Editors Recommend
25 October 2022, Volume 43 Issue 10
Papers
Channel interleaver design and performance analysis for ultrasonic through-metal communication
Linsen XU, Wei YANG, Hongxian TIAN
2022, 43(10):  1-11.  doi:10.11959/j.issn.1000-436x.2022204
Asbtract ( 77 )   HTML ( 25)   PDF (873KB) ( 38 )   Knowledge map   
Figures and Tables | References | Related Articles | Metrics

Aiming at the problem that the UTM channel can produce successive error bits, a multiple input channel interleaver for UTM communication was proposed.By taking advantages of the grouping idea in multiple input interleaver and the periodic oscillation characteristic of the power gain in the UTM channel, encoded bits were first divided into several groups so that error probabilities of bits in each group varied smoothly.And then, the shift operation and the rectangular interleaver were applied to encoded bits in each group.This not only ensured that interleaved bits in the same group were dispersed into different oscillation cycles, which avoided that the successive bits suffer the high error probability, but also maintained the original bit position sequences, which reduced the influence of UEP.Approximate BER performances for the random interleaver and the proposed interleaver were analyzed and verified by simulation.Simulation results indicate that the proposed interleaver increases the frequency diversity of the UTM communication system and has a lower BER than the random interleaver at high SNR.

Method based on contrastive learning for fine-grained unknown malicious traffic classification
Yifeng WANG, Yuanbo GUO, Qingli CHEN, Chen FANG, Renhao LIN
2022, 43(10):  12-25.  doi:10.11959/j.issn.1000-436x.2022180
Asbtract ( 96 )   HTML ( 22)   PDF (2736KB) ( 75 )   Knowledge map   
Figures and Tables | References | Related Articles | Metrics

In order to protect against unknown threats and evasion attacks, a new method based on contrastive learning for fine-grained unknown malicious traffic classification was proposed.Specifically, based on variational auto-encoder (CVAE), it included two classification stages, and cross entropy and reconstruction errors were used for known and unknown traffic classification respectively.Different form other methods, contrastive learning was adopted in different classification stages, which significantly improved the classification performance of the few-shot and unknown (zero-shot) classes.Moreover, some techniques (e.g., re-training and re-sample) combined with contrastive learning further improved the classification performance of the few-shot classes and the generalization ability of model.Experimental results indicate that the proposed method has increased the macro recall of few-shot classes by 20.3% and the recall of unknown attacks by 9.1% respectively, and it also has protected against evasion attacks on partial classes to some extent.

Privacy-preserving attribute ticket scheme based on mobile terminal with smart card
Rui SHI, Huamin FENG, Huiqin XIE, Guozhen SHI, Biao LIU, Yang YANG
2022, 43(10):  26-41.  doi:10.11959/j.issn.1000-436x.2022156
Asbtract ( 72 )   HTML ( 11)   PDF (1566KB) ( 32 )   Knowledge map   
Figures and Tables | References | Related Articles | Metrics

To solve the problem that the existing electronic ticket systems are challenging to deploy in resource-constrained devices and cannot prevent the sharing of tickets among unauthorized devices, a privacy-preserving attribute ticket scheme based on mobile terminal with a smart card was proposed.The smart card was a secure and constrained-yet-trusted core device that holds secret information and performs lightweight operations.The mobile terminal was a powerful helper device that handles key-independent and time-consuming operations.Firstly, the efficient attribute-based ticket scheme deployed on the mobile terminal with a smart card was constructed by combining a pseudorandom function, anonymous ephemeral identities scheme, aggregatable signatures with randomizable tags, and Pointcheval-Sanders signatures.Secondly, the security model of the electronic tickets system was presented, and the proposed scheme was proved to be unlinkable and unforgeable.Finally, the proposed scheme was implemented on a personal computer, a smart card (Aisinochip ACH512), and a smart phone (Huawei Honor 9i), and the comparison and experimental results show that it is efficient.

