基于个性化联邦学习的无线通信流量预测

提出一种基于分布式的城市全域通信流量预测算法Fed-DenseNet,各个边缘计算服务器在中心服务器的协调下进行协同训练,中心服务器利用KL散度挑选出流量分布相似的区域流量模型,并采用联邦平均算法对具有相似流量分布的区域流量模型的参数进行融合,以较低的复杂度和通信开销实现城市全域流量预测。此外,城市范围内不同地区流量具有高度差异化的特征,为此,在Fed-DenseNet算法基础上,提出基于合作博弈的个性化联邦学习算法p-Fed-DenseNet,将本地区的各个区域性数据特征作为合作博弈的参与者,通过合作博弈的超可加性准则,进行本地区特征的筛选,从而达到既能提高模型的泛化性,又能够保持对本地流量精准刻画的目的。     

The blind demodulation scheme based on MP algorithm in chirp-BOK UWB system

In this paper, a blind demodulation scheme for chirp-binary orthogonal keying (BOK)-ultra wide band (UWB) system was proposed based on matching pursuit (MP) algorithm. The scheme was validated in additive white Gaussion noise (AWGN) and indoor multi-path channels that suggested by the IEEE P802.15 criterion. From the simulation results, it shows that the performance of the proposed MP method is consistent well with that of the traditional coherent method in communication circumstance with high quality requirement, and the performance difference of MP method and coherent method is less than 0.8 dB when the bit error rate (BER) is set as 0.001. As the requested BER getting small, the MP method has a comparable performance with the coherent method. It also presented an efficient way for spectrum sharing with other communication systems.     

X型超宽带复合左右手传输线设计与仿真

基于X型金属结构,提出了一种超宽带复合左右手传输线材料结构单元,该结构单元由介质板及其两侧反向对称的X型金属结构组成。从分布参数电路理论角度对材料单元的左右手特性成因进行了定性分析;利用等效参数提取法,通过S散射参数提取了该结构单元的相对介电常数和相对磁导率,并结合折射率进一步验证了这种左右手传输线材料的传输特性。仿真结果表明,在电磁波平行于介质板入射的情况下,该结构单元同时存在左右手频带,在S波段表现出超宽带的左手特性,并且在其他多频点处得到了零折射率,从而构造了一种正零负复合媒质材料。     

基于累计量和SPWVD谱对消的物联网OFDM和FH信号识别

Considering the Gaussian asymptotic features of OFDM signals, the identification method of it is proposed in this paper by using the cumulants of the wavelet transform coefficients in different layer in a low SNR circumstance. Furthermore, taking the coexistence of the OFDM and Frequency Hopping (FH) signals into account, a new way to separate FH and OFDM signals is proposed based on SPWVD spectrum cancellation, and it can be used to estimate the FH parameters. The simulation results show that the OFDM and single-carrier signals can be identified with a high correct rate of 95% even at -6 dB SNR; meanwhile, the separation of mixed OFDM and FH signals can be achieved with a low SNR of-6 dB, and FH parameters can be estimated accurately. It shows that the recognition performance is improved by about 5 dB compared with the traditional method.     

衰落信道下基于中继选择与功率控制的节能协作通信

In order to save energy and make more efficient use of wireless channel, this article puts forward an energy saving cooperative relaying scheme which actuates the cooperative transmission only when the feedback from the destination indicates failure of the direct transmission. The proposed scheme selects the optimal relay and its corresponding transmission power in each time slot based on channel condition and residual energy with the objective of minimizing energy consumption and extending network lifetime. In the study, the finitestate Markov channel model is used to characterize the correlation structure of channel fading in wireless networks, and the procedure of relay selection and transmission power decision is formulated as a Markov decision process. Numerical and simulation results show that the proposed scheme consumes less energy and prolongs the network lifetime.     

An efficient privacy-preserving scheme for secure network coding based on compressed sensing

Network coding (NC) provides an elegant solution for improving capacity and robustness in computer networks. Different to traditional “store-and-forward” transmission paradigm, each intermediate node linearly combines received data packets, and the original files can be decoded at the sink nodes in NC settings. This brand-new paradigm is vulnerable to pollution attack, which means that some malicious nodes inject fake data packets into the network and this will lead to incorrect decoding. There are some information-theoretical solutions and cryptographic solutions for solving this security issue, and most existing schemes can thwart data pollution attacks. However, the privacy of the original files are vital to some application environments (e.g. military network). To the best of our knowledge, there is not a secure scheme which can thwart pollution attack and can protect the privacy of transmitted data simultaneously. In this paper, we present an efficient privacy-preserving scheme for secure network coding based on compressed sensing (CS), which has attracted considerable research interest in the signal processing community. Specifically, we embed CS into the general NC framework, i.e., the source node needs to compress each original data packet using the sensing matrix before creating the augmented vector and the sink nodes require to perform an additional CS reconstruction algorithm for reconstructing the original file. In addition, we construct a simple key distribution protocol and each intermediate node just needs two secret keys for verifying the integrity of received data packets. Such novel hybrid construction enables the privacy-preserving guarantee, and the performance comparison shows the high-efficiency of our scheme in terms of the computational complexity and communication overhead.     

Modeling and analysis of nano-sized GMRs based on Co,NiFe and Ni materials

Magnetic simulation method is introduced to analyze giant magnetoresistances(GMRs)in nanoscale for nano-sized biosensors.A spin valve model with special gridding corresponding to the exchange interaction length is proposed to study the influence of easy axes,exchange coefcients,pinning fields and feature widths on magnetization reversals and hysteresis characteristics of nano-sized GMRs with diferent pinned layer and free layer materials of Co,NiFe and Ni.The switching field is found to be almost linear with the pinning field and decrease with the absolute exchange coefcients and the feature widths for the nano-sized GMRs.The increase rate of each depends on the spin valve stacks.Further investigations into variations of the magnetization distribution reveal that the initial magnetization distribution and the magnetization reversal mode depend greatly on easy axes and materials The dependence on easy axes based mainly on the magnetocrystalline anisotropy is illustrated in detail.     

Deep Q-Learning Based Computation Offloading Strategy for Mobile Edge Computing

To reduce the transmission latency and mitigate the backhaul burden of the centralized cloud-based network services, the mobile edge computing (MEC) has been drawing increased attention from both industry and academia recently. This paper focuses on mobile users’ computation offloading problem in wireless cellular networks with mobile edge computing for the purpose of optimizing the computation offloading decision making policy. Since wireless network states and computing requests have stochastic properties and the environment’s dynamics are unknown, we use the model-free reinforcement learning (RL) framework to formulate and tackle the computation offloading problem. Each mobile user learns through interactions with the environment and the estimate of its performance in the form of value function, then it chooses the overhead-aware optimal computation offloading action (local computing or edge computing) based on its state. The state spaces are high-dimensional in our work and value function is unrealistic to estimate. Consequently, we use deep reinforcement learning algorithm, which combines RL method Q-learning with the deep neural network (DNN) to approximate the value functions for complicated control applications, and the optimal policy will be obtained when the value function reaches convergence. Simulation results showed that the effectiveness of the proposed method in comparison with baseline methods in terms of total overheads of all mobile users.     

Applications and prospects of artificial intelligence in covert satellite communication: a review

Science China Information Sciences - Due to the privacy preserving capabilities and the low communication costs, federated learning has emerged as an efficient technique for distributed deep...