Time Series Prediction Based on Complex-Valued S-System Model by Bin Yang, Wenzheng Bao, Yuehui Chen

“…The hybrid evolutionary algorithm based on complex-valued restricted additive tree and firefly algorithm is proposed to search the optimal CVSS model. …”
Get full text

Optimal structural similarity constraint for reversible data hiding by Jia-jia XU, Wei-ming ZHANG, Rui-qi JIANG, Neng-hai YU, Xiao-cheng HU

“…Most reversible data hiding (RDH) techniques have been evaluated by PSNR,which is based on MSE.Unfortunately,MSE turns out to be an extremely poor measure when the purpose is to predict perceived signal fidel-ity or quality.The structural similarity index has gained widespread popularity as an alternative motivating principle for the design of image quality measures.How to utilize the characterize of SSIM to design RDH algorithm is very critical.An optimal RDH algorithm under structural similarity constraint was proposed.Firstly,the metric of the structural similarity constraint was deduced.Secondly,the rate-distortion function of optimal structural similarity constraint was constructed,which was equivalent to minimize the average distortion for a given embedding rate.Fi-nally,the optimal transition probability matrix under the structural similarity constraint was obtained.Experiments show that the proposed method can be used to improve the performance of previous RDH schemes evaluated by SSIM.…”
Get full text

Scrambler blind recognition method based on soft information by Ze-liang CHEN, Hua PENG, Ke-xian GONG, Pei-dong YU

“…Two scrambler blind recognition methods based on soft information were proposed for received signal in non-cooperative ways.The first method established a cost function of the scrambler coefficients by using the soft information,and adopted the optimization theory of real number field for positive solution.So it didn’t need to traverse the closed set of test polynomial any more.The second method built conformity degree concept with the soft information,and used the size of conformity of each test scrambler polynomial as the discriminant criteria.So it made more full use of the received information compared to the hard sentence recognition algorithm.Simulation results show that the first method can shorten the recognition time of a synchronous scrambler polynomial from 5 min 18 s to 8 s compared with the traversal method put forward by Cluzeau,and the second method has 2 dB SNR gain when to achieve the relatively high accuracy compared with the hard sentence recognition algorithm.…”
Get full text

Modeling of Dual-Spinning Projectile with Canard and Trajectory Filtering by Jun Guan, Wenjun Yi

“…The trajectory filtering performed according to the unscented Kalman filter algorithm can improve the accuracy of measurement data and eliminate the measurement error effectively, so as to obtain more accurate and reliable measurement data.…”
Get full text

Semantic segmentation of 3D point cloud based on contextual attention CNN by Jun YANG, Jisheng DANG

“…Aiming at the under-segmentation of 3D point cloud semantic segmentation caused by the lack of contextual fine-grained information of the point cloud,an algorithm based on contextual attention CNN was proposed for 3D point cloud semantic segmentation.Firstly,the fine-grained features in local area of the point cloud were mined through the attention coding mechanism.Secondly,the contextual features between multi-scale local areas were captured by the contextual recurrent neural network coding mechanism and compensated with the fine-grained local features.Finally,the multi-head mechanism was used to enhance the generalization ability of the network.Experiments show that the mIoU of the proposed algorithm on the three standard datasets of ShapeNet Parts,S3DIS and vKITTI are 85.4%,56.7% and 38.1% respectively,which has good segmentation performance and good generalization ability.…”
Get full text

A blockchain sharding scheme in edge computing by Jun WANG, Jianwei MA, Jinxi LUO

“…The low security and poor privacy of the data in edge computing restrict the development of edge computing.Block chains can provide security for data in edge computing using their own tamper resistance, while protecting privacy by use of traceability.But the bottleneck of blockchain's scalability has become a barrier to their application in the field of edge computing.To solve the problem that blockchain can not meet the needs of a large number of nodes to process data at the same time when applied to edge computing, a two-layer sharding scheme was presented, which meets the needs of edge computing scenarios.Geographic location-based partitioning of nodes was implemented using the improved K-means algorithm, and a local blockchain network consensus (LBNC) algorithm was designed based on the idea of delegated proof of stake (DPoS) and practical Byzantine fault tolerance (PBFT).Simulation results show that the proposed scheme has less delay and higher throughput than those of PBFT, and the total throughput increases with the number of shards.…”
Get full text

