Dense Network Research Articles

Sustainable Spatial Distribution and Determinants of Key Rural Tourism Villages in China: Promoting Balanced Regional Development

Understanding the spatial distribution and sustainable development of rural tourism is essential for promoting balanced regional growth and formulating optimized policy strategies. This study aims to provide insights into sustainable development and policy optimization. Utilizing geographic information system technology, dominance analysis, and Geodetector statistical methods, this research offers a comprehensive examination of the spatial patterns and determinants of these distributions. The findings reveal significant regional disparities and clustering, with a higher concentration of key villages in economically developed eastern and central regions and fewer in the less developed western regions. The dominance analysis highlights that provinces such as Zhejiang, Shandong, and Beijing demonstrate strong advantages across multiple dimensions, including ecological environment, economic development, tourism infrastructure, transportation accessibility, policy support, and social development. Conversely, regions such as Ningxia, Qinghai, and Tibet exhibit lower dominance scores, indicating challenges in rural tourism development due to limited resources and infrastructure. Key influencing factors include forest coverage, GDP per capita, the number of star-rated hotels, transportation network density, policy initiatives, and urbanization rates. The results underscore the importance of a multi-dimensional approach to enhance rural tourism competitiveness and suggest targeted strategies for underperforming regions. This study contributes to advancing the theoretical framework of sustainable rural tourism and provides actionable insights for policymakers to foster balanced regional development, ecological conservation, and community-centered tourism practices.

ANALYSIS OF SOCIAL CAPITAL AND ENTREPRENEURIAL INTENTION OF FARMERS IN NIGERIA

This study aimed at analysing social capital and the entrepreneurial intention of farmers in Nigeria. The study specifically investigated the effect of social capital on Attitude towards Behaviour (ATB) of farmers; and Perceived Social Norms (PSN) of farmers. This study employed survey. 120 questionnaires were mailed to respondents, and 158 were physically administered. The study analysed data using both descriptive and inferential analytical technique (regression analysis). Social trust, network density, network size and demographic diversity were used as proxies of social capital, and ATB of farmers and PSN of farmers as entrepreneurial intention. Finding showed that network size, network and social trust have significant positive effects on ATB of farmers in Nigeria, and that demographic diversity has significant negative effects on ATB of farmers in Nigeria. Furthermore, finding showed that network density and social trust have significant negative effects on PSN of farmers in Nigeria. The study concluded that entrepreneurial intention of farmers depends on social capital. The study recommended that network size, network density and social trust within the social capital should be improved and sustained, and that farmers should take advantage of network size and demographic diversity as these contribute to PSN.

Transparent sparse graph pathway network for analyzing the internal relationship of lung cancer.

While it is important to find the key biomarkers and improve the accuracy of disease models, it is equally important to understand their interaction relationships. In this study, a transparent sparse graph pathway network (TSGPN) is proposed based on the structure of graph neural networks. This network simulates the action of genes in vivo, adds to prior knowledge, and improves the model's accuracy. First, the graph connection was constructed according to protein-protein interaction networks and competing endogenous RNA (ceRNA) networks, from which some noise or unimportant connections were spontaneously removed based on the graph attention mechanism and hard concrete estimation. This realized the reconstruction of the ceRNA network representing the influence of other genes in the disease on mRNA. Next, the gene-based interpretation was transformed into a pathway-based interpretation based on the pathway database, and the hidden layer was added to realize the high-dimensional analysis of the pathway. Finally, the experimental results showed that the proposed TSGPN method is superior to other comparison methods in F1 score and AUC, and more importantly, it can effectively display the role of genes. Through data analysis applied to lung cancer prognosis, ten pathways related to LUSC prognosis were found, as well as the key biomarkers closely related to these pathways, such as HOXA10, hsa-mir-182, and LINC02544. The relationship between them was also reconstructed to better explain the internal mechanism of the disease.