Active defense technology against intelligent jammer
Zhibin FENG, Yuhua XU, Zhiyong DU, Xin LIU, Wen LI, Hao HAN, Xiaobo ZHANG
2022, 43(10):  42-54.  doi:10.11959/j.issn.1000-436x.2022198
Asbtract ( 96 )   HTML ( 17)   PDF (1477KB) ( 81 )   Knowledge map   
Figures and Tables | References | Related Articles | Metrics

In the complex electromagnetic countermeasure environment, the intelligent development of jammer has caused a serious threat to wireless communication, while the traditional anti-jamming methods often passively adjusted the working mode or parameters, which will be at a disadvantage or even suppressed in the face of intelligent jammer.To solve this problem, a technical framework of active defense against jammer was proposed, aiming to disrupt the learning process of the intelligent jammer and reduce the jamming efficacy.In order to gradually achieve the goals of “understanding opponent”“controlling opponent” and “defeating opponent”, under the guidance of game theory and adversarial machine learning, the key technologies were discussed from three aspects: backward reasoning of jammer, algorithm vulnerability analysis and confrontational strategy design, independent optimization and online decision-making of anti-jamming strategy.Finally, combined with two specific cases, the feasibility and effectiveness of the proposed technical framework were verified.

Research on deterministic computing power network
Qingmin JIA, Yujiao HU, Huayu ZHANG, Kailai PENG, Pingping CHEN, Renchao XIE, Tao HUANG
2022, 43(10):  55-64.  doi:10.11959/j.issn.1000-436x.2022191
Asbtract ( 97 )   HTML ( 18)   PDF (806KB) ( 66 )   Knowledge map   
Figures and Tables | References | Related Articles | Metrics

In order to meet the development requirements of time-sensitive and computing-intensive businesses, the guarantee problem of real-time transmission and real-time computing of computing tasks was studied.Firstly, the research progress of computing power network and deterministic networking was briefly overviewed.Then, the technical scheme of deterministic computing power network was proposed, and the technical architecture and working mechanism were designed.Real-time transmission and real-time computing of computing tasks were realized through the technical capabilities such as computing-network perception, planning and scheduling, resource management and control.The simulation results also verified the effectiveness of the proposed technical scheme.Finally, the representative application scenarios of deterministic computing power network were analyzed, and the future development trends and technical challenges were discussed.

Network traffic anomaly detection method based on multi-scale characteristic
Xueyuan DUAN, Yu FU, Kun WANG, Taotao LIU, Bin LI
2022, 43(10):  65-76.  doi:10.11959/j.issn.1000-436x.2022195
Asbtract ( 76 )   HTML ( 23)   PDF (1290KB) ( 51 )   Knowledge map   
Figures and Tables | References | Related Articles | Metrics

Aiming at the problem that most of the traditional network traffic anomaly detection methods only pay attention to the fine-grained features of traffic data, and make insufficient use of multi-scale feature information, which may lead to low accuracy of anomaly detection results, a network traffic anomaly detection method based on multi-scale features was proposed.The original traffic was divided into sub-sequences with multiple observation spans by using multiple sliding windows of different scales, and the multi-level sequences of each sub-sequence were reconstructed by wavelet transform technology.Multi-level reconstructed sequences were generated by Chain SAE through feature space mapping, and a preliminary judgment of abnormality was made by the classifiers of each level according to the errors of the reconstructed sequences.The weighted voting strategy was adopted to summarize the preliminary judgment results of each level to form the final result judgment.Experimental results show that the proposed method can effectively mine the multi-scale feature information of network traffic, and the detection performance of abnormal traffic is obviously improved compared with traditional methods.

Research on task offloading strategy of Internet of vehicles based on improved hybrid genetic algorithm
Yuliang CONG, Wenxi SUN, Ke XUE, Zhihong QIAN, Mianshu CHEN
2022, 43(10):  77-85.  doi:10.11959/j.issn.1000-436x.2022188
Asbtract ( 74 )   HTML ( 18)   PDF (979KB) ( 48 )   Knowledge map   
Figures and Tables | References | Related Articles | Metrics

Aiming at the problem of unreasonable resource allocation caused by the unloading decision in the multi-vehicle and multi-server IoV scenario, a two-stage heuristic IoV task offloading strategy was proposed.This strategy used the improved hybrid genetic algorithm (IHGA) and the improved artificial fish swarm algorithm (AFSA), combined with the system’s internal average overhead, delay and energy consumption requirements, the two improved algorithm was used for multiple iterations to achieve optimal resource allocation in the process of task unloading.The simulation results show that the proposed scheme can effectively reduce the system internal overhead and improve the task offloading efficiency compared with the benchmark scheme.

