Two-level Network Research Articles

Fast flow field prediction of pollutant leakage diffusion based on deep learning.

Predicting pollutant leakage and diffusion processes is crucial for ensuring people's safety. While the deep learning method offers high simulation efficiency and superior generalization, there is currently a lack of research on predicting pollutant leakage and diffusion flow field using deep learning. Therefore, it is necessary to conduct further studies in this area. This paper introduces a two-level network method to model the flow characteristics of pollutant diffusion. The proposed method in this study demonstrates a significant enhancement in flow field prediction accuracy compared to traditional deep learning methods. Moreover, it improves computational efficiency by over 800 times compared to traditional computational fluid dynamics (CFD) methods. Unlike conventional CFD methods that require grid expansion to calculate all operation conditions, the deep learning method is not confined by grid limitations. While deep learning methods may not entirely replace CFD methods, they can serve as a valuable supplementary tool, expanding the versatility of CFD methods. The findings of this research establish a robust foundation for incorporating deep learning methods in addressing pollutant leakage and diffusion challenges.

Flexible and Thermally Conductive Phase-Change Films with a Two-Level Network for Dual-Mode Thermal Management of Batteries

Flexible and Thermally Conductive Phase-Change Films with a Two-Level Network for Dual-Mode Thermal Management of Batteries

Delay-sensitive resource allocation for IoT systems in 5G O-RAN networks

The rapid advancement in sensors and communications has led to the expansion of the Internet of Things (IoT) services, where many devices need access to the transport network using fixed or wireless access technologies and mobile Radio Access Networks (RAN). However, supporting IoT in RAN is challenging as IoT services may produce many short and variable sessions, impacting the performance of mobile users sharing the same RAN. To address this issue, network slicing is a promising solution to support heterogeneous service segments sharing the same RAN, which is a crucial requirement of the upcoming fifth-generation (5G) mobile network. This paper proposes a two-level network slicing mechanism for enhanced mobile broadband (eMBB) and Ultra-Reliable and Low Latency communications (URLLC) in order to provide end-to-end slicing at the core and edge of the network with the aim of reducing latency for IoT services and mobile users sharing the same core and RAN using the O-RAN architecture. The problem is modeled at both levels as a Markov decision process (MDP) and solved using hierarchical reinforcement learning. At a high level, an SDN controller using an agent that has been trained by a Double Deep Q-network (DDQN) allocates radio resources to gNodeBs (next-generation NodeB, a 5G base station) based on the requirements of eMBB and URLLC services. At a low level, each gNodeB using an agent that has been trained by a DDQN allocates its pre-allocated resources to its end-users. The proposed approach has been demonstrated and validated through a real testbed. Notably, it surpasses the prevalent approaches in terms of end-to-end latency.

Beyond spiking networks: The computational advantages of dendritic amplification and input segregation.

The brain can efficiently learn a wide range of tasks, motivating the search for biologically inspired learning rules for improving current artificial intelligence technology. Most biological models are composed of point neurons and cannot achieve state-of-the-art performance in machine learning. Recent works have proposed that input segregation (neurons receive sensory information and higher-order feedback in segregated compartments), and nonlinear dendritic computation would support error backpropagation in biological neurons. However, these approaches require propagating errors with a fine spatiotemporal structure to all the neurons, which is unlikely to be feasible in a biological network. To relax this assumption, we suggest that bursts and dendritic input segregation provide a natural support for target-based learning, which propagates targets rather than errors. A coincidence mechanism between the basal and the apical compartments allows for generating high-frequency bursts of spikes. This architecture supports a burst-dependent learning rule, based on the comparison between the target bursting activity triggered by the teaching signal and the one caused by the recurrent connections, providing support for target-based learning. We show that this framework can be used to efficiently solve spatiotemporal tasks, such as context-dependent store and recall of three-dimensional trajectories, and navigation tasks. Finally, we suggest that this neuronal architecture naturally allows for orchestrating "hierarchical imitation learning", enabling the decomposition of challenging long-horizon decision-making tasks into simpler subtasks. We show a possible implementation of this in a two-level network, where the high network produces the contextual signal for the low network.

