluated on a hybrid dataset combining GWHD2021 and a self-collected field dataset, FEWheat-YOLO achieved a COCO-style AP of 51.11%, AP@50 of 89.8%, and AP scores of 18.1%, 50.5%, and 61.2% for small, medium, and large targets, respectively, with an average recall (AR) of 58.1%. In wheat spike counting tasks, the model achieved an R² of 0.941, MAE of 3.46, and RMSE of 6.25, demonstrating high counting accuracy and robustness. The proposed model requires only 0.67 M parameters, 5.3 GFLOPs, and 1.6 MB of storage, while achieving an inference speed of 54 FPS. Compared to YOLOv11n, FEWheat-YOLO improved AP@50, AP_s, AP_m, AP_l, and AR by 0.53%, 0.7%, 0.7%, 0.4%, and 0.3%, respectively, while reducing parameters by 74%, computation by 15.9%, and model size by 69.2%. These results indicate that FEWheat-YOLO provides an effective balance between detection accuracy, counting performance, and model efficiency, offering strong potential for real-time agricultural applications on resource-limited platforms. Full article

This paper provides a comprehensive overview of the application of fractional calculus in modern optimization methods, with a focus on its impact in artificial intelligence (AI) and computational science. We examine how fractional-order derivatives have been integrated into traditional methodologies, including gradient descent, least mean squares algorithms, particle swarm optimization, and evolutionary methods. These modifications leverage the intrinsic memory and nonlocal features of fractional operators to enhance convergence, increase resilience in high-dimensional and non-linear environments, and achieve a better trade-off between exploration and exploitation. A systematic and chronological analysis of algorithmic developments from 2017 to 2025 is presented, together with representative pseudocode formulations and application cases spanning neural networks, adaptive filtering, control, and computer vision. Special attention is given to advances in variable- and adaptive-order formulations, hybrid models, and distributed optimization frameworks, which highlight the versatility of fractional-order methods in addressing complex optimization challenges in AI-driven and computational settings. Despite these benefits, persistent issues remain regarding computational overhead, parameter selection, and rigorous convergence analysis. This review aims to establish both a conceptual foundation and a practical reference for researchers seeking to apply fractional calculus in the development of next-generation optimization algorithms. Full article

The emergence of advanced mobility systems, including Demand Responsive Transport (DRT), shared mobility, and Mobility as a Service (MaaS), has required a reassessment of the evaluation indicators for public transportation systems. Existing studies often address only limited aspects and lack a comprehensive, structured classification, while the unique impacts of advanced systems remain insufficiently captured. Moreover, little attention has been given to which indicators are suitable for simulation despite their growing role in transport planning. To fill these gaps, this study develops a structured classification of quantitative evaluation indicators from the existing literature, serving as a foundation for assessing advanced mobility systems. It highlights system-specific characteristics, identifies relevant indicators, and examines their correspondence with conventional ones. Furthermore, it explores the applicability of these indicators in simulation environments, offering guidance for selecting representative indicators in simulation setup, operational monitoring, and impact assessment. Finally, it highlights the potential of quantitative indicators to approximate qualitative ones, suggesting directions for future research in simulation-based evaluation. By integrating environmental, economic, and societal dimensions, this study contributes to a sustainability-oriented framework for evaluating advanced mobility systems, providing insights for both academic research and practical mobility planning. Full article

Unimodal brain–computer interfaces (BCIs) often suffer from inherent limitations due to the characteristic of using single modalities. While hybrid BCIs combining electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) offer complementary advantages, effectively integrating their spatiotemporal features remains a challenge due to inherent signal asynchrony. This study aims to develop a novel deep fusion network to achieve synergistic integration of EEG and fNIRS signals for improved classification performance across different tasks. We propose a novel Temporal-Spatial Fusion Network (TSFNet), which consists of two key sublayers: the EEG-fNIRS-guided Fusion (EFGF) layer and the Cross-Attention-based Feature Enhancement (CAFÉ) layer. The EFGF layer extracts temporal features from EEG and spatial features from fNIRS to generate a hybrid attention map, which is utilized to achieve more effective and complementary integration of spatiotemporal information. The CAFÉ layer enables bidirectional interaction between fNIRS and fusion features via a cross-attention mechanism, which enhances the fusion features and selectively filters informative fNIRS representations. Through the two sublayers, TSFNet achieves deep fusion of multimodal features. Finally, TSFNet is evaluated on motor imagery (MI), mental arithmetic (MA), and word generation (WG) classification tasks. Experimental results demonstrate that TSFNet achieves superior classification performance, with average accuracies of 70.18% for MI, 86.26% for MA, and 81.13% for WG, outperforming existing state-of-the-art multimodal algorithms. These findings suggest that TSFNet provides an effective solution for spatiotemporal feature fusion in hybrid BCIs, with potential applications in real-world BCI systems. Full article

