In recent years, deep learning methods have achieved remarkable success in hyperspectral image classification (HSIC), and the utilization of convolutional neural networks (CNNs) has proven to be highly effective. However, there are still several critical issues that need to be addressed in the HSIC task, such as the lack of labeled training samples, which constrains the classification accuracy and generalization ability of CNNs. To address this problem, a deep multi-scale attention fusion network (DMAF-NET) is proposed in this paper. This network is based on multi-scale features and fully exploits the deep features of samples from multiple levels and different perspectives with an aim to enhance HSIC results using limited samples. The innovation of this article is mainly reflected in three aspects: Firstly, a novel baseline network for multi-scale feature extraction is designed with a pyramid structure and densely connected 3D octave convolutional network enabling the extraction of deep-level information from features at different granularities. Secondly, a multi-scale spatial–spectral attention module and a pyramidal multi-scale channel attention module are designed, respectively. This allows modeling of the comprehensive dependencies of coordinates and directions, local and global, in four dimensions. Finally, a multi-attention fusion module is designed to effectively combine feature mappings extracted from multiple branches. Extensive experiments on four popular datasets demonstrate that the proposed method can achieve high classification accuracy even with fewer labeled samples. Full article

Venezuelan (VEE), eastern (EEE), and western (WEE) equine encephalitis viruses are encephalitic New World alphaviruses that cause periodic epizootic and epidemic outbreaks in horses and humans that may cause severe morbidity and mortality. Currently there are no FDA-licensed vaccines or effective antiviral therapies. Each year, there are a limited number of human cases of encephalitic alphaviruses; thus, licensure of a vaccine or therapeutic would require approval under the FDA animal rule. Approval under the FDA animal rule requires the disease observed in the animal model to recapitulate what is observed in humans. Currently, initial testing of vaccines and therapeutics is performed in the mouse model. Unfortunately, alphavirus disease manifestations in a mouse do not faithfully recapitulate human disease; the VEEV mouse model is lethal whereas in humans VEEV is rarely lethal. In an effort to identify a more appropriate small animal model, we evaluated hamsters in an aerosol exposure model of encephalitic alphavirus infection. The pathology, lethality, and viremia observed in the infected hamsters was inconsistent with what is observed in NHP models and humans. These data suggest that hamsters are not an appropriate model for encephalitic alphaviruses to test vaccines or potential antiviral therapies. Full article

Background: (-)-Fenchone is a naturally occurring monoterpene found in the essential oils of Foeniculum vulgare Mill., Thuja occidentalis L., and Peumus boldus Molina. Pharmacological studies have reported its antinociceptive, antimicrobial, anti-inflammatory, antidiarrheal, and antioxidant activities. Methods: The preventive antiulcer effects of (-)-Fenchone were assessed through oral pretreatment in cysteamine-induced duodenal lesion models. Gastric healing, the underlying mechanisms, and toxicity after repeated doses were evaluated using the acetic acid-induced gastric ulcer rat model with oral treatment administered for 14 days. Results: In the cysteamine-induced duodenal ulcer model, fenchone (37.5–300 mg/kg) significantly decreased the ulcer area and prevented lesion formation. In the acetic acid-induced ulcer model, fenchone (150 mg/kg) reduced (p < 0.001) ulcerative injury. These effects were associated with increased levels of reduced glutathione (GSH), superoxide dismutase (SOD), interleukin (IL)-10, and transforming growth factor-beta (TGF-β). Furthermore, treatment with (-)-Fenchone (150 mg/kg) significantly reduced (p < 0.001) malondialdehyde (MDA), myeloperoxidase (MPO), interleukin-1 beta (IL-1β), tumor necrosis factor-alpha (TNF-α), and nuclear transcription factor kappa B (NF-κB). A 14-day oral toxicity investigation revealed no alterations in heart, liver, spleen, or kidney weight, nor in the biochemical and hematological parameters assessed. (-)-Fenchone protected animals from body weight loss while maintaining feed and water intake. Conclusion: (-)-Fenchone exhibits low toxicity, prevents duodenal ulcers, and enhances gastric healing activities. Antioxidant and immunomodulatory properties appear to be involved in its therapeutic effects. Full article

