Optimal Network Research Articles

Optimizing sustainable concrete compressive strength prediction: A new particle swarm optimization‐based metaheuristic approach to neural network modeling for circular economy and disaster resilience

AbstractThis study aims to predict the final‐age compressive strengths of sustainable concrete series produced using different aggregate types with high accuracy using an artificial intelligence model and to reduce environmental degradation and conserve rapidly decreasing natural resources within the scope of sustainable development and circular economy goals. For this purpose, 45 different sustainable concrete series containing all‐natural, recycled, natural, and recycled concrete aggregates were produced and subjected to compressive strength tests at 7 and 28 days. In addition, this study also considers whether deep neural network models, which have gained popularity in recent years but have high time and resource costs, or shallow models are more suitable for determining the compressive strength values with high accuracy. For this purpose, a method is proposed that can automatically generate the optimal neural network model using a metaheuristic approach that eliminates the human factor. For this purpose, the proposed method was extensively compared with different classical machine learning algorithms. The proposed method predicted the 7 and 28‐day compressive strength with a coefficient of determination of 0.999 and presented better compressive strength predictions than all other algorithms. Considering the number of buildings to be constructed after earthquakes, the widespread use of concrete, and the importance of compressive strength, the proposed method will likely provide significant gains within sustainable development, circular economy, and disaster risk reduction.

Oral epithelial dysplasia detection and grading in oral leukoplakia using deep learning

BackgroundThe grading of oral epithelial dysplasia is often time-consuming for oral pathologists and the results are poorly reproducible between observers. In this study, we aimed to establish an objective, accurate and useful detection and grading system for oral epithelial dysplasia in the whole-slides of oral leukoplakia.MethodsFour convolutional neural networks were compared using the image patches from 56 whole-slide of oral leukoplakia labeled by pathologists as the gold standard. Sequentially, feature detection models were trained, validated and tested with 1,000 image patches using the optimal network. Lastly, a comprehensive system named E-MOD-plus was established by combining feature detection models and a multiclass logistic model.ResultsEfficientNet-B0 was selected as the optimal network to build feature detection models. In the internal dataset of whole-slide images, the prediction accuracy of E-MOD-plus was 81.3% (95% confidence interval: 71.4–90.5%) and the area under the receiver operating characteristic curve was 0.793 (95% confidence interval: 0.650 to 0.925); in the external dataset of 229 tissue microarray images, the prediction accuracy was 86.5% (95% confidence interval: 82.4–90.0%) and the area under the receiver operating characteristic curve was 0.669 (95% confidence interval: 0.496 to 0.843).ConclusionsE-MOD-plus was objective and accurate in the detection of pathological features as well as the grading of oral epithelial dysplasia, and had potential to assist pathologists in clinical practice.

Dynamic Bayesian network structure learning based on an improved bacterial foraging optimization algorithm

With the rapid development of artificial intelligence and data science, Dynamic Bayesian Network (DBN), as an effective probabilistic graphical model, has been widely used in many engineering fields. And swarm intelligence algorithm is an optimization algorithm based on natural selection with the characteristics of distributed, self-organization and robustness. By applying the high-performance swarm intelligence algorithm to DBN structure learning, we can fully utilize the algorithm's global search capability to effectively process time-based data, improve the efficiency of network generation and the accuracy of network structure. This study proposes an improved bacterial foraging optimization algorithm (IBFO-A) to solve the problems of random step size, limited group communication, and the inability to maintain a balance between global and local searching. The IBFO-A algorithm framework comprises four layers. First, population initialization is achieved using a logistics-sine chaotic mapping strategy as the basis for global optimization. Second, the activity strategy of a colony foraging trend is constructed by combining the exploration phase of the Osprey optimization algorithm. Subsequently, the strategy of bacterial colony propagation is improved using a "genetic" approach and the Multi-point crossover operator. Finally, the elimination-dispersal activity strategy is employed to escape the local optimal solution. To solve the problem of complex DBN learning structures due to the introduction of time information, a DBN structure learning method called IBFO-D, which is based on the IBFO-A algorithm framework, is proposed. IBFO-D determines the edge direction of the structure by combining the dynamic K2 scoring function, the designed V-structure orientation rule, and the trend activity strategy. Then, according to the improved reproductive activity strategy, the concept of "survival of the fittest" is applied to the network candidate solution while maintaining species diversity. Finally, the global optimal network structure with the highest score is obtained based on the elimination-dispersal activity strategy. Multiple tests and comparison experiments were conducted on 10 sets of benchmark test functions, two non-temporal and temporal data types, and six data samples of two benchmark 2T-BN networks to evaluate and analyze the optimization performance and structure learning ability of the proposed algorithm under various data types. The experimental results demonstrated that IBFO-A exhibits good convergence, stability, and accuracy, whereas IBFO-D is an effective approach for learning DBN structures from data and has practical value for engineering applications.

