Multilayer Network Model Research Articles

Multilayer networks with higher-order interaction reveal the impact of collective behavior on epidemic dynamics

The ongoing COVID-19 pandemic has inflicted tremendous economic and societal losses. In the absence of pharmaceutical interventions, the population behavioral response, including situational awareness and adherence to non-pharmaceutical intervention policies, has a significant impact on contagion dynamics. Game-theoretic models have been used to reproduce the concurrent evolution of behavioral responses and disease contagion, and social networks are critical platforms on which behavior imitation between social contacts, even dispersed in distant communities, takes place. Such joint contagion dynamics has not been sufficiently explored, which poses a challenge for policies aimed at containing the infection. In this study, we present a multi-layer network model to study contagion dynamics and behavioral adaptation. It comprises two physical layers that mimic the two solitary communities, and one social layer that encapsulates the social influence of agents from these two communities. Moreover, we adopt high-order interactions in the form of simplicial complexes on the social influence layer to delineate the behavior imitation of individual agents. This model offers a novel platform to articulate the interaction between physically isolated communities and the ensuing coevolution of behavioral change and spreading dynamics. The analytical insights harnessed therefrom provide compelling guidelines on coordinated policy design to enhance the preparedness for future pandemics.

Prediction of the Compressive Strength of Waste-Based Concretes Using Artificial Neural Network.

In the 21st century, numerous numerical calculation techniques have been discovered and used in several fields of science and technology. The purpose of this study was to use an artificial neural network (ANN) to forecast the compressive strength of waste-based concretes. The specimens studied include different kinds of mineral additions: metakaolin, silica fume, fly ash, limestone filler, marble waste, recycled aggregates, and ground granulated blast furnace slag. This method is based on the experimental results available for 1303 different mixtures gathered from 22 bibliographic sources for the ANN learning process. Based on a multilayer feedforward neural network model, the data were arranged and prepared to train and test the model. The model consists of 18 inputs following the type of cement, water content, water to binder ratio, replacement ratio, the quantity of superplasticizer, etc. The ANN model was built and applied with MATLAB software using the neural network module. According to the results forecast by the proposed neural network model, the ANN shows a strong capacity for predicting the compressive strength of concrete and is particularly precise with satisfactory accuracy (R² = 0.9888, MAPE = 2.87%).

Ndist2vec: Node with Landmark and New Distance to Vector Method for Predicting Shortest Path Distance along Road Networks

The ability to quickly calculate or query the shortest path distance between nodes on a road network is essential for many real-world applications. However, the traditional graph traversal shortest path algorithm methods, such as Dijkstra and Floyd–Warshall, cannot be extended to large-scale road networks, or the traversal speed on large-scale networks is very slow, which is computational and memory intensive. Therefore, researchers have developed many approximate methods, such as the landmark method and the embedding method, to speed up the processing time of graphs and the shortest path query. This study proposes a new method based on landmarks and embedding technology, and it proposes a multilayer neural network model to solve this problem. On the one hand, we generate distance-preserving embedding for each node, and on the other hand, we predict the shortest path distance between two nodes of a given embedment. Our approach significantly reduces training time costs and is able to approximate the real distance with a relatively low Mean Absolute Error (MAE). The experimental results on a real road network confirm these advantages.

Diffusion of resources and their impact on epidemic spreading in multilayer networks with simplicial complexes

Recent studies have shown that personal resources have a significant impact on the dynamics of epidemic spreading. In previous studies, the main way for individuals to be able to obtain resources was through pairwise interactions. However, the human relationship network is often characterized also by group interactions, not just by pairwise interactions. To study the impact of resource diffusion on disease propagation in such higher-order networks, we therefore propose a multilayer network model, where the upper-layer network represents a resource network composed of random simplicial complexes to transmit resources, while the lower-layer network represents the network of physical contacts where the disease can spread. We derive the outbreak threshold expression for the epidemic by means of the micro Markov chain method, which reveals that the diffusion of resources may substantially change the epidemic threshold. We also show that the final fractions of infected individuals obtained via the micro Markov chain method and the classical Monte Carlo method are very similar, thus confirming that the model can predict well the epidemic spreading within the networked population. Finally, through extensive simulations, we show also that increasing the spread of resources on 2-simplexes can suppress the epidemic spreading and outbreaks, thus outlining possibilities for novel containment strategies.

