Set Of Networks Research Articles

Toward Generalized Artificial Intelligence by Assessment Aggregation With Applications to Standard and Extreme Classifications.

The article proposes a plural learning framework combining the ingredients found in a tribunal for the derivation of a more generalized artificial intelligence (GAI) when starting from a specialized set of convolutional neural networks (CNNs). This framework involves at least two different training stages called, respectively, specialization and generalization. In the specialization stage, any CNN considered in a given set learns to predict independently of other elements of the set. In the second stage called generalization, an integration network learns to predict from assessment measures fed by downstream specialized CNNs. The assessment measures considered are categorical softmax probabilities and learning to judge from these assessments relies on independent CNNs. Generalization proof of concepts is provided in terms of multimodel, multimodal, and distributed schemes. The multimodel framework is such that different CNN models operating on the same modality cooperate for decision purpose. The multimodal framework implies specializations of CNN with respect to different input modalities. The distributed framework proposed is associated with assessment exchanges: it such that the aggregation aims at determining relevant joint assessments for mapping a given input to a single or a multiple output category. The performance of these aggregation frameworks is shown to be outstanding for both standard and extreme classification issues.

Financial Risk Early Warning Model for Listed Companies Using BP Neural Network and Rough Set Theory

Financial Risk Early Warning Model for Listed Companies Using BP Neural Network and Rough Set Theory

IL1A regulates the inflammation in gout through the Toll-like receptors pathway.

Objective: Gout is a dangerous metabolic condition related to monosodium urate (MSU). Our aim is to study the molecular mechanisms underlying gout and to identify potential clinical biomarkers by bioinformatics analysis and experimental validation. Methods: In this study, we retrieved the overlapping genes between GSE199950-Differential Expressed Genes (DEGs) dataset and key module in Weighted Gene Co-Expression Network Analysis (WGCNA) on GSE199950. These genes were then analyzed by protein-protein interaction (PPI) network, expression and Gene Set Enrichment Analysis to identify the hub gene related to gout. Then, the gene was investigated by peripheral blood mononuclear cells (PBMCs), immunoassay and cell experiments like western blotting to uncover its underlying mechanism in gout cells. Results: From the turquoise module and 83 DEGs, we identified 62 overlapping genes, only 11 genes had mutual interactions in PPI network and these genes were highly expressed in MSU-treated samples. Then, it was found that the IL1A (interleukin 1 alpha) was the only one gene related to Toll-like receptor signaling pathway that was associated with the occurrence of gout. Thus, IL1A was determined as the hub gene in this study. In immunoassay, IL1A was significantly positively correlated with B cells and negatively correlated with macrophages. Moreover, IL1A is highly expressed in gout patients,it has a good clinical diagnostic value. Finally, the results of in vitro experiments showed that after knocking down IL1A, the expressions of pro-inflammatory cytokines and Toll-like receptor signaling pathway-related proteins (TLR2, TLR4, MyD88) were all reduced. Conclusion: It is confirmed that IL1A is a promoting gene in gout with a good diagnostic value, and specifically it affects the inflammation in gout through Toll-like receptor pathway. Our research offers fresh perspectives on the pathophysiology of gout and valuable directions for future diagnosis and treatment.

Infliximab monitoring in Crohn’s disease: a neural network approach for evaluating disease activity and immunogenicity