Robust expansion of networks against cascading failures with reinforcement learning

The network infrastructures, such as the power grids and Internet, are expanding in size due to the increasing needs of our society. This brings about the problem of expanding networks with a guarantee of robustness against network disturbances that may cause catastrophic consequences. In this paper, we study the optimal network expansion in terms of network robustness against cascading failures. Specifically, we consider the network expansion as a Markovian decision process and further propose a reinforcement learning based network expansion method. Simulation results in model networks and real-world networks demonstrate that our expansion method can greatly improve network robustness. Our work provides some insights for the optimal expansion of network infrastructures.

Swarm-based multi-objective optimization of double-layered microchannel heat sink with hybrid solid-porous ribs

The current article focuses on the thermal and hydraulic optimization of a double-layered microchannel with hybrid solid-porous ribs. Therefore, for both upper and lower layers, solid-porous ribs, having different thickness ratios of porous and solid, are considered. The ratio of solid-porous thickness in the upper and lower layers and Reynolds number variations are taken into account as design variables. The present study is conducted to find an optimum design by which not only thermal performance improves, but also power consumption reduces. At the initial step, the double-layer microchannel is simulated using artificial neural network. The second step involves the application of the optimum network and the microchannel inputs for minimizing the thermal resistance and the power consumption single-objective and multi-objective type’s optimization problems are solved. The two mentioned optimization problems in the proposed strategy are targeted using four swarm-based algorithms. Results indicated that the designed neural network has a maximum error of 4% for producing the desired outputs. Moreover, the single-objective optimization of the second stage showed that by the porous ratios of 0.19 and 1 for the upper and lower layers, respectively, and Reynolds number of 578.7, the minimum values of pressure drop and overall thermal resistance are achieved.

Simultaneous Optimization of Work and Heat Exchange Networks

This paper introduces a simultaneous optimization approach to synthesizing work and heat exchange networks (WHENs). The proposed work and heat integration (WHI) superstructure enables different thermodynamic paths of pressure and temperature-changing streams. The superstructure is connected to a heat exchanger network (HEN) superstructure, enabling the heat integration of hot and cold streams identified within the WHI superstructure. A two-step solution strategy is proposed, consisting of initialization and design steps. In the first step, a thermodynamic path model based on the WHI superstructure is combined with a model for simultaneous optimization and heat integration. This nonlinear programming (NLP) model aims to minimize operating expenditures and provide an initial solution for the second optimization step. In addition, hot and cold streams are identified, enabling additional model reduction. In the second step of the proposed solution approach, a thermodynamic path model is combined with the modified HEN model to minimize the network’s total annualized cost (TAC). The proposed mixed integer nonlinear programming (MINLP) model is validated by several examples, exploring the impact of the equipment costing and annualization factor on the optimal network design. The results from these case studies clearly indicate that the new synthesis approach proposed in this paper produces solutions that are consistently similar to or better than the designs presented in the literature using other methodologies.

Pinning control of simplicial complexes

In this paper, pinning control of simplicial complexes is investigated. The D-dimensional simplicial complex can be successfully pinned to a desired state (i.e., an equilibrium of the intrinsic dynamics) under the proposed control scheme. The local stability of synchronization in the pinned simplicial complex is analyzed and discussed. The relationship between pinning synchronization and the individual dynamics, higher-order structures, coupling strengths, as well as the control strategy is established. Moreover, the effects of control gain and the number of controlled nodes on synchronizability are examined in detail. The obtained results can provide valuable references for designing optimal higher-order networks in practical applications.