Electrochemical CO₂ reduction reaction (CO₂RR) is a key technology for achieving carbon neutrality and efficient utilization of renewable energy, capable of converting CO₂ into high-value-added carbon-based fuels and chemicals. Copper (Cu)-based catalysts have attracted significant attention due to their unique performance in generating multi-carbon (C₂₊) products such as ethylene and ethanol; however, there are still many controversies regarding their complex reaction mechanisms, active sites, and the dynamic evolution of intermediates. In situ Raman spectroscopy, with its high surface sensitivity, applicability in aqueous environments, and precise detection of molecular vibration modes, has become a powerful tool for studying the structural evolution of Cu catalysts and key reaction intermediates during CO₂RR. This article reviews the principles of electrochemical in situ Raman spectroscopy and its latest developments in the study of CO₂RR on Cu-based catalysts, focusing on its applications in monitoring the dynamic structural changes of the catalyst surface (such as Cu⁺, Cu⁰, and Cu²⁺ oxide species) and identifying key reaction intermediates (such as *CO, *OCCO(*O=C-C=O), *COOH, etc.). Numerous studies have shown that Cu-based oxide precursors undergo rapid reduction and surface reconstruction under CO₂RR conditions, resulting in metallic Cu nanoclusters with unique crystal facets and particle size distributions. These oxide-derived active sites are considered crucial for achieving high selectivity toward C₂₊ products. Time-resolved Raman spectroscopy and surface-enhanced Raman scattering (SERS) techniques have further revealed the dynamic characteristics of local pH changes at the electrode/electrolyte interface and the adsorption behavior of intermediates, providing molecular-level insights into the mechanisms of selectivity control in CO₂RR. However, technical challenges such as weak signal intensity, laser-induced damage, and background fluorescence interference, and opportunities such as coupling high-precision confocal Raman technology with in situ X-ray absorption spectroscopy or synchrotron radiation Fourier transform infrared spectroscopy in researching the mechanisms of CO₂RR are also put forward. Full article

Chaenomeles japonica (Chaenomeles japonica Thunb. Lindl. ex Spach.) is gaining increasing attention due to its high nutritional value and potential for industrial use. The development of new breeding clones (potential new cultivars) with improved morphological and chemical properties is essential for enhancing its commercial cultivation. In this study, the impact of ozone in its gaseous form and cold storage on the morphological and chemical properties of newly selected Polish clones of Chaenomeles japonica was determined. Breeding clone ‘3b/1’ produced the largest fruits, with a significantly higher average weight of 99.8 g compared to other clones. Fruits of clones ‘3b/1’ and ‘7d/8’ had the greatest tolerance to mechanical damage, requiring the highest force and energy for puncture and showing the most extensive deformation. The highest ascorbic acid content was recorded in clone ‘4c/1’ (117.3 mg·100 g⁻¹), while clone ‘3b/1’ had the highest total phenolic content, reaching 373.92 mg GAE·100 g⁻¹. A 15 min ozone treatment led to an average increase of 5.3% in both ascorbic acid and total phenolic content. In contrast, cold storage for 60 days caused a reduction of approximately 29.66% of ascorbic acid. Clone ‘3b/1’ appears to be the potential new Polish cultivar and an introduction for cultivation due to its large fruit size, their high mechanical tolerance and relatively favorable chemical composition. Full article

