Network Formulation Research Articles

Retracted: QGMS: A query growth model for personalization and diversification of semantic search based on differential ontology semantics using artificial intelligence

AbstractThe inclusion of collective intelligence through a semantic focused affective computing can incorporate intelligence to web search and ensure its compliance with the Web 3.0. In this article, a query growth model with inclusive and exclusive ontology semantics has been proposed for diversification of query recommendation in semantic search. The ontology semantics include query augmented ontology generation, agent‐driven attractor‐distractor generation to yield a merged ontology, and endowment of merged ontology by using hybridization of a series of knowledge bases. The strategy further includes the formulation of a semantic network and entity leveraging based on description logics (DLs) to improve the quality of query recommendation. A novel hierarchical entropy cognitive similarity covariance model has been proposed for yielding the most appropriate recommendable query words. The strategy also encompasses the user‐click information for capturing the current user intents to improve the quality queries recommended in semantic search, and thereby incorporate personalization. Experimentations are conducted for the CHiC dataset and the Spring 2006 Query Log dataset and an average accuracy of 96.27% and 92.01%, respectively, with a very low false discovery rate of 0.06 and 0.1 for the respective datasets.

Graph-Informed Neural Networks for Regressions on Graph-Structured Data

In this work, we extend the formulation of the spatial-based graph convolutional networks with a new architecture, called the graph-informed neural network (GINN). This new architecture is specifically designed for regression tasks on graph-structured data that are not suitable for the well-known graph neural networks, such as the regression of functions with the domain and codomain defined on two sets of values for the vertices of a graph. In particular, we formulate a new graph-informed (GI) layer that exploits the adjacent matrix of a given graph to define the unit connections in the neural network architecture, describing a new convolution operation for inputs associated with the vertices of the graph. We study the new GINN models with respect to two maximum-flow test problems of stochastic flow networks. GINNs show very good regression abilities and interesting potentialities. Moreover, we conclude by describing a real-world application of the GINNs to a flux regression problem in underground networks of fractures.

Pricing strategy of ride-sourcing services under travel time variability

Ride-sourcing services are burgeoning urban mobility services provided by transportation network companies (TNCs), consisting of non-pooling service and ride-pooling service. By receiving online orders and offering efficient door-to-door services, ride-sourcing services are becoming popular alternatives to public transit. Meanwhile, unignorable travel time variability influences passengers’ travel behavior and TNC’s pricing strategy. To investigate the effect of travel time variability, this paper proposes a bi-level framework. The mode choice of passengers, zone choice of searching drivers and the subsequent route choice traffic equilibrium in a transportation network is formulated as the lower level. And the upper level investigates the optimal pricing strategy. In the network formulation, passengers encounter variability of waiting time, detour time and highway travel time. Two pricing strategies are proposed to accommodate the risk of unsuccessful pairing. Pricing strategy 1 charges a fixed price even when a ride-pooling request becomes a non-pooling service due to unsuccessful pairing; whereas pricing strategy 2 increases the price of a ride-pooling request to that of non-pooling service if pairing is unsuccessful. The results show that pricing strategy 1 produces more profit and induces more ride-pooling demand. In addition, under more reliable traffic conditions, the optimal prices for ride-sourcing services are higher and the network travel time decreases. The results illustrate the influence of travel time variability on the ride-sourcing market and provide guidance on the company’s pricing strategy regarding a network under travel time variability.

Enhancing the scalability of fuzzy rough set approximate reduct computation through fuzzy min–max neural network and crisp discernibility relation formulation

Fuzzy rough sets (FRS) framework is proven to be useful in computing predictive features in the presence of incompleteness and uncertainty in hybrid systems. However, the existing FRS methods for feature subset selection (reduct computation) are not scalable to large datasets due to higher space and time complexities. Towards increasing the scalability of FRS reduct computation, FMNN-FRS approach is proposed earlier, utilizing fuzzy min–max neural network (FMNN) preprocessing to enable reduct computation in fuzzy hyperbox space instead of object space. FMNN-FRS approach considers fuzzy discernibility matrix (DM) for computation of an approximate reduct. However, it is observed that the space utilization of fuzzy DM limits the scalability of FMNN-FRS. To further increase the scalability of FMNN-FRS method by the reduction in the space complexity, in this work, a novel way of crisp DM construction is proposed from the knowledge derived from FMNN preprocessing (CDM-FMFRS). Extended overlapping criteria, with tolerance parameter, are also designed for arriving at the crisp discernibility relation through fuzzy hyperboxes. The proposed CDM-FMFRS approach computes an approximate reduct using SFS strategy on the generated crisp DM. Empirically, the experimental results established that the classifiability of the induced model from the proposed algorithm is similar or better than FMNN-FRS and other state-of-the-art FRS reduct approaches with a significant reduction in computational time. Results also established better scalability achieved by CDM-FMFRS than FMNN-FRS.

