Edge Computing-Based Joint Client Selection and Networking Scheme for Federated Learning in Vehicular IoT

In order to support advanced vehicular Internet-of-Things(IoT)applications,information exchanges among different vehicles are required to find efficient solutions for catering to different application requirements in complex and dynamic vehicular environments.Federated learning(FL),which is a type of distributed learning technology,has been attracting great interest in recent years as it performs knowledge exchange among different network entities without a violation of user privacy.However,client selection and networking scheme for enabling FL in dynamic vehicular environments,which determines the communication delay between FL clients and the central server that aggregates the models received from the clients,is still under-explored.In this paper,we propose an edge computing-based joint client selection and networking scheme for vehicular IoT.The proposed scheme assigns some vehicles as edge vehicles by employing a distributed approach,and uses the edge vehicles as FL clients to conduct the training of local models,which learns optimal behaviors based on the interaction with environments.The clients also work as forwarder nodes in information sharing among network entities.The client selection takes into account the vehicle velocity,vehicle distribution,and the wireless link connectivity between vehicles using a fuzzy logic algorithm,resulting in an efficient learning and networking architecture.We use computer simulations to evaluate the proposed scheme in terms of the communication overhead and the information covered in learning.

CONTROL SCHEMES FOR CMAC NEURAL NETWORK-BASED VISUAL SERVOING

In IBVS (image based visual servoing), the error signal in image space should be transformed into the control signal in the input space quickly. To avoid the iterative adjustment and complicated inverse solution of image Jacobian, CMAC (cerebellar model articulation controller) neural network is inserted into visual servo control loop to implement the nonlinear mapping. Two control schemes are used. Simulation results on two schemes are provided, which show a better tracking precision and stability can be achieved using scheme 2.

A Transductive Scheme Based Inference Techniques for Network Forensic Analysis

Network forensics is a security infrastructure,and becomes the research focus of forensic investigation.However many challenges still exist in conducting network forensics:network has produced large amounts of data;the comprehensibility of evidence extracting from collected data;the efficiency of evidence analysis methods,etc.To solve these problems,in this paper we develop a network intrusion forensics system based on transductive scheme that can detect and analyze efficiently computer crime in networked environments,and extract digital evidence automatically.At the end of the paper,we evaluate our method on a series of experiments on KDD Cup 1999 dataset.The results demonstrate that our methods are actually effective for real-time network forensics,and can provide comprehensible aid for a forensic expert.

可见光通信技术与无源光网络的结合方案探讨

元宇宙业务及应用前景广阔,高带宽、低延迟、无线缆连接等特性对用户终端带来巨大挑战。文章简要介绍VLC(可见光通信技术)的发展应用,讨论可见光通信技术与PON(无源光网络)的异构组网方案。得出可行的方案是让元宇宙终端下行采用可见光通信,上行的数据和信令传输使用Wi-Fi 6千兆无线连接。这种组合将为终端用户提供无线缆束缚的10 Gbit/s级别的可独享数据传输速率,并保障终端用户的沉浸式体验。

Two-Phase Bidirectional Dual-Relay Selection Strategy for Wireless Relay Networks

In this article,we introduce a new bi-directional dual-relay selection strategy with its bit error rate(BER)performance analysis.During the first step of the proposed strategy,two relays out of a set of N relay-nodes are selected in a way to optimize the system performance in terms of BER,based on the suggested algorithm which checks if the selected relays using the maxmin criterion are the best ones.In the second step,the chosen relay-nodes perform an orthogonal space-time coding scheme using the two-phase relaying protocol to establish a bi-directional communication between the communicating terminals,leading to a significant improvement in the achievable coding and diversity gain.To further improve the overall system performance,the selected relay-nodes apply also a digital network coding scheme.Furthermore,this paper discusses the analytical approximation of the BER performance of the proposed strategy,where we prove that the analytical results match almost perfectly the simulated ones.Finally,our simulation results show that the proposed strategy outperforms the current state-of-the-art ones.

A Beamforming Technique Using Rotman Lens Antenna for Wireless Relay Networks

Rotman lens,which is a radio frequency beam-former that consists of multiple input and multiple output beam ports,can be used in industrial,scientific,and medical applications as a beam steering device.The input ports collect the signals to be propagated through the lens cavity toward the output ports before being transmitted by the antenna arrays to the destination in order to enhance the error performance by optimizing the overall signal to noise ratio(SNR).In this article,a low-cost Rotman lens antenna is designed and deployed to enhance the overall performance of the conventional cooperative communication systems without needing any additional power,extra time or frequency slots.In the suggested system,the smart Rotman lens antennas generate a beam steering in the direction of the destination to maximize the received SNR at the destination by applying the proposed optimal beamforming technique.The suggested optimal beamforming technique enjoys high diversity,as well as,low encoding and decoding complexity.Furthermore,we proved the advantages of our suggested strategy through both theoretical results and simulations using Monte Carlo runs.The Monte Carlo simulations show that the suggested strategy enjoys better error performance compared to the current state-of-the-art distributed multiantenna strategies.In addition,the bit error rate(BER)curves drawn from the analytical results are closely matching to those drawn from our conducted Monte Carlo simulations.

