Network Structure Research Articles

A Deep Learning-Based Two-Branch Generative Adversarial Network for Image De-Raining

Raindrops can scatter and absorb light, causing images to become blurry or distorted. To improve image quality by reducing the impact of raindrops, this paper proposes a novel generative adversarial network for image de-raining. The network comprises two parts: a generative network and an adversarial network. The generative network performs image de-raining. The adversarial network determines whether the input image is rain-free or de-rained. The generative network comprises two branches: the A branch, which follows a traditional convolutional network structure, and the U branch, which utilizes a U-Net architecture. The A branch includes a multi-scale module for extracting information at different scales and a residual attention module to reduce redundant information interference. The U branch contains an encoder module designed to address the loss of details and local information caused by conventional down-sampling. To improve the performance of the generative network in image de-raining, this paper employs a relative discriminator incorporating a mean squared error loss. This discriminator better measures the differences between rainy and rain-free images while effectively preventing the occurrence of gradient vanishing. Finally, this study performs visual and quantitative comparisons of the proposed method and existing methods on three established rain image datasets. In the quantitative experiments, the proposed method outperforms existing methods regarding PSNR, SSIM, and VIF metrics. Specifically, our method achieves an average PSNR, SSIM, and VIF of approximately 5%, 3%, and 4% higher than the MFAA-GAN method, respectively. These results indicate that the de-rained images generated via the proposed method are closer to rain-free images.

Research on Smart City Road Network Capacity Optimization Configuration Based on Deep Learning Algorithms

At present, the urban traffic system is faced with the problems of congestion and low efficiency, and the traditional methods have certain limitations when dealing with the complex urban road network. This paper aims to explore a new method of capacity Optimization of Road Networks in a Smart City environment and proposes a method based on a Graph Neural network, named “Smart City Road optimization Graph Neural Network” (SCRO-GNN). SCRO-GNN first collects and preprocesses multi-source data, including road network data, traffic flow, accident records, environmental factors, etc. The key node and edge features, including the number of lanes at the intersection, the traffic flow of the section, and the adjacency matrix of the road network are defined to characterize the structure of the road network. Then, the graph neural network model is constructed and trained to predict the traffic flow of different sections and evaluate the road capacity by using the graph structure of the road network. This paper tests the performance of SCRO-GNN on real road networks in multiple cities. The results show that, compared with the traditional traffic flow prediction model, SCRO-GNN can significantly improve the prediction accuracy, especially when dealing with the highly complex urban road network structure. Based on these predictions, the proposed optimization strategy performed well in reducing traffic congestion and improving the efficiency of road use. The research in this paper not only demonstrates the potential of graph neural networks in smart city road network optimization, but also provides a new direction for future traffic system research. The successful implementation of the SCRO-GNN approach is expected to provide more efficient and intelligent solutions for urban traffic management and planning.

Approximation Algorithms for Dynamic Inventory Management on Networks

We provide the first approximation algorithm for dynamic inventory management on a network with stochastic demand and backlogging. Specifically, under a mild cost condition, we prove the cost of a specially designed base-stock policy is less than 1.618 times the cost of an optimal policy. We develop a novel stochastic programming analysis to prove this result: We carefully calibrate two stochastic programs (providing upper and lower bounds on the optimal policy), and compare their objectives. The upper bound arises from a new class of base-stock policies we define to address the currently unresolved issue of how to assign and fulfill backlogs in a system with fulfillment flexibility. We show the optimal policy in this class takes a simple and intuitive form: backlogs are assigned to their lowest cost activities for replenishment, and the ordered resources for those activities are committed to the backlogs for fulfillment. Next, the lower bound stochastic program is derived through a novel cost accounting scheme that captures the tradeoff between current inventory decisions and future backlog decisions. We then exploit this tradeoff to bound the ratio of the two stochastic program objectives and prove our main result. We also demonstrate our policy’s practicality with numerical simulations that show it performs within 1% of optimal on average across a wide range of problem instances. Finally, we show that our techniques and results extend to more general settings, demonstrating their potential for broader applicability. Importantly, our approach extends to problems with lead times, where we prove an approximation guarantee for base-stock policies that is independent of both the lead time and network structure. Thus, our work provides the new managerial insight that properly designed base-stock policies can be effective in network settings. This paper was accepted by Victor Martínez-de-Albéniz, operations management. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2022.02965 .