Does China's high-speed rail network promote inter-city technology transfer? ——A multilevel network analysis based on the electronic information industry

Even though the influence of high-speed rail (HSR) on innovation has drawn sustained attention, few studies have investigated the effect on technology transfer (TT), and even fewer studies have examined the structural dependency between transportation and TT. Using the exponential random graph model for multilevel networks, this study attempts to provide an in-depth analysis of the impact from a two-level network perspective, with the associated network configuration providing insights into how HSR shapes intercity TT. Our findings suggest that HSR facilitates inter-city TT and promotes innovation convergence. Specifically, cities with a higher degree centrality are more active in exporting technology rather than absorbing it. In contrast, the betweenness and closeness centrality of cities have no significant effect on TT. The effect of HSR, which is apparent among cities with direct connections along HSR lines, decays significantly in cities with indirect connections. This work allows for the identification of the conducive HSR layout for promoting inter-regional TT.

A Recursive Algorithm for Constructing Dual-CISTs in Hierarchical Folded Cubic Networks

Let [Formula: see text] be a set of [Formula: see text] spanning trees in a graph [Formula: see text]. The [Formula: see text] spanning trees are called completely independent spanning trees (CISTs for short) if the paths joining every pair of vertices [Formula: see text] and [Formula: see text] in any two trees have neither vertex nor edge in common except for [Formula: see text] and [Formula: see text]. Particularly, [Formula: see text] is called a dual-CIST provided [Formula: see text]. For data transmission applications in reliable networks, the existence of a dual-CIST can provide a configuration of fault-tolerant routing called protection routing. This paper investigates the problem of constructing a dual-CIST in the [Formula: see text]-dimensional hierarchical folded cubic network [Formula: see text]. The network is a two-level network using folded hypercube [Formula: see text] as clusters to reduce the diameter, hardware overhead and improve the fault tolerance ability. We propose a recursive algorithm to construct a dual-CIST of [Formula: see text] in [Formula: see text] time for [Formula: see text], where the time required is the same scale as the number of vertices of [Formula: see text]. Also, the diameter of each constructed CIST is [Formula: see text].

Two new mathematical models for two level electricity network design with distributed generation

In the new millennium, traditional electrical power systems have undergone a significant change driven by a set of requirements arising from evolving and changing technology. Thus, fundamental changes have occurred in the way electrical energy is produced, transmitted, and distributed. This situation has revealed the need to expand existing networks or to establish new networks. The available literature revealed that particular attention to the latter one is still limited due to the complexity of the power system. The purpose of this study is to contribute to the body of literature that tries to address the gap at overall design of a power distribution network. Moreover, distributed generation integration is also considered simultaneously with network design. In this paper, a two-level electricity distribution system design with distributed generation (TLEDS_DG) for green-field planning is considered. The TLEDS_DG is defined to find the locations of distribution transformers, to decide the number of distributed generators, and to design underlying two-level network in such a way that demand and capacity constraints are satisfied, and the overall design cost is minimized. Two mathematical models, a node-based and flow-based, are proposed and compared in terms of solution quality and CPU times. Within the flow-based formulation which is a new technique, called node cloning, is used to transform a two-level network into a single-level one. To validate the effectiveness and efficiency of the proposed approach (flow-based formulation with node cloning), we conduct numerical studies based on randomly generated instances up to 300 customers. Additionally, sensitivity analysis is also applied to demonstrate the impacts of initial parameter settings. Computational results on a large suite of test problems show that the proposed approach (flow-based formulation with node cloning) is efficient and highly effective for the generated test problems.

Оцінка пропускної спроможності міської дорожньої мережі з урахуванням пропозиції паркування

In order to improve the estimation of network capacity for a given urban road system, it is assumed that the impact of destination parking management strategies should be considered in the network capacity estimation model. This study presents an extended road network capacity model that takes into account both the number of parking spaces and parking rates in each traffic zone. The network capacity model is formulated as a two-level programming problem with maximizing the total trip generation at the upper level and the combined trip distribution and traffic assignment (CTDTA) problem at the lower level. In order to reasonably characterize the impact of parking pricing and parking delays due to congestion, the CTDTA model involves two classes of travel demand. An efficient and practical algorithm for solving the two-level network capacity model is presented. Numerical experiments show the advantages of the proposed model and demonstrate the impact of parking supply and pricing on the results of road network capacity assessment.