Feasibility Study on Infiltration of Sidetracking Horizontal Wells in Fuyu Tight Oil Field

Abstract The Fuyu oil layer in well area 1 is a tight reservoir. Due to poor reservoir properties, conventional fracturing production wells have low production and rapid decline, with a recovery rate of only 2.22%.. Moreover, the surface of the well area is a wetland protection zone along the river. Under the new safety and environmental protection policies, new drilling is not allowed in the protection zone. In order to improve the development effect of the well area and increase the recovery rate, based on the geological and development characteristics of the oil reservoir, and in response to the problem of fast water breakthrough in east-west oil wells and ineffective water injection in non east-west oil wells in the Fuyu oil layer, the main oil layer with high well control degree, small well network density, and well-developed reservoir is selected. The original development well points are used to sidedrill stepped horizontal wells, combined with volume fracturing of tight oil horizontal wells, to avoid adjacent reserve losses, Exploring a new infill model for sidetracking horizontal wells in tight oil reservoirs in Fuyu, providing reference for effective development of similar reservoirs.

Performance Study of Collection Tree Protocol in Mobile Wireless Sensor Network

The Mobile Wireless Sensor Networks (MWSN) are defined as the successor of Wireless Sensor Networks (WSN); geographically distributed autonomous mobile sensors for physical and environmental conditions monitoring. Mobile sensor networks are more flexible than static sensor networks as they can cope with rapid topology changes. Sensor networks are deployed by having their sensors collect information reliably and then relay the sensor readings to a central base station using wireless multi-hop transmission. Multi-hop routes within a rapid-changed topology requires a routing protocol that can adapt to network changes with an efficient communication mechanism among the nodes; to comply with the energy-constraint nature of the wireless sensor networks. Through significant simulation on this study using the AVRora simulator, the Collection Tree Protocol’s (CTP) capacity to respond to MWSN’s changing network topology was assessed by analysing the performance indicators; specifically, the average of packet loss and energy use of mobile nodes with different circumstances considering varied quantities of mobile nodes in the simulation region, with different velocities and network density. In several circumstances, the implementation of CTP in MWSN indicates a rise in energy usage because of broken linkages along with regular tree regeneration brought on by node mobility.

Machine‐Learning Based Multi‐Layer Soil Moisture Forecasts—An Application Case Study of the Montana 2017 Flash Drought

AbstractSoil moisture (SM) is an essential climate variable, governing land‐atmosphere interactions, runoff generation, and vegetation growth and productivity. Timely forecasts of SM spatial distribution and vertical profiles are needed for early detection and prediction of potential droughts. However, previous studies have primarily concentrated on historical or near real‐time soil moisture mapping, with less effort devoted to the development and integration of soil moisture forecast components within drought assessment systems. A satellite‐driven machine‐learning approach was developed in this study to build complex relationships between diversified predictor data sets and in situ multi‐layer SM measurements from the Montana Mesonet, a regionally dense environmental station network in the US upper Missouri and Columbia basins. The resulting 30‐m daily SM predictions showed strong performance against in situ SM measurements from 4‐, 8‐ and 20‐inch soil layers, and with 1‐ to 2‐week forecast lead times (R > 0.91; RMSE ≤ 0.047 cm3/cm3). The machine‐learning model was subsequently applied to the entire Montana region, and the SM deficit forecasts with both 1‐ and 2‐week lead times successfully depicted onset, progression, and termination phases of the 2017 Montana flash drought, which was not effectively identified from prevailing operational systems. The resulting system is capable of delineating local scale SM heterogeneity, and could be extended to predict other critical water cycle variables, potentially enhancing future drought forecasts through multivariate assessments and benefiting water resource management, agricultural practices, and the provision of ecosystem services.

Quantitative assessment of the nanoanatomy of the contractile vacuole complex in Trypanosoma cruzi.

Trypanosoma cruzi uses various mechanisms to cope with osmotic fluctuations during infection, including the remodeling of organelles such as the contractile vacuole complex (CVC). Little is known about the morphological changes of the CVC during pulsation cycles occurring upon osmotic stress. Here, we investigated the structure-function relationship between the CVC and the flagellar pocket domain where fluid discharge takes place-the adhesion plaque-during the CVC pulsation cycle. Using TcrPDEC2 and TcVps34 overexpressing mutants, known to have low and high efficiency for osmotic responses, we described a structural phenotype for the CVC that matches their corresponding physiological responses. Quantitative tomography provided data on the volume of the CVC and spongiome connections. Changes in the adhesion plaque during the pulsation cycle were also quantified and a dense filamentous network was observed. Together, the results suggest that the adhesion plaque mediates fluid discharge from the central vacuole, revealing new aspects of the osmoregulatory system in T. cruzi.

