A graph neural network approach to the inverse design for thermal transparency with periodic interparticle system

Recent years have witnessed significant advances in utilizing machine learning-based techniques for thermal metamaterial-based structures and devices to attain favorable thermal transport behaviors.Among the various thermal transport behaviors,achieving thermal transparency stands out as particularly desirable and intriguing.Our earlier work demonstrated the use of a thermal metamaterial-based periodic interparticle system as the underlying structure for manipulating thermal transport behavior and achieving thermal transparency.In this paper,we introduce an approach based on graph neural network to address the complex inverse design problem of determining the design parameters for a thermal metamaterial-based periodic interparticle system with the desired thermal transport behavior.Our work demonstrates that combining graph neural network modeling and inference is an effective approach for solving inverse design problems associated with attaining desirable thermal transport behaviors using thermal metamaterials.

A Pricing-Based Cooperative Relay Selection Scheme for Reliable Communications

With the rapid development and application of energy harvesting technology,it has become a prominent research area due to its significant benefits in terms of green environmental protection,convenience,and high safety and efficiency.However,the uneven energy collection and consumption among IoT devices at varying distances may lead to resource imbalance within energy harvesting networks,thereby resulting in low energy transmission efficiency.To enhance the energy transmission efficiency of IoT devices in energy harvesting,this paper focuses on the utilization of collaborative communication,along with pricing-based incentive mechanisms and auction strategies.We propose a dynamic relay selection scheme,including a ladder pricing mechanism based on energy level and a Kuhn-Munkre Algorithm based on an auction theory employing a negotiation mechanism,to encourage more IoT devices to participate in the collaboration process.Simulation results demonstrate that the proposed algorithm outperforms traditional algorithms in terms of improving the energy efficiency of the system.

Analysis and Optimization on Partition-Based Caching and Delivery in Satellite-Terrestrial Edge Computing Networks

As a viable component of 6G wireless communication architecture,satellite-terrestrial networks support efficient file delivery by leveraging the innate broadcast ability of satellite and the enhanced powerful file transmission approaches of multi-tier terrestrial networks.In the paper,we introduce edge computing technology into the satellite-terrestrial network and propose a partition-based cache and delivery strategy to make full use of the integrated resources and reducing the backhaul load.Focusing on the interference effect from varied nodes in different geographical distances,we derive the file successful transmission probability of the typical user and by utilizing the tool of stochastic geometry.Considering the constraint of nodes cache space and file sets parameters,we propose a near-optimal partition-based cache and delivery strategy by optimizing the asymptotic successful transmission probability of the typical user.The complex nonlinear programming problem is settled by jointly utilizing standard particle-based swarm optimization(PSO)method and greedy based multiple knapsack choice problem(MKCP)optimization method.Numerical results show that compared with the terrestrial only cache strategy,Ground Popular Strategy,Satellite Popular Strategy,and Independent and identically distributed popularity strategy,the performance of the proposed scheme improve by 30.5%,9.3%,12.5%and 13.7%.

High Stable and Accurate Vehicle Selection Scheme Based on Federated Edge Learning in Vehicular Networks

Federated edge learning(FEEL)technology for vehicular networks is considered as a promising technology to reduce the computation workload while keeping the privacy of users.In the FEEL system,vehicles upload data to the edge servers,which train the vehicles’data to update local models and then return the result to vehicles to avoid sharing the original data.However,the cache queue in the edge is limited and the channel between edge server and each vehicle is time-varying.Thus,it is challenging to select a suitable number of vehicles to ensure that the uploaded data can keep a stable cache queue in edge server while maximizing the learning accuracy.Moreover,selecting vehicles with different resource statuses to update data will affect the total amount of data involved in training,which further affects the model accuracy.In this paper,we propose a vehicle selection scheme,which maximizes the learning accuracy while ensuring the stability of the cache queue,where the statuses of all the vehicles in the coverage of edge server are taken into account.The performance of this scheme is evaluated through simulation experiments,which indicates that our proposed scheme can perform better than the known benchmark scheme.