The increasing prevalence of antimicrobial resistance and the persistent challenge of infectious diseases highlight the critical necessity for novel approaches that integrate pathogen management with swift detection methods. Carbon dots (CDs) are a versatile class of fluorescent nanomaterials that have garnered increasing attention owing to their tunable surface chemistry, strong photoluminescence, high stability, and biocompatibility. Recent studies demonstrate that CDs possess broad-spectrum antibacterial and antifungal activities via multiple mechanisms, including the generation of reactive oxygen species, disruption of membranes, inhibition of biofilms, and synergistic interactions with conventional antimicrobials. The performance is significantly affected by precursor selection, heteroatom doping, and surface functionalization, with minimum inhibitory concentrations reported to range from highly potent at the microgram level to moderate at elevated concentrations. The intrinsic fluorescence of CDs, in addition to their antimicrobial activity, facilitates their use as sensitive and selective probes for microbial detection, allowing for rapid and real-time monitoring in biomedical, food safety, and environmental settings. This review summarizes recent advancements in the antimicrobial properties of carbon dots (CDs) and their fluorescence-based applications in microbial detection. It emphasizes their theranostic potential and future prospects as multifunctional nanomaterials for combating infectious diseases and ensuring microbial safety. Full article

Electrocardiogram (ECG) waveform delineation is fundamental to cardiac disease diagnosis. This task requires precise localization of key fiducial points, specifically the onset, peak, and offset positions of P-waves, QRS complexes, and T-waves. Current methods exhibit significant performance degradation in noisy clinical environments (baseline drift, electromyographic interference, powerline interference, etc.), compromising diagnostic reliability. To address this limitation, we introduce ECG-SCFNet: a novel dual-stream architecture employing selective context fusion. Our framework is further enhanced by a consistency training paradigm, enabling it to maintain robust waveform delineation accuracy under challenging noise conditions.The network employs a dual-stream architecture: (1) A temporal stream captures dynamic rhythmic features through sequential multi-branch convolution and temporal attention mechanisms; (2) A morphology stream combines parallel multi-scale convolution with feature pyramid integration to extract multi-scale waveform structural features through morphological attention; (3) The Selective Context Fusion (SCF) module adaptively integrates features from the temporal and morphology streams using a dual attention mechanism, which operates across both channel and spatial dimensions to selectively emphasize informative features from each stream, thereby enhancing the representation learning for accurate ECG segmentation. On the LUDB and QT datasets, ECG-SCFNet achieves high performance, with F1-scores of 97.83% and 97.80%, respectively. Crucially, it maintains robust performance under challenging noise conditions on these datasets, with 88.49% and 86.25% F1-scores, showing significantly improved noise robustness compared to other methods and demonstrating exceptional robustness and precise boundary localization for clinical ECG analysis. Full article

With the proliferation of multimedia data, controllable summarization generation has become a key focus in Artificial Intelligence Content Generation. However, many traditional methods lack precise control over output length, often resulting in summaries that are either too verbose or too brief, thus failing to meet diverse user needs. In this paper, we propose a length-customizable approach for multimodal image-text summarization. Our method integrates combinatorial optimization with deep learning to address the length-control challenge. Specifically, we formulate the summarization task as a knapsack optimization problem, enhanced by a greedy algorithm to strictly adhere to user-defined length constraints. Additionally, we introduce a multimodal attention mechanism to ensure balanced and coherent integration of textual and visual information. To further enhance semantic alignment, we employ a cross-modal matching strategy for image selection based on pre-trained vision-language models. Experimental evaluations on the MSMO dataset and validate against baselines like LEAD-3, Seq2Seq, Attention, and Transformer that our method achieves a ROUGE-1 score of 40.52, ROUGE-2 of 16.07, and ROUGE-L of 35.15, outperforming existing length-controllable baselines. Moreover, our approach attains the lowest length variance, confirming its precise adherence to target summary lengths. These results validate the effectiveness of our method in generating high-quality, length-constrained multimodal summaries. Full article

Cannabidiol (CBD) and other phytocannabinoids are gaining attention for their therapeutic potential in cardiovascular disease (CVD), the world’s leading cause of death. This review highlights advances in understanding the endocannabinoid system, including CB1 and CB2 receptors, and the mechanisms by which CBD exerts anti-inflammatory, antioxidative, vasoprotective, and immunomodulatory effects. Preclinical and translational studies indicate that selective activation of CB2 receptors may attenuate atherogenesis, limit infarct size in ischemia–reperfusion injury, decrease oxidative stress, and lessen chronic inflammation, while avoiding the psychotropic effects linked to CB1. CBD also acts on multiple molecular targets beyond the CB receptors, affecting redox-sensitive transcription factors, vascular tone, immune function, and endothelial integrity. Early clinical trials and observational studies suggest that CBD may lower blood pressure, improve endothelial function, and reduce sympatho-excitatory peptides such as catestatin, with a favorable safety profile. However, limited bioavailability, small sample sizes, short study durations, and uncertainty about long-term safety present challenges to its clinical use. Further research is needed to standardize dosing, refine receptor targeting, and clarify the role of the endocannabinoid system in cardiovascular health. Overall, current evidence supports CBD’s promise as an adjunct in CVD treatment, but broader clinical use requires more rigorous, large-scale studies. Full article

The prediction of stock prices is challenging due to their volatility, irregular patterns, and complex time-series structure. Reliably forecasting stock market data plays a crucial role in minimizing financial risk and optimizing investment strategies. However, traditional models often struggle to capture temporal dependencies and extract relevant features from noisy inputs, which limits their predictive performance. To improve this, we developed an enhanced recursive feature elimination (RFE) method that blends the importance of impurity-based features from random forest and gradient boosting models with Kendall tau correlation analysis, and we applied SHapley Additive exPlanations (SHAP) analysis to externally validate the reliability of the selected features. This approach leads to more consistent and reliable feature selection for short-term stock prediction over 1-, 3-, and 7-day intervals. The proposed deep learning (DL) architecture integrates a temporal convolutional network (TCN) for long-term pattern recognition, a gated recurrent unit (GRU) for sequence capture, and multi-head attention (MHA) for focusing on critical information, thereby achieving superior predictive performance. We evaluate the proposed approach using daily stock price data from three leading companies—HDFC Bank, Tata Consultancy Services (TCS), and Tesla—and two major stock indices: Nifty 50 and S&P 500. The performance of our model is compared against five benchmark models: temporal convolutional network (TCN), long short-term memory (LSTM), GRU, Bidirectional GRU, and a hybrid TCN–GRU model. Our method consistently shows lower error rates and higher predictive accuracy across all datasets, as measured by four commonly used performance metrics. Full article

Background/Objectives: Behavioral variant frontotemporal dementia (bvFTD), the most prevalent clinical subtype within the frontotemporal lobar degeneration spectrum disorders, is characterized by early and prominent changes that significantly disrupt everyday functioning. This study aims to identify the key correlates of functional status in bvFTD by investigating the relative contributions of cognitive deficits, behavioral disturbances, personality changes, and brain perfusion abnormalities. Additionally, it seeks to develop a theoretical framework to elucidate how these factors may interconnect and shape unique functional profiles. Methods: A total of 26 individuals diagnosed with bvFTD were recruited from the 2nd Neurology Clinic of “AHEPA” University Hospital in Thessaloniki, Greece, and underwent a comprehensive neuropsychological assessment to evaluate their cognitive functions. Behavioral disturbances, personality traits, and functional status were rated using informant-based measures. Regional cerebral blood flow was assessed using Single Photon Emission Computed Tomography (SPECT) imaging to evaluate brain perfusion patterns. Penalized Least Absolute Shrinkage and Selection Operator (LASSO) regression analysis was performed to identify the most robust correlates of functional impairment, followed by path analyses using structural equation modeling to explore how these factors may interrelate and contribute to functional disability. Results: The severity of negative behavioral symptoms (e.g., apathy), conscientiousness levels, and performance on neuropsychological measures of semantic verbal fluency, visual attention, visuomotor speed, and global cognition were identified as the strongest correlates of performance in activities of daily living. Neuroimaging analysis revealed hypoperfusion in the right prefrontal (Brodmann area 8) and inferior parietal (Brodmann area 40) cortices as statistically significant neural correlates of functional impairment in bvFTD. Path analyses indicated that reduced brain perfusion was associated with attentional and processing speed deficits, which were further linked to more severe negative behavioral symptoms. These behavioral disturbances were subsequently correlated with declines in global cognition and conscientiousness, which were ultimately associated with poorer daily functioning. Conclusions: Hypoperfusion in key prefrontal and parietal regions, along with the subsequent cognitive and neuropsychiatric manifestations, appears to be associated with the pronounced functional limitations observed in individuals with bvFTD, even in early stages. Understanding the key determinants of the disease can inform the development of more targeted, personalized treatment strategies aimed at mitigating functional deterioration and enhancing the quality of life for affected individuals. Full article