Structured Reinforcement Learning for Delay-Optimal Data Transmission in Dense mmWave Networks

Structured Reinforcement Learning for Delay-Optimal Data Transmission in Dense mmWave Networks

Profiling of MicroRNAs for the Identification of Unique and Common MicroRNAs in Preeclamptic Patients of South India Using Next-Generation Sequencing.

Preeclampsia (PE) is a serious pregnancy complication with an unclear cause. Recent studies suggest that microRNAs (miRNAs), particularly miR-1, may play a role in controlling the genes associated with this condition. This study aimed to compare the expression of miRNAs in the blood and placental tissues of women with PE to those with normal pregnancies. We conducted small RNA sequencing on blood and placental samples from three groups: (a) early-onset preeclampsia (EOPE), (b) late-onset preeclampsia (LOPE), and (c) normal pregnancies. Bioinformatics tools were used to compare the miRNA profiles across these groups. A total of 744 miRNAs were detected in placental samples, while 913 miRNAs were found in blood samples. We further analyzed the target genes using protein-protein interaction (PPI) maps to understand how these miRNAs may influence gene functions. Our analysis revealed significant differences in miRNA expression between the EOPE, LOPE, and control groups. Eight miRNAs were consistently detected in both blood and placental samples across all groups, while other miRNAs were either specific to PE or certain tissue types. The 492 target genes identified formed dense interaction networks, with several key genes occupying central roles. These findings suggest that altered miRNA expression and the resulting disruption of gene networks may contribute to the development of PE. The distinct differences between EOPE and LOPE indicate that these two subtypes may be driven by different underlying mechanisms. This paves the way for future research to explore new treatments targeting these miRNAs and their associated genes.

Smart material selection strategies for sustainable and cost-effective high-performance concrete production using deep learning

The creation of high-performing concrete (HPC) is greatly influenced by the selection of materials, with cost and sustainability factors playing a bigger part in contemporary building techniques. To overcome these limitations, we developed a Multi-Objective Ant Colony Adaptive Dense Convolutional Neural Network (MOAC-ADenseNet) with 5-K-Fold cross validation, a dependable and precise forecasting model for the cost-effective selection of HPC material. First, we collect a concrete material dataset for evaluating the suggested method. MOAC-ADenseNet utilized Dense convolutional neural networks and ant colony optimization for complex material data analysis, which makes it easier to choose expensive and sustainable materials for high-performance concrete manufacturing operations. The experimental findings of the suggested approach are evaluated for the relative measure such as Pearson's Linear Correlation Coefficient (R) is 0.93, the Root Mean Square Error (RMSE) is 91.38, Mean Absolute Error (MAE) of 58.15, and Mean Absolute Percentage Error (MAPE) is 8.79. The outcomes demonstrated that the material cost of HPC was correctly predicted by the MOAC-ADenseNet. The actual measured value and the MOAC-ADenseNet model predictions, following 5-K-fold cross-validation and input feature improvement, shows its effectiveness. A The MOAC-ADenseNet approach provides feasible method for enhancing material selection in HPC manufacturing accomplishing sustainability and cost-effectiveness goals.

Afterslip and Creep in the Rate‐Dependent Framework: Joint Inversion of Borehole Strain and GNSS Displacements for the Mw 7.1 Ridgecrest Earthquake

AbstractThe elusive transition toward afterslip following an earthquake is challenging to capture with typical data resolution limits. A dense geodetic network recorded the Mw 7.1 Ridgecrest earthquake, including 16 Global Navigation Satellite System (GNSS) stations and 3 borehole strainmeters (BSM). The sub‐nanostrain precision and sub‐second sampling rate of BSMs bridges a gap between conventional seismologic and geodetic methods, exemplified by atypical postseismic shear strain reversals observed at nearfield (<2 km) station B921 that remain unexplained. We jointly invert GNSS displacements and BSM strains for coseismic and postseismic slip spanning hours to months over 7 independent periods. Cosiesmically, our model resolves the largest slip magnitudes of up to 6.6 m on the mainshock rupture plane, with similar patterns to other inferred slip distributions. The foreshock fault appears to slip coincidently with mainshock, revealing potential asperities activated during the preceding Mw 6.4 event. Postseismically, the best‐fitting models adhere to mechanical rate‐and‐state expectations of logarithmically decaying slip adjacent to the coseismic rupture terminus, and where deep rheologic conditions favor creep. Most spatial variation occurs in the early postseismic timeframe (<1–2 weeks), with evidence for regional rheologic control and static stress dependence. Triggered creep on the neighboring Garlock Fault unexpectedly persists for >178 days—further highlighting the importance of fault networks in postseismic stress redistribution, critical to assessing future hazard.

MSAACNN for intense noise suppression in DAS-VSP records

Distributed optical fiber sensor (DAS) is an emerging acquisition technique and has begun to be widely applied in seismic exploration owing to its advantages in acquisition and deployment. Nonetheless, DAS record has a low signal-to-noise ratio (SNR) due to the intense background noise. How to suppress the DAS background noise and increase the SNR of the DAS records has gradually become one of the hot issues in the field of seismic data processing. To solve the challenging tasks in intense DAS noise suppression, a multiscale sparse asymmetric attention convolutional neural network (MSAACNN) is proposed. The network uses dilated convolutions to expand the receptive field and map more feature information. Moreover, asymmetric convolutions are introduced to form an asymmetric unit, aiming to strengthen the feature extraction ability and realize the interaction between feature information of different scales. Finally, a pyramid attention module is used to enhance the primary features and improve the network denoising performance. The experimental results show that MSAACNN can effectively suppress the complex background noise in DAS records, compared with the traditional denoising methods and typical convolutional neural network (CNN) architecture. Additionally, the recovered signal components in the processing results are clear and complete, with significantly improved SNR.

Bayesian Optimization for Sparse Neural Networks With Trainable Activation Functions.

In the literature on deep neural networks, there is considerable interest in developing activation functions that can enhance neural network performance. In recent years, there has been renewed scientific interest in proposing activation functions that can be trained throughout the learning process, as they appear to improve network performance, especially by reducing overfitting. In this paper, we propose a trainable activation function whose parameters need to be estimated. A fully Bayesian model is developed to automatically estimate from the learning data both the model weights and activation function parameters. An MCMC-based optimization scheme is developed to build the inference. The proposed method aims to solve the aforementioned problems and improve convergence time by using an efficient sampling scheme that guarantees convergence to the global maximum. The proposed scheme has been tested across a diverse datasets, encompassing both classification and regression tasks, and implemented in various CNN architectures to demonstrate its versatility and effectiveness. Promising results demonstrate the usefulness of our proposed approach in improving models accuracy due to the proposed activation function and Bayesian estimation of the parameters.

Deep Learning-based Emotion Recognition Algorithms in Music Performance

In the realm of artificial intelligence and musicology, emotion recognition in music performance has emerged as a pivotal area of research. This paper introduces EmoTrackNet, an integrated deep learning framework that combines sparse attention networks, enhanced one-dimensional residual Convolutional Neural Networks (CNNs) with an improved Inception module, and Gate Recurrent Units (GRUs). The synergy of these technologies aims to decode complex emotional cues embedded in music. Our methodology revolves around leveraging the sparse attention network to efficiently process temporal sequences, thereby capturing the intricate dynamics of musical pieces. The incorporation of the 1D residual CNN with an upgraded Inception module facilitates the extraction of nuanced features from audio signals, encompassing a broad spectrum of musical tones and textures. The GRU component further refines the model’s capability to retain and process sequential information over longer timeframes, essential for understanding evolving emotional expressions in music. We evaluated EmoTrackNet on the Soundtrack dataset a comprehensive collection of music pieces annotated with emotional labels. The results demonstrated remarkable improvements in the accuracy of emotion recognition, outperforming existing models. This enhanced performance can be attributed to the integrated approach, which efficiently combines the strengths of each component, leading to a more robust and sensitive emotion detection system. EmoTrackNet’s novel architecture and promising results pave the way for new avenues in musicology, particularly in understanding and interpreting the emotional depth of musical performances. This framework not only contributes significantly to the field of music emotion recognition but also has potential applications in music therapy, entertainment, and interactive media where emotional engagement is key.