Cooperative Content Caching and Delivery in Vehicular Networks: A Deep Neural Network Approach

The growing demand for low delay vehicular content has put tremendous strain on the backbone network.As a promising alternative,cooperative content caching among different cache nodes can reduce content access delay.However,heterogeneous cache nodes have different communication modes and limited caching capacities.In addition,the high mobility of vehicles renders the more complicated caching environment.Therefore,performing efficient cooperative caching becomes a key issue.In this paper,we propose a cross-tier cooperative caching architecture for all contents,which allows the distributed cache nodes to cooperate.Then,we devise the communication link and content caching model to facilitate timely content delivery.Aiming at minimizing transmission delay and cache cost,an optimization problem is formulated.Furthermore,we use a multi-agent deep reinforcement learning(MADRL)approach to model the decision-making process for caching among heterogeneous cache nodes,where each agent interacts with the environment collectively,receives observations yet a common reward,and learns its own optimal policy.Extensive simulations validate that the MADRL approach can enhance hit ratio while reducing transmission delay and cache cost.

Incremental Learning of Radio Modulation Classification Based on Sample Recall

Radio modulation classification has always been an important technology in the field of communications.The difficulty of incremental learning in radio modulation classification is that learning new tasks will lead to catastrophic forgetting of old tasks.In this paper,we propose a sample memory and recall framework for incremental learning of radio modulation classification.For data with different signal-to-noise ratios,we use a partial memory strategy by selecting appropriate samples for memorizing.We compare the performance of our proposed method with three baselines through a large number of simulation experiments.Results show that our method achieves far higher classification accuracy than finetuning method and feature extraction method.Furthermore,it performs closely to joint training method which uses all old data in terms of classification accuracy which validates the effectiveness of our method against catastrophic forgetting.

Deep-learning-based methods for super-resolution fluorescence microscopy

The algorithm used for reconstruction or resolution enhancement is one of the factors affectingthe quality of super-resolution images obtained by fluorescence microscopy.Deep-learning-basedalgorithms have achieved stateof-the-art performance in super-resolution fluorescence micros-copy and are becoming increasingly attractive.We firstly introduce commonly-used deep learningmodels,and then review the latest applications in terms of the net work architectures,the trainingdata and the loss functions.Additionally,we discuss the challenges and limits when using deeplearning to analyze the fluorescence microscopic data,and suggest ways to improve the reliability and robustness of deep learning applications.

A Hybrid Model Based on ResNet and GCN for sEMG-Based Gesture Recognition

The surface electromyography(sEMG)is one of the basic processing techniques to the gesture recognition because of its inherent advantages of easy collection and non-invasion.However,limited by feature extraction and classifier selection,the adaptability and accuracy of the conventional machine learning still need to promote with the increase of the input dimension and the number of output classifications.Moreover,due to the different characteristics of sEMG data and image data,the conventional convolutional neural network(CNN)have yet to fit sEMG signals.In this paper,a novel hybrid model combining CNN with the graph convolutional network(GCN)was constructed to improve the performance of the gesture recognition.Based on the characteristics of sEMG signal,GCN was introduced into the model through a joint voting network to extract the muscle synergy feature of the sEMG signal.Such strategy optimizes the structure and convolution kernel parameters of the residual network(ResNet)with the classification accuracy on the NinaPro DBl up to 90.07%.The experimental results and comparisons confirm the superiority of the proposed hybrid model for gesture recognition from the sEMG signals.

亚言语的理论与应用

成晓光,辽 宁 师 范 大

Optimal Power Allocation for Multiuser OFDM-Based Cognitive Heterogeneous Networks

Heterogeneous network(HetNet) as a promising technology to improve spectrum efficiency and system capacity has been concerned by many scholars, which brings huge challenges for power allocation and interference management in multicell network structures. Although some works have been done for power allocation in heterogeneous femtocell networks, most of them focus centralized schemes for single-cell network under interference constraint of macrocell user. In this paper, a sum-rate maximization based power allocation algorithm is proposed for a downlink cognitive Het Net with one macrocell network and multiple microcell networks. The original power allocation optimization problem with the consideration of cross-tier interference constraint, maximum transmit power constraint of microcell base station and inter-cell interference of microcell networks is converted into a geometric programming problem which can be solved by Lagrange dual method in a distributed way. Simulation results demonstrate the performance and effectiveness of the proposed algorithm by comparing with the equal power allocation scheme.

A TCP Performance Enhancement Scheme in Infrastructure based Vehicular Networks

Transmission Control Protocol （TCP） in infrastructure based vehicular net- works is dedicated to support reliable Intemet services for mobile users. However, an end-to- end TCP flow not only experiences some com- mon challenges in wireless mobile networks, such as high packet loss rate, medium access competition, unstable wireless bandwidth, and dynamic topology, etc., but also suffers from performance degradation due to traffic congestion at the Road-Side Units （RSUs） that connect the wireline and wireless networks. In order to address the challenging issues related to reliable TCP transmissions in infrastruc- ture based vehicular networks, we propose an RSU based TCP （R-TCP） scheme. For wireline source nodes, R-TCP adopts a novel flow control mechanism to adjust transmission rates according to the status of bottleneck link. Specifically, during the short wireless connec- tion time in Infrastructure based vehicular net- works, R-TCP quickly chooses an ideal trans- mission rate for data transmissions instead of activating the slow start algorithm after the connection is established, and successfully avoids the oscillation of the transmission rate. Simulation results show that R-TCP achieves great advantages than some relate proposals in terms of throughput, end-to-end delay, and packet loss rate.

The Impact of Delay in Software-Defined Integrated Terrestrial-Satellite Networks

Satellite communication networks have been evolving from standalone networks with ad-hoc infrastructures to possibly interconnected portions of a wider Future Internet architecture. Experts belonging to the fifth-generation(5 G) standardization committees are considering satellites as a technology to integrate in the 5 G environment. Software Defined Networking(SDN) is one of the paradigms of the next generation of mobile and fixed communications. It can be employed to perform different control functionalities, such as routing, because it allows traffic flow identification based on different parameters and traffic flow management in a centralized way. A centralized set of controllers makes the decisions and sends the corresponding forwarding rules for each traffic flow to the involved intermediate nodes that practically forward data up to the destination. The time to perform this process in integrated terrestrial-satellite networks could be not negligible due to satellite link delays. The aim of this paper is to introduce an SDN-based terrestrial satellite network architecture and to estimate the mean time to deliver the data of a new traffic flow from the source to the destination including the time required to transfer SDN control actions. The practical effect is to identify the maximum performance than can be expected.

Impacts of Packet Collisions on Link Throughput in CSMA Wireless Networks

It is known that packet collisions in wireless networks will deteriorate system performance, hence substantial efforts have been made to avoid collision in multi-user access designs. Also, there have been many studies on throughput analysis of CSMA wireless networks. However, for a typical CSMA network in which not all nodes can sense each other, it is still not well investigated how link throughputs are affected by collisions. We note that in practical 802.11-like networks, the time is divided into mini-timeslots and packet collisions are in fact unavoidable. Thus, it is desirable to move forward to explore how collisions in such a network will affect system performance. Based on the collision-free ideal CSMA network(ICN) model, this paper attempts to analyze link throughputs when taking the backoff collisions into account and examine the effect of collisions on link throughputs. Specifically, we propose an Extended Ideal CSMA Network(EICN) model to characterize the collision effects as well as the interactions and dependency among links in the network. Based on EICN, we could directly compute link throughputs and collision probabilities. Simulations show that the EICN model is of high accuracy. Under various network topologies and protocol parameter settings, the computation error of link throughputs using EICN is kept to 4% or below. Interestingly, we find that unlike expected, the effect of collisions on link throughputs in a modest CSMA wireless network is not significant, which enriches our understanding on practical CSMA wireless networks such as Wi-Fi.