Optimizing the ground intra-city express delivery network: An integrated multiple centrality assessment, multi-criteria decision-making, and multi-objective integer programming model

Optimization of an intra-city express delivery network from three to two levels is of great interest to suppliers and customers for reducing costs and improving service efficiency. One feasible solution is to identify critical nodes in the three-level network and upgrade them as transshipment facilities in the two-level one. However, traditional optimization models seldom combine empirical business data, composite metrics, and objective evaluation rules. We proposed an approach integrating empirical data, multi-criteria decision-making methods based on the real-world application of the SF Express Chengdu branch. We also developed a mathematical optimization model using statistical and operations management techniques combined with logistics expertise for a location decision. First, the appropriateness of each service point as a candidate transshipment facility is evaluated from internal and external perspectives by applying multiple centrality assessment from complex network theory and fuzzy Technique for Order Preference by Similarity to an Ideal Solution, respectively. Second, 16 candidate transshipment facilities are selected by combining these two ways. Then, a multi-objective integer programming model is built to obtain the optimal number, locations of transshipment facilities, and the corresponding service points covered by each transshipment facility. Using this multi-methodologic approach, we show that the optimized two-level network is economically feasible and simply applicable, with the total cost and average delivery time reduced by 18.41% and 6 h, respectively. This article is of practical significance and provides an important reference for optimizing ground express service networks for other large cities.

Bayesian Estimation of Land Deformation Combining Persistent and Distributed Scatterers

Persistent Scatterer Interferometry (PSI) has been widely used for monitoring land deformation in urban areas with millimeter accuracy. In natural terrain, combining persistent scatterers (PSs) and distributed scatterers (DSs) to jointly estimate deformation, such as SqueeSAR, can enhance PSI results for denser and better coverage. However, the phase quality of a large number of DSs is far inferior to that of PSs, which deteriorates the deformation measurement accuracy. To solve the contradiction between measurement accuracy and coverage, a Bayesian estimation method of land deformation combining PSs and DSs is proposed in this paper. First, a two-level network is introduced into the traditional PSI to deal with PSs and DSs. In the first-level network, the Maximum Likelihood Estimation (MLE) of deformation parameters at PSs and high-quality DSs is obtained accurately. In the secondary-level network, the remaining DSs are connected to the nearest PSs or high-quality DSs, and the deformation parameters are estimated by Maximum A Posteriori (MAP) based on Bayesian theory. Due to the poor phase quality of the remaining DSs, MAP can achieve better estimation results than the MLE based on the spatial correlation of the deformation field. Simulation and Sentinel-1A satellite data results verified the feasibility and reliability of the proposed method. Regularized by the spatial deformation field derived from the high-quality PSs and DSs, the proposed method is expected to achieve robust results even in low-coherence areas, such as rural areas, vegetation coverage areas, or deserts.

MEDICAL ASSIST FOR ISOLATED WARD PATIENTS IN HOSPITALS

Monitoring daily activities is essential for home service robots to take care of the older adults who live alone in their homes. In this article, we proposed a Medical Assist for isolated ward pateints in hospital framework by recognizing sound events in a home environment. First, the method of context-aware sound event recognition (CoSER) is developed, which uses contextual information to disambiguate sound events. The locational context of sound events is estimated by fusing the data from the distributed passive infrared (PIR) sensors deployed in the home. A two-level dynamic Bayesian network (DBN) is used to model the intratemporal and intertemporal constraints between the context and the sound events. Second, dynamic sliding time window-based human action recognition (DTW-HaR) is developed to estimate active sound event segments with their labels and durations, then infer actions and their durations. Finally, a conditional random field (CRF) model is proposed to predict human activities based on the recognized action, location, and time. We conducted experiments in our robot-integrated smart home (RiSH) testbed to evaluate the proposed framework. The obtained results show the effectiveness and accuracy of CoSER, action recognition, and human activitymonitoring. Key Words: Activity monitoring, context-awareness, elderly care, sound event.