Trends in Water Quality Research: A Bibliometric Study of Factors and Parameters in Drinking Water

ABSTRACT This study examines trends in water quality research through a bibliometric approach with the aim of mapping dominant factors and parameters and identifying research gaps in this area. The introduction of this research highlights the importance of water quality as a global issue that affects public health and environmental sustainability. The main objective of the study was to analyze water quality-related publications published between 2017 and 2024 using the Publish or Perish application to identify trends, distribution, and research focus. The method used involved collecting data from the 50 highest-ranked journals on Google Scholar, then classifying them by year of publication, publication type, number of citations, and author country. The data obtained was analyzed with the VOSviewer application to generate network visualizations, overlays, and densities to reveal the linkages between research topics. The analysis showed that research on water quality is highly diversified with the main focus on factors affecting water quality and the development of assessment methods. The publications reviewed highlighted global challenges in water quality management and the need for cross-disciplinary collaboration. The conclusions of this study emphasize several research gaps, such as the need for the development of more sensitive water quality indices, the application of new technologies, and further research in local and regional contexts. This research provides valuable insights into current research trends and encourages further exploration to improve water quality management effectively and sustainably. Keywords: Water Quality, Bibliometrics, Assessment Methods, Emerging Technologies, Research Gaps.

Clinical relationships between the intratumoral microbiome and risk factors for head and neck cancer

A bioinformatic analysis is a promising approach to understand the relationship between the vast tumor microbiome and cancer development. In the present study, we studied the relationships between the intratumoral microbiome and classical clinical risk factors using bioinformatics analysis of the Cancer Genome Atlas (TCGA) and the Cancer Microbiome Atlas (TCMA) datasets. We used TCMA database and investigated the abundance of microbes at the genus level in solid normal tissue (n = 22) and the primary tumors of patients with head and neck squamous cell carcinoma (HNSCC) (n = 154) and identified three major tumor microbiomes, Fusobacterium, Prevotella, and Streptococcus. The tissue level of Fusobacterium was higher in primary tumors than in solid normal tissue. However, univariate and multivariate analyses of these 3 microbes showed no significant effects on patient survival. We then extracted 43, 55, or 59 genes that were differentially expressed between the over and under the median groups for Fusobacterium, Prevotella, or Streptococcus using the criteria of >2.5, >1.5, or >2.0 fold and p < 0.05 in the Mann-Whitney U test. The results of a pathway analysis revealed the association of Fusobacterium- and Streptococcus-related genes with the IL-17 signaling pathway and Staphylococcus aureus infection, while Prevotella-associated pathways were not extracted. A protein-protein interaction analysis revealed a dense network in the order of Fusobacterium, Streptococcus, and Prevotella. An investigation of the relationships between the intratumoral microbiome and classical clinical risk factors showed that high levels of Fusobacterium were associated with a good prognosis in the absence of alcohol consumption and smoking, while high levels of Streptococcus were associated with a poor prognosis in the absence of alcohol consumption. In conclusion, intratumoral Fusobacterium and Streptococcus may affect the prognosis of patients with HNSCC, and their effects on HNSCC are modulated by the impact of drinking and smoking.

A cell-free system for functional studies of small membrane proteins

Numerous small proteins have been discovered across all domains of life, among which many are hydrophobic and predicted to localize to the cell membrane. Based on a few that are well-studied, small membrane proteins are regulators involved in various biological processes, such as cell signaling, nutrient transport, drug resistance, and stress response. However, the function of most identified small membrane proteins remains elusive. Their small size and hydrophobicity make protein production challenging, hindering function discovery. Here, we combined a cell-free system with lipid sponge droplets and synthesized small membrane proteins in vitro. Lipid sponge droplets contain a dense network of lipid bilayers, which accommodates and extracts newly synthesized small membrane proteins from the aqueous surroundings. Using small bacterial membrane proteins MgrB, SafA, and AcrZ as proof of principle, we showed that the in vitro produced membrane proteins were functionally active, for example, modulating the activity of their target kinase as expected. The cell-free system produced small membrane proteins, including one from human, up to micromolar concentrations, indicating its high level of versatility and productivity. Furthermore, AcrZ produced in this system was used successfully for in vitro co-immunoprecipitations to identify interaction partners. This work presents a robust alternative approach for producing small membrane proteins, which opens a door to their function discovery in different domains of life.

