Intelligent anti-jamming decision algorithm based on proximal policy optimization by MA Song, LI Li, LI Wei, HUANG Wei, WANG Jun

“…The simulation results demonstrate that the convergence speed of the proposed algorithm is increased by 37%, and the system capacity after convergence is increased by 25%, compared with the decision algorithms of policy gradient and deep Q-learning.…”
Get full text

Fast dynamic channel allocation algorithm based on priority channel reservation by SHI Wen-xiao, ZHAO Jun, CHI Xue-fen, LI Na

“…Aiming at overcoming the shortages of the current fast dynamic channel allocation algorithm in TD-SCDMA system,a novel fast dynamic channel allocation algorithm based on priority channel reservation was proposed.This algorithm defined call priority by equipment attribution of baton handover user,reserved channels for baton handover calls.Combining with grouping borrowed algorithm,the algorithm made MB DCA strategy more flexible.Simulation results show that,comparing to the mixed-data rate grouping borrowed algorithm,the proposed algorithm achieves the preferential access of VIP and high rate mobile user,reduces the call failure probability resulted from the baton handover,improves the performance of data service,and increases the channel utilization efficiency.…”
Get full text

Flow-splitting algorithm of MPLS single label based on programmable router by Lai-quan HAN, Jin-kuan WANG, Xing-wei WANG

“…To increase the QoS (quality of service) of data transmission, a novel flow-splitting algorithm, multipathMPLS, was proposed, which combined three technologies of MPLS (multi protocol label switching), concurrent multi-path and programmable router. …”
Get full text

Beamspace Unitary ESPRIT Algorithm for Angle Estimation in Bistatic MIMO Radar by Dang Xiaofang, Chen Baixiao, Yang Minglei, Zheng Guimei

“…The proposed algorithm does not require peak searching, presents low complexity, and provides a significant better performance compared to some existing methods, such as the element-space ESPRIT (E-ESPRIT) algorithm and the beamspace ESPRIT (B-ESPRIT) algorithm for bistatic MIMO radar. …”
Get full text

An Enhanced Sine Cosine Algorithm for Feature Selection in Network Intrusion Detection by zahra asgari varzaneh, soodeh hosseini

Subjects: “…sine cosine algorithm…”
Get full text

Exoskeleton Follow-Up Control Based on Parameter Optimization of Predictive Algorithm by Shijia Zha, Tianyi Li, Lidan Cheng, Jihua Gu, Wei Wei, Xichuan Lin, Shaofei Gu

“…In this paper, an improved method for the prediction algorithm of exoskeleton sensor data is proposed. Through an algorithm simulation test and two-link simulation experiment, the algorithm improves the prediction accuracy by 14.23 ± 0.5%, and the sensor data is smooth. …”
Get full text

Energy dissipation balanced and reliable clustering algorithm for wireless sensor networks by Jun YUE, Wei-ming ZHANG, Wei-dong XIAO, Da-quan TANG, Jiu-yang TANG

“…A novel clustering algorithm for wireless sensor networks was proposed to resolve the hot spot problem and the single failure problem.The algorithm divided the network into unequal grids,and the nodes in the same grid form a cluster.The number of cluster heads in each grid was determined according to the failure probability of nodes,and the data collection of nodes in a grid was implemented by multiple cluster heads of the grid cooperatively.By adjusting the number of nodes that could participate in cluster head rotation of each grid,the algorithm was able to balance the energy dissipation of nodes on a long view.The algorithm reduced the reliance of cluster members to single cluster head by forming cluster with multiple cluster heads.Furthermore,the algorithm adopted some measures to diminish energy consumption.Simulation results show that the algorithm has higher balanced extent of energy dissipation and reliability of data collection,and prolongs the lifetime of network.…”
Get full text

Self-Identification Algorithm for the Autonomous Control of Lateral Vibration in Flexible Rotors by Thiago Malta Buttini, Rodrigo Nicoletti

“…In this work, a self-identification algorithm is proposed for the autonomous decision and control of a flexible shaft rotating system with electromagnetic actuators. …”
Get full text

Algorithm of grey correlation analysis for radar target recognition based on similarity by Rupeng ZHAO, Runlan TIAN, Xuzhou ZHANG, Yibin XIE

“…According to the algorithm can't better identify complex radar targets and improve the accuracy while facing parameters overlapping,an algorithm of similarity-grey relational analysis based on similarity was proposed.Firstly,the similarity matrix between the parameters was extracted by the algorithm.And then the grey correlation analysis was used to get the corresponding grey correlation coefficient.At the same time,the weight value was determined according to the matching degree of each parameter,the grey correlation degree of the signal was identified and the library signal was obtained by combining with the grey correlation coefficient,and the target recognition was completed according to the grey correlation degree.Finally,having the grey correlation between the signal and the grey correlation coefficient,which can realize the identification of the complex radar target.The simulation results show that the impact of parame-ters overlapping with high recognition accuracy was reduced,the recognition accuracy was improved,and the identifica-tion of complex system radar targets were quickly realized by the proposed algorithm.…”
Get full text

Using Camshift and Kalman Algorithm to Trajectory Characteristic Matching of Basketball Players by Shuang Liang, Yang Li

“…The matching of players’ track characteristics is realized by the CamShift algorithm based on the color model, which makes full use of players’ color information and realizes real-time performance. …”
Get full text

Dual threshold cooperative spectrum sensing algorithm based on stochastic resonance by Shunlan LIU, Yide XIAO, Jianrong BAO