Constructive Approximation by Superposition of Sigmoidal Functions

In this paper, a constructive theory is developed for approximating func- tions of one or more variables by superposition of sigmoidal functions. This is done in the uniform norm as well as in the L^p norm. Results for the simultaneous approx- imation, with the same order of accuracy, of a function and its derivatives （whenever these exist）, are obtained. The relation with neural networks and radial basis func- tions approximations is discussed. Numerical examples are given for the purpose of illustration.

Adaptive coupled synchronization of non-autonomous systems in ring networks

The adaptive coupled synchronization method for non-autonomous systems is proposed. This method can avoid estimating the value of coupling coefficient. Under the uniform Lipschitz assumption, we derive the asymptotical synchronization for a general coupling ring network with N identical non-autonomous systems~ even when N is large enough. Strict theoretical proofs are given. Numerical simulations illustrate the effectiveness of the present method.

Mobile user forecast and power-law acceleration invariance of scale-free networks

This paper studies and predicts the number growth of China＇s mobile users by using the power-law regression. We find that the number growth of the mobile users follows a power law. Motivated by the data on the evolution of the mobile users, we consider scenarios of self-organization of accelerating growth networks into scale-free structures and propose a directed network model, in which the nodes grow following a power-law acceleration. The expressions for the transient and the stationary average degree distributions are obtained by using the Poisson process. This result shows that the model generates appropriate power-law connectivity distributions. Therefore, we find a power-law acceleration invariance of the scale-free networks. The numerical simulations of the models agree with the analytical results well.

Study of Total Process Energy Integration

The energy utilization consistency method in process integration extracts the key component of process energy utilization, and simplifies the procedure of process analysis and integration. The method allows the conversion of the total process energy integration into a synthesis problem of a pseudo-heat exchanger network. The advantages of using the energy utilization consistency and the pseudo-temperature methods are presented by two examples of integration of large-scale complex processes. The improved genetic algorithm is proved to be an effective tool in the retrofitting procedures.

A Novel Method for Solving Nonlinear Schrödinger Equation with a Potential by Deep Learning

The improved physical information neural network algorithm has been proven to be used to study integrable systems. In this paper, the improved physical information neural network algorithm is used to study the defocusing nonlinear Schrödinger (NLS) equation with time-varying potential, and the rogue wave solution of the equation is obtained. At the same time, the influence of the number of network layers, neurons and the number of sampling points on the network performance is studied. Experiments show that the number of hidden layers and the number of neurons in each hidden layer affect the relative L2-norm error. With fixed configuration points, the relative norm error does not decrease with the increase in the number of boundary data points, which indicates that in this case, the number of boundary data points has no obvious influence on the error. Through the experiment, the rogue wave solution of the defocusing NLS equation is successfully captured by IPINN method for the first time. The experimental results of this paper are also compared with the results obtained by the physical information neural network method and show that the improved algorithm has higher accuracy. The results of this paper will be contributed to the generalization of deep learning algorithms for solving defocusing NLS equations with time-varying potential.

Heuristic Solutions of Virtual Network Embedding： A Survey

Network virtualization(NV) is considered as an enabling tool to remove the gradual ossification of current Internet. In the network virtualization environment, a set of heterogeneous virtual networks(VNs), isolated from each other, share the underlying resources of one or multiple substrate networks(SNs) according to the resource allocation strategy. This kind of resource allocation strategy is commonly known as so called Virtual Network Embedding(VNE) algorithm in network virtualization. Owing to the common sense that VNE problem is NP-hard in nature, most of VNE algorithms proposed in the literature are heuristic. This paper surveys and analyzes a number of representative heuristic solutions in the literature. Apart from the analysis of representative heuristic solutions, a taxonomy of the heuristic solutions is also presented in the form of table. Future research directions of VNE, especially for the heuristics, are emphasized and highlighted at the end of this survey.