Modeling the interplay between water capillary transport and species diffusion in gas diffusion layers of proton exchange fuel cells using a hybrid computational fluid dynamics formulation

Improved modeling of the membrane electrode assembly (MEA) and operation is essential to optimize proton exchange fuel cells (PEFCs). In this work, a hybrid model, which includes a pore network formulation to describe water capillary transport and a continuum formulation to describe gas diffusion, is presented. The model is validated with previous data of carbon-paper gas diffusion layers (GDL), including capillary pressure curve, relative effective diffusivity, g ( s ) , and saturation profile. The model adequately captures the increase of capillary pressure with compression, the nearly cubic dependency of g ( s ) on average saturation, s avg , and the shape of the saturation profile in conditions dominated by capillary fingering (e.g., running PEFC at low temperature). Subsequently, an analysis is presented in terms of the area fraction of water at the inlet and the outlet of the GDL, A w i n and A w o u t , respectively. The results show that gas diffusion is severely hindered when A w i n is exceedingly high (¿80%), a situation that can arise due to the bottleneck created by flooded interfacial gaps. Furthermore, it is found that s avg increases with A w o u t , reducing the GDL effective diffusivity. Overall, the work shows the importance of an appropriate design of MEA porous media and interfaces in PEFCs. • A hybrid model for gas diffusion layers in proton exchange fuel cells is presented. • Pore network & continuum models are used for water transport & gas diffusion, resp. • The model is extensively compared with experimental data, showing good agreement. • The limiting current density dramatically reduces when interfacial flooding occurs. • More isolated evacuation sites toward the channel decrease effective diffusivity.

The Impacts of the Cross-Chain Collaboration Center Model on Transportation Performance: A Case Study of a Bulk Transportation Network in Thailand

This paper studies the impacts of a cross-chain collaboration center model (4CM) on bulk transportation network performance. The 4CM is based on the interaction and collaboration between shippers and carriers participating in the transportation network. The network formulation is based on collaborative bidirectional multi-period vehicle routing (CBMVRP). The performance of the 4CM is represented by three transportation performance indices, including the percentage differences in the total cost, shipper cost and carrier cost between the 4CM and single-chain collaboration model (SCCM). The impacts of the 4CM are investigated using five uncertain input parameters: fuel cost, holding cost, maximum acceptable proportion of the differences between the cost of a carrier and average cost of all carriers, demand per job and number of vehicles per carrier. An experiment was conducted according to a central composite design (CCD). The proposed methodology was applied to assess bulk transportation in Thailand. The computational results revealed that a 4CM can significantly reduce the differences in the total cost, shipper cost and carrier cost. Moreover, we organized a focus group to collect data about the criteria and the probability of changing from an SCCM to a 4CM of the case study network and generated a classification tree of the levels of possibility to change from an SCCM to a 4CM for each possible situation using the ID3 algorithm.

An Efficient Iterative Method for the Formulation of Flow Networks

An Efficient Iterative Method for the Formulation of Flow Networks

Network models for nonlocal traffic flow

We present a network formulation for a traffic flow model with nonlocal velocity in the flux function. The modeling framework includes suitable coupling conditions at intersections to either ensure maximum flux or distribution parameters. In particular, we focus on 1-to-1, 2-to-1 and 1-to-2 junctions. Based on an upwind type numerical scheme, we prove the maximum principle and the existence of weak solutions on networks. We also investigate the limiting behavior of the proposed models when the nonlocal influence tends to infinity. Numerical examples show the difference between the proposed coupling conditions and a comparison to the Lighthill-Whitham-Richards network model.