Official logo recognition based on multilayer convolutional neural network model

Deep learning has gained high popularity in the field of image processing and computer vision applications due to its unique feature extraction property. For this characteristic, deep learning networks used to solve different issues in computer vision applications. In this paper the issue has been raised is classification of logo of formal directors in Iraqi government. The paper proposes a multi-layer convolutional neural network (CNN) to classify and recognize these official logos by train the CNN model on several logos. The experimental show the effectiveness of the proposed method to recognize the logo with high accuracy rate about 99.16%. The proposed multi-layers CNN model proves the effectiveness to classify different logos with various conditions.

Global and individualized community detection in inhomogeneous multilayer networks

In network applications, it has become increasingly common to obtain datasets in the form of multiple networks observed on the same set of subjects, where each network is obtained in a related but different experiment condition or application scenario. Such datasets can be modeled by multilayer networks where each layer is a separate network itself while different layers are associated and share some common information. The present paper studies community detection in a stylized yet informative inhomogeneous multilayer network model. In our model, layers are generated by different stochastic block models, the community structures of which are (random) perturbations of a common global structure while the connecting probabilities in different layers are not related. Focusing on the symmetric two block case, we establish minimax rates for both global estimation of the common structure and individualized estimation of layerwise community structures. Both minimax rates have sharp exponents. In addition, we provide an efficient algorithm that is simultaneously asymptotic minimax optimal for both estimation tasks under mild conditions. The optimal rates depend on the parity of the number of most informative layers, a phenomenon that is caused by inhomogeneity across layers. The method is extended to handle multiple and potentially asymmetric community cases. We demonstrate its effectiveness on both simulated examples and a real multimodal single-cell dataset.

Investigating the COVID-19 vaccine discussions on Twitter through a multilayer network-based approach

Modeling discussions on social networks is a challenging task, especially if we consider sensitive topics, such as politics or healthcare. However, the knowledge hidden in these debates helps to investigate trends and opinions and to identify the cohesion of users when they deal with a specific topic. To this end, we propose a general multilayer network approach to investigate discussions on a social network. In order to prove the validity of our model, we apply it on a Twitter dataset containing tweets concerning opinions on COVID-19 vaccines. We extract a set of relevant hashtags (i.e., gold-standard hashtags) for each line of thought (i.e., pro-vaxxer, neutral, and anti-vaxxer). Then, thanks to our multilayer network model, we figure out that the anti-vaxxers tend to have ego networks denser (+14.39%) and more cohesive (+64.2%) than the ones of pro-vaxxer, which leads to a higher number of interactions among anti-vaxxers than pro-vaxxers (+393.89%). Finally, we report a comparison between our approach and one based on single networks analysis. We prove the effectiveness of our model to extract influencers having ego networks with more nodes (+40.46%), edges (+39.36%), and interactions with their neighbors (+28.56%) with respect to the other approach. As a result, these influential users are much more important to analyze and can provide more valuable information.

Dermoscopy lesion classification based on GANs and a fuzzy rank-based ensemble of CNN models