Dysregulation of cyclin-dependent kinase 8 (CDK8) activity has been associated with many diseases, including colorectal and breast cancer. As usual in the CDK family, the activity of CDK8 is controlled by a regulatory protein called cyclin C (CycC). But, while human CDK family members are generally activated in two steps, that is, the binding of the cyclin to CDK and the phosphorylation of a residue in the CDK activation loop, CDK8 does not require the phosphorylation step to be active. Another peculiarity of CDK8 is its ability to be associated with CycC while adopting an inactive form. These specificities raise the question of the role of CycC in the complex CDK8–CycC, which appears to be more complex than the other members of the CDK family. Through molecular dynamics (MD) simulations and binding free energy calculations, we investigated the effect of CycC on the structure and dynamics of CDK8. In a second step, we particularly focused our investigation on the structural and molecular basis of the protein–protein interaction between the two partners by finely analyzing the energetic contribution of residues and simulating the transition between the active and the inactive form. We found that CycC has a stabilizing effect on CDK8, and we identified specific interaction hotspots within its interaction surface compared to other human CDK/Cyc pairs. Targeting these specific interaction hotspots could be a promising approach in terms of specificity to effectively disrupt the interaction between CDK8. The simulation of the conformational transition from the inactive to the active form of CDK8 suggests that the residue Glu99 of CycC is involved in the orientation of three conserved arginines of CDK8. Thus, this residue may assume the role of the missing phosphorylation step in the activation mechanism of CDK8. In a more general view, these results point to the importance of keeping the CycC in computational studies when studying the human CDK8 protein in both the active and the inactive form. Full article

Older women without children, like all older adults, evaluate their lives and face a conflict between despair and ego integrity as proposed by Erikson’s theory of development. Their uniqueness lies in their deviation from the societal norm of parenthood prevalent in pro-natalist societies such as Israel. This study aims to explore how older childless women evaluate their lives. Using a qualitative approach, 20 semi-structured, in-depth interviews were conducted with women over 60 years of age who do not have children. Three main themes emerged from the participants’ responses: their experiences as women without children in a pro-natalist society, the significance of freedom in their lives, and their life experiences from conflicting perspectives—an internal and external locus of control. The study’s findings demonstrate that older childless women adeptly utilize different perspectives across various aspects of their lives, contributing to ego integrity, contrary to the prevailing societal notion that in the absence of children, women are damaged and lack identity. It is conceivable that other segments of the older adult population, diverging from mainstream societal norms, may similarly leverage these different perspectives to uphold their ego. Full article

Providing employees with proper work conditions should be one of the main concerns of any employer. Even so, in many cases, work shifts chronically expose the workers to a wide range of potentially harmful compounds, such as ammonia. Ammonia has been present in the composition of products commonly used in a wide range of industries, namely production in lines, and also laboratories, schools, hospitals, and others. Chronic exposure to ammonia can yield several diseases, such as irritation and pruritus, as well as inflammation of ocular, cutaneous, and respiratory tissues. In more extreme cases, exposure to ammonia is also related to dyspnea, progressive cyanosis, and pulmonary edema. As such, the use of ammonia needs to be properly regulated and monitored to ensure safer work environments. The Occupational Safety and Health Administration and the European Agency for Safety and Health at Work have already commissioned regulations on the acceptable limits of exposure to ammonia. Nevertheless, the monitoring of ammonia gas is still not normalized because appropriate sensors can be difficult to find as commercially available products. To help promote promising methods of developing ammonia sensors, this work will compile and compare the results published so far. Full article

Music genre classification is significant to users and digital platforms. To enhance the classification accuracy, this study proposes a hybrid model based on VMD-IWOA-XGBOOST for music genre classification. First, the audio signals are transformed into numerical or symbolic data, and the crucial features are selected using the maximal information coefficient (MIC) method. Second, an improved whale optimization algorithm (IWOA) is proposed for parameter optimization. Third, the inner patterns of these selected features are extracted by IWOA-optimized variational mode decomposition (VMD). Lastly, all features are put into the IWOA-optimized extreme gradient boosting (XGBOOST) classifier. To verify the effectiveness of the proposed model, two open music datasets are used, i.e., GTZAN and Bangla. The experimental results illustrate that the proposed hybrid model achieves better performance than the other models in terms of five evaluation criteria. Full article

The West Nile Virus (WNV), a member of the family Flaviviridae, is an emerging mosquito-borne flavivirus causing potentially severe infections in humans and animals involving the central nervous system (CNS). Due to its emerging tendency, WNV now occurs in many areas where other flaviviruses are co-occurring. Cross-reactive antibodies with flavivirus infections or vaccination (e.g., tick-borne encephalitis virus (TBEV), Usutu virus (USUV), yellow fever virus (YFV), dengue virus (DENV), Japanese encephalitis virus (JEV)) therefore remain a major challenge in diagnosing flavivirus infections. Virus neutralization tests are considered as reference tests for the detection of specific flavivirus antibodies, but are elaborate, time-consuming and need biosafety level 3 facilities. A simple and straightforward assay for the differentiation and detection of specific WNV IgG antibodies for the routine laboratory is urgently needed. In this study, we compared two commercially available enzyme-linked immunosorbent assays (anti-IgG WNV ELISA and anti-NS1-IgG WNV), a commercially available indirect immunofluorescence assay, and a newly developed in-house ELISA for the detection of WNV-NS1-IgG antibodies. All four tests were compared to an in-house NT to determine both the sensitivity and specificity of the four test systems. None of the assays could match the specificity of the NT, although the two NS1-IgG based ELISAs were very close to the specificity of the NT at 97.3% and 94.6%. The in-house WNV-NS1-IgG ELISA had the best performance regarding sensitivity and specificity. The specificities of the ELISA assays and the indirect immunofluorescence assays could not meet the necessary specificity and/or sensitivity. Full article

In satellite health management, anomalies are mostly resolved after an event and are rarely predicted in advance. Thus, trend prediction is critical for avoiding satellite faults, which may affect the accuracy and quality of satellite data and even greatly impact safety. However, it is difficult to predict satellite operation using a simple model because satellite systems are complex and telemetry data are copious, coupled, and intermittent. Therefore, this study proposes a model that combines an attention mechanism and bidirectional long short-term memory (attention-BiLSTM) with telemetry correlation to predict satellite behaviour. First, a high-dimensional K-nearest neighbour mutual information method is used to select the related telemetry variables from multiple variables of satellite telemetry data. Next, we propose a new BiLSTM model with an attention mechanism for telemetry prediction. The dataset used in this study was generated and transmitted from the FY3E meteorological satellite power system. The proposed method was compared with other methods using the same dataset used in the experiment to verify its superiority. The results confirmed that the proposed method outperformed the other methods owing to its prediction precision and superior accuracy, indicating its potential for application in intelligent satellite health management systems. Full article

Chemokines are key proteins that regulate cell migration and immune responses and are essential for modulating the tumor microenvironment. Despite their close association with colon cancer, the expression patterns, prognosis, immunity, and specific roles of chemokines in colon cancer are still not fully understood. In this study, we investigated the mutational features, differential expression, and immunological characteristics of chemokines in colon cancer (COAD) by analyzing the Tumor Genome Atlas (TCGA) database. We clarified the biological functions of these chemokines using Gene Ontology (GO) annotation and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis. By univariate and multivariate COX regression analyses, we developed chemokine-based prognostic risk models. In addition, using Gene Set Enrichment Analysis (GSEA) and Gene Set Variant Analysis (GSVA), we analyzed the differences in immune responses and signaling pathways among different risk groups. The results showed that the mutation rate of chemokines was low in COAD, but 25 chemokines were significantly differentially expressed. These chemokines function in several immune-related biological processes and play key roles in signaling pathways including cytokine–cytokine receptor interactions, NF-kappa B, and IL-17. Prognostic risk models based on CCL22, CXCL1, CXCL8, CXCL9, and CXCL11 performed well. GSEA and GSVA analyses showed significant differences in immune responses and signaling pathways across risk groups. In conclusion, this study reveals the potential molecular mechanisms of chemokines in COAD and proposes a new prognostic risk model based on these insights. Full article

Information on the state of the environment is important to achieve the objectives of the European Green Deal, including the EU’s Biodiversity Strategy for 2030. The existing regulatory provisions for genetically modified organisms (GMOs) foresee an obligatory post-market environmental monitoring (PMEM) of potential adverse effects upon release into the environment. So far, GMO monitoring activities have focused on genetically modified crops. With the advent of new genomic techniques (NGT), novel GMO applications are being developed and may be released into a range of different, non-agricultural environments with potential implications for ecosystems and biodiversity. This challenges the current monitoring concepts and requires adaptation of existing monitoring programs to meet monitoring requirements. While the incorporation of existing biodiversity monitoring programs into GMO monitoring at the national level is important, additional monitoring activities will also be required. Using case examples, we highlight that monitoring requirements for novel GMO applications differ from those of GM crop plants previously authorized for commercial use in the European Union. Full article