Securing Dynamic Source Routing by Neighborhood Monitoring in Wireless Adhoc Network

Wireless Adhoc Network (WANET) significantly contributes to cost-effective network formulation due to decentralized and infrastructure-less schemes. One of the primary forms of WANET in Mobile Adhoc Network (MANET) is still evolving in research and a continued set of research problems associated with security. A review of existing security approaches shows that identifying malicious behavior in MANET is still an open-end problem irrespective of various methods. This paper introduces an improved DSR protocol mechanism of neighborhood monitoring scheme towards analyzing the malicious behavior in the presence of an unknown attacker of dynamic type. The proposed method contributes to deploying auxiliary relay nodes and retaliation nodes to control the communication process and prevent the attacker from joining the network. Using analytical research methodology, the proposed system can offer better communication performance with effective resistance from threats in MANET.

Cyber-Physical System Demonstration of an Automated Shuttle-Conveyor-Belt Operation for Inventory Control of Multiple Stockpiles: A Proof of Concept

Smart manufacturing in the so-called Industry 4.0 age pushes the research and development of laboratory-scale proof of concepts before its deployment in pilots and real-size equipment. As such, we present a cyber-physical system (CPS) demonstration in the mining industry field engineered to autonomously manage the handling of solids flowing in a conveyor-belt that drops materials in containers, forming multiple stockpiles per belt. The CPS operates to control multiple stockpiles’ inventories using mixed-integer optimization that minimizes the square deviation of the measured inventory to their targets (heights). Within the sensing-optimizing-actuating (SOA) cycle, the CPS demonstration is performed as follows. First, the sensing (data measurement, data processing, and system evaluation) uses a deep neural network in real-time to assess the level of materials stored in transparent containers. Second, the optimizing (mathematical programming, optimization techniques, and decision-making capabilities) is performed using a flowsheet network formulation called unit-operation-port-state superstructure (UOPSS) that permits a fast solution for the position-idle-time-varying discrete manipulated variables as operational schedules. Third, the actuating (cyber-physical integration) implements a physical actuation solution through an integrated CPS environment. According to the findings of our experimentation, stockpiling process control in a smart manufacturing context has enormous potentials to control multiple stockpiles’ inventory autonomously.

Optimal Diffusion Learning Over Networks—Part II: Multitask Algorithms

In Part I of this presentation, we have formulated single and multitask quadratic optimization problems, where agents are subject to quadratic, smoothing constraints over a graph. We have focused particularly on single task designs, whereby node uncertainties and their strength relative to un-regularized cost are tackled altogether by means of an adaptive penalty function. In this sequel, we readdress the multitask problem and propose new distributed implementations for their corresponding exact <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">leaky</i> -RLS solutions. We motivate a network formulation from a standalone viewpoint by capitalizing on the fact that 1) for regressors having uncorrelated entries, the performance of an efficient <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">${\mathcal O}(M^2)$</tex-math></inline-formula> conjugate-gradient (CG) realization of the leaky LS solution is identical to the one of an RLS filter; 2) a CG implementation does not require inversion of the underlying sample covariance matrix. Simple arguments yield an extended network-CG algorithm that relies on node-level recursions employing distinct step-sizes. Unlike the exponentially-weighted RLS algorithm, which tapers off regularization over time, a persistent penalty strength conforms with the very purpose of the equivalent network trust-region problem, while granting a well-conditioned solution. The approach further yields another family of single-task algorithms in terms of network linearly constrained solutions, which can be contrasted to the ones proposed in Part I. In particular, the exact linearly-constrained network LMS implementation proposed here outperforms the adaptive relative-variance NLMS, under much lower computational requirements.

Deep Learning for Automatic Image Segmentation in Stomatology and Its Clinical Application.

Deep learning has become an active research topic in the field of medical image analysis. In particular, for the automatic segmentation of stomatological images, great advances have been made in segmentation performance. In this paper, we systematically reviewed the recent literature on segmentation methods for stomatological images based on deep learning, and their clinical applications. We categorized them into different tasks and analyze their advantages and disadvantages. The main categories that we explored were the data sources, backbone network, and task formulation. We categorized data sources into panoramic radiography, dental X-rays, cone-beam computed tomography, multi-slice spiral computed tomography, and methods based on intraoral scan images. For the backbone network, we distinguished methods based on convolutional neural networks from those based on transformers. We divided task formulations into semantic segmentation tasks and instance segmentation tasks. Toward the end of the paper, we discussed the challenges and provide several directions for further research on the automatic segmentation of stomatological images.