Background and Objective. Skin lesion classification by using deep learning technologies is still a considerable challenge due to high similarity among classes and large intraclass differences, serious class imbalance in data, and poor classification accuracy with low robustness. Approach. To address these issues, a two-stage framework for dermoscopy lesion classification using adversarial training and a fuzzy rank-based ensemble of multilayer feature fusion convolutional neural network (CNN) models is proposed. In the first stage, dermoscopy dataset augmentation based on generative adversarial networks is proposed to obtain realistic dermoscopy lesion images, enabling significant improvement for balancing the number of lesions in each class. In the second stage, a fuzzy rank-based ensemble of multilayer feature fusion CNN models is proposed to classify skin lesions. In addition, an efficient channel integrating spatial attention module, in which a novel dilated pyramid pooling structure is designed to extract multiscale features from an enlarged receptive field and filter meaningful information of the initial features. Combining the cross-entropy loss function with the focal loss function, a novel united loss function is designed to reduce the intraclass sample distance and to focus on difficult and error-prone samples to improve the recognition accuracy of the proposed model. Main results. In this paper, the common dataset (HAM10000) is selected to conduct simulation experiments to evaluate and verify the effectiveness of the proposed method. The subjective and objective experimental results demonstrate that the proposed method is superior over the state-of-the-art methods for skin lesion classification due to its higher accuracy, specificity and robustness. Significance. The proposed method effectively improves the classification performance of the model for skin diseases, which will help doctors make accurate and efficient diagnoses, reduce the incidence rate and improve the survival rates of patients.

Prediction of mean radiant temperature distribution around a building in hot summer days using optimized multilayer neural network model

Urban warming has become increasingly serious in recent years. Especially in the case of hot summer days (with maximum daily temperature greater than 30°C), the number of people suffering from heat stroke increases every year. To mitigate urban warming and adapt to it, many researchers have focused on improving outdoor thermal comfort. The mean radiant temperature (MRT) is one of the most important variables affecting human thermal comfort in outdoor urban spaces; however, the process of MRT calculation requires a lot of computing power and time. The main objective of this study is the optimization of the back propagation and genetic algorithms on the basis of a multilayer neural network (MLNN), as an alternative to the time-consuming and computationally intensive process for quick MRT prediction. In this research work, a neural network was trained using the relevant weather-related and building morphology-related parameters that may affect the MRT from 2014-2018 as training parameters, the distributions of MRT around buildings in hot summer days of 2019 were predicted using an optimized neural network model. The results show that the mean absolute percentage error (MAPE) and root-mean-square error (RMSE) of the optimized model were lower than 1% and 1°C.

A novel adaptive predictive control strategy of hybrid radiant-air cooling systems operating in desert climates

Hydronic radiant-air cooling systems have proved to be highly energy-efficient compared to all-air systems. However, such systems require advanced control strategies to overcome their slow thermal response and potential water vapor condensation on the radiant surfaces. Yet, there is a clear lack of proposed adaptive controllers in the literature to collaboratively manage both radiant and air sides of the system. Such adaptive controllers are necessary for reliable and stable operation with minimal energy consumption. In this study, a novel offline adaptive predictive control strategy is proposed for the advantages of maximizing the energy savings of hybrid radiant-air systems, located in desert climate zones, while maintaining a higher quality indoor environment. A transient simulation model is developed in TRNSYS v.18 based on a typical medium-office space, located in Cairo, Egypt, with two air-cooled chiller loops serving a thermally activated building system and a dedicated outdoor air system. A multi-input multi-output multi-layered perceptron artificial neural network model has been developed in MATLAB based on batch simulations, performed in TRNSYS, to predict the electricity consumption and Predicted Percentage Dissatisfied (PPD) for different setpoints. The trained model was used as a fitness function of a multi-objective genetic algorithm, coupled with a decision-making criterion, to determine chillers’ setpoint temperatures that minimize the electricity consumption and thermal discomfort on a half-hourly simulation basis. The proposed controller was compared to a baseline three-step feedback controller, which turns the water circulation pumps on or off depending on the difference between the setpoint temperature and the indoor air temperature, as well as the initial state of the pumps (on or off). The results show that the proposed strategy substantially improves the indoor thermal environment, where the percentage of comfortable occupied hours is increased by 25.1%. The proposed controller also reduced the peak electricity consumption by 18.8%. However, the total energy consumption of the cooling season was lower by only 2.7% due to the longer operating hours of the chillers and the circulation pumps with this controller. Different strategies for further reduction of total energy consumption with a minimal tuning of the proposed controller are recommended for future studies.