Parallel heterogeneous data‐fusion convolutional neural networks for improved rail bridge strike detection

AbstractLow clearance rail bridges provide vital crossings for freight and passenger trains and are susceptible to frequent strikes from overheight vehicles or equipment. Impact detection systems can help ensure the safety of railroad bridges and their users; such systems streamline monitoring efforts by providing near real‐time strike notifications to rail managers responsible for assessing a bridge after a strike. This paper develops parallel heterogeneous data‐fusion convolutional neural networks (PHD‐CNN) operating on data collected from in‐service rail bridges that improves detection and classification of from overheight vehicles. Convolutional neural networks (CNNs) automatically extract features from multiple data streams from different sensor modalities. The method provides a mechanism to homogenize and fuse disparate data streams for use as inputs to a classifier that distinguishes bridge strikes from passing trains. The study also provides practical implementation guidelines through a framework sensitivity characterization to examine the effects on performance of input data stream type, data set size, and CNN architecture complexity. Optimum networks detect, on average, 95% of bridge strikes with false positive rates less than 2%.

I-FENN with Temporal Convolutional Networks: Expediting the load-history analysis of non-local gradient damage propagation

In this paper, we demonstrate for the first time how the Integrated Finite Element Neural Network (I-FENN) framework, previously proposed by the authors [1,2], can efficiently simulate the entire loading history of non-local gradient damage propagation. To achieve this goal, we first adopt a Temporal Convolutional Network (TCN) as the neural network of choice to capture the history-dependent evolution of the non-local strain in a coarsely meshed domain. The quality of the network predictions governs the computational performance of I-FENN, and therefore we perform an extended investigation aimed at enhancing them. We explore a data-driven vs. physics-informed TCN setup to arrive at an optimum network training, evaluating the network based on a coherent set of relevant performance metrics. We address the crucial issue of training a physics-informed network with input data that span vastly different length scales by proposing a systematic way of input normalization and output un-normalization. We then integrate the trained TCN within the nonlinear iterative FEM solver and apply I-FENN to simulate the damage propagation analysis. I-FENN is always applied in mesh idealizations different from the one used for the TCN training, showcasing the framework’s ability to be used at progressively refined mesh resolutions. We illustrate several cases that I-FENN completes the simulation using either a modified or a full Newton–Raphson scheme, and we showcase its computational savings compared to both the classical monolithic and staggered FEM solvers. We underline that we satisfy very strict convergence criteria for every increment across the entire simulation, providing clear evidence of the robustness and accuracy of I-FENN. All the code and data used in this work will be made publicly available upon publication of the article.

RETRACTED ARTICLE: Optimal convolutional neural network classifier for asthma disease detection using speech signals

ABSTRACT Statement of Retraction: Optimal convolutional neural network classifier for asthma disease detection using speech signals We, the Editors and Publisher of the International Journal of Healthcare Management, have retracted the following article: Md. Asim Iqbal, K. Devarajan & Syed Musthak Ahmed (06 Feb 2023): Optimal convolutional neural network classifier for asthma disease detection using speech signals, International Journal of Healthcare Management, DOI: 10.1080/20479700.2023.2173774 Since publication, significant concerns have been raised about the integrity of the data and reported results in the article. When approached for an explanation, the authors did not provide their original data or any necessary supporting information. As verifying the validity of published work is core to the integrity of the scholarly record, we are therefore retracting the article. The corresponding author listed in this publication has been informed. We have been informed in our decision-making by our policy on publishing ethics and integrity and the COPE guidelines on retractions. The retracted article will remain online to maintain the scholarly record, but it will be digitally watermarked on each page as ‘Retracted’.

Statement of Retraction: Optimal convolutional neural network classifier for asthma disease detection using speech signals

Statement of Retraction: Optimal convolutional neural network classifier for asthma disease detection using speech signals

MACHINE LEARNING FOR AUTOMATIC EXTRACTION OF WATER BODIES USING SENTINEL-2 IMAGERY

Context. Given the aggravation of environmental and water problems, there is a need to improve automated methods for extracting and monitoring water bodies in urban ecosystems. The problem of efficient and automated extraction of water bodies is becoming relevant given the large amount of data obtained from satellite systems. The object of study is water bodies that are automatically extracted from Sentinel-2 optical satellite images using machine learning methods.
 Objective. The goal of the work is to improve the efficiency of the process of extracting the boundaries of water bodies on digital optical satellite images by using machine learning methods.
 Method. The paper proposes an automated information technology for delineating the boundaries of water bodies on Sentinel-2 digital optical satellite images. The process includes eight stages, starting with data download and using topographic maps to obtain basic information about the study area. Then, the process involved data pre-processing, which included calibrating the images, removing atmospheric noise, and enhancing contrast. Next, the EfficientNet-B0 architecture is applied to identify water features, facilitating optimal network width scaling, depth, and image resolution. ResNet blocks compress and expand channels. It allows for optimal connectivity of large-scale and multi-channel links across layers. After that, the Regional Proposal Network defines regions of interest (ROI), and ROI alignment ensures data homogeneity. The Fully connected layer helps in segmenting the regions, and the Fully connected network creates binary masks for accurate identification of water bodies. The final step of the method is to analyze spatial and temporal changes in the images to identify differences, changes, and trends that may indicate specific phenomena or events. This approach allows automating and accurately identifying water features on satellite images using machine learning.
 Results. The implementation of the proposed technology is development through Python software development. An assessment of the technology’s accuracy, conducted through a comparative analysis with existing methods, such as water indices and K-means, confirms a high level of accuracy in the period from 2017 to 2023 (up to 98%). The Kappa coefficient, which considers the degree of consistency between the actual and predicted classification, confirms the stability and reliability of our approach, reaching a value of 0.96.
 Conclusions. The experiments confirm the effectiveness of the proposed automated information technology and allow us to recommend it for use in studies of changes in coastal areas, decision-making in the field of coastal resource management, and land use. Prospects for further research may include new methods that seasonal changes and provide robustness in the selection and mapping of water surfaces.

Hub overload and failure as a final common pathway in neurological brain network disorders.

Understanding the concept of network hubs and their role in brain disease is now rapidly becoming important for clinical neurology. Hub nodes in brain networks are areas highly connected to the rest of the brain, which handle a large part of all the network traffic. They also show high levels of neural activity and metabolism, which makes them vulnerable to many different types of pathology. The present review examines recent evidence for the prevalence and nature of hub involvement in a variety of neurological disorders, emphasizing common themes across different types of pathology. In focal epilepsy, pathological hubs may play a role in spreading of seizure activity, and removal of such hub nodes is associated with improved outcome. In stroke, damage to hubs is associated with impaired cognitive recovery. Breakdown of optimal brain network organization in multiple sclerosis is accompanied by cognitive dysfunction. In Alzheimer's disease, hyperactive hub nodes are directly associated with amyloid-beta and tau pathology. Early and reliable detection of hub pathology and disturbed connectivity in Alzheimer's disease with imaging and neurophysiological techniques opens up opportunities to detect patients with a network hyperexcitability profile, who could benefit from treatment with anti-epileptic drugs.

Advancing producer mobility management in Named Data Networking: A comprehensive analytical model

This paper introduces a transformative approach to managing producer mobility in Named Data Networking (NDN). It presents a novel analytical model known as Producer Mobility Management Model (PMMM) that significantly improves handoff latency, signalling cost, and packet delivery efficiency, overcoming limitations of traditional static anchor-based methods. This model serves as an extension of well-established theories drawn from existing literature, thus offering an advanced approach towards managing producer mobility. The model provides the dynamic mobility management solution to adapt to efficiently manage producer movements, ensuring optimal routing and efficient network performance. Comparative evaluations demonstrate marked advancements over existing solutions, establishing the model as a scalable and robust solution for NDN environments that solves high handoff latency, excessive signalling and long packet delivery issues. This work not only addresses current challenges in producer mobility but also sets a new direction for future research and practical applications in NDN architecture.