Iterative rake equalization method for low-complexity OTSM in high-speed mobile environment
Guojun LI, Kun LONG, Changrong YE, Jiawen LIANG
2022, 43(10):  86-93.  doi:10.11959/j.issn.1000-436x.2022203
Asbtract ( 47 )   HTML ( 6)   PDF (1129KB) ( 30 )   Knowledge map   
Figures and Tables | References | Related Articles | Metrics

Aiming at the problems of poor anti-noise performance and high computational complexity of the existing orthogonal time sequency multiplexing (OTSM) equalization methods, a low-complexity iterative rake equalizer based on maximum ratio combining (MRC) was proposed.The main idea was to use MRC to iteratively extract and coherently combine the received multipath components of the transmitted symbols in the delay-time domain to improve the signal-to-noise ratio of the combined signal.In order to speed up the convergence of the MRC iterative algorithm, a single-tap time-frequency equalizer was designed to provide an initial estimate, and then combined with an external error correction code to further improve the bit error performance.The simulation results show that the performance of the iterative rake equalizer based on MRC is significantly better than that of the LMMSE linear equalizer, and the performance and computational complexity are greatly improved compared with the currently widely used Gauss-Seidel (GS) iterative equalizer.

Research on federated learning approach based on local differential privacy
Haiyan KANG, Yuanrui JI
2022, 43(10):  94-105.  doi:10.11959/j.issn.1000-436x.2022189
Asbtract ( 74 )   HTML ( 13)   PDF (1156KB) ( 51 )   Knowledge map   
Figures and Tables | References | Related Articles | Metrics

As a type of collaborative machine learning framework, federated learning is capable of preserving private data from participants while training the data into useful models.Nevertheless, from a viewpoint of information theory, it is still vulnerable for a curious server to infer private information from the shared models uploaded by participants.To solve the inference attack problem in federated learning training, a local differential privacy federated learning (LDP-FL) approach was proposed.Firstly, to ensure the federated model training process was protected from inference attacks, a local differential privacy mechanism was designed for transmission of parameters in federated learning.Secondly, a performance loss constraint mechanism for federated learning was proposed and designed to reduce the performance loss of local differential privacy federated model by optimizing the constraint range of the loss function.Finally, the effectiveness of proposed LDP-FL approach was verified by comparative experiments on MNIST and Fashion MNIST datasets.

Deception defense method against intelligent penetration attack
Jinyin CHEN, Shulong HU, Changyou XING, Guomin ZHANG
2022, 43(10):  106-120.  doi:10.11959/j.issn.1000-436x.2022202
Asbtract ( 63 )   HTML ( 8)   PDF (1458KB) ( 39 )   Knowledge map   
Figures and Tables | References | Related Articles | Metrics

The intelligent penetration attack based on reinforcement learning aims to model the penetration process as a Markov decision process, and train the attacker to optimize the penetration path in a trial-and-error manner, so as to achieve strong attack performance.In order to prevent intelligent penetration attacks from being maliciously exploited, a deception defense method for intelligent penetration attack based on reinforcement learning was proposed.Firstly, obtaining the necessary information for the attacker to construct the penetration model, which included state, action and reward.Secondly, conducting deception defense against the attacker through inverting the state dimension, disrupting the action generation, and flipping the reward value sign, respectively, which corresponded to the early, middle and final stages of the penetration attack.At last, the three-stage defense comparison experiments were carried out in the same network environment.The results show that the proposed method can effectively reduce the success rate of intelligent penetration attacks based on reinforcement learning.Besides, the deception method that disrupts the action generation of the attacker can reduce the penetration attack success rate to 0 when the interference ratio is 20%.

Generative blockchain-based covert communication model based on Markov chain
Wei SHE, Xinpeng RONG, Wei LIU, Zhao TIAN
2022, 43(10):  121-132.  doi:10.11959/j.issn.1000-436x.2022194
Asbtract ( 71 )   HTML ( 16)   PDF (1070KB) ( 36 )   Knowledge map   
Figures and Tables | References | Related Articles | Metrics

To solve the problems of high channel construction risk, information crossover, and insufficient concealment in the blockchain covert communication, a generative blockchain-based covert communication model based on Markov chain was proposed.First, the text data set was used by sender to obtain the candidate words set and trained the Markov model to obtain the transition probability matrix, generated the Huffman tree set.Secret message to be transmitted was performed iterative Huffman decoding on the binary stream to obtain a set of highly readable carring-secret message statements that conformed to normal language and semantic characteristics, a generative steganography was used to complete secret message embedding.Then, the carring-secret message was ring-signed and published to the blockchain as a normal transaction packing and block generation were completed in the network.Finally, the same text data set was used by the receiver to obtain the Huffman tree of transition probability weights, the binary stream of secret message was obtained by reverse operation.Simulation results demonstrate that, compares with the current similar models, the proposed model can further improve the embedding strength and time efficiency, reduce the risk of covert channel construction, avoid information crossover, and improve the concealment.