Background: The treatment for Crohn’s disease (CD) has increasingly required the use of biological agents. Safe and affordable tests have led to the active implementation of therapeutic drug monitoring (TDM) in clinical practice, which, although not yet widely available across all health services, has been proven effective. Objective: To analyze serum infliximab (IFX) and antidrug antibody (ADA) levels in CD patients, compare two tests, as well as construct a prediction of neural network using a combination of clinical, epidemiological, and laboratory variables. Design: Cross-sectional observational study. Method: A cross-sectional observational study was conducted on 75 CD patients in the maintenance phase of IFX treatment. The participants were allocated into two groups: CD in activity (CDA) and in remission (CDR). Disease activity was defined by endoscopic or radiological criteria. Serum IFX levels were measured by enzyme-linked immunosorbent assay (ELISA) and rapid lateral flow assay; ADA levels were measured by ELISA. A nonparametric test was used for statistical analysis; p value of ⩽0.05 was considered significant. Differences between ELISA and rapid lateral flow results within the measurement range were assessed by the Wilcoxon test, Passing–Bablok regression, and Bland–Altman method. Prediction models were created using four neural network sets. Neural networks and performance receiver operating characteristic curves were created using the Keras package in Python software. Results: Most participants exhibited supratherapeutic IFX levels (>7 mg/mL). Both tests showed no difference in IFX levels between the CDA and CDR groups ( p > 0.05). The use of immunosuppressive therapy did not affect IFX levels ( p > 0.05). Only 14.66% of patients had ADA levels >5 AU/mL, and all ADA-positive participants exhibited subtherapeutic IFX levels in both tests. The median results of both tests showed significant differences and moderate agreement ( r = −0.6758, p < 0.001). Of the four neural networks developed, two showed excellent performance, with area under the curve (AUCs) of 82–92% and 100%. Conclusion: Most participants exhibited supratherapeutic IFX levels, with no significant serum level difference between the groups. There was moderate agreement between tests. Two neural network sets showed disease activity and the presence of ADA, noninvasively determined in patients using IFX by presenting an AUC of >80%.

A scalable blockchain-enabled federated learning architecture for edge computing.

Various deep learning techniques, including blockchain-based approaches, have been explored to unlock the potential of edge data processing and resultant intelligence. However, existing studies often overlook the resource requirements of blockchain consensus processing in typical Internet of Things (IoT) edge network settings. This paper presents our FLCoin approach. Specifically, we propose a novel committee-based method for consensus processing in which committee members are elected via the FL process. Additionally, we employed a two-layer blockchain architecture for federated learning (FL) processing to facilitate the seamless integration of blockchain and FL techniques. Our analysis reveals that the communication overhead remains stable as the network size increases, ensuring the scalability of our blockchain-based FL system. To assess the performance of the proposed method, experiments were conducted using the MNIST dataset to train a standard five-layer CNN model. Our evaluation demonstrated the efficiency of FLCoin. With an increasing number of nodes participating in the model training, the consensus latency remained below 3 s, resulting in a low total training time. Notably, compared with a blockchain-based FL system utilizing PBFT as the consensus protocol, our approach achieved a 90% improvement in communication overhead and a 35% reduction in training time cost. Our approach ensures an efficient and scalable solution, enabling the integration of blockchain and FL into IoT edge networks. The proposed architecture provides a solid foundation for building intelligent IoT services.

On the design of cost minimization for D2D‐enabled wireless caching networks: A joint recommendation, caching, and routing perspective

AbstractCache‐enabled device‐to‐device (D2D) network has been deemed as an effective technique to offload the data traffic. However, the gain of the caching schemes is closely related to the homogeneity among users' preference distribution. To tackle this issue, recommendation is a promising proactive approach. It increases the request probability of recommended contents, reshaping users' contents demand patterns, and improving caching performance. Moreover, considering the heterogeneous network settings, i.e. content retrieval costs vary, the routing design becomes a non‐negligible factor on caching performance optimization. On these grounds, the average system cost of D2D‐enabled wireless caching networks with multiple BSs is first described. Then the routing strategies are designed together with caching and recommendation policies by minimizing the average cost of these networks. The optimization problem is proven as NP‐hard. To facilitate the analysis, the original problem is decoupled into two sub‐problems and solve them respectively. Afterwards, all the variables are optimized in an alternating manner until the convergence is achieved. The proposed algorithm's convergence performance and benefits over benchmark strategies in terms of total cost and cache hit ratio are supported by Monte‐Carlo simulation results.

From the visibility graph (VG) to a complementary visibility graph (CVG) and an image complementary visibility graph (ICVG): Algorithms and applications

A new algorithm for bridging the gap between time series and networks is proposed in this short paper called the complementary visibility graph (CVG). The visibility graphs (VGs) method makes it easy to fulfill complex network topology modeling, which is effective for nonlinear dynamic analysis. Based on the proposed CVG, an image complementary visibility graph (ICVG) is also proposed. The algorithmic procedure has three steps. First, the texture images were converted into the corresponding ICVG. Then, the feature descriptors of the texture image datasets were extracted from the associated complex network set. Finally, texture image classification can be successfully achieved by using the most popular classifiers. Experimentally validated on the classic datasets Kylberg and KTHTIPS2b. The results show that the proposed ICVG model and cubic support vector machine classifier on the two datasets have classification accuracies of 100.0% and 93.0%, respectively. On the same image datasets, the results are better than most results in the existing literature, easily extending to similar situations. The source code is available at https://github.com/LaifanPei/CVG.