A novel differentiated services supporting scheme for optical burst switched networks

In this letter, we analyze the drawback of tail-dropping contention resolution in optical burst switched networks. Once contention occurs, we adopt modified head-dropping policy to resolve contention. This policy drops the head of the contending burst only if the overlapping region of the two bursts is less than the whole contending burst size, otherwise drops the whole contending burst. In order to have a better support of differentiated service, a new burst assembly policy, namely, Priority-based proportional mixed burst assembly, is proposed. Simulation results show that the proposed scheme performs very well in terms of performance metrics such as the times of contention and packet loss probability.

A congestion alleviated scheme in optical burst switching network

An optical burst switching （OBS） network platform is established with a ring topology of three nodes. A congestion Mleviated scheme using advanced token protocol and wavelength tunable receivers is demon- strated to optimize the network platform. Experimental results testify that this scheme can resist collision at the level of 0.1% congestion rate.

Performance analysis of an integrated scheme in optical burst switching high-speed networks

A new integrated scheme based on resource-reservation and adaptive network flow routing to alleviate contention in optical burst switching networks is proposed. The objective of the proposed scheme is to reduce the overall burst loss in the network and at the same time to avoid the packet out-of-sequence arrival problem. Simulations are carried out to assess the feasibility of the proposed scheme. Its performance is compared with that of contention resolution schemes based on conventional routing. Through extensive simulations, it is shown that the proposed scheme not only provides significantly better burst loss performance than the basic equal proportion and hop-length based traffic routing algorithms, but also is void of any packet re-orderings.

Novel virtual user scheme to increase data confidentiality against eavesdropping in OCDMA network

We propose a novel technique to increase the confidentiality of an optical code division multiple access （OCDMA） system. A virtual user technique is analyzed and implemented to make an OCDMA system secure. Using this technique, an eavesdropper will never find an isolated authorized user＇s signal. When authorized users and virtual users transmit data synchronously and asynehronously, network security increases by 25% and 37.5%, respectively.

Intelligent computing networks for nonlinear influenza-A epidemic model

The differential equations having delays take paramount interest in the research community due to their fundamental role to interpret and analyze the mathematical models arising in biological studies.This study deals with the exploitation of knack of artificial intelligence-based computing paradigm for numerical treatment of the functional delay differential systems that portray the dynamics of the nonlinear influenza-A epidemic model(IA-EM)by implementation of neural network backpropagation with Levenberg-Marquardt scheme(NNBLMS).The nonlinear IA-EM represented four classes of the population dynamics including susceptible,exposed,infectious and recovered individuals.The referenced datasets for NNBLMS are assembled by employing the Adams method for sufficient large number of scenarios of nonlinear IA-EM through the variation in the infection,turnover,disease associated death and recovery rates.The arbitrary selection of training,testing as well as validation samples of dataset are utilizing by designed NNBLMS to calculate the approximate numerical solutions of the nonlinear IA-EM develop a good agreement with the reference results.The proficiency,reliability and accuracy of the designed NNBLMS are further substantiated via exhaustive simulations-based outcomes in terms of mean square error,regression index and error histogram studies.

Decoding early myelopoiesis from dynamics of core endogenous network

A decade ago mainstream molecular biologists regarded it impossible or biologically ill-motivated to understand the dynamics of complex biological phenomena, such as cancer genesis and progression, from a network perspective. Indeed, there are numerical difficulties even for those who were determined to explore along this direction. Undeterred, seven years ago a group of Chinese scientists started a program aiming to obtain quantitative connections between tumors and network dynamics. Many interesting results have been obtained. In this paper we wish to test such idea from a different angle: the connection between a normal biological process and the network dynamics. We have taken early myelopoiesis as our biological model. A standard roadmap for the cell-fate diversification during hematopoiesis has already been well established experimentally, yet little was known for its underpinning dynamical mechanisms. Compounding this difficulty there were additional experimental challenges, such as the seemingly conflicting hematopoietic roadmaps and the cell-fate inter-conversion events. With early myeloid cell-fate determination in mind, we constructed a core molecular endogenous network from well-documented gene regulation and signal transduction knowledge. Turning the network into a set of dynamical equations, we found computationally several structurally robust states. Those states nicely correspond to known cell phenotypes. We also found the states connecting those stable states.They reveal the developmental routes—how one stable state would most likely turn into another stable state. Such interconnected network among stable states enabled a natural organization of cell-fates into a multi-stable state landscape. Accordingly, both the myeloid cell phenotypes and the standard roadmap were explained mechanistically in a straightforward manner. Furthermore,recent challenging observations were also explained naturally. Moreover, the landscape visually enables a prediction of a pool of additional cell states and developmental routes, including the non-sequential and cross-branch transitions, which are testable by future experiments. In summary, the endogenous network dynamics provide an integrated quantitative framework to understand the heterogeneity and lineage commitment in myeloid progenitors.