Advancements in electroencephalography (EEG) technology and feature extraction methods have paved the way for wearable, non-invasive systems that enable continuous sleep monitoring outside clinical environments. This study presents the development and evaluation of an EEG-based acquisition system for sleep staging, which can be adapted for wearable applications. The system utilizes a custom experimental setup with the ADS1299EEG-FE-PDK evaluation board to acquire EEG signals from the forehead and in-ear regions under various conditions, including visual and auditory stimuli. Afterward, the acquired signals were processed to extract a wide range of features in time, frequency, and non-linear domains, selected based on their physiological relevance to sleep stages and disorders. The feature set was reduced using the Minimum Redundancy Maximum Relevance (mRMR) algorithm and Principal Component Analysis (PCA), resulting in a compact and informative subset of principal components. Experiments were conducted on the Bitbrain Open Access Sleep (BOAS) dataset to validate the selected features and assess their robustness across subjects. The feature set extracted from a single EEG frontal derivation (F4-F3) was then used to train and test a two-step deep learning model that combines Long Short-Term Memory (LSTM) and dense layers for 5-class sleep stage classification, utilizing attention and augmentation mechanisms to mitigate the natural imbalance of the feature set. The results—overall accuracies of 93.5% and 94.7% using the reduced feature sets (94% and 98% cumulative explained variance, respectively) and 97.9% using the complete feature set—demonstrate the feasibility of obtaining a reliable classification using a single EEG derivation, mainly for unobtrusive, home-based sleep monitoring systems. Full article

The selection of an appropriate technological process is essential to achieve optimal results in manufacturing companies. This affects quality, efficiency and competitiveness. In the modern industry, multi-criteria decision-making (MCDM) methods are increasingly used to evaluate, optimize and solve various manufacturing challenges. In this review article, existing methodologies and patents related to optimization and decision making are investigated. The main characteristics and applications of the methods are outlined. The purpose of this article is to provide a systematic review and evaluation of the main MCDM methods used in industrial practice, including through an analysis of relevant methodologies and patents. The methodology involves a structured literature and patent review, focusing on applications of widely used MCDM techniques such as the AHP (analytic hierarchy process), ANP (analytic network process), FUCOM (full consistency method), TOPSIS (technique for order preference by similarity to ideal solution), and VIKOR (višekriterijumsko kompromisno rangiranje). The analysis outlines each method’s strengths, limitations and areas of applicability. Special attention is given to the potential of the FUCOM for process evaluation in manufacturing. The findings are intended to guide researchers and practitioners in selecting appropriate decision-making tools based on specific industrial contexts and objectives. In conclusion, from the comparative analysis made, the methodologies reveal their advantages and disadvantages as well as limitations that arise in their application. Full article

This study investigated the immediate and cumulative effects of attentional focus (external vs. internal), practice autonomy, and their combination on soccer penalty kick performance. Methods: Ninety physically active male university students (average age 22.8 ± 1.5 years) were selected from a pool of 330 students who completed a 60 h university soccer course. Participants were randomly divided into six groups: external focus with target choice (EF-TC), external focus without target choice (EF-NTC), internal focus with target choice (IF-TC), internal focus without target choice (IF-NTC), autonomy support (AS), and a control group (C). Results: The EF-TC group demonstrated significantly higher accuracy than the IF-TC, IF-NTC, and C groups while performing comparably to the EF-NTC and AS groups in between-group analyses. Notably, the EF-NTC group showed the largest within-group improvement from pre-test to acquisition. Conclusions: The findings indicate that combining attentional focus with practice autonomy enhances the accuracy of penalty kicks, emphasizing the potential of tailored training methods for improving penalty kick performance in soccer. Full article