Indistinguishable sub-nanosecond pulse generator

The indistinguishable laser pulse is predominant in the realization of qubits in decoy state-based quantum cryptography. Such cryptography in an automotive framework needs to be compact and inexpensive. However, their implementation is cumbrous and uneconomical. Significant effort has been put into reducing the form factor of quantum cryptography implementation. We report a compact, low-cost, indistinguishable, sub-nanosecond pulse generator with adjusted delay and amplitude using a Fabry–Perot laser diode. The approach was derived based on algebraic topology formulation of the electrical network, and the implementation involves time-dependent perturbation of a constant current node to generate tunable, sub-nanosecond excitation with a constant pre-bias. The simulation model of the laser diode accounted for effects of spontaneous emission and relaxation oscillation. The shortest excitation pulse thus generated was measured to have FWHM of 496 ps. Further, the indistinguishability of two laser pulses is statistically evaluated.

Optimal Network Slicing for Service-Oriented Networks With Flexible Routing and Guaranteed E2E Latency

Network function virtualization is a promising technology to simultaneously support multiple services with diverse characteristics and requirements in the 5G and beyond networks. In particular, each service consists of a predetermined sequence of functions, called service function chain (SFC), running on a cloud environment. To make different service slices work properly in harmony, it is crucial to appropriately select the cloud nodes to deploy the functions in the SFC and flexibly route the flow of the services such that these functions are processed in the order defined in the corresponding SFC, the end-to-end (E2E) latency constraints of all services are guaranteed, and all cloud and communication resource budget constraints are respected. In this paper, we first propose a new mixed binary linear program (MBLP) formulation of the above network slicing problem that optimizes the system energy efficiency while jointly considers the E2E latency requirement, resource budget, flow routing, and functional instantiation. Then, we develop another MBLP formulation and show that the two formulations are equivalent in the sense that they share the same optimal solution. However, since the numbers of variables and constraints in the second problem formulation are significantly smaller than those in the first one, solving the second problem formulation is more computationally efficient especially when the dimension of the corresponding network is large. Numerical results demonstrate the advantage of the proposed formulations compared with the existing ones.

Modeling Capillary Transport and Gas Diffusion in Carbon-Fiber Papers Using a Hybrid CFD Formulation

Improved modeling of the membrane electrode assembly (MEA) and operation is essential to optimize proton exchange fuel cells (PEFCs). In this work, a hybrid model, which includes a pore network formulation to describe water capillary transport and a continuum formulation to describe gas diffusion, is presented. The model is validated with previous data of carbon-paper gas diffusion layers (GDL), including capillary pressure curve, relative effective diffusivity, g(s), and saturation profile. The model adequately captures the increase of capillary pressure with compression, the nearly cubic dependency of g(s) on average saturation, s^{\\rm avg}, and the shape of the saturation profile in conditions dominated by capillary fingering (e.g., running PEFC at low temperature). Subsequently, an analysis is presented in terms of the area fraction of water at the inlet and the outlet of the GDL, A_w^{in} and A_w^{out}, respectively. The results show that gas diffusion is severely hindered when A_w^{in} is exceedingly high (>80%), a situation that can arise due to the bottleneck created by flooded interfacial gaps. Furthermore, it is found that s^{avg} increases with A_w^{out}, reducing the GDL effective diffusivity. Overall, the work shows the importance of an appropriate design of MEA porous media and interfaces in PEFCs.

QRnet: Optimal Regulator Design With LQR-Augmented Neural Networks

In this paper we propose a new computational method for designing optimal regulators for high-dimensional nonlinear systems. The proposed approach leverages physics-informed machine learning to solve high-dimensional Hamilton-Jacobi-Bellman equations arising in optimal feedback control. Concretely, we augment linear quadratic regulators with neural networks to handle nonlinearities. We train the augmented models on data generated without discretizing the state space, enabling application to high-dimensional problems. We use the proposed method to design a candidate optimal regulator for an unstable Burgers' equation, and through this example, demonstrate improved robustness and accuracy compared to existing neural network formulations.