A socio-economic and quality-oriented optimal fruit supply chain network design in a multi-market and multi-product environment: A real case study

This paper focuses on developing an optimal sustainable fruit Closed-Loop Supply Chain (CLSC). A novel multi-objective Mixed-Integer Linear Programming (MILP) model is suggested to formulate a multi-product, multi-market, multi-period, multi-level, multi-mode selling problem which aims to minimize cost and emissions and maximize the whole social segments’ responsiveness to fruit, vinegar, and compost. The model is solved by the LP-metric method and implemented in a real case in Iran. The findings indicate that achieving the highest level of responsiveness comes with a substantial cost for the network. However, this does not apply to environmental considerations. For decision-makers prioritizing sustainability, the proposed decision support system strongly advises against buying fruit from fruit cars. Due to the absence of positive impacts on the level of responsiveness, buying from fruit cars results in increased costs and emissions. For a cost- and environmentally-sensitive decision-maker, it is recommended to provide higher-quality fruits. Because the lower the quality of the fruit, leads to increased waste rates and emissions. Meeting increased vinegar demand, with its elevated costs and emissions, becomes justifiable only when the policymaker is actively seeking to achieve maximum responsiveness.

Emulation techniques for scenario and classical control design of tokamak plasmas

The optimization of scenarios and design of real-time-control in tokamaks, especially for machines still in design phase, requires a comprehensive exploration of solutions to the Grad–Shafranov (GS) equation over a high-dimensional space of plasma and coil parameters. Emulators can bypass the numerical issues in the GS equation, if a large enough library of equilibria is available. We train an ensemble of neural networks to emulate the typical shape-control targets (separatrix at midplane, X-points, divertor strike point, flux expansion, and poloidal beta) as a function of plasma parameters and active coil currents for the range of plasma configurations relevant to spherical tokamaks with a super-X divertor, with percent-level accuracy. This allows a quick calculation of the classical-control shape matrices, potentially allowing real-time calculation at any point in a shot with submillisecond latency. We devise a hyperparameter sampler to select the optimal network architectures and quantify uncertainties on the model predictions. To generate the relevant training set, we devise a Markov-chain Monte Carlo algorithm to produce large libraries of forward Grad–Shafranov solutions without the need for user intervention. The algorithm promotes equilibria with desirable properties, while avoiding parameter combinations resulting in problematic profiles or numerical issues in the integration of the GS equation.

Parametrical synthesis of various radio devices with the set quantity of cascades of type «the mixed two-port network – nonlinear part»

Background. Presence of possibility of analytical definition of a part of parametres of various radio devices, optimum by criterion of maintenance of preset values of modules and phases of transfer functions on necessary quantity of frequencies, considerably reduces time of numerical optimisation of other part of parametres by criterion of formation demanded PFC and FFC in a strip of frequencies. Till now such problems dared concerning radio devices only with one cascade of type «a nonlinear part - the coordination the device» or «the coordination the device - a nonlinear part». In quality coordination devices were used the jet, resistive, complex or mixed two-port networks. The problem of multicascade radio devices with jet two-port networks is solved also. Change of basis for the coordination two-port networks and a place of inclusion of a nonlinear part leads to change of area of a physical realizability.
 Aim. Working out of algorithms of parametrical synthesis of radio devices with any quantity of identical and unequal cascades of type «the coordination the mixed two-port network – a nonlinear part» by criterion of maintenance of the set frequency characteristics. Nonlinear parts are presented in the form of a nonlinear element and parallel either consecutive on a current or pressure of a feedback.
 Methods. The theory of two-port networks, matrix algebra, a decomposition method, a method of synthesis of actuation microwave devices, numerical methods of optimisation.
 Results. In interests of achievement of the specified purpose systems of the algebraic equations are generated and solved. Models of optimum two-port networks in the form of mathematical expressions for definition of interrelations between elements of their classical matrix of transfer and for search of dependences of mixed of two-poles from frequency are received. It is shown, that at certain parities between quantity of identical cascades and values of resistance of a source of a signal and loading of the one-cascade radio device frequency characteristics of one-cascade and multicascade radio devices appear identical or similar. Such schemes are named by equivalent. Use of unequal cascades leads to substantial growth of a working strip of frequencies.
 Conclusion. The comparative analysis of theoretical results (PFC and FFC radio devices, value of parametres), received by mathematical modelling in system «MathCad», and the experimental results received by scheme modelling in systems «OrCad» and «MicroCap», shows their satisfactory coincidence.