Forest fires often pose serious hazards, and the timely monitoring and extinguishing of residual forest fires using unmanned aerial vehicles (UAVs) can prevent re-ignition and mitigate the damage caused. Due to the urgency of forest fires, drones need to respond quickly during firefighting operations, while traditional drone formation deployment requires a significant amount of time. This paper proposes a pure azimuth passive positioning strategy for circular UAV formations and utilizes the Deep Q-Network (DQN) algorithm to effectively adjust the formation within a short timeframe. Initially, a passive positioning model for UAVs based on the relationships between the sides and angles of a triangle is established, with the closest point to the ideal position being selected as the position for the UAV to be located. Subsequently, a multi-target optimization model is developed, considering 10 UAVs as an example, with the objective of minimizing the number of adjustments while minimizing the deviation between the ideal and adjusted UAV positions. The DQN algorithm is employed to solve and design experiments for validation, demonstrating that the deviation between the UAV positions and the ideal positions, as well as the number of adjustments, are within acceptable ranges. In comparison to genetic algorithms, it saves approximately 120 s. Full article

Piecewise fractional-order differential operators have received more attention in recent years because they can be used to describe various evolutionary dynamical problems to investigate crossover behaviors. In this manuscript, we use the aforementioned operators to investigate a mathematical model of COVID-19. By utilizing fractional calculus, our approach aims to capture the crossover dynamics of disease spread, considering heterogeneity and transitions between epidemic phases. This research seeks to develop a framework using specialized mathematical techniques, such as the Caputo fractional derivative, with the potential to investigate the crossover dynamical behaviors of the considered epidemic model. The anticipated contribution lies in bridging fractional calculus and epidemiology, offering insights for both theoretical advancements and practical public health interventions. In order to improve our understanding of epidemic dynamics and support, we used MATLAB to simulate numerical results for a visual representation of our findings. For this interpretation, we used various fractional-order values. In addition, we also compare our simulated results with some reported results for infected and death classes to demonstrate the efficiency of our numerical method. Full article

Malus sieversii f. niedzwetzkyan, a wild species capable of growing on saline-alkali soil in Xinjiang, is the most promising horticultural crop for improving the saline-alkali wasteland. However, the tolerance of M. niedzwetzkyan to saline-alkali stress and the underlying molecular mechanisms remains largely unknown. Here, we conducted a hydroponic experiment in which M. niedzwetzkyana and M. domestica “Royal Gala” seedlings were subjected to 150 mM saline-alkali stress. Physiological data showed that M. niedzwetzkyana had a strong ROS scavenging ability and ion transport ability, and its saline-alkali resistance was higher than that of M. “Royal Gala”. Saline-alkali stress also promoted the synthesis of anthocyanins in M. niedzwetzkyana. Transcriptome analysis was conducted on the leaves and roots of M. niedzwetzkyana at different time points under saline-alkali stress (0 h, 6 h, and 12 h). Transcriptome analysis revealed that saline stress down-regulated most genes involved in the anthocyanin flavonoid synthesis pathway. Transcription levels of genes involved in antioxidant enzyme activity and ion transport were altered. We identified hub genes related to superoxide dismutase as well as Na⁺ and K⁺ transport using weighted gene co-expression network analysis. This study elucidated, for the first time at the molecular level, the saline-alkali tolerance of M. niedzwetzkyana, including the complex changes in pathways that regulate reactive oxygen species homeostasis, ion uptake, and anthocyanoside synthesis under saline-alkali stress conditions. This research provides an important genetic resource for identifying genes involved in responses to saline-alkali stress. Full article