“…In view of the poor performance of the existing spectrum sensing algorithm in the low signal-noise ratio (SNR) environment and the limitations of traditional stochastic resonance (SR) detection methods for weak signals in practical applications,a dual threshold cooperative spectrum sensing algorithm based on stochastic resonance (DCSSR) by setting the optimal threshold was proposed and the optimal number of cooperative users was calculated.At last,the performance of the proposed algorithm was analyzed.This algorithm further improves the detection performance of the spectrum sensing algorithm under low signal-to-noise ratio by passing the statistical data located in the double-threshold uncertain region through a stochastic resonance system.Simulation results show that the detection performance of DCSSR algorithm is improved compared with traditional single threshold energy cooperation algorithm,double threshold energy cooperation algorithm and single threshold stochastic resonance cooperation algorithm.When the SNR is -20 dB,the proposed DCSSR algorithm improves the detection probability by 80% compared with the traditional single threshold energy detection cooperation algorithm.…”
Get full text

Algorithm of Strawberry Disease Recognition Based on Deep Convolutional Neural Network by Li Ma, Xueliang Guo, Shuke Zhao, Doudou Yin, Yiyi Fu, Peiqi Duan, Bingbing Wang, Li Zhang

“…In this paper, based on the deep convolution neural network technology, the recognition of strawberry common diseases was studied, as well as a new method based on deep convolution neural network (DCNN) strawberry disease recognition algorithm, through the normal training of strawberry image feature representation in different scenes, and then through the application of transfer learning method, the strawberry disease image features are added to the training set, and finally the features are classified and recognized to achieve the goal of disease recognition. …”
Get full text

Research on Network Selection Algorithm Based on User Preference in Heterogeneous System by Cun Yang, Jihong Zhao, Shuyuan Zhao

“…Most network selection algorithms did not pay more attention to user preference for networks which was based on service requirements.For this circumstance,a new network selection algorithm based on user prefenence was proposed.The algorithm was fully considerd service reqirements,user prefernece and network performance.The AHP algorithm and distance analysis were used to calculate subjective and objective user preference weight respectively for different heterogeneous networks.Then the user preference weight for networks could be obtained dynamically on the basis of user strategy.The performance of each candidate network was counted,based on which the optimum network was selected.Simulation results show that the algorithm performs well in network selection and reduces the number of handoff times as the user moves through the network boundary frequently.…”
Get full text

A Multiswarm Intelligence Algorithm for Expensive Bound Constrained Optimization Problems by Wali Khan Mashwani, Ruqayya Haider, Samir Brahim Belhaouari

“…All these developed algorithms have some merits and also demerits. Particle swarm optimization (PSO), firefly algorithm, ant colony optimization (ACO), and bat algorithm (BA) have gained much popularity and they have successfully tackled various test suites of benchmark functions and real-world problems. …”
Get full text

Research on Optimal Control for the Vehicle Suspension Based on the Simulated Annealing Algorithm by Jie Meng, Qingzhang Chen, Ren He

“…A method is designed to optimize the weight matrix of the LQR controller by using the simulated annealing algorithm. This method utilizes the random searching characteristics of the algorithm to optimize the weight matrices with the target function of suspension performance indexes. …”
Get full text

OPTIMIZATION DESIGN OF UNIVERSAL COUPLING FORK BASED ON PARTICLE SWARM ALGORITHM by TANG Shu, LIU Yuan, YU XiangDong, SHI GuanLin

Subjects: Get full text

Improved Genetic Algorithm of Helical Gear Reducer and 3D Modeling by Hao Liping

“…Based on the penalty function method combined with the improved genetic algorithm,the multi-objective and multi-restriction reliability optimal design of the reducer with hardened tooth surface and modified helical cylinder gear is carried out.According to the properties of the constraint conditions,the different methods are used for effectively avoiding the local optimum problem.The accurate three-dimensional description of the involute gear is carried out by the establishment of the tooth profile curve coordinate equation of the involute gear.According to the interface technology of VB and SolidWorks,the three-dimensional parametric modeling of the involute gear is achieved based on the optimal design results.…”
Get full text

Image Noise Removal Method Based on Improved Nonlocal Mean Algorithm by Keya Huang, Hairong Zhu

“…This algorithm combines the adaptive median filter algorithm with the traditional nonlocal mean algorithm, first adjusts the image window adaptively, selects the corresponding pixel weight, and then denoises the image, which can have a good filtering effect on the mixed noise. …”
Get full text

BeSnake: A Routing Algorithm for Scalable Spin-Qubit Architectures by Nikiforos Paraskevopoulos, Carmen G. Almudever, Sebastian Feld

Subjects: Get full text

Novel virtual topology configuration algorithm for IP over WDM network by LE Zi-chun, FU Ming-lei

“…The load balancing for the whole network was chosen as the optimal objective and a novel virtual topology configuration algorithm was proposed.In the proposed algorithm,the load distribution variance was chosen as a key criterion for judging the load balancing.And the definition and the computing method of the load distribution variance were introduced.In addition,the blocking probability was chosen as the main performance parameter for comparing with other algorithms.In the optical layer,the algorithm proposed was compared with the routing with load balancing heuristics（RLBH） algorithm.Similarly,in IP layer,the algorithm was compared with the fixed-path least-congestion（FPLC） algorithm.Moreover,the numerical results of the algorithm comparison were shown and discussed.The simulation results show that the performance of the algorithm is better than RLBH algorithm and FPLC algorithm on the blocking probability.…”
Get full text