다층신경망 학습 알고리즘 변화에 따른 건물 냉방부하 예측 모델의 성능 비교 평가

Purpose: In this study, among the methods of applying machine learning when predicting the load of a building, the cooling load of a building was predicted using a neural network model. To investigate the appropriateness of the learning algorithm of the multi-layer neural network model, the main purpose is to compare the predictive performance according to the change in the learning algorithm. Method: Among the learning algorithms applicable to multilayer neural networks, a total of 16 algorithms were used to predict the cooling load and compare the prediction results. The input variables of the input layer of the neural network model are outdoor dry bulb temperature, outdoor humidity, and Seasonally Data. The training period is 70% and the test period was 30%. The number of layers in the hidden layer is 3, the number of neurons is 20, and Epochs is 100. CvRMSE and MBE are used as performance index of the prediction model. The maximum, minimum, average, and standard deviation of the 20 prediction results are calculated, and the prediction performance according to the change in the learning algorithm was compared. Result: As a result of analyzing the predictive performance for each learning algorithm, the predictive performance according to the learning algorithm was different. Considering the results and deviations of the two indicators of predictive performance comprehensively, the model using the Levenberg-Marquardt (LM) learning algorithm is judged to have the best predictive performance.

Designing a new fast solution to control isolation rooms in hospitals depending on artificial intelligence decision

Decreasing the COVID spread of infection among patients at physical isolation hospitals during the coronavirus pandemic was the main aim of all governments in the world. It was required to increase isolation places in the hospital's rules to prevent the spread of infection. To deal with influxes of infected COVID-19 patients’ quick solutions must be explored. The presented paper studies converting natural rooms in hospitals into isolation sections and constructing new isolation cabinets using prefabricated components as alternative and quick solutions. Artificial Intelligence (AI) helps in the selection and making of a decision on which type of solution will be used. A Multi-Layer Perceptron Neural Network (MLPNN) model is a type of artificial intelligence technique used to design and implement on time, cost, available facilities, area, and spaces as input parameters. The MLPNN result decided to select a prefabricated approach since it saves 43% of the time while the cost was the same for the two approaches. Forty-five hospitals have implemented a prefabricated solution which gave excellent results in a short period of time at reduced costs based on found facilities and spaces. Prefabricated solutions provide a shorter time and lower cost by 43% and 78% in average values respectively as compared to retrofitting existing natural ventilation rooms.

An Internet-Oriented Multilayer Network Model Characterization and Robustness Analysis Method.

The Internet creates multidimensional and complex relationships in terms of the composition, application and mapping of social users. Most of the previous related research has focused on the single-layer topology of physical device networks but ignored the study of service access relationships and the social structure of users on the Internet. Here, we propose a composite framework to understand how the interaction between the physical devices network, business application network, and user role network affects the robustness of the entire Internet. In this paper, a multilayer network consisting of a physical device layer, business application layer and user role layer is constructed by collecting experimental network data. We characterize the disturbance process of the entire multilayer network when a physical entity device fails by designing nodal disturbance to investigate the interactions that exist between the different network layers. Meanwhile, we analyze the characteristics of the Internet-oriented multilayer network structure and propose a heuristic multilayer network topology generation algorithm based on the initial routing topology and networking pattern, which simulates the evolution process of multilayer network topology. To further analyze the robustness of this multilayer network model, we combined a total of six target node ranking indicators including random strategy, degree centrality, betweenness centrality, closeness centrality, clustering coefficient and network constraint coefficient, performed node deletion simulations in the experimental network, and analyzed the impact of component types and interactions on the robustness of the overall multilayer network based on the maximum component change in the network. These results provide new insights into the operational processes of the Internet from a multi-domain data fusion perspective, reflecting that the coupling relationships that exist between the different interaction layers are closely linked to the robustness of multilayer networks.