Maritime mobile edge computing offloading method based on deep reinforcement learning
Xin SU, Leilei MENG, Yiqing ZHOU, Wu CELIMUGE
2022, 43(10):  133-145.  doi:10.11959/j.issn.1000-436x.2022197
Asbtract ( 86 )   HTML ( 22)   PDF (1184KB) ( 50 )   Knowledge map   
Figures and Tables | References | Related Articles | Metrics

The strong heterogeneity among the network nodes of the maritime information system brings complex and high-dimensional constraints for optimizing task offloading of the maritime mobile edge computing.The complex and diverse maritime applications also lead to the overload processing of computing tasks in local areas of the maritime network.In order to optimize the task offloading and resource management of maritime network, as well as meet the maritime application service requirements of low-latency and high-reliability, a hierarchical classification method of maritime nodes based on multi-layers attributes and a novel offloading method for maritime mobile edge computing based on deep reinforcement learning were proposed.Compared with conventional methods, simulation results show that the proposed method can effectively reduce the computing task offloading delay of the marine information system, and maintain the robustness of the maritime network with large-scale task flows.

Positioning optimization method based on indoor map deduction and signal through-wall correction
Dayang SUN, Wenxiao SHI, Dingguo ZHANG
2022, 43(10):  146-156.  doi:10.11959/j.issn.1000-436x.2022187
Asbtract ( 52 )   HTML ( 6)   PDF (1434KB) ( 28 )   Knowledge map   
Figures and Tables | References | Related Articles | Metrics

An optimization method of through-wall corrected positioning based on mixed measurements of through-wall ranging and LoS ranging was proposed to solve the problem caused by NLoS measurement error.An approximate model of through-wall measurements was first proposed aiming at the typical through-wall NLoS scenario, which made indoor positioning method independent to the factors of the signal incident angle, the structure, the dielectric constant and the thickness of the wall.Then with the help of map deduction, whether there was a wall between the to-be-located node and the anchor node could be judged, and the positioning optimization method was proposed so that localization can be solved with only the redundant measurements.Simulations and UWB experiments show that in a variable map scenario considering through-wall propagation the proposed method outperforms SR-WLS (squared-range and weighted least square) in the aspect of average accuracy of indoor positioning.

Improved optical generalized spatial modulation in Málaga turbulent channel
Hui ZHAO, Weiwen MA, Jin LI, Wenchao DENG, Hui WAN, Tianqi ZHANG, Yuanni LIU
2022, 43(10):  157-166.  doi:10.11959/j.issn.1000-436x.2022200
Asbtract ( 47 )   HTML ( 2)   PDF (1336KB) ( 23 )   Knowledge map   
Figures and Tables | References | Related Articles | Metrics

Aiming at the problems of space resource waste and error bit performance limitation caused by fixed optical antenna combination set used in traditional optical generalized spatial modulation (OGSM), an improved scheme based on low complexity adaptive optical antenna combination set selection algorithm was proposed.First, the Euclidean distance matrix between optical antenna combinations was calculated using channel state information.Then, based on the principle of Euclidean distance equivalence and the idea of maximum norm antenna selection, the optical antenna combination with poor channel state was deleted, and the final reserved optical antenna combination was the optimal optical antenna combination set in the current state.The traversal of all optical antenna combinations was avoided and the complexity of the algorithm was reduced to a large extent.The simulation results show that the BER performance of the improved OGSM scheme outperforms the conventional OGSM under different conditions.

Time series generation model based on multi-discriminator generative adversarial network
Yanhui LU, Han LIU, Hang LI, Guangxu ZHU
2022, 43(10):  167-176.  doi:10.11959/j.issn.1000-436x.2022205
Asbtract ( 48 )   HTML ( 4)   PDF (3938KB) ( 30 )   Knowledge map   
Figures and Tables | References | Related Articles | Metrics

Aiming at the problems of expensive collection cost and missing data due to the privacy and continuity of time series data set, a multi-discriminator generative adversarial network model based on recurrent neural network was proposed, which could synthesize time series dataset that were approximately distributed with real data of a small scale dataset.Multi-discriminator included four discriminators in time domain, frequency domain, time-frequency domain and autocorrelation.Different discriminators could effectively recognize the features of the time series in different domains.In the experiment, the convergence of loss function, principal component analysis and error analysis were performed to evaluate the performance of the model from qualitative and quantitative perspectives.The experimental results show that the proposed model has better performance than other reference models.