Prediction of Sea Surface Current Around the Korean Peninsula Using Artificial Neural Networks

AbstractThe prediction of sea surface currents is essential for various marine activities such as disaster monitoring, fishing industries, and search and rescue operations. Continuous improvements in numerical models have made it possible to predict more realistic oceans using data assimilation and fine spatial resolution. However, such complicated ocean models require high computational power and time, making them difficult to use for near‐real time forecasting. To compensate for these high computational costs, novel approaches with efficient computational costs combined with numerical model outputs need to be developed. Artificial neural networks could be one of the solutions as they require low computational power for prediction, owing to pre‐trained networks. Here, we present a prediction framework applicable to surface current prediction in the seas around the Korean Peninsula using three‐dimensional (3‐D) convolutional neural networks. The network is based on a 3‐D U‐shaped network structure and is modified to predict sea surface currents using oceanic and atmospheric variables. The forecast procedure is optimized to minimize the error of the next day's sea surface current field with a spatial resolution of 1/24° and its recursively predicting structure allows more days to be predicted. The network performance is evaluated by changing the input days and variables to find the optimal surface‐current‐prediction artificial neural network model. The optimized model shows a root mean squared error of 2.3 cm/s for the first forecast day, demonstrating its strong potential for practical use in the near future.

Flexible Krylov Methods for Group Sparsity Regularization

Abstract This paper introduces new solvers for efficiently computing solutions to large-scale inverse problems with group sparsity regularization, including both non- overlapping and overlapping groups. Group sparsity regularization refers to a type of structured sparsity regularization, where the goal is to impose additional structure in the regularization process by assigning variables to predefined groups that may represent graph or network structures. Special cases of group sparsity regularization include l1 and isotropic total variation regularization. In this work, we develop hybrid projection methods based on flexible Krylov subspaces, where we first recast the group sparsity regularization term as a sequence of 2-norm penalization terms using adaptive regularization matrices in an iterative reweighted norm fashion. Then, we exploit flexible preconditioning techniques to efficiently incorporate the weight updates. The main advantages of these methods are that they are computationally efficient (leveraging the advantages of flexible methods), they are general (and therefore very easily adaptable to new regularization term choices), and they are able to select the regularization parameters automatically and adaptively (exploiting the advantages of hybrid methods). Extensions to multiple regularization terms and solution decomposition frameworks (e.g., for anomaly detection) are described, and a variety of numerical examples demonstrate both the efficiency and accuracy of the proposed approaches compared to existing solvers.

Identifying successful football teams in the European player transfer network

This paper considers the European transfer market for professional football players as a network to study the relation between a team’s position in this network and performance in its domestic league. Our analysis is centered on eight top European leagues. The market in each season is represented as a weighted directed network capturing the transfers of players to or from the teams in these leagues, and we also consider the cumulative network over the past 28 years. We find that the overall structure of this transfer market network has properties commonly observed in real-world networks, such as a skewed degree distribution, high clustering, and small-world characteristics. To assess football teams we first construct a measure of within-league performance that is comparable across leagues. Regression analysis is used to relate league performance with both the network position and level of engagement of the team in the transfer market, under two complimentary setups. Network position variables include, e.g., betweenness centrality, closeness centrality and node clustering coefficient, whereas market engagement variables capture a team’s activity in the transfer market, e.g., total number of player transfers and total paid for players. For the season snapshots, the number of transfers correspond to weighted in- and out-degree. Our analysis first corroborates several recent findings relating aspects of market engagement with teams’ league performance. A higher number of incoming transfers indicates worse performance and better resourced teams perform better. Then, and across specifications, we find that network position variables remain salient even when engagement variables are already considered. This substantiates the notion in the existing literature that a high degree corresponds to better team performance and suggests that network aspects of trading strategy may affect a team’s success in their respective domestic league (or vice versa). In this sense, the approach and findings presented in this paper may in the future guide team’s player acquisition policies.

FGYOLO: An Integrated Feature Enhancement Lightweight Unmanned Aerial Vehicle Forest Fire Detection Framework Based on YOLOv8n

To address the challenges of complex backgrounds and small, easily confused fire and smoke targets in Unmanned Aerial Vehicle (UAV)-based forest fire detection, we propose an improved forest smoke and fire detection algorithm based on YOLOv8. Considering the limited computational resources of UAVs and the lightweight property of YOLOv8n, the original model of YOLOv8n is improved, the Bottleneck module is reconstructed using Group Shuffle Convolution (GSConv), and the residual structure is improved, thereby enhancing the model’s detection capability while reducing network parameters. The GBFPN module is proposed to optimize the neck layer network structure and fusion method, enabling the more effective extraction and fusion of pyrotechnic features. Recognizing the difficulty in capturing the prominent characteristics of fire and smoke in a complex, tree-heavy environment, we implemented the BiFormer attention mechanism to boost the model’s ability to acquire multi-scale properties while retaining fine-grained features. Additionally, the Inner-MPDIoU loss function is implemented to replace the original CIoU loss function, thereby improving the model’s capacity for detecting small targets. The experimental results of the customized G-Fire dataset reveal that FGYOLO achieves a 3.3% improvement in mean Average Precision (mAP), reaching 98.8%, while reducing the number of parameters by 26.4% compared to the original YOLOv8n.