A speed inference planning of groove cutting robot based on machine vision and improved fuzzy neural network

To ensure the cutting speed during the cutting operation, this paper proposes a groove cutting speed inference planning system that relies on production experience and set parameters and is based on machine vision and a two-level fuzzy neural hybrid network. The overall structure of the inference system is designed, including the mechanical body, vision system, and fuzzy neural hybrid network. The contour information of the part is obtained using industrial cameras and digital image processing systems. The cutting speed of the trajectory segment is inferred based on the related processing parameters and the secondary fuzzy neural hybrid network. Finally, all of the processing parameters are transmitted to the PLC, so that the robot can work according to the predetermined displacement and speed. Simulations verify that the speed inference planning system offers certain advantages compared to the traditional one. The appearance of the speed inference planning realises independent design and planning of the cutting speed, and further ensures the unity of the cutting quality and cutting speed. This proposed method provides a new direction for the development and transformation of machining processes that rely on manual experience and in which expert systems cannot be used.

Green routing in a two-level network of cross docks given the shipping price (Case study: Pegah Co.)

In this study, a green routing model is provided in a two-level network of cross docking given the shipping price. Three objectives were proposed in this model including: total cost reduction, shipping costs reduction and carbon emissions reduction. The overall objective of the model, is getting the best route in the distribution network which will impose the least cost and also minimizes emissions of environmental pollutants. For the model to approach the real situation, Pegah corporation’s warehouses and distribution network are considered as a case study. Solving the developed model was carried out by GAMS. By the size of the problem increasing, the running time of the program is notably increased and this means the problem is np-hard. So, in order to solve the model in medium and large dimensions, we used meta-heuristic MOGWO and NSGA II algorithm. The results of investigating various problems with meta-heuristics, indicates the high performance of the proposed algorithm in terms of the time needed and the response achieved. Results indicated that the proposed model reduced the emission of environmental pollutants along with total cost and shipping cost reduction. Also given the time window, the products were shipped to customers in a timely manner.

DETECTION OF ATTACKS ON A COMPUTER NETWORK BASED ON THE USE OF NEURAL NETWORKS COMPLEX

Purpose. The article is aimed at the development of a methodology for detecting attacks on a computer network. To achieve this goal the following tasks were solved: to develop a methodology for detecting attacks on a computer network based on an ensemble of neural networks using normalized data from the open KDD Cup 99 database; when performing machine training to identify the optimal parameters of the neural network which will provide a sufficiently high level of reliability of detection of intrusions into the computer network. Methodology. As an architectural solution of the attack detection module, a two-level network system is proposed, based on an ensemble of five neural networks of the multilayer perceptron type. The first neural network to determine the category of attack class (DoS, R2L, U2R, Probe) or the fact that there was no attack; other neural networks – to detect the type of attack, if any (each of these four neural networks corresponds to one class of attack and is able to identify types that belong only to this class). Findings. The created software model was used to study the parameters of the neural network configuration 41–1–132–5, which determines the category of the attack class on the computer network. It is determined that the optimal training speed is 0.001. The ADAM algorithm proved to be the best for optimization. The ReLU function is the most suitable activation function for the hidden layer, and the hyperbolic tangent function – for the output layer activation function. Accuracy in test and validation samples was 92.86 % and 91.03 %, respectively. Originality. The developed software model, which uses the Python 3.5 programming language, the integrated development environment PyCharm 2016.3 and the Tensorflow 1.2 framework, makes it possible to detect all types of attacks of DoS, U2R, R2L, Probe classes. Practical value. Graphical dependencies of accuracy of neural networks at various parameters are received: speed of training; activation function; optimization algorithm. The optimal parameters of neural networks have been determined, which will ensure a sufficiently high level of reliability of intrusion detection into a computer network.

Deep Insights of Erroneous Bengali–English Code-Mixed Bilingual Language

ABSTRACT Code-switching, the combination of more than one language within a single utterance is popular in social media sites for informal communication, generating a huge amount of data, though not fully analysed for knowledge extraction due to lack of documentation. Moreover, the code-mixed data is erroneous, and to detect and correct different types of errors, the model requires large erroneous code-mixed language data, not publicly available. This paper first defines generic rules to write Bengali–English code-mixed language in English script, considering the inherent complexity of the Bengali language. Different types of typographical and cognitive errors are induced to obtain the huge erroneous data, based on human behaviour and perception as consulted with the language experts. The errors considered here are applicable to other code-mixed Indic languages and would be beneficial for the researchers. To demonstrate the applicability of the model, we have included the errors in the Hindi–English code-mixed Indic language. An attention-based two-level deep network architecture (uses LSTM as a basic unit) is used for error detection, correction, and translation of code-mixed sentences into a monolingual sentence. Results are reported in terms of accuracy, ROUGE score, and BLEU scores at word level and sentence level for both Bengali–English and Hindi–English code-mixed languages.