Ranging localization method for nodes in underwater wireless sensor network based on zeroing neural dynamics
Xiujuan DU, Lijuan WANG, Jingping LIU, Long JIN
2022, 43(10):  177-185.  doi:10.11959/j.issn.1000-436x.2022192
Asbtract ( 45 )   HTML ( 7)   PDF (1141KB) ( 21 )   Knowledge map   
Figures and Tables | References | Related Articles | Metrics

In underwater wireless sensor network (UWSN), the AoA/TDoA-based ranging localization problem for nodes was formulated from a time-variant perspective, and a zeroing neural dynamics model was proposed to solve it.Then, the convergence of the proposed model was theoretically analyzed.Furthermore, computer simulations on UWSN localization were carried out to demonstrate the effectiveness of the proposed models in terms of accuracy and robustness to the mobile localization.Additionally, through tests performed in Qinghai lake, the coordinates of nodes of UWSN test-bed were leverage to illustrate the potential applicability of the proposed model in the true underwater environment.

Outlier detection algorithm based on fast density peak clustering outlier factor
Zhongping ZHANG, Sen LI, Weixiong LIU, Shuxia LIU
2022, 43(10):  186-195.  doi:10.11959/j.issn.1000-436x.2022193
Asbtract ( 48 )   HTML ( 12)   PDF (991KB) ( 32 )   Knowledge map   
Figures and Tables | References | Related Articles | Metrics

For the problem that peak density clustering algorithm requires human set parameters and high time complexity, an outlier detection algorithm based on fast density peak clustering outlier factor was proposed.Firstly, k nearest neighbors algorithm was used to replace the density peak of density estimate, which adopted the KD-Tree index data structure calculation of k close neighbors of data objects, and then the way of the product of density and distance was adopted to automatic selection of clustering centers.In addition, the centripetal relative distance and fast density peak clustering outliers were defined to describe the degree of outliers of data objects.Experiments on artificial data sets and real data sets were carried out to verify the algorithm, and compared with some classical and novel algorithms.The validity and time efficiency of the proposed algorithm are verified.

Comprehensive Review
Millimeter-wave array enabled UAV-to-UAV communication technology
Zhenyu XIAO, Ke LIU, Lipeng ZHU
2022, 43(10):  196-209.  doi:10.11959/j.issn.1000-436x.2022158
Asbtract ( 67 )   HTML ( 10)   PDF (1676KB) ( 31 )   Knowledge map   
Figures and Tables | References | Related Articles | Metrics

As the application scope of unmanned aerial vehicle (UAV) expands and the tasks become more complicated, the demands for large bandwidth, high data rate and antijamming capability in UAV-to-UAV (V2V) communication grow rapidly.With abundant spectrum resource, millimeter-wave (mmWave) array communication has been one of the key technologies to support V2V communications.Focusing on the emerging field of mmWave array V2V communication, the difficulties and challenges in point-to-point communication and unmanned aerial vehicle ad-hoc network were analyzed.The problems and approaches for channel modeling, robust beamforming, secure communication in point-to-point communication and neighbor discovery, routing decisions, resource allocation, distributed deployment in unmanned aerial vehicle ad-hoc network were reviewed.Some valuable research directions were summarized to provide inspiration for future relevant research.

Correspondences
Four-path unsupervised learning-based image defogging network
Wei LIU, Cheng CHEN, Rui JIANG, Tao LU
2022, 43(10):  210-222.  doi:10.11959/j.issn.1000-436x.2022201
Asbtract ( 50 )   HTML ( 5)   PDF (5180KB) ( 28 )   Knowledge map   
Figures and Tables | References | Related Articles | Metrics

To solve the problems of supervised network and unsupervised network in the field of single image defogging, a four-path unsupervised learning-based image defogging network based on cycle generative adversarial network (CycleGAN) was proposed, which mainly included three sub-networks: defogging network, synthetic fog network and attention feature fusion network.The three sub-networks were sequentially combined to construct four learning paths, which were the defogging path, the color-texture recovery path for defogged result, the synthetic fog path, and the color-texture recovery path for synthetic fog result.Specifically, in the synthetic fog network, to better constrain the defogging network to generate higher quality fogfree images, the atmospheric scattering model (ASM)was introduced to enhance the mapping transformation of the network from the foggy image domain to the fogfree image domain.Furthermore, to further improve the image generation quality of the defogging network and the synthetic fog network, an attention feature fusion network was proposed.The proposed network was based on several fog-derived images, which adopts a multi-channel mapping structure and an attention mechanism to enhance the recovery of color and texture details.Extensive experiments on both synthetic and real-world datasets show that the proposed method can better restore the color and texture details information of foggy images in various scenes.