Visible light infrared matching algorithm based on improved SuperPoint and linear converter

In order to solve the problems of high difficulty and mismatch rate in heterogeneous image matching of visible light and infrared images, a deep learning matching algorithm based on improved SuperPoint and linear transformer is proposed. The algorithm first introduces the idea of feature pyramid to construct a feature description branch based on the SuperPoint network structure, and trains it based on the hinge loss function, so as to better learn the multi-scale deep features of visible light and infrared images and increase the similarity of image point pair descriptors with the same name; in the feature matching module, the linear transformer is used to improve the SuperGlue matching algorithm and aggregate features to improve matching performance. The proposed algorithm is experimentally verified on multiple data sets. The results show that compared with the existing algorithms, the algorithm achieves better matching results and improves the matching accuracy.

Forecasting future earthquakes with deep neural networks: Application to California

Summary We use the spatial map of the logarithm of past estimated released earthquake energies as input of Fully Convolutional Networks (FCN) to forecast future earthquakes. This model is applied to California and compared with an elaborated version of the Epidemic Type Aftershock Sequence (ETAS) model. Our long-term earthquake forecast simulations show that the FCN model is close to the ETAS model in predicting earthquakes with $M \ge 3.0,\ 4.0,\ {\rm{and\ }}5.0$ according to the Molchan diagram. Moreover, training and implementing the FCN model is 2000∼4000 times faster than calibrating the ETAS model and generating its probabilistic forecasts. The FCN model is straightforward in terms of its neural network structure and feature engineering. It does not require extensive knowledge of statistical seismology or the analysis of earthquake catalog completeness. Using the earthquake catalog with $M \ge 0$ as FCN input can enhance the model's performance in some time-magnitude prediction windows.

Highly Filled Waste Polyester Fiber/Low-Density Polyethylene Composites with a Better Fiber Length Retention Fabricated by a Two-Rotor Continuous Mixer

A key challenge in the utilization of waste polyester fibers (PET fibers) is the development of fiber-reinforced composites with high filler content and the improvement of fiber length retention. Herein, the effects of a two-rotor continuous mixer and a twin-screw extruder on the structure and properties of waste polyester fiber composites were evaluated. The results revealed that the mechanical properties of the composites were improved significantly with increasing fiber content, especially when processed using the twin-rotor continuous mixer. This mixer facilitated the formation of a robust fiber network structure, leading to substantial enhancements in tensile strength, flexural strength, and heat resistance. Specifically, compared to those processed by the twin-screw extruder, with 60 wt% fibers content, the tensile and flexural strengths of specimens processed by the twin-rotor continuous mixer increase by 21% and 13%, respectively. The average fiber length in specimens processed by the twin-rotor continuous mixer was 32% longer than that in specimens processed by the twin-screw extruder, attributable to the lower shear frequency and the higher tensile ratio of the former. This blending technique emerges as an effective strategy, contributing significantly to promoting the development and practical application of waste textile fiber-reinforced polymer composites.

Modeling complex network perturbations on resilience of the bilateral regional trade agreements

The resilience of cooperative relationships within a trade agreement network, when subjected to external shocks or internal disturbances, underscores the role of network structure in the robustness and adaptability of the trade agreement system. Addressing the gap in understanding the resilience of trade agreement network dynamics, this study constructs a complex network based on the bilateral regional trade agreements. By applying reciprocal dynamics to measure cooperative relationships among countries in the network, we model the impact of complex network perturbations on the resilience of bilateral regional trade agreements. Various complex network perturbations are considered, including node removal, link removal, and three orders of null models for network reshuffling, which correspond to the failure of a trade agreement, simultaneous agreement failure, and signing. Experimental findings reveal that network resilience gradually diminishes with the random removal of nodes and links. However, when nodes are removed based on their degree, removing nodes with larger degrees first proves to be more effective than the reverse. Specifically, network resilience decreases more rapidly when smaller nodes are removed. This highlights the significant contribution of countries with numerous trade agreements to the overall network resilience. In network reshuffling experiments, an increase in the order of reshuffling correlates with a gradual decrease in network resilience, ultimately converging toward real values. These findings emphasize the importance of network structure in maintaining the stability and adaptability of trade agreement systems.