Advancing Network Infrastructure: Integrating VXLAN Technology with Automated Circuit Operations and NOS Configurations

Enhancing network infrastructure is achieved through integrating VXLAN technology, Python-automated circuit operations, and Ansible-driven Network Operating System (NOS) configurations, complemented by GitHub for reliable configuration backups. VXLAN, a robust network virtualization protocol, addresses the challenges of managing extensive network segments. Python scripts facilitate the automated analysis, creation, and management of network circuits, significantly boosting efficiency and accuracy. Ansible, a powerful automation tool, is employed to streamline NOS configurations, ensuring consistency and reducing manual overhead in network settings. Concurrently, GitHub, working in tandem with crontab scheduling, offers a dependable platform for the automated, regular backup of configurations, thus enhancing network resilience and simplifying recovery processes. The collective implementation of VXLAN, Python, and Ansible automation, along with GitHub for configuration management, marks a notable advancement in operational efficiency, underscoring their importance as critical components in the modernization and security of network infrastructures.

Estimation of Astronomical Seeing with Neural Networks at the Maidanak Observatory

In the present article, we study the possibilities of machine learning for the estimation of seeing at the Maidanak Astronomical Observatory (38∘40′24″ N, 66∘53′47″ E) using only Era-5 reanalysis data. Seeing is usually associated with the integral of the turbulence strength Cn2(z) over the height z. Based on the seeing measurements accumulated over 13 years, we created ensemble models of multi-layer neural networks under the machine learning framework, including training and validation. For the first time in the world, we have simulated optical turbulence (seeing variations) during night-time with deep neural networks trained on a 13-year database of astronomical seeing. A set of neural networks for simulations of night-time seeing variations was obtained. For these neural networks, the linear correlation coefficient ranges from 0.48 to 0.68. We show that modeled seeing with neural networks is well-described through meteorological parameters, which include wind-speed components, air temperature, humidity, and turbulent surface stresses. One of the fundamental new results is that the structure of small-scale (optical) turbulence over the Maidanak Astronomical Observatory does not depend or depends negligibly on the large-scale vortex component of atmospheric flows.

Throughput-enhanced FTIR spectrometers with deep learning-based spectral recovery

Fourier transform infrared (FTIR) spectrometers are widely employed for spectroscopic characterization with high optical throughput, owing to the circular Jacquinot Stop (J-Stop). While the throughput increases with the J-Stop diameter, it has been theoretically and experimentally found that the divergent beam entering the Michelson interferometer induces spectral broadening and shifting, resulting in the obvious degradation of spectral resolution and wavenumber accuracy. This work has validated the deep learning-based spectral recovery for numerically eliminating the spectral distortions in a rapid and accurate way, effectively replacing the previously proposed time-consuming iterative calculation. Considering the influence of spectral complexity on the spectral recovery, the spectra are segmented and classified in terms of peak number with the convolutional neural network (CNN), before the parallel spectral reconstruction with a set of generative adversarial networks (GANs). The spectral recovery has been performed on the transmission spectra of water vapor collected by a commercial FTIR spectrometer, demonstrating that the spectra of 4 mm-diameter J-Stop with ∼12 times higher throughput can be recovered to coincide well with those of 1 mm-diameter J-Stop. With the enhanced throughput, the signal-to-noise ratio of FTIR spectrometers can be improved by >6 times for weak-light detection.

Between Art Historical Representation and Didactic Functionality: The Cast Collection of the Royal Academy of Fine Arts of Antwerp