Boolean factor graph model for biological systems: the yeast cell-cycle network

BackgroundThe desire to understand genomic functions and the behavior of complex gene regulatory networks has recently been a major research focus in systems biology. As a result, a plethora of computational and modeling tools have been proposed to identify and infer interactions among biological entities. Here, we consider the general question of the effect of perturbation on the global dynamical network behavior as well as error propagation in biological networks to incite research pertaining to intervention strategies.ResultsThis paper introduces a computational framework that combines the formulation of Boolean networks and factor graphs to explore the global dynamical features of biological systems. A message-passing algorithm is proposed for this formalism to evolve network states as messages in the graph. In addition, the mathematical formulation allows us to describe the dynamics and behavior of error propagation in gene regulatory networks by conducting a density evolution (DE) analysis. The model is applied to assess the network state progression and the impact of gene deletion in the budding yeast cell cycle. Simulation results show that our model predictions match published experimental data. Also, our findings reveal that the sample yeast cell-cycle network is not only robust but also consistent with real high-throughput expression data. Finally, our DE analysis serves as a tool to find the optimal values of network parameters for resilience against perturbations, especially in the inference of genetic graphs.ConclusionOur computational framework provides a useful graphical model and analytical tools to study biological networks. It can be a powerful tool to predict the consequences of gene deletions before conducting wet bench experiments because it proves to be a quick route to predicting biologically relevant dynamic properties without tunable kinetic parameters.

Neural-Network Quantum States for Spin-1 Systems: Spin-Basis and Parameterization Effects on Compactness of Representations.

Neural network quantum states (NQS) have been widely applied to spin-1/2 systems, where they have proven to be highly effective. The application to systems with larger on-site dimension, such as spin-1 or bosonic systems, has been explored less and predominantly using spin-1/2 Restricted Boltzmann Machines (RBMs) with a one-hot/unary encoding. Here, we propose a more direct generalization of RBMs for spin-1 that retains the key properties of the standard spin-1/2 RBM, specifically trivial product states representations, labeling freedom for the visible variables and gauge equivalence to the tensor network formulation. To test this new approach, we present variational Monte Carlo (VMC) calculations for the spin-1 anti-ferromagnetic Heisenberg (AFH) model and benchmark it against the one-hot/unary encoded RBM demonstrating that it achieves the same accuracy with substantially fewer variational parameters. Furthermore, we investigate how the hidden unit complexity of NQS depend on the local single-spin basis used. Exploiting the tensor network version of our RBM we construct an analytic NQS representation of the Affleck-Kennedy-Lieb-Tasaki (AKLT) state in the spin-1 basis using only hidden units, compared to required in the basis. Additional VMC calculations provide strong evidence that the AKLT state in fact possesses an exact compact NQS representation in the basis with only hidden units. These insights help to further unravel how to most effectively adapt the NQS framework for more complex quantum systems.

SOCIAL NETWORKS USER CLASSIFICATION FOR PROFESSIONAL ORIENTATION

The article deals with a complex formulation of the topic social networks users classification to determine professional orientation.

Neural network perturbation theory and its application to the Born series

Deep Learning using the eponymous deep neural networks (DNNs) has become an attractive approach towards various data-based problems of theoretical physics in the past decade. There has been a clear trend to deeper architectures containing increasingly more powerful and involved layers. Contrarily, Taylor coefficients of DNNs still appear mainly in the light of interpretability studies, where they are computed at most to first order. However, especially in theoretical physics numerous problems benefit from accessing higher orders, as well. This gap motivates a general formulation of neural network (NN) Taylor expansions. Restricting our analysis to multilayer perceptrons (MLPs) and introducing quantities we refer to as propagators and vertices, both depending on the MLP's weights and biases, we establish a graph-theoretical approach. Similarly to Feynman rules in quantum field theories, we can systematically assign diagrams containing propagators and vertices to the corresponding partial derivative. Examining this approach for S-wave scattering lengths of shallow potentials, we observe NNs to adapt their derivatives mainly to the leading order of the target function's Taylor expansion. To circumvent this problem, we propose an iterative NN perturbation theory. During each iteration we eliminate the leading order, such that the next-to-leading order can be faithfully learned during the subsequent iteration. After performing two iterations, we find that the first- and second-order Born terms are correctly adapted during the respective iterations. Finally, we combine both results to find a proxy that acts as a machine-learned second-order Born approximation.