Gelation properties and swallowing characteristics of heat-induced whey protein isolate/chia seed gum composite gels as dysphagia food

Soft gels based on protein-polysaccharide composite systems play a crucial role in the dietary management of people with dysphagia. The effect of chia seed gum (CSG) on the gelling and swallowing properties of heat-induced whey protein isolate (WPI) gels (3.125–75 mg/mL) was investigated. The results showed that adding CSG reduced the gelation concentration of WPI and weak gels could form at 12.5 mg/mL WPI concentration. In addition, the viscoelasticity and water-binding capacity of the WPI/CSG composite gels were gradually enhanced with increasing WPI concentrations. The WPI/CSG composite systems can be classified as level 2–5 dysphagia-oriented foods according to the International Dysphagia Diet Standardization Initiative (IDDSI) framework. The incorporation of CSG promoted the cross-linking of protein aggregates and the formation of compact and continuous network structures, resulting in improved gelling properties of composite systems. This study contributes to the development of novel soft gel-type dysphagia foods with better textural characteristics.

Exploring the Effect of Road Network Structure on Inter-Regional Accessibility in a Diverse Road Network

Abstract. Accessibility analyses quantify the level of access to certain areas or opportunities, such as employment and healthcare facilities. Since public data is often aggregated at the level of regions, such as administrative units, it is useful to quantify accessibility between regions. Many factors influence inter-regional accessibility, most notably the accessibility metric used, and the way in which regions are chosen. This paper investigates the effects of road network structure on accessibility, using a previously developed inter-regional accessibility model that bases its accessibility metric on travel distance via the road network. This paper considers an area within the City of Tshwane municipality in South Africa. We investigate the effects of road structure in two ways. Firstly, regions are chosen based on the road network structure, which is done by extending a previously developed road network clustering algorithm for this novel use. Different spatial scales of regionalisation are considered, and the accessibility between these regions is compared to the accessibility between administrative units within the study area. Secondly, the effect of road network homogeneity on accessibility is investigated, where homogeneity corresponds to a uniform concentration of roads across a region. The results show that although road network homogeneity does not significantly correlate with accessibility, the way in which regions are chosen and their spatial scale has a strong effect on the results of the accessibility model. Our novel method of obtaining regions thus provides fresh insights into road-based accessibility within the City of Tshwane.

Robust Estimation of Crowd Density Using Vision Transformers

Estimating and predicting crowd density at large events or during disasters is of paramount importance for enhancing emergency management systems. This includes planning effective evacuation routes, optimizing rescue operations, and ensuring efficient deployment of emergency services. Traditionally, surveillance systems that rely on cameras have been employed to monitor crowd movements. However, accurately estimating crowd density using such systems presents several challenges. These challenges stem primarily from the interaction between large crowds and the limitations of two-dimensional cameras in capturing the full scope of three-dimensional spaces. Optical distortions, environmental factors, and variations in camera angles further complicate the task, making accurate estimations difficult to achieve. To address these challenges, this paper introduces a robust method for calculating crowd density that leverages advanced vision transformers. By combining the output of these transformers with a two-stage neural network, the method effectively mitigates the limitations of traditional approaches. One of the key advantages of the proposed system is its robustness, which allows it to perform well across different camera specifications, installation locations, and image aspect ratios. The method applies and evaluates various deep learning techniques, introducing improvements to existing network structures that are better suited for the problem at hand. Extensive experimental verification demonstrates that the proposed method consistently produces accurate crowd density estimates, even in diverse and complex crowd environments. This robust performance underscores its potential for improving emergency management and crowd control in real-world situations.

Enhanced Speech Processing for Air Traffic Control Using an Optimized Generative Adversarial Network

In order to improve the quality of voice calls during air traffic control, an improved SEGAN air traffic control speech enhancement algorithm is proposed. Aiming at the problem that the traditional speech enhancement algorithm based on generative adversarial network (SEGAN) is drowned under low signal-to-noise ratio conditions, a multi-stage, multi-mapping, multi-dimensional output generator and a multi-scale, multi-discriminator network model are proposed based on the SEGAN network model. First, the speech semantic features are extracted based on the deep neural network structure to complete the semantic segmentation of air traffic control speech. Secondly, multiple generators are set to further optimize the speech signal. Then, a downsampling module is added to the convolution layer to improve the model's utilization of speech information and reduce the loss of speech information. Finally, multi-scale, multiple discriminators are used to learn the distribution law and information of speech samples in multiple directions. The results show that under low signal-to-noise ratio conditions, the improved SEGAN model improves the short-term objective intelligibility (STOI) and the perceptual evaluation of speech quality (PESQ) by and respectively , which can quickly and effectively perform air traffic control speech enhancement and provide preparation for subsequent air traffic control speech recognition.