During the long nineteenth century, the Royal Academy of Fine Arts of Antwerp – just like many other art schools in this period – assembled a collection of some 500 plaster casts after ancient and modern sculptures, which played an essential role in the education of young art students. The creation of such collections went in parallel with the blossoming of cast museums all over Europe, as well as the emergence of a large-scale exchange network set up to facilitate the international dissemination of plaster casts. However, in contrast to cast museums, which brought together masterpieces of classical Western sculpture in order to contribute to the aesthetic edification of the public, the cast collections of art academies had a more pragmatic and didactic function. This article focuses on cast collections at art academies, and how the formation and functioning of such collections related to broader educational concepts and practices at these schools. Taking the collection of plaster casts at the Royal Academy of Fine Arts of Antwerp as a case study, we will trace the various actors, methods and strategies employed to create the collection, uncover how the collection related to the artistic idea(l)s expressed in the educational programme of that institution, and discuss how and where it was located and displayed. Based on the rich archives of the academy, it examines a broad range of different sources, including purchase lists, inventories and correspondence concerning the formation of the collection, as well as floor plans, photographs and original drawings attesting to the location and use of the casts. It traces the provenance of the objects, analyzes the profiles of the individuals and institutions involved in creating the collection, and identifies to what extent and how creative repurposing played a role in the collection’s functioning. The article argues how cast collections formed by art academies – in addition to representing the art historical canon of a given place or period – are an important reflection of the didactic practices, aesthetic priorities and, above all, the creative encounters that distinguish these institutions from the purposes of the public (cast) museum.

Modeling of forced-vibration systems using continuous-time state-space neural network

Dynamic analysis of forced-vibration systems in civil engineering could be computationally inefficient or even hard to converge if the systems are stiff or highly complicated. Rapid advances in machine learning make it possible to formulate surrogate models for forced-vibration systems using neural networks. The widely used neural networks such as the convolutional neural network (CNN), recurrent neural network (RNN), etc., usually require a constant sampling rate and data length, thus they are difficult to be implemented for real-time calculation of the dynamic system with varying sampling rates. Recently, the continuous-time state-space neural network (CSNN) has shown the capability to lift these restrictions and has been drawing growing attention from the community. In this paper, we propose a generalized CSNN model for various forced-vibration systems (linear and nonlinear). The CSNN model comprises two sets of independent neural networks aiming to compute the state derivative and system response, respectively. Both neural networks adopt linear and nonlinear layers in parallel, instead of only fully connected nonlinear layers as adopted in the literature. This configuration is aimed to enhance the CSNN model with its capability to recognize the linear and nonlinear behaviors of systems. Additionally, the bias options in the CSNN model are all turned off to improve the stability of the model in the long-term time-series forecast, premised on the assumption that the forced-vibration systems are dissipative systems without drift, which is the most common case in civil engineering. Integration on the state derivative at the current time step is executed to obtain the state at the next time step using the explicit 4th-order Runge–Kutta method. Both numerical and experimental illustrative examples are provided, demonstrating that the CSNN model can achieve high performance and training efficiency with a few hyper-parameters, and thus is highly promising for engineering applications.

Routing in Mobile ad Hoc Networks Using Machine Learning Techniques

The significance of Mobile Ad Hoc Networks (MANETs) has increased in the current period due to the proliferation of mobile devices and the emergence of Internet of Things (IoT) applications. The function of routing in decentralized wireless networks is of paramount importance in facilitating efficient data transfer. Conventional routing techniques need help in effectively adjusting to the dynamic changes in network topology and the constraints imposed by restricted network resources. To tackle these concerns, a Machine Learning-Based Optimized Routing Algorithm (ML-ORA) is proposed in this research. ML-ORA has been developed to offer adaptable and intelligent routing solutions, especially in MANET. This is achieved via the integration of parameter settings, the use of a Hybrid Particle Swarm Optimization (HPSO) algorithm for Cluster Head (CH) selection, the inclusion of a clustering stage, and the incorporation of a k-Nearest Neighbors (k-NN)-based intrusion detection system. The performance of ML-ORA is assessed by conducting simulations using Network Simulator 3 (NS-3), demonstrating its efficacy in dynamic network settings. The findings exhibit a latency of 15 milliseconds, a packet delivery ratio of 95%, a network throughput of 4Mbps, and an energy efficiency of 85%. ML-ORA presents a potentially advantageous resolution for tackling the obstacles encountered in MANET routing, thereby creating opportunities for enhanced efficacy and security in the transmission of data inside dynamic wireless networks.

A novel local alignment algorithm for Multilayer networks

Multilayer Network (MN) is a complex network comprising a set of graphs (also referred to as layers) interconnected by edges or interlayer edges (or inter-edges) linking the nodes of different layers. In biology, a MN may model interactions among diseases, genes, and drugs, only using its structure. Recently, there has been a growing interest in comparing two MNs by revealing local regions of similarity as a counterpart of Network Alignment algorithms (NA) for simple networks. However, classical algorithms for NA such as Local NA (LNA) cannot be applied on multilayer networks, since they are not able to deal with interlayer edges. Therefore, there is a need for the introduction of novel algorithms. In this paper, we present MuLan, an algorithm for the local alignment of multilayer networks. MuLan is based on the building of a multilayer alignment graph starting from a set of seed nodes. Then it analyses such a graph by revealing conserved regions. We first show as proof of concept the performances of MuLaN on a set of synthetic multilayer networks. Then, we used as a case study a real multilayer network in the biomedical domain. Our results show that MuLaN can build high-quality alignments and can extract knowledge about the aligned multilayer networks. MuLaN is available at https://github.com/pietrocinaglia/mulan.

Connecting Structural Characteristics and Material Properties in Phase-Separating Polymer Solutions: Phase-Field Modeling and Physics-Informed Neural Networks.

The formed morphology during phase separation is crucial for determining the properties of the resulting product, e.g., a functional membrane. However, an accurate morphology prediction is challenging due to the inherent complexity of molecular interactions. In this study, the phase separation of a two-dimensional model polymer solution is investigated. The spinodal decomposition during the formation of polymer-rich domains is described by the Cahn-Hilliard equation incorporating the Flory-Huggins free energy description between the polymer and solvent. We circumvent the heavy burden of precise morphology prediction through two aspects. First, we systematically analyze the degree of impact of the parameters (initial polymer volume fraction, polymer mobility, degree of polymerization, surface tension parameter, and Flory-Huggins interaction parameter) in a phase-separating system on morphological evolution characterized by geometrical fingerprints to determine the most influential factor. The sensitivity analysis provides an estimate for the error tolerance of each parameter in determining the transition time, the spinodal decomposition length, and the domain growth rate. Secondly, we devise a set of physics-informed neural networks (PINN) comprising two coupled feedforward neural networks to represent the phase-field equations and inversely discover the value of the embedded parameter for a given morphological evolution. Among the five parameters considered, the polymer-solvent affinity is key in determining the phase transition time and the growth law of the polymer-rich domains. We demonstrate that the unknown parameter can be accurately determined by renormalizing the PINN-predicted parameter by the change of characteristic domain size in time. Our results suggest that certain degrees of error are tolerable and do not significantly affect the morphology properties during the domain growth. Moreover, reliable inverse prediction of the unknown parameter can be pursued by merely two separate snapshots during morphological evolution. The latter largely reduces the computational load in the standard data-driven predictive methods, and the approach may prove beneficial to the inverse design for specific needs.

Linear and Non-Linear Spatio-Temporal Input Selection In Wireless Traffic Networks Prediction using Recurrent Neural Networks

For the optimization of computer networks with high bandwidth requirements, it is necessary to predict the traffic of the wireless network. Its goal is to reduce maintenance costs and improve internet services. Feature selection is a major issue in multivariate time series (MTS) spatio-temporal modeling. Another problem is the dependency between input features, time lags, and spatial factors, so an appropriate model is needed. This study aims to provide solutions to two problems. The first is to improve a feature extraction and selection process in spatio-temporal MTS data for relevant features using Detrended Partial Cross-Correlation Analysis (DPPCA) and nonredundant features associated with linear using Pearson's correlation (PC) filters and non-linear associations using Symmetrical Uncertainty (SU) and a combination of both PCSUF. The second is to develop a spatiotemporal framework model using recurrent neural networks (RNNs) to get better performance than the traditional model. These methods are combined and tested using a data set of cellular networks with one hour intervals during November in three locations. Testing the effectiveness of the feature selection technique showed that 27.6% of the total extracted features were. The forecasting model with the DPCCA-SU-RNN combination method is the best performance by having RMSE = 380.7, R2 = 97% and MAPE = 10%.

Exploring the Transformation of Movie Publicity Strategies under the Perspective of New Media Communication

Recently, the network set off a short video medium for the movie publicity craze, so that film publicity is gradually attached importance by film officials, and getting into the public's field of vision. Movie publicity cannot be separated from the support of the media, and the role of the media in promoting movie publicity activities should not be underestimated. Based on this background, through literature analysis and case study method, it was found that with the different mainstream media, movie publicity is also exploring new modes and methods. In terms of the direction and content of publicity, regardless of the medium used, the core always revolves around the theme of the film, the cast of the film, and the film's reputation. However, the use of media in different periods can lead to different strategies for the partial weight of the three in film publicity. In terms of publicity methods, before the emergence of online media, paper media was the main method of publicity, using text and posters. After the emergence of online media, online interaction and short-term marketing became popular. However, although it has a dissemination effect similar to the "magic bullet theory", it has a potential negative impact on the film's reputation and still needs further improvement.

Optimized Cross-Path Attacks via Adversarial Reconnaissance

While softwarization and virtualization technologies make modern communication networks appear easier to manage, they also introduce highly complex interactions within the networks that can cause unexpected security threats. In this work, we study a particular security threat due to the sharing of links between high-security paths and low-security paths, which enables a new type of DoS attacks, called cross-path attacks, that indirectly attack a set of targeted high-security paths (target paths) by congesting the shared links through a set of attacker-controlled low-security paths (attack paths). While the feasibility of such attacks has been recently demonstrated in the context of SDN, their potential performance impact has not been characterized. To this end, we develop an approach for designing an optimized cross-path attack under a constrained total attack rate, consisting of (i) novel reconnaissance algorithms that can provide consistent estimates of the locations and parameters of the shared links via network tomography, and (ii) efficient optimization methods to design the optimal allocation of attack rate over the attack paths to maximally degrade the performance of the target paths. The proposed attack has achieved a significantly larger performance impact than its non-optimized counterparts in extensive evaluations based on multiple network settings, signaling the importance of addressing such intelligent attacks in network design.

Properties of a Random Bipartite Geometric Associator Graph Inspired by Vehicular Networks.

We consider a point process (PP) generated by superimposing an independent Poisson point process (PPP) on each line of a 2D Poisson line process (PLP). Termed PLP-PPP, this PP is suitable for modeling networks formed on an irregular collection of lines, such as vehicles on a network of roads and sensors deployed along trails in a forest. Inspired by vehicular networks in which vehicles connect with their nearest wireless base stations (BSs), we consider a random bipartite associator graph in which each point of the PLP-PPP is associated with the nearest point of an independent PPP through an edge. This graph is equivalent to the partitioning of PLP-PPP by a Poisson Voronoi tessellation (PVT) formed by an independent PPP. We first characterize the exact distribution of the number of points of PLP-PPP falling inside the ball centered at an arbitrary location in R2 as well as the typical point of PLP-PPP. Using these distributions, we derive cumulative distribution functions (CDFs) and probability density functions (PDFs) of kth contact distance (CD) and the nearest neighbor distance (NND) of PLP-PPP. As intermediate results, we present the empirical distribution of the perimeter and approximate distribution of the length of the typical chord of the zero-cell of this PVT. Using these results, we present two close approximations of the distribution of node degree of the random bipartite associator graph. In a vehicular network setting, this result characterizes the number of vehicles connected to each BS, which models its load. Since each BS has to distribute its limited resources across all the vehicles connected to it, a good statistical understanding of load is important for an efficient system design. Several applications of these new results to different wireless network settings are also discussed.

Beyond individual, population, and community: Considering information, cell number, and energy flux as fundamental dimensions of life across scales

We suggest rethinking ecology as a set of continuous, interconnected dynamics and spatial networks that would represent an alternative framework to the traditional organizational levels—cell, organism, population, community, and ecosystem. We draw on unifying biological theories—information theory, cell theory, and metabolic theories—to propose a continuous space for living systems that avoids epistemological constraints imposed by a priori assumptions of discrete levels of biological organization. The discrete levels of organization that ecologists have traditionally envisioned can be viewed instead as coarse-grained, localized groupings within continuous dimensions of information (I), cell number (C), and energy flux (E). Moving from levels of organization to emergent properties of information, cells, and energy flux allows us to illustrate how diverse ecological and evolutionary phenomena—such as allometric and diversity-related scaling patterns, predator-prey dynamics, evolutionary trajectories, and alternative stable states—can be represented within the same continuum. We suggest that there may be structure within this information-cells-energetic flux (ICE) framework that unifies ecology from the beginning of life to the present and provides a useful lens through which patterns and processes in nature can be viewed.