Artificial neural network approach for investigating the impact of convector design parameters on the heat transfer and total weight of panel radiators

The difficulty of the production stages of panel radiators used for heating purposes reveals the importance of determining the heat transfer performance and panel radiator weight values, which are determined depending on the design parameters. In the present work, an artificial neural network model is proposed for predicting the heat transfer and weight values of a panel radiator as outputs depending on the design parameters of convectors. In the multilayer network model developed with 78 numerically obtained data sets, 8 different design parameters were defined as input parameters and heat transfer and in the output layer panel weight values were obtained. The design parameters of the convectors, in other words, input parameters of network model were chosen as the height of convector, thickness of convector sheet, the trapezoidal height of convector, convector base length, opposing convector distance, tip width of convector, convector vertical location and distance between convectors. For the proposed neural network model, the mean squared errors obtained for the heat transfer and panel radiator weight are −1.25E-04 and -7.54E-05 respectively. In addition, an R-value of 0.99999 has been obtained, and the average deviation value has been calculated as 0.001%. The obtained results show that, depending on the design parameters, the proposed artificial neural network model can predict the rate of heat transfer and weight of the panel radiator with high accuracy. This investigation is supposed to fill a significant gap since it is the pioneer one in open sources on machine learning modeling of panel radiators. Thus, it can possibly make a crucial contribution to the related manufacturing industry.

A multilayer network model for studying the impact of non-pharmaceutical interventions implemented in response to COVID-19

Non-pharmaceutical interventions (NPIs) are essential for the effective prevention and control of the COVID-19 pandemic. However, the scenarios for disease transmission are complicated and varied, and it remains unclear how real-world networks respond to the changes in NPIs. Here, we propose a multi-layer network combining structurally fixed social contact networks with a time-varying mobility network, select the COVID-19 outbreak in two metropolitans in China as case studies, and assess the effectiveness of NPIs. Human mobility, both in relatively fixed places and in urban commuting, is considered. Enclosed places are simulated by three different types of social contact networks, while urban commuting is represented by a time-varying commute network. We provide a composite framework that captures the heterogeneity and time variation of the real world and enables us to simulate large populations with low computational costs. We give out a thorough evaluation of the effectiveness of NPIs (i.e., work from home, school closure, close-off management, public transit limitation, quarantine, and mask use) under certain vaccine coverage varying with implementation timing and intensity. Our results highlight the strong correlation between the NPI pattern and the epidemic mitigation effect and suggest important operational strategies for epidemic control.

Systemic risk of multi-layer financial network system under macroeconomic fluctuations

As the global economy continues to integrate, COVID-19 is affecting businesses around the world, causing the financial system to become more complicated. The complicated relationship between various agents in the financial system makes potential hazards more easily transmitted. Most studies of systemic risks have focused on single-layer networks, and macroeconomic fluctuations have not been quantified in multi-layer models of financial networks. In this paper, three different macroeconomic shock scenarios (showing upward, downward, and random trends) are constructed to affect the firm’s business activities, and a multi-layer financial network model is developed to simulate systemic risk under macroeconomic fluctuations. Firms with medium and high leverage and small asset sizes, as well as banks with smaller asset sizes and fewer bank-firm credit linkages, are found to be more likely to default. The study also found that average firm leverage exhibits two inflection points, causing banks’ default probabilities to “rise, then fall, and then rise,” with the inflection point value being the lowest under the upward trend of macroeconomics. In addition, the higher the ratio of firm loans to total bank assets, the more likely the bank is to default. Appropriate loan maturity extension has also helped to reduce systemic risk, especially in light of the macroeconomic downward trend. Furthermore, improving the capital adequacy ratio can reduce the bank’s default probability under macroeconomic fluctuations.

Investigation of the usability of machine learning algorithms in determining the specific electrical parameters of Schottky diodes

Schottky diodes continue to be the favorite of the electronics industry with their ever-expanding usage areas. The electrical parameters that can be obtained by the characterization of Schottky diodes are of high importance as they provide important information in terms of the usage area of the diode. In this study, the usability of the machine learning algorithm has been investigated in the determination of important electrical parameters such as ideality factor, barrier height and resistance of Schottky diodes. Voltage and temperature values were defined in the hidden layer of the multi-layer artificial neural network model, which was developed with a total of 368 data sets, and current values were estimated in the output layer. The developed neural network model was able to predict the electrical parameters of Schottky diodes with an average deviation of 0.11%. Using the data obtained from the artificial neural network, the Ideality factor was calculated with an error margin of 1.645, and the resistance value with a margin of error of 5.694.