Computation offloading scheme for RIS-empowered UAV edge network
Bin LI, Wenshuai LIU, Wancheng XIE, Zesong FEI
2022, 43(10):  223-233.  doi:10.11959/j.issn.1000-436x.2022196
Asbtract ( 52 )   HTML ( 16)   PDF (28596KB) ( 30 )   Knowledge map   
Figures and Tables | References | Related Articles | Metrics

In order to address the challenge of low offloading rate caused by the obstacles blocking in the links between unmanned aerial vehicle (UAV) and ground users (GU) in urban scene, a partial task offloading scheme for UAV-enabled mobile edge computing with the aid of reconfigurable intelligence surface was proposed.A nonconvex and multivariable coupling stochastic optimization problem was formulated by the joint design of the computation task allocation, the transmit power of GU, the phase shift of RIS, UAV computation resource, and UAV trajectory, aiming at maximizing the minimum average data throughput of GU.By leveraging the properties of mathematical expectation, the stochastic optimization problem was transformed into a deterministic optimization problem.Then, the deterministic optimization problem was decomposed into three subproblems by using the block coordinate descent (BCD) algorithm.By introducing auxiliary variables, the nonconvex problems were transformed into convex optimization problems via the successive convex approximation and semidefinite relaxation, and then the approximate suboptimal solution of the original problem was obtained.The simulation results show that the proposed algorithm has good convergence performance and effectively improves the average data throughput of GU.

Construction of De Bruijn Sequences from Whole LFSRs with 4 Cycles
ZHOU Cong wei, HU Bin, GUAN Jie
Online First: 2022-07-25
A Review of Threat Discovery and Forensic Analysis Based on System-level Provenance Graphs
LENG Tao , , CAI lijun lijun, YU Aimin , , ZHU ziyuan , M A Jian ganggang, LI Caofei , , NIU Ruicheng , , MENG Dan ,
Online First: 2022-07-25
Improved Meet-in -the-Middle Attack on ReducedReduced-Round KiasuKiasu-BC Cipher
LI Manman , CHEN Shaozhen ,
Online First: 2022-07-25
New Dimension in Orbital Angular Momentum Transmission
Online First: 2022-06-25
A Review of Threat Discovery and Forensic Analysis Based on System-level Provenance Graphs
LENG T Tao , , CAI lijun lijun, YU Aimin , , ZHU ziyuan , M A Jian ganggang, LI Caofei , , NIU Ruicheng , , MENG Dan ,
Online First: 2022-06-25
Joint QoS prediction for Web services based on deep fusion of features
LIU Jianxun , , DING Linghang , , KANG Guosheng , , CAO Buqing , , XIAO Yong ,
Online First: 2022-06-25
Multi-level recommendation framework for local differential privacy algorithms
WANG Hanyi, LI Xiaoguang, BI Wenqing, CHEN Yahong, LI Fenghua, NIU Ben
10.11959/j.issn.1000?436x.2020029
Online First: 2022-06-25
6G-Oriented cross-modal signal reconstruction technology
LI Ang, CHEN Jianxin, WEI Xin, ZHOU Liang,
Online First: 2022-06-25
Joint QoS Prediction for Web Services based on Deep Fusion of Features
Online First: 2022-06-24
Multi-level recommendation framework for local differential privacy algorithms
WANG Hanyi, LI Xiaoguang, BI Wenqing, CHEN Yahong, LI Fenghua, NIU Ben
10.11959/j.issn.1000?436x.2020029
Online First: 2022-06-24
Copyright Information
Authorized by: China Association for Science and Technology
Sponsored by: China Institute of Communications
Editor-in-Chief: Zhang Ping
Associate Editor-in-Chief:
Zhang Yanchuan, Ma Jianfeng, Yang Zhen, Shen Lianfeng, Tao Xiaofeng, Liu Hualu
Editorial Director: Yi Dongshan
Address: F8, You Dian Publisher Building, No.11, Chengshousi Road, Fengtai District, Beijing, China
Post: 100078
Tel: 010-81055478/5481/5480/5362
Email: xuebao@ptpress.com.cn
Email: txxb@bjxintong.com.cn
ISSN 1000-436X
CN 11-2102/TN
Visited
Total visitors:
Visitors of today:
Now online: