Finite-time Prescribed Performance Time-Varying Formation Control for Second-Order Multi-Agent Systems With Non-Strict Feedback Based on a Neural Network Observer

This paper studies the problem of time-varying formation control with finite-time prescribed performance for nonstrict feedback second-order multi-agent systems with unmeasured states and unknown nonlinearities.To eliminate nonlinearities,neural networks are applied to approximate the inherent dynamics of the system.In addition,due to the limitations of the actual working conditions,each follower agent can only obtain the locally measurable partial state information of the leader agent.To address this problem,a neural network state observer based on the leader state information is designed.Then,a finite-time prescribed performance adaptive output feedback control strategy is proposed by restricting the sliding mode surface to a prescribed region,which ensures that the closed-loop system has practical finite-time stability and that formation errors of the multi-agent systems converge to the prescribed performance bound in finite time.Finally,a numerical simulation is provided to demonstrate the practicality and effectiveness of the developed algorithm.

Set-Membership Filtering Approach to Dynamic Event-Triggered Fault Estimation for a Class of Nonlinear Time-Varying Complex Networks

The present study addresses the problem of fault estimation for a specific class of nonlinear time-varying complex networks,utilizing an unknown-input-observer approach within the framework of dynamic event-triggered mechanism(DETM).In order to optimize communication resource utilization,the DETM is employed to determine whether the current measurement data should be transmitted to the estimator or not.To guarantee a satisfactory estimation performance for the fault signal,an unknown-input-observer-based estimator is constructed to decouple the estimation error dynamics from the influence of fault signals.The aim of this paper is to find the suitable estimator parameters under the effects of DETM such that both the state estimates and fault estimates are confined within two sets of closed ellipsoid domains.The techniques of recursive matrix inequality are applied to derive sufficient conditions for the existence of the desired estimator,ensuring that the specified performance requirements are met under certain conditions.Then,the estimator gains are derived by minimizing the ellipsoid domain in the sense of trace and a recursive estimator parameter design algorithm is then provided.Finally,a numerical example is conducted to demonstrate the effectiveness of the designed estimator.

Time-varying parameters estimation with adaptive neural network EKF for missile-dual control system

In this paper, a filtering method is presented to estimate time-varying parameters of a missile dual control system with tail fins and reaction jets as control variables. In this method, the long-short-term memory(LSTM) neural network is nested into the extended Kalman filter(EKF) to modify the Kalman gain such that the filtering performance is improved in the presence of large model uncertainties. To avoid the unstable network output caused by the abrupt changes of system states,an adaptive correction factor is introduced to correct the network output online. In the process of training the network, a multi-gradient descent learning mode is proposed to better fit the internal state of the system, and a rolling training is used to implement an online prediction logic. Based on the Lyapunov second method, we discuss the stability of the system, the result shows that when the training error of neural network is sufficiently small, the system is asymptotically stable. With its application to the estimation of time-varying parameters of a missile dual control system, the LSTM-EKF shows better filtering performance than the EKF and adaptive EKF(AEKF) when there exist large uncertainties in the system model.

A UAV-Assisted V2X Network Architecture with Separated Data Transmission and Network Control

With the explosive increasing number of connecting devices such as smart phones, vehicles,drones, and satellites in the wireless networks, how to manage and control such a huge number of networking nodes has become a great challenge. In this paper, we combine the advantages of centralized networks and distributed networks approaches for vehicular networks with the aid of Unmanned Aerial Vehicle(UAV), and propose a Center-controlled Multihop Wireless(CMW) networking scheme consisting of data transmission plane performed by vehicles and the network control plane implemented by the UAV.Besides, we jointly explore the advantages of Medium Access Control(MAC) protocols in the link layer and routing schemes in the network layer to facilitate the multi-hop data transmission for the ground vehicles.Particularly, the network control plane in the UAV can manage the whole network effectively via fully exploiting the acquired network topology information and traffic requests from each vehicle, and implements various kinds of control based on different traffic demands, which can enhance the networking flexibility and scalability significantly in vehicular networks.Simulation results validate the advantages of the proposed scheme compared with existing methods.