Radio signal recognition based on image deep learning by Xin ZHOU, Xiaoxin HE, Changwen ZHENG

“…A technical idea was innovatively proposed that uses image deep learning to solve the problem of radio signal recognition.First,the radio signal was transformed into a two-dimensional picture,and the radio signal recognition problem was transformed into the object detection problem in the field of image recognition.Then,the advanced achievements about image recognition were used to improve the intelligence and ability of radio signal recognition in complex electromagnetic environment.Based on the proposed idea,a novel radio signal recognition algorithm named RadioImageDet was proposed.The experimental results show that the algorithm can effectively identify the waveform types and time/frequency coordinates of radio signals.After training and testing on the self-collected data set with 12 types and 4 740 samples,the accuracy reaches 86.04% and the mAP value reaches 77.72,while the detection time is only 33 ms on the medium configured desktop computer.…”
Get full text

Auto-calibration method and performance analysis for noncircular sources based on instrumental sensors by Jie-xin YIN, Ying WU, Ding WANG

“…An improved direction-finding algorithm for noncircular sources was proposed in the presence of angularly dependent gain and phase errors, which is called NC-ISM based on the fundamental principle of ISM (instrumental sen-sor method). …”
Get full text

QoS modeling and evaluation of mobile application service based on scene by Yan-zhi HU, Feng-bin ZHANG, Zhi-chun GAN, Tian TIAN, Cai-hua YIN

“…The current static QoS model can not reflect the QoS time varying and location correlation of mobile application service.An QoS model was presented based on scene for mobile applications service.The QoS index system of mobile application service was defined and the QoS value matrix was constructed.Further,three types of assessment problems were proposed,which were QoS overall assessment,QoS assessment of specific region or specific time periods,and QoS assessment of hot region and busy time.By using genetic algorithm and data clustering algorithm,the location and time of the two scene conditions were quantified,which combine the region division of service request location density and the time division of service request frequency.According to the limiting conditions,QoS value matrix was reconstructed,and the service evaluation method was introduced based on the statistical analysis of the matrix.Finally,the normalized evaluation process and application framework of QoS were given.…”
Get full text

纯电动物流车动力系统设计与优化 by 王永鼎, 李恒

“…In order to reasonably match the parameters of the electric logistics vehicle power system,according to the technical requirements of the electric logistics vehicle,the preliminary design and calculation of the relevant parameters of the electric logistics vehicle are carried out,and the whole vehicle simulation model is built by AVL-Cruise on the basis of the simulation conditions.Based on the complexity of parameter matching of pure electric logistics vehicle power system,various parameters need to be considered comprehensively,and a multi-objective genetic algorithm optimization method is proposed.The optimization method takes the vehicle’s power and economy as the optimization goal at the same time,and takes the maximum vehicle speed and acceleration time as constraints,establishes the transmission system optimization model and finds its optimal solution.Through the simulation analysis of the optimized parameters,the feasibility and rationality of the multi-objective genetic algorithm for the optimization of the power system of the electric logistics vehicle is presented,which provides a new way for the optimization of the power system parameters of the electric logistics vehicle.…”
Get full text

Complex Discrete System Analysis of Process Design and Tourist Souvenir Making Based on Artificial Intelligence 3D Printing by Yuchuan Guo

“…To this end, the artificial intelligence algorithm is introduced, and using the data measured by the built-in modeling instruction of LAMMPS of the artificial intelligence algorithm, the program is used to reset its coordinates, length, width, height, and focal length. …”
Get full text

Finite-Time Control for a Coupled Four-Tank Liquid Level System Based on the Port-Controlled Hamiltonian Method by Tao Xu, Haisheng Yu, Jinpeng Yu

“…A novel parameter autotuning algorithm is given to clarify the principle of choosing parameters of the PCH method. …”
Get full text

The Optimization of Transportation Costs in Logistics Enterprises with Time-Window Constraints by Qingyou Yan, Qian Zhang

“…This multiobjective optimization is solved by using a modified genetic algorithm approach. The output of the algorithm is a set of optimal solutions that represent the trade-off between total transportation cost and the fleet size required to service customers. …”
Get full text

Objective assessment of communication speech interference effect based on feature fusion by Yun LIN, Huaitao XU, Sen WANG, Sicheng ZHANG, Long ZHUANG

“…In view of the objective assessment problem of the effect of communication speech interference, methods based on multi-measurements and multimodal fusion were proposed.First, the interfered speech was preprocessed by the endpoint detection algorithm and time warping algorithm.Then, the content of speech was extracted and performed measurement calculated with the standard speech to obtain five kinds of measure.After the fusion of five measures, random forest model was used to assessed the quality level.Finally, a neural network model based on residual structure was designed combined multimodal fusion technique, which fused the graph domain and measure domain features of the interfered speech data and performed quality level assessment.Experimental results show that the accuracy of two methods have reached more than 90%.Among them, the multimodal assessment method improves the accuracy by about 3.269% compared with the existing research methods, which proves that it has a better performance.…”
Get full text

Research on the Integration of Preschool Language Education Resources Based on Metadata Storage by Sun Weiwei

“…The data collector of preschool language education resources is set up by using random forest algorithm to complete the data collection of preschool language education resources. …”
Get full text

Secure communication optimization for double-IRS assisted SWIPT system by Jianfeng CHEN, Miao CUI, Guangchi ZHANG, Qingqing WU, Hui ZENG

“…Two intelligent reflecting surfaces (IRS) was applied to ensure the physical layer security of the information transmission in a simultaneous wireless information and power transfer (SWIPT) system, where a multi-antenna base station (BS) simultaneously transmits information and energy to multiple single-antenna information receivers (IR) and energy receivers (ER) and the ERs are regarded as potential information eavesdroppers.The system deploys two IRSs to ensure the security of information transmission while meeting the requirements of energy transmission.Due to the inter-IRS signal reflection, the variables of the considered optimization problem are highly coupled, thus the problem is difficult to solve.To tackle this difficulty, an algorithm based on the alternating optimization, semidefinite relaxation, and successive convex approximation methods was proposed to obtain a suboptimal solution to the problem.Simulation results show that the proposed algorithm can significantly increase the total rate of the IRs and guarantee the security of the information transmission and the requirement of energy transmission, as compared to some existing benchmark schemes.…”
Get full text

Traffic matrix-based load balancing routing in flow-based smart identifier network by ARu JI, Shuai GAO, Hong-bin LUO, Hong-ke ZHANG, Ming WAN

“…Finally, a proof-of-concept was built implementation and carry out experiments for testing the overhead of TM-LB algorithm.…”
Get full text

Mobile malware traffic detection approach based on value-derivative GRU by Hanxun ZHOU, Chen CHEN, Runze FENG, Junkun XIONG, Hong PAN, Wei GUO

“…For the dramatic increase in the number and variety of mobile malware had created enormous challenge for information security of mobile network users,a value-derivative GRU-based mobile malware traffic detection approach was proposed in order to solve the problem that it was difficult for a RNN-based mobile malware traffic detection approach to capture the dynamic changes and critical information of abnormal network traffic.The low-order and high-order dynamic change information of the malicious network traffic could be described by the value-derivative GRU approach at the same time by introducing the concept of “accumulated state change”.In addition,a pooling layer could ensure that the algorithm can capture key information of malicious traffic.Finally,simulation were performed to verify the effect of accumulated state changes,hidden layers,and pooling layers on the performance of the value-derivative GRU algorithm.Experiments show that the mobile malware traffic detection approach based on value-derivative GRU has high detection accuracy.…”
Get full text

Redistribution of Nodes with Two Constraints in Meshless Method of Line to Time-Dependent Partial Differential Equations by Jafar Biazar, Mohammad Hosami

“…In this paper, to produce smooth adaptive points in each step of the method, two constraints are enforced in Equidistribution algorithm. These constraints lead to two different meshes known as quasi-uniform and locally bounded meshes. …”
Get full text

Improved sub-band JND model with textural decomposition and its application in perceptual image coding by Ming-kui ZHENG, Kai-xiong SU, Wei-xing WANG, Cheng-dong LAN, Xiu-zhi YANG

“…The proposed algorithm is also applicable to the perceptual video coding.…”
Get full text