An expert system for hybrid edge to cloud computational offloading in heterogeneous MEC–MCC environments

Mobile Cloud Computing (MCC) integrates cloud computing into the mobile environment, effectively tackling performance, environmental, and security constraints. However, the proliferation of clouds and applications introduces complexities in offloading decisions. Mobile Edge Computing (MEC) has emerged as a solution to bolster MCC performance, capitalizing on the proximity to edge devices. However, optimizing computation offloading remains paramount for heterogeneous smart (mobile phones, wearables, and IoT) devices, necessitating efficient utilization of network resources and computational offloading. To address these challenges, this paper introduces NSANNOM (Network and Device Resources Utilization through Smart ANN-based Offloading Mechanism), an expert system designed for optimal computational offloading decision-making and efficient network resource allocation mechanisms. NSANNOM employs Artificial Neural Networks (ANN) for precise decision-making by validating real-world datasets, underscoring ANN’s superiority over existing algorithms, and showcasing enhanced energy savings, cost efficiency, and latency response. Experimental evaluations demonstrate that the proposed ANN model for the offloading decision-making algorithm achieves a training accuracy of 97% and a validation accuracy of 99%. The system consumes minimal energy (10 MJ) for task scheduling and exhibits remarkable accuracy in resource utilization across multiple tasks (10–50) ranging in size (from 1 to 16 GB). Additionally, it minimizes time delays (in milliseconds) during the offloading process.

Multimodal Graph Neural Architecture Search under Distribution Shifts

Multimodal graph neural architecture search (MGNAS) has shown great success for automatically designing the optimal multimodal graph neural network (MGNN) architecture by leveraging multimodal representation, crossmodal information and graph structure in one unified framework. However, existing MGNAS fails to handle distribution shifts that naturally exist in multimodal graph data, since the searched architectures inevitably capture spurious statistical correlations under distribution shifts. To solve this problem, we propose a novel Out-of-distribution Generalized Multimodal Graph Neural Architecture Search (OMG-NAS) method which optimizes the MGNN architecture with respect to its performance on decorrelated OOD data. Specifically, we propose a multimodal graph representation decorrelation strategy, which encourages the searched MGNN model to output representations that eliminate spurious correlations through iteratively optimizing the feature weights and controller. In addition, we propose a global sample weight estimator that facilitates the sharing of optimal sample weights learned from existing architectures. This design promotes the effective estimation of the sample weights for candidate MGNN architectures to generate decorrelated multimodal graph representations, concentrating more on the truly predictive relations between invariant features and ground-truth labels. Extensive experiments on real-world multimodal graph datasets demonstrate the superiority of our proposed method over SOTA baselines.

MHIF-MSEA: a novel model of miRNA set enrichment analysis based on multi-source heterogeneous information fusion.

Introduction: MicroRNAs (miRNAs) are a class of non-coding RNA molecules that play a crucial role in the regulation of diverse biological processes across various organisms. Despite not encoding proteins, miRNAs have been found to have significant implications in the onset and progression of complex human diseases. Methods: Conventional methods for miRNA functional enrichment analysis have certain limitations, and we proposed a novel method called MiRNA Set Enrichment Analysis based on Multi-source Heterogeneous Information Fusion (MHIF-MSEA). Three miRNA similarity networks (miRSN-DA, miRSN-GOA, and miRSN-PPI) were constructed in MHIF-MSEA. These networks were built based on miRNA-disease association, gene ontology (GO) annotation of target genes, and protein-protein interaction of target genes, respectively. These miRNA similarity networks were fused into a single similarity network with the averaging method. This fused network served as the input for the random walk with restart algorithm, which expanded the original miRNA list. Finally, MHIF-MSEA performed enrichment analysis on the expanded list. Results and Discussion: To determine the optimal network fusion approach, three case studies were introduced: colon cancer, breast cancer, and hepatocellular carcinoma. The experimental results revealed that the miRNA-miRNA association network constructed using miRSN-DA and miRSN-GOA exhibited superior performance as the input network. Furthermore, the MHIF-MSEA model performed enrichment analysis on differentially expressed miRNAs in breast cancer and hepatocellular carcinoma. The achieved p-values were 2.17e(-75) and 1.50e(-77), and the hit rates improved by 39.01% and 44.68% compared to traditional enrichment analysis methods, respectively. These results confirm that the MHIF-MSEA method enhances the identification of enriched miRNA sets by leveraging multiple sources of heterogeneous information, leading to improved insights into the functional implications of miRNAs in complex diseases.