Comprehensive Study of Large‐Scale Traveling Ionospheric Disturbances (LSTIDs) Observed Over Iran

AbstractA dense network of GNSS receivers is employed to study temporal and spatial characteristics of large‐scale traveling ionospheric disturbances (LSTIDs) in Iran. Three geomagnetic storms in 2021 are selected. To determine LSTID propagation, an eighth‐order Butterworth bandpass filter was applied to the data to remove the diurnal variability of the total electron content (TEC). Moreover, two‐dimensional TEC perturbation maps are provided to explore the meridional and zonal structures of the LSTIDs. Analysis of a major storm on November 4 (Kp = 7, Dst = −99 nT) revealed two single LSTIDs and three groups of multiple LSTIDs. The phase velocity and wavelength of LSTIDs in this event varied between 190 and 930 m/s and 1,030–5,022 km, respectively. Southward propagating LSTIDs appeared to be more frequent than northward. The complex propagation of two simultaneous LSTIDs is resolved. A large‐amplitude mixed front showing broadening both latitudinally and meridionally is revealed. No nighttime propagating LSTID is reported. In addition, global differential TEC data are explored to examine the detection of LSTID propagation. The global data validates the timing, direction of propagation, and strength of LSTIDs detected over Iran. The auroral oval extension is consistent with generating and propagating reported LSTIDs. The second storm studied occurred on August 27 (Kp = 4, Dst = −82 nT). This storm exhibited weaker LSTIDs in terms of both observed numbers and amplitude. Finally, the storm case of May 12 (Kp = 7, Dst = −61 nT) was examined. The results underscores the vital role of the Dst index in studying LSTIDs.

Proof of concept study on early forecasting of antimicrobial resistance in hospitalized patients using machine learning and simple bacterial ecology data.

Antibiotic resistance in bacterial pathogens is a major threat to global health, exacerbated by the misuse of antibiotics. In hospital practice, results of bacterial cultures and antibiograms can take several days. Meanwhile, prescribing an empirical antimicrobial treatment is challenging, as clinicians must balance the antibiotic spectrum against the expected probability of susceptibility. We present here a proof of concept study of a machine learning-based system that predicts the probability of antimicrobial susceptibility and explains the contribution of the different cofactors in hospitalized patients, at four different stages prior to the antibiogram (sampling, direct examination, positive culture, and species identification), using only historical bacterial ecology data that can be easily collected from any laboratory information system (LIS) without GDPR restrictions once the data have been anonymised. A comparative analysis of different state-of-the-art machine learning and probabilistic methods was performed using 44,026 instances over 7 years from the Hôpital Européen Marseille, France. Our results show that multilayer dense neural networks and Bayesian models are suitable for early prediction of antibiotic susceptibility, with AUROCs reaching 0.88 at the positive culture stage and 0.92 at the species identification stage, and even 0.82 and 0.92, respectively, for the least frequent situations. Perspectives and potential clinical applications of the system are discussed.

Thin Cloud Removal Generative Adversarial Network Based on Sparse Transformer in Remote Sensing Images

Thin clouds in Remote Sensing (RS) imagery can negatively impact subsequent applications. Current Deep Learning (DL) approaches often prioritize information recovery in cloud-covered areas but may not adequately preserve information in cloud-free regions, leading to color distortion, detail loss, and visual artifacts. This study proposes a Sparse Transformer-based Generative Adversarial Network (SpT-GAN) to solve these problems. First, a global enhancement feature extraction module is added to the generator’s top layer to enhance the model’s ability to preserve ground feature information in cloud-free areas. Then, the processed feature map is reconstructed using the sparse transformer-based encoder and decoder with an adaptive threshold filtering mechanism to ensure sparsity. This mechanism enables that the model preserves robust long-range modeling capabilities while disregarding irrelevant details. In addition, inverted residual Fourier transformation blocks are added at each level of the structure to filter redundant information and enhance the quality of the generated cloud-free images. Finally, a composite loss function is created to minimize error in the generated images, resulting in improved resolution and color fidelity. SpT-GAN achieves outstanding results in removing clouds both quantitatively and visually, with Structural Similarity Index (SSIM) values of 98.06% and 92.19% and Peak Signal-to-Noise Ratio (PSNR) values of 36.19 dB and 30.53 dB on the RICE1 and T-Cloud datasets, respectively. On the T-Cloud dataset, especially with more complex cloud components, the superior ability of SpT-GAN to restore ground details is more evident.