An evaluation method of contribution rate based on fuzzy Bayesian networks for equipment system-of-systems architecture

The contribution rate of equipment system-of-systems architecture(ESoSA)is an important index to evaluate the equipment update,development,and architecture optimization.Since the traditional ESoSA contribution rate evaluation method does not make full use of the fuzzy information and uncertain information in the equipment system-of-systems(ESoS),and the Bayesian network is an effective tool to solve the uncertain information,a new ESoSA contribution rate evaluation method based on the fuzzy Bayesian network(FBN)is proposed.Firstly,based on the operation loop theory,an ESoSA is constructed considering three aspects:reconnaissance equipment,decision equipment,and strike equipment.Next,the fuzzy set theory is introduced to construct the FBN of ESoSA to deal with fuzzy information and uncertain information.Furthermore,the fuzzy importance index of the root node of the FBN is used to calculate the contribution rate of the ESoSA,and the ESoSA contribution rate evaluation model based on the root node fuzzy importance is established.Finally,the feasibility and rationality of this method are validated via an empirical case study of aviation ESoSA.Compared with traditional methods,the evaluation method based on FBN takes various failure states of equipment into consideration,is free of acquiring accurate probability of traditional equipment failure,and models the uncertainty of the relationship between equipment.The proposed method not only supplements and improves the ESoSA contribution rate assessment method,but also broadens the application scope of the Bayesian network.

Scale adaptive fitness evaluation‐based particle swarm optimisation for hyperparameter and architecture optimisation in neural networks and deep learning

Research into automatically searching for an optimal neural network(NN)by optimi-sation algorithms is a significant research topic in deep learning and artificial intelligence.However,this is still challenging due to two issues:Both the hyperparameter and ar-chitecture should be optimised and the optimisation process is computationally expen-sive.To tackle these two issues,this paper focusses on solving the hyperparameter and architecture optimization problem for the NN and proposes a novel light‐weight scale‐adaptive fitness evaluation‐based particle swarm optimisation(SAFE‐PSO)approach.Firstly,the SAFE‐PSO algorithm considers the hyperparameters and architectures together in the optimisation problem and therefore can find their optimal combination for the globally best NN.Secondly,the computational cost can be reduced by using multi‐scale accuracy evaluation methods to evaluate candidates.Thirdly,a stagnation‐based switch strategy is proposed to adaptively switch different evaluation methods to better balance the search performance and computational cost.The SAFE‐PSO algorithm is tested on two widely used datasets:The 10‐category(i.e.,CIFAR10)and the 100−cate-gory(i.e.,CIFAR100).The experimental results show that SAFE‐PSO is very effective and efficient,which can not only find a promising NN automatically but also find a better NN than compared algorithms at the same computational cost.

Deep Neural Network Architecture Search via Decomposition-Based Multi-Objective Stochastic Fractal Search

Deep neural networks often outperform classical machine learning algorithms in solving real-world problems.However,designing better networks usually requires domain expertise and consumes significant time and com-puting resources.Moreover,when the task changes,the original network architecture becomes outdated and requires redesigning.Thus,Neural Architecture Search(NAS)has gained attention as an effective approach to automatically generate optimal network architectures.Most NAS methods mainly focus on achieving high performance while ignoring architectural complexity.A myriad of research has revealed that network performance and structural complexity are often positively correlated.Nevertheless,complex network structures will bring enormous computing resources.To cope with this,we formulate the neural architecture search task as a multi-objective optimization problem,where an optimal architecture is learned by minimizing the classification error rate and the number of network parameters simultaneously.And then a decomposition-based multi-objective stochastic fractal search method is proposed to solve it.In view of the discrete property of the NAS problem,we discretize the stochastic fractal search step size so that the network architecture can be optimized more effectively.Additionally,two distinct update methods are employed in step size update stage to enhance the global and local search abilities adaptively.Furthermore,an information exchange mechanism between architectures is raised to accelerate the convergence process and improve the efficiency of the algorithm.Experimental studies show that the proposed algorithm has competitive performance comparable to many existing manual and automatic deep neural network generation approaches,which achieved a parameter-less and high-precision architecture with low-cost on each of the six benchmark datasets.

Space-Air-Ground Integrated Network (SAGIN) for 6G: Requirements, Architecture and Challenges

As the fifth-generation(5G)mobile communication network may not meet the requirements of emerging technologies and applications,including ubiquitous coverage,industrial internet of things(IIoT),ubiquitous artificial intelligence(AI),digital twins(DT),etc.,this paper aims to explore a novel space-air-ground integrated network(SAGIN)architecture to support these new requirements for the sixth-generation(6G)mobile communication network in a flexible,low-latency and efficient manner.Specifically,we first review the evolution of the mobile communication network,followed by the application and technology requirements of 6G.Then the current 5G non-terrestrial network(NTN)architecture in supporting the new requirements is deeply analyzed.After that,we proposes a new flexible,low-latency and flat SAGIN architecture,and presents corresponding use cases.Finally,the future research directions are discussed.

The SOLIDS 6G Mobile Network Architecture:Driving Forces,Features,and Functional Topology

With the large-scale commercial launch of fifth generation(5G)mobile network,the development of new services and applications catering to the year 2030,along with the deep convergence of information,communication,and data technologies(ICDT),and the lessons and experiences from 5G practice will drive the evolution of the next generation of mobile networks.This article surveys the history and driving forces of the evolution of the mobile network architecture and proposes a logical function architecture for sixth generation(6G)mobile network.The proposed 6G network architecture is termed SOLIDS(related to the following basic features:soft,on-demand fulfillment,lite,native intelligence,digital twin,and native security),which can support self-generation,self-healing,self-evolution,and self-immunity without human involvement and address the primary issues in the legacy 5G network(e.g.,high cost,high power consumption,and highly complicated operation and maintenance),significantly well.

A Flexible Three Clouds 5G Mobile Network Architecture Based on NFV & SDN

Along with the completion of the development of 4G technologies, the global mobile community starts the study of the next generation technologies, i.e. 5G technologies. This paper proposes a new flexible architecture for 5G mobile networks based on Network Function Virtualization(NFV) and Software Defined Network(SDN) technologies, which is adaptable to use cases and scenarios. Then implementation reference architecture and some typical 5G network deployment cases are discussed. Besides, some key issues for further study are also indicated at the end.

Effective distributed convolutional neural network architecture for remote sensing images target classification with a pre-training approach

How to recognize targets with similar appearances from remote sensing images(RSIs) effectively and efficiently has become a big challenge. Recently, convolutional neural network(CNN) is preferred in the target classification due to the powerful feature representation ability and better performance. However,the training and testing of CNN mainly rely on single machine.Single machine has its natural limitation and bottleneck in processing RSIs due to limited hardware resources and huge time consuming. Besides, overfitting is a challenge for the CNN model due to the unbalance between RSIs data and the model structure.When a model is complex or the training data is relatively small,overfitting occurs and leads to a poor predictive performance. To address these problems, a distributed CNN architecture for RSIs target classification is proposed, which dramatically increases the training speed of CNN and system scalability. It improves the storage ability and processing efficiency of RSIs. Furthermore,Bayesian regularization approach is utilized in order to initialize the weights of the CNN extractor, which increases the robustness and flexibility of the CNN model. It helps prevent the overfitting and avoid the local optima caused by limited RSI training images or the inappropriate CNN structure. In addition, considering the efficiency of the Na¨?ve Bayes classifier, a distributed Na¨?ve Bayes classifier is designed to reduce the training cost. Compared with other algorithms, the proposed system and method perform the best and increase the recognition accuracy. The results show that the distributed system framework and the proposed algorithms are suitable for RSIs target classification tasks.

A Survey of Accelerator Architectures for Deep Neural Networks

Recently,due to the availability of big data and the rapid growth of computing power,artificial intelligence(AI)has regained tremendous attention and investment.Machine learning(ML)approaches have been successfully applied to solve many problems in academia and in industry.Although the explosion of big data applications is driving the development of ML,it also imposes severe challenges of data processing speed and scalability on conventional computer systems.Computing platforms that are dedicatedly designed for AI applications have been considered,ranging from a complement to von Neumann platforms to a“must-have”and stand-alone technical solution.These platforms,which belong to a larger category named“domain-specific computing,”focus on specific customization for AI.In this article,we focus on summarizing the recent advances in accelerator designs for deep neural networks(DNNs)-that is,DNN accelerators.We discuss various architectures that support DNN executions in terms of computing units,dataflow optimization,targeted network topologies,architectures on emerging technologies,and accelerators for emerging applications.We also provide our visions on the future trend of AI chip designs.

Architecture for Cellular Enabled Integrated Communication and Sensing Services

There is growing interest in the integrated sensing and communication(ISAC)to extend the 5G+/6G network capabilities by introducing sensing capability.While the solutions for mono-static or bi-static ISAC have shown feasibility and benefits based on existing 5G physical layer design,whether and how to coordinate multiple ISAC devices to better exert networking performance are rarely discussed.3 rd Partnership Project(3GPP)has initiated the ISAC use cases study,and the follow-up studies for network architecture could be anticipated.In this article,we focus on gNB-based sensing mode and propose ISAC functional framework with given of highlevel service procedures to enable cellular based ISAC services.In the proposed ISAC framework,three types of network functions for sensing service as Sensing Function(SF),lightweight-Edge Sensing Function(ESF)and full-version-ESF are designed with interaction with network nodes to fulfill the latency requirements of ISAC use cases.Finally,with simulation evaluations and hardware testbed results,we further verify the performance benefit and feasibility to enable ISAC in 5G for the gNB-based sensing mode with new design on SF and related signaling protocols.

Service Customized Space-Air-Ground Integrated Network for Immersive Media: Architecture, Key Technologies, and Prospects

The space-air-ground integrated network(SAGIN) is regarded as the key approach to realize global coverage in future network and it reaches broad access for various services. Being the new paradigm of service, immersive media(IM) has attracted users’ attention for its virtualization, but it poses challenges to network performance, e.g. bandwidth, rate, latency. However, the SAGIN has limitations in supporting IM services, such as 4 K/8 K video, virtual reality, and interactive games. In this paper, a novel service customized SAGIN architecture for IM applications(SAG-IM) is proposed, which achieves content interactive and real-time communication among terminal users. State-of-the-art research is investigated in detail to facilitate the combination of SAGIN and service customized technology, which provides endto-end differentiated services for users. Besides, the functional components of SAG-IM contain the infrastructure layer, perception layer, intelligence layer, and application layer, reaching the capabilities of intelligent management of the network. Moreover, to provide IM content with ultra-high-definition and high frame rate for the optimal user experience, the promising key technologies on intelligent routing and delivery are discussed. The performance evaluation shows the superiority of SAG-IM in supporting IM service.Finally, the prospects in practical application are high-lighted.

Data Center Network Architecture

1 Introduction The history of data centers can be traced back to the 1960s. Early data centers were deployed on main- frames that were time-shared by users via remote terminals. The boom in data centers came duringthe internet era. Many companies started building large inter- net-connected facililies,

A Double-Branch Xception Architecture for Acute Hemorrhage Detection and Subtype Classification

This study presents a deep learning model for efficient intracranial hemorrhage(ICH)detection and subtype classification on non-contrast head computed tomography(CT)images.ICH refers to bleeding in the skull,leading to the most critical life-threatening health condition requiring rapid and accurate diagnosis.It is classified as intra-axial hemorrhage(intraventricular,intraparenchymal)and extra-axial hemorrhage(subdural,epidural,subarachnoid)based on the bleeding location inside the skull.Many computer-aided diagnoses(CAD)-based schemes have been proposed for ICH detection and classification at both slice and scan levels.However,these approaches performonly binary classification and suffer from a large number of parameters,which increase storage costs.Further,the accuracy of brain hemorrhage detection in existing models is significantly low for medically critical applications.To overcome these problems,a fast and efficient system for the automatic detection of ICH is needed.We designed a double-branch model based on xception architecture that extracts spatial and instant features,concatenates them,and creates the 3D spatial context(common feature vectors)fed to a decision tree classifier for final predictions.The data employed for the experimentation was gathered during the 2019 Radiologist Society of North America(RSNA)brain hemorrhage detection challenge.Our model outperformed benchmark models and achieved better accuracy in intraventricular(99.49%),subarachnoid(99.49%),intraparenchymal(99.10%),and subdural(98.09%)categories,thereby justifying the performance of the proposed double-branch xception architecture for ICH detection and classification.

Design of Network Architecture Using Mobile Gateways for DLNA Devices in Wide Area Networks

The prevalence of information appliances supporting DLNA (Digital Living Network Alliance) such as televisions, recorders, and mobile phones has made it possible to share digital contents (e.g. videos, music and pictures) among appliances connected to a local network. However, DLNA does not let you share contents over different networks via the Internet. In this paper, we propose a network architecture where we adopt our SOAP method to mobile devices and use them as mobile gateways to consume digital contents from remote networks. We also confirm its practicality with a prototype.

An Optimized Convolution Neural Network Architecture for Paddy Disease Classification

Plant disease classification based on digital pictures is challenging.Machine learning approaches and plant image categorization technologies such as deep learning have been utilized to recognize,identify,and diagnose plant diseases in the previous decade.Increasing the yield quantity and quality of rice forming is an important cause for the paddy production countries.However,some diseases that are blocking the improvement in paddy production are considered as an ominous threat.Convolution Neural Network(CNN)has shown a remarkable performance in solving the early detection of paddy leaf diseases based on its images in the fast-growing era of science and technology.Nevertheless,the significant CNN architectures construction is dependent on expertise in a neural network and domain knowledge.This approach is time-consuming,and high computational resources are mandatory.In this research,we propose a novel method based on Mutant Particle swarm optimization(MUT-PSO)Algorithms to search for an optimum CNN architecture for Paddy leaf disease classification.Experimentation results show that Mutant Particle swarm optimization Convolution Neural Network(MUTPSO-CNN)can find optimumCNNarchitecture that offers better performance than existing hand-crafted CNN architectures in terms of accuracy,precision/recall,and execution time.

Software-Defined Space-Air-Ground Integrated Network Architecture with the Multi-Layer Satellite Backbone Network

Under the background of the rapid development of ground mobile communication,the advantages of high coverage,survivability,and flexibility of satellite communication provide air support to the construction of space information network.According to the requirements of the future space information communication,a software-defined Space-Air-Ground Integrated network architecture was proposed.It consisted of layered structure satellite backbone network,deep space communication network,the stratosphere communication network and the ground network.The Space-Air-Ground Integrated network was supported by the satellite backbone network.It provided data relay for the missions such as deep space exploration and controlled the deep-space spacecraft when needed.In addition,it safeguarded the anti-destructibility of stratospheric communication and assisted the stratosphere to supplement ground network communication.In this paper,algorithm requirements of the congestion control and routing of satellite backbone protocols for heterogeneous users’services were proposed.The algorithm requirements of distinguishing different service objects for the deep space communication and stratospheric communication network protocols were described.Considering the realistic demand for the dynamic coverage of the satellite backbone network and node cost,the multi-layer satellite backbone network architecture was constructed.On this basis,the proposed Software-defined Space-Air-Ground Integrated network architecture could be built as a large,scalable and efficient communication network that could be integrated into space,air,and ground.

QoS-Guaranteed Secure Multicast Routing Protocol for Satellite IP Networks Using Hierarchical Architecture

Most recent satellite network research has focused on providing routing services without considering security. In this paper, for the sake of better global coverage, we introduce a novel triple-layered satellite network architecture including Geostationary Earth Orbit (GEO), Highly Elliptical Orbit (HEO), and Low Earth Orbit (LEO) satellite layers, which provides the near-global coverage with 24 hour uninterrupted over the areas varying from 75° S to 90° N. On the basis of the hierarchical architecture, we propose a QoS-guaranteed secure multicast routing protocol (QGSMRP) for satellite IP networks using the logical location concept to isolate the mobility of LEO and HEO satellites. In QGSMRP, we employ the asymmetric cryptography to secure the control messages via the pairwise key pre-distribution, and present a least cost tree (LCT) strategy to construct the multicast tree under the condition that the QoS constraints are guaranteed, aiming to minimize the tree cost. Simulation results show that the performance benefits of the proposed QGSMRP in terms of the end-to-end tree delay, the tree cost, and the failure ratio of multicasting connections by comparison with the conventional shortest path tree (SPT) strategy.