Performance Evaluation of HTTP, DHCP and DNS Protocols of Data Packets for Vulnerabilities Using the Isolation Forest Algorithm

In the contemporary digital landscape, network security is paramount to safeguard data integrity and prevent unauthorized access as data have been structured in the network through protocols. In term of data structure IPv6 protocol has extended data size due to the robust addresses of 128 bits as compare to 32 bits of IPv4. Due to the improved security data structure of IPv6, the study focuses on identifying vulnerabilities in HTTP, DHCP, and DNS packets using the Isolation Forest algorithm approach, a machine-learning technique designed for anomaly detection. By analyzing packet lengths, size, payload and addressing, the study visualizes normal and anomalous behavior, providing insights into potential security threats in IPv4 network structure. The results highlight the effectiveness of Goodput, Quality of service and risk as essential factors in the network, using Little's theorem analysis and the Isolation Forest in detecting anomalies across these different network protocols, offering valuable implications for network security structures, due to IoT in recent networks. The time response determination in this paper explained details information on the time the treats entered the network, the duration of the vulnerabilities within the network, leading to a certain threshold, and traffic delay factors due to deviation of packet length and other social engineering activities. Sensitive multipurpose security devices are involved; MikroTik routers were configured and installed in the network under evaluation. Which the normal DPI technique was unable to effectively and efficiently addressed. ADPI principles and operations where the needed security measures adopted to detect those vulnerabilities which were eventually addressed and have contributed to recent measures of network security.

A Generalized Deep Reinforcement Learning Model for Distribution Network Reconfiguration with Power Flow-Based Action-Space Sampling

Distribution network reconfiguration (DNR) is used by utilities to enhance power system performance in various ways, such as reducing line losses. Conventional DNR algorithms rely on accurate values of network parameters and lack scalability and optimality. To tackle these issues, a new data-driven algorithm based on reinforcement learning is developed for DNR in this paper. The proposed algorithm comprises two main parts. The first part, named action-space sampling, aims at analyzing the network structure, finding all feasible reconfiguration actions, and reducing the size of the action space to only the most optimal actions. In the second part, deep Q-learning (DQN) and dueling DQN methods are used to train an agent to take the best switching actions according to the switch states and loads of the system. The results show that both DQN and dueling DQN are effective in reducing system losses through grid reconfiguration. The proposed methods have faster execution time compared to the conventional methods and are more scalable.

Matrix expressions of symmetric n-player games

The symmetric property in n-player games is explored in this paper. First of all, some algebraically verifiable conditions are provided respectively for the totally symmetric, weakly symmetric and anonymous games, which are based on the construction of permutation matrix, and some interesting properties are revealed. Then we investigate how network structures affect the symmetry in a networked game. Some sufficient conditions are proposed and several nice properties are preserved when traditional networked games are extended to generalized networked games, in which the resulting network structure is more complex than a classical network graph.

Supplemental Material for Evidence of Community Structure in Phonological Networks of Multiple Languages

Supplemental Material for Evidence of Community Structure in Phonological Networks of Multiple Languages

Dynamics of second-language learners' semantic memory networks: Evidence from a snowball sampling paradigm.

This article provides an analysis of structural changes in second-language (L2)-based semantic memory networks-graphs composed of L2 words as nodes and semantic relations between them as edges, during L2 learning. We used snowball sampling paradigm to create individual semantic networks of participants divided into two groups differing in L2 learning time and then compare their structural characteristics cross-sectionally. The results showed that as L2 learning progresses, semantic memory networks tend to become more connected (by increasing the average node degree), more efficient (by decreasing the average shortest path length), less fragmented (by decreasing the modularity), less centralized (by decreasing the centralization), less dense (by decreasing the density), and no more "small-worlded" (by similar average clustering coefficients and small-world indices). The findings provide quantitative evidence of how the duration of L2 learning shapes the structure of L2-based semantic memory networks generated in the snowball sampling paradigm. (PsycInfo Database Record (c) 2024 APA, all rights reserved).