The global increase in population has placed significant pressure on food security, leading to the emergence of aquaculture as a vital source of aquatic foods. However, rising costs and limited fish meal availability in aquafeeds have driven the search for alternative protein sources. While plant-based ingredients have been integrated into commercial aquafeeds, they come with challenges such as low protein content, palatability issues, and the presence of antinutritional factors. In this context, fish silage, made from fish waste and discarded fish, stands out as a promising alternative technology due to its cost-effectiveness and sustainability attributes. The production of fish silage involves the addition of organic/inorganic acids or lactic acid bacteria to homogenized fish waste, yielding a valuable mixture rich in peptides and free amino acids, offering significant nutritional benefits for animal diets. This review aims to promote sustainable practices in the aquaculture industry by analyzing research results related to ensiling technology, appraising the advantages and disadvantages of using fish silage as a feed ingredient, and focusing on emerging trends in this field. Full article

Eco-friendly lighting systems, like LED lights, can reduce energy consumption in greenhouse operations, have a long lifespan, and enable precise control over plant growth through spectrum selection. On the other hand, Selenium (Se) is a micronutrient with a beneficial role in plant metabolism and an essential element for human health. In this study, we aim to unravel the effects of LED lighting combined with Se supplementation on the physiological behavior, yield, and quality of arugula (Eruca sativa). Arugula plants were cultivated under controlled conditions using two distinct LED lights: full white spectrum (W) and a mix of 80%/20% of red/blue light (R:B). These plants were then supplemented with three levels of Se: 0 mg Se kg⁻¹ soil [⁰], 0.3 mg Se kg⁻¹ soil [0.3], and 0.6 mg Se kg⁻¹ soil [0.6]. The results showed that stomatal conductance remained unaffected by the light script. However, the plants exposed to R:B displayed more pronounced signs of photodamage and reduced net photosynthetic rate. Supplementation with Se plays a significant role in mitigating light-induced stress and in improving the antioxidant defense system; this was especially notable in R:B plants. Finally, R:B light decreased the accumulation of aboveground biomass, while no significant impact of Se was noticed on this outcome. Se accumulation exhibited a direct and proportional relationship with the concentration of Se applied. The integration of LED technology and Se supplementation not only enhances crop nutritional value but also aligns with the adoption of more sustainable agricultural practices. Full article

This article presents an assessment of sustainable mobility initiatives developed in Montevideo, Uruguay, in the period from 2020 to 2023. The significance of sustainable mobility is underscored due to its far-reaching implications for the environment, energy efficiency, and the overall quality of life of citizens. This study focuses on crucial aspects of four initiatives deployed in Montevideo in 2020–2023: electric mobility solutions using scooters, the development of infrastructure and services for urban cycling, the development of electric public transportation, and private electric transportation. Important results are obtained and commented on for each of the studied initiatives, regarding efficiency, environmental impact, accessibility, the quality of the service, and other relevant indicators. Based on the analysis, valuable knowledge is acquired to guide the future development of efficient and sustainable transportation modes in Montevideo, Uruguay. Full article

Deploying an airbag when a vehicle occupant is too close to it can cause injury. An adaptive Airbag Control Unit (ACU) would improve the effectiveness of the safety system, provided it is aware of the actual position of the occupants once the crash is going to occur. Occupants can be monitored with vision-based and radar-based sensing in the vehicle, but the research question is whether other reliable devices exist. In this research, a real seat is equipped with four sensors in the supports from the floor, as well as an Inertial Measurement Unit (IMU) and a microcontroller. The device is capable of identifying correct position or different Out of Position (OP) conditions and inform an adaptive ACU. The paper presents the seat layout in detail and its testing in extensive driving experiments with multiple participants. Depending on the position of the driver, the identification is correct 45–100% of the time. Monitoring the occupant position by a sensorized seat is feasible and can improve the reliability of the onboard safety system when integrated with other occupant monitoring devices. Full article

Is additive manufacturing (AM) a sustainable process? Can the process be optimised to produce sustainable AM parts and production techniques? Additive manufacturing offers the production of parts made of different types of materials in addition to the complex geometry that is difficult or impossible to produce by using the traditional subtractive methods. This study is focused on the optimisation of laser powder bed fusion (L-PBF), one of the most common technologies used in additive manufacturing and 3D printing. This research was carried out by modulating the build layer thickness of the deposited metal powder and the input volumetric energy density. The aim of the proposed strategy is to save the build time by maximizing the applied layer thickness of nitinol powder while retrieving the different AM part properties. The saving in the process time has a direct effect on the total cost of the produced part as a result of several components like electric energy, inert gas consumption, and labour. Nickel-rich nitinol (52.39 Ni at.%) was selected for investigation in this study due to its extremely high superplastic and shape memory properties in addition to the wide application in various industries like aerospace, biomedical, and automotive. The results obtained show that significant energy and material consumption can be found by producing near full dens AM parts with limited or no alteration in chemical and mechanical properties. Full article

This study examined the impact of tea polyphenols (TPs) on the intestinal flora of loaches (Paramisgurnus dabryanus) under chronic ammonia nitrogen stress using high-throughput sequencing. Two groups of 600 loaches were studied over one month, and they were separated into a control group and tea polyphenol group. Alpha and beta diversity analyses showed diverse bacterial communities, with significant differences in the abundance and uniformity observed initially but not between sampling time points. Cluster analyses revealed distinct differences in microbial communities between groups. A predictive function analysis indicated enrichment in pathways related to amino acid and nucleotide biosynthesis. These findings offer initial insights into how tea polyphenols may affect intestinal microbial communities in loaches under ammonia nitrogen stress. Full article

Porphyridium aerugineum is a unicellular freshwater red microalga that synthesizes and secretes into the culture medium an extracellular polysaccharide (EPS). In this study, algal growth and polysaccharide production, as well as the antioxidant capacity and antitumor effect of Porphyridium aerugineum EPS (PaEPS), were investigated. Cultivation of the microalgae was carried out in a photobioreactor under controlled conditions. Algal growth and the amount of EPS were monitored daily. The accumulated polysaccharide was extracted and lyophilized. At the end of cultivation, the concentration of microalgal biomass and PaEPS reached 3.3 and 1.2 g L⁻¹, respectively. To examine the antioxidant capacity of PaEPS, FRAP and ABTS assays were performed. The cytotoxic activity of PaEPS was evaluated on the tumor cell lines MCF-7 (breast cancer) and HeLa (cervical adenocarcinoma) and on BJ (a non-tumor human skin fibroblast cell line), using MTT assay. The results obtained indicated that P. aerugineum polysaccharide exhibited a high ABTS radical-scavenging activity reaching up to 55%. The cytotoxic effect was best expressed in MCF-7 cells treated for 72 h with 1000 µg/mL PaEPS, where tumor cell proliferation was inhibited by more than 70%. Importantly, the PaEPS treatments did not significantly affect the viability of BJ cells. These findings promote the biotechnological production of P. aerugineum extracellular polysaccharide and reveal its potential as an anticancer and antioxidant agent for future applications. Full article

(1) Problem Statement: In graph theory, the weighted Laplacian matrix is the most utilized technique to interpret the local and global properties of a complex graph structure within computer vision applications. However, with increasing graph nodes, the Laplacian matrix’s dimensionality also increases accordingly. Therefore, there is always the “curse of dimensionality”; (2) Methodology: In response to this challenge, this paper introduces a new approach to reducing the dimensionality of the weighted Laplacian matrix by utilizing the Gershgorin circle theorem by transforming the weighted Laplacian matrix into a strictly diagonal domain and then estimating rough eigenvalue inclusion of a matrix. The estimated inclusions are represented as reduced features, termed GC features; (3) Results: The proposed Gershgorin circle feature extraction (GCFE) method was evaluated using three publicly accessible computer vision datasets, varying image patch sizes, and three different graph types. The GCFE method was compared with eight distinct studies. The GCFE demonstrated a notable positive Z-score compared to other feature extraction methods such as I-PCA, kernel PCA, and spectral embedding. Specifically, it achieved an average Z-score of 6.953 with the 2D grid graph type and 4.473 with the pairwise graph type, particularly on the E_Balanced dataset. Furthermore, it was observed that while the accuracy of most major feature extraction methods declined with smaller image patch sizes, the GCFE maintained consistent accuracy across all tested image patch sizes. When the GCFE method was applied to the E_MNSIT dataset using the K-NN graph type, the GCFE method confirmed its consistent accuracy performance, evidenced by a low standard deviation (SD) of 0.305. This performance was notably lower compared to other methods like Isomap, which had an SD of 1.665, and LLE, which had an SD of 1.325; (4) Conclusions: The GCFE outperformed most feature extraction methods in terms of classification accuracy and computational efficiency. The GCFE method also requires fewer training parameters for deep-learning models than the traditional weighted Laplacian method, establishing its potential for more effective and efficient feature extraction in computer vision tasks. Full article