Ranking community detection algorithms for complex social networks using multilayer network design approach

Purpose Community detection is a significant research field in the study of social networks and analysis because of its tremendous applicability in multiple domains such as recommendation systems, link prediction and information diffusion. The majority of the present community detection methods considers either node information only or edge information only, but not both, which can result in loss of important information regarding network structures. In real-world social networks such as Facebook and Twitter, there are many heterogeneous aspects of the entities that connect them together such as different type of interactions occurring, which are difficult to study with the help of homogeneous network structures. The purpose of this study is to explore multilayer network design to capture these heterogeneous aspects by combining different modalities of interactions in single network. Design/methodology/approach In this work, multilayer network model is designed while taking into account node information as well as edge information. Existing community detection algorithms are applied on the designed multilayer network to find the densely connected nodes. Community scoring functions and partition comparison are used to further analyze the community structures. In addition to this, analytic hierarchical processing-technique for order preference by similarity to ideal solution (AHP-TOPSIS)-based framework is proposed for selection of an optimal community detection algorithm. Findings In the absence of reliable ground-truth communities, it becomes hard to perform evaluation of generated network communities. To overcome this problem, in this paper, various community scoring functions are computed and studied for different community detection methods. Research limitations/implications In this study, evaluation criteria are considered to be independent. The authors observed that the criteria used are having some interdependencies, which could not be captured by the AHP method. Therefore, in future, analytic network process may be explored to capture these interdependencies among the decision attributes. Practical implications Proposed ranking can be used to improve the search strategy of algorithms to decrease the search time of the best fitting one according to the case study. The suggested study ranks existing community detection algorithms to find the most appropriate one. Social implications Community detection is useful in many applications such as recommendation systems, health care, politics, economics, e-commerce, social media and communication network. Originality/value Ranking of the community detection algorithms is performed using community scoring functions as well as AHP-TOPSIS methods.

COVID-19 Spread Simulation in a Crowd Intelligence Network

In this paper, the Crowd Intelligence Network Model is applied to the simulation of epidemic spread. This model combines the multi-layer coupling network model and the two-stage feedback member model to study the epidemic spread mechanisms under multiple-scene intervention. First, this paper establishes a multi-layer coupled network structure based on the characteristic of Social Network, Information Network, and Monitor Network, namely, the Crowd Intelligence Network structure. Then, based on this structure, the digital-self model, which has a multiple-scene effect and two-stage feedback structure, is designed. It has an emotional state and infection state quantified by using attitude and self-protection levels. This paper uses the attitude level and self-protection level to quantify individual emotions and immune levels, and discusses the impact of individual emotions on epidemic prevention and control. Finally, the availability of the Crowd Intelligence Network Model on the epidemic spread is verified by comparing the simulation trend with the actual spread trend of COVID-19.

Inferring Flight Performance Under Different Maneuvers With Pilot’s Multi-Physiological Parameters

The relationship between flight performance and multi-physiological parameters under different flight operating patterns is unknown. This work proposes a Stacked Gaussian Process Network (SGPN) to reveal it. SGPN is a multi-layer network model formed by recursion from a regular Gaussian process and random disturbance. This work constructs an auxiliary variable strategy with the induced points to improve its learning efficiency, thus leading to a sparse SGPN model. In it, a Gaussian process acts as an activation function of each node, but the entire model is no longer a Gaussian process and thus very challenging to solve it. This work presents its solution via variational approximate inference. Experimental results of pilot flight performance evaluation show that the proposed model has stronger learning and generalization ability than its seven competitive peers. It is able to approximate non-linear coupling relationship between multi-physiological parameters and flight height differences.