The bionics-based swarm intelligence optimization algorithm is a typical natural heuristic algorithm whose goal is to find the global optimal solution of the optimization problem. It simulates the group behavior of various animals and uses the information exchange and cooperation between individuals to achieve optimal goals through simple and effective interaction with experienced and intelligent individuals. This paper first introduces the principles of various swarm intelligent optimization algorithms. Then, the typical application of these swarm intelligence optimization algorithms in various fields is listed. After that, the advantages and defects of all swarm intelligence optimization algorithms are summarized. Next, the improvement strategies of various swarm intelligence optimization algorithms are explained. Finally, the future development of various swarm intelligence optimization algorithms is prospected.

Network traffic classification, which matches network traffic for a specific class of different granularities, plays a vital role in the domain of network administration and cyber security. With the rapid development of network communication techniques, more and more network applications adopt encryption techniques during communication, which brings significant challenges to traditional network traffic classification methods. On the one hand, traditional methods mainly depend on matching features on the application layer of the ISO/OSI reference model, which leads to the failure of classifying encrypted traffic. On the other hand, machine learning-based methods require human-made features from network traffic data by human experts, which renders it difficult for them to deal with complex network protocols. In this paper, the convolution attention network (CAT) is proposed to overcom those difficulties. As an end-to-end model, CAT takes raw data as input and returns classification results automatically, with engineering by human experts. In CAT, firstly, the importance of different bytes with an attention mechanism of network traffic is achieved. Then, convolution neural network (CNN) is used to learn features automatically and feed the output into a softmax function to get classification results. It enables CAT to learn enough information from network traffic data and ensure the classified accuracy. Extensive experiments on the public encrypted network traffic dataset ISCX2016 demonstrate the effectiveness of the proposed model.

In order to improve the learning speed and reduce computational complexity of twin support vector hypersphere (TSVH), this paper presents a smoothed twin support vector hypersphere (STSVH) based on the smoothing technique. STSVH can generate two hyperspheres with each one covering as many samples as possible from the same class respectively. Additionally, STSVH only solves a pair of unconstraint differentiable quadratic programming problems (QPPs) rather than a pair of constraint dual QPPs which makes STSVH faster than the TSVH. By considering the differentiable characteristics of STSVH, a fast Newton-Armijo algorithm is used for solving STSVH. Numerical experiment results on normally distributed clustered datasets ( NDC) as well as University of California Irvine (UCI) data sets indicate that the significant advantages of the proposed STSVH in terms of efficiency and generalization performance.

While solving unimodal function problems, conventional meta-heuristic algorithms often suffer from low accuracy and slow convergence. Therefore, in this paper, a novel meta-heuristic optimization algorithm, named proton-electron swarm (PES), is proposed based on physical rules. This algorithm simulates the physical phenomena of like-charges repelling each other while opposite charges attracting in protons and electrons, and establishes a mathematical model to realize the optimization process. By balancing the global exploration and local exploitation ability, this algorithm achieves high accuracy and avoids falling into local optimum when solving target problem. In order to evaluate the effectiveness of this algorithm, 23 classical benchmark functions were selected for comparative experiments. Experimental results show that, compared with the contrast algorithms, the proposed algorithm cannot only obtain higher accuracy and convergence speed in solving unimodal function problems, but also maintain strong optimization ability in solving multimodal function problems.

In order to meet various challenges in the Internet of things (IoT), such as identity authentication, privacy preservation of distributed data and network security, the integration of blockchain and IoT became a new trend in recent years. As the key supporting technology of blockchain, the consensus algorithm is a hotspot of distributed system research. At present, the research direction of the consensus algorithm is mainly focused on improving throughput and reducing delay. However, when blockchain is applied to IoT scenario, the storage capacity of lightweight IoT devices is limited, and the normal operations of blockchain system cannot be guaranteed. To solve this problem, an improved version of Raft (Imp Raft) based on Raft and the storage compression consensus (SCC) algorithm is proposed, where initialization process and compression process are added into the flow of Raft. Moreover, the data validation process aims to ensure that blockchain data cannot be tampered with. It is obtained from experiments and analysis that the new proposed algorithm can effectively reduce the size of the blockchain and the storage burden of lightweight IoT devices.

In this paper, a power allocation to maximize tradeoff between spectrum efficiency (SE) and energy efficiency (EE) is considered for the downlink non-orthogonal multiple access (NOMA) system with arbitrarily clusters and arbitrarily users, where the subcarriers of clusters are mutually orthogonal to each other. Specifically, an optimization problem of maximizing SE-EE tradeoff is formulated by optimizing power allocation among users under the constraints of user rate requirements. Then, the optimization problem is decomposed into a group of sub-problems with the aim of maximizing SE-EE tradeoff for each cluster, which is solved by using bisection method and monotonicity of function. Finally, the power allocation optimization problem among users is transformed into that between clusters, and a two steps inter-cluster power allocation algorithm is developed to solve this problem. Simulation results show that SE-EE tradeoff of the proposed scheme is better than that of the existing schemes.

In order to detect and cancel the self-interference (SI) signal from desired binary phase-shift keying (BPSK) signal, the polarization-based optimal detection (POD) scheme for cancellation of digital SI in a full-duplex (FD) system is proposed. The POD scheme exploits the polarization domain to isolate the desired signal from the SI signal and then cancel the SI to obtain the interference-free desired signal at the receiver. In FD communication, after antenna and analog cancellation, the receiver still contains residual SI due to non-linearities of hardware imperfections. In POD scheme, a likelihood ratio expression is obtained, which isolates and detects SI bits from the desired bits. After isolation of these signal points, the POD scheme cancels the residual SI. As compared to the conventional schemes, the proposed POD scheme gives significantly low bit error rate (BER), a clear constellation diagram to obtain the boundary between desired and SI signal points, and increases the receiver's SI cancellation performance in low signal to interference ratio (SIR) environment.

The energy-efficiency(EE) optimization problem was studied for resource allocation in an uplink single-cell network, in which multiple mobile users with different quality of service (QoS) requirements operate under a non-orthogonal multiple access (NOMA) scheme. Firstly, a multi-user feasible power allocation region is derived as a multidimensional body that provides an efficient scheme to determine the feasibility of original channel and power assignment problem. Then, the size of feasible power allocation region was first introduced as utility function of the subchannel-user matching game in order to get high EE of the system and fairness among the users. Moreover, the power allocation optimization to the EE maximization is proved to be a monotonous decline function. The simulation results show that compared with the conventional schemes, the network connectivity of the proposed scheme is significantly enhanced and besides, for low rate massive connectivity networks, the proposed scheme obtains performance gains in the EE of the system.

In the post quantum era, public key cryptographic scheme based on lattice is considered to be the most promising cryptosystem that can resist quantum computer attacks. However, there are still few efficient key agreement protocols based on lattice up to now. To solve this issue, an improved key agreement protocol with post quantum security is proposed. Firstly, by analyzing the Wess-Zumino model + ( WZM + ) key agreement protocol based on small integer solution (SIS) hard problem, it is found that there are fatal defects in the protocol that cannot resist man-in-the-middle attack. Then based on the bilateral inhomogeneous small integer solution (Bi-ISIS) problem, a mutual authenticated key agreement (AKA) protocol with key confirmation is proposed and designed. Compared with Diffie-Hellman (DH) protocol, WZM + key agreement protocol, and the AKA agreement based on the ideal lattice protocol, the improved protocol satisfies the provable security under the extend Canetti-Krawczyk (eCK) model and can resist man-in-the-middle attack, replay attack and quantum computing attack.