Accessibility to urgent and emergency care services in low-density territories: the case of Baixo Alentejo, Portugal.

Access to health care is a sensitive issue in low population density territories, as these areas tend to have a lower level of service provision. One dimension of access is accessibility. This paper focuses on measuring the accessibility to urgent and emergency care services in the Portuguese region of Baixo Alentejo, a territory characterized by low population density. Data for the calculation of accessibility is the road network, and the methodology considers the application of a two-level network analyst method: time-distance by own mean (car or taxi) to the urgent care services and the time distance to emergency services as a way to get assistance and to go to urgent care services. While urgent care accessibility meets the requirements stipulated in the Integrated Medical Emergency System's current legislative framework, the simulation of different scenarios of potential accessibility shows intra-regional disparities. Some territories have a low level of accessibility. Older adults, the poorly educated, and low-income population, also have the lowest levels of accessibility, which translates into dually disadvantageous situation since the potential users of emergency services are most likely to belong to this group of citizens.

Partial Phase Cohesiveness in Networks of Networks of Kuramoto Oscillators

Partial, instead of complete, synchronization has been widely observed in various networks, including, in particular, brain networks. Motivated by data from human brain functional networks, in this article, we analytically show that partial synchronization can be induced by strong regional connections in coupled subnetworks of Kuramoto oscillators. To quantify the required strength of regional connections, we first obtain a critical value for the algebraic connectivity of the corresponding subnetwork using the incremental two-norm. We then introduce the concept of the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">generalized complement graph</i> , and obtain another condition on the node strength by using the incremental <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\infty$</tex-math></inline-formula> -norm. Under these two conditions, regions of attraction for partial phase cohesiveness are estimated in the forms of the incremental two- and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\infty$</tex-math></inline-formula> -norms, respectively. Our result based on the incremental <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\infty$</tex-math></inline-formula> -norm is the first known criterion that applies to noncomplete graphs. Numerical simulations are performed on a two-level network to illustrate our theoretical results; more importantly, we use real anatomical brain network data to show how our results may contribute to a better understanding of the interplay between anatomical structure and empirical patterns of synchrony.

Set-aware Entity Synonym Discovery with Flexible Receptive Fields

Entity synonym discovery (ESD) from text corpus is an essential problem in many entity-leveraging applications, e.g., web search and question answering. This paper aims to address three limitations that widely exist in the current ESD solutions: 1) the lack of effective utilization for synonym set information; 2) the feature extraction of entities from restricted receptive fields; and 3) the incapacity to capture higher-order contextual information. We propose a novel set-aware ESD model that enables a flexible receptive field for ESD by making a breakthrough in using entity synonym set information. The contextual information of entities and entity synonym sets are arranged by a two-level network from which entities and entity synonym sets can be mapped into the same embedding space to facilitate ESD by encoding the high-order contexts from flexible receptive fields. Extensive experimental results on public datasets show that our model consistently outperforms the state-of-the-art with significant improvement.

A branch-and-price algorithm for the ring/ring problem

The ring/ring problem is a hierarchical network design problem that uses a two-level network, in which each level is a ring with limited capacity. It is related to other hierarchical design problems and also to the vehicle routing problem. Rings are used in telecommunications because of their survivability, while hierarchical networks are useful for large networks. We propose an extended integer programming formulation for the problem and a branch-and-price algorithm to solve it. A relaxation of the pricing problem is considered and also primal and pricing heuristics to improve the performance of the algorithm. Computational experiments were conducted on instances derived from the literature and show the hardness to solve instances with high capacity.

Robust control of pricing and inventory in a two-level supply network with competing retailers and delays in decision

Robust control of pricing and inventory in a two-level supply network with competing retailers and delays in decision