Volume 43,Issue 11,2020 Table of Contents

1 Methods of encryption algorithm performance detection oriented to embedded system

KE Yawen , CAI Ting , XIA Xiaofeng , XIANG Hong

2020, 43(11):1-10. DOI: 10.11835/j.issn.1000-582X.2020.11.001

[Abstract](604) [HTML](721) [PDF 658.05 K](836)

Abstract:
Embedded system security is an inevitable requirement for ensuring the security of industrial control systems. However, the cost-limited hardware resources may not be able to effectively support the additional calculation overhead brought by the application of encryption algorithms. In this paper, we focusd on the feasibility of the migration of encryption algorithms for embedded systems and the impact on the system performance. And a performance benchmark method of encryption algorithm for embedded system was proposed to realize the connection between the system side and the cipher side by constructing equivalent metrics. The experiment carried out by this method covered the performance benchmark of encryption algorithms with different configurations including domestic encryption algorithm and lightweight cryptography algorithm with running time delay, throughput and system resource utilization as metrics. The experimental results show that the increase in the encryption algorithm key length will increase the algorithm execution delay, and the increase in the algorithm packet size will accelerate the algorithm's running speed. The performance impact caused by the use of different encryption modes will vary with the encryption algorithm. Direct deployment of encryption algorithm to detect system index values during task execution can simplify the measurement and is more practical than the application of other abstract models in industrial scene.

2 Design of energy efficiency online monitor for MC-WPT system

WANG Zichi , SU Yugang , LI Haoran , WANG Zhihui , FAN Zhonghua

2020, 43(11):11-20. DOI: 10.11835/j.issn.1000-582X.2020.11.002

[Abstract](504) [HTML](703) [PDF 3.33 M](764)

Abstract:
Wireless power transfer (WPT) technology has been applied to many fields of production and life. When the WPT system is running and debugging, the system needs to be monitored to understand the actual working conditions of the system. In this paper, a design scheme of energy efficiency monitor for wireless power transfer system combined with upper computer and lower computer was proposed. The LCC-S magnetic coupling WPT system was used as the monitoring object to analyze the monitoring system requirements. The calculation formulas of the WPT system energy efficiency parameters were given. The hardware and software design method of the lower computer based on STM32 and the upper computer system based on PC and LabVIEW was presented. The experiment results show the proposed design scheme and design method are suited for the energy efficiency online monitor of the wireless energy transmission system.

3 Extended sparse representation for face recognition in feature space

ZHANG Hong , FAN Zizhu , WANG Song , LI Zhengming

2020, 43(11):21-28. DOI: 10.11835/j.issn.1000-582X.2020.11.003

[Abstract](593) [HTML](741) [PDF 1.63 M](622)

Abstract:
Sparse representation for classification (SRC) has attracted much attention in the field of pattern recognition in recent years. If each class has few training samples, SRC usually cannot achieve the desirable recognition performance. To address the above problem, extended sparse representation for classification (ESRC) is proposed,which uses the intraclass variant matrix to supplement the training sample information. Nevertheless, ESRC can hardly capture the nonlinear information in complex data such as images. An extended sparse representation in a feature space for classification algorithm was proposed, in which the original data were mapped into a new high dimensional space through a nonlinear mapping to evaluate the contribution of each training sample in the representation of test sample, and each sample was given a certain weight according to the contribution. Then, the proposed algorithm used the weighted training samples combining the intraclass variant matrix to represent the test samples. Experiments show that the proposed algorithm is superior to other typical sparse representation for classification algorithms.

4 Prediction traffic flow based on teaffic data of urban road check points

LI Hao , ZHANG Shan , CAO Bin , FAN Jing

2020, 43(11):29-40. DOI: 10.11835/j.issn.1000-582X.2020.11.004

[Abstract](2112) [HTML](3118) [PDF 1.64 M](1458)

Abstract:
The prediction of traffic flow can be greatly useful for the work of traffic management departments and the travel planning of drivers. How to make accurate and efficient traffic flow prediction is a very important issue.Traditional traffic flow prediction data sources are usually vehicle speed and driving trajectory which are obtained by arranging traffic sensors on the highway at regular intervals. Although the existing method applied to suburban areas and highways have achieved good results, it can not be used to make the predictions on dense and complicated urban roads for the inconvenience of large-scale deployment of sensors to obtain the required data. This paper proposed a forecasting method by using traffic flow data of urban road checkpoints. We first got the characteristics of cyclic changes in traffic flow by analyzing existing traffic data.Then we extracted corresponding features based on these cyclic changes. Finally we trained traffic flow prediction models suitable for urban checkpoints based on these features. A large number of experiments have been carried out according to real traffic data sets, and the results show that our traffic flow prediction model has a good prediction effect. With RMSE (15.3)and MAPE(7.3) of the predicted values, the accuracy can reach 92.7%.

5 Intranet file encryption system fused with quantum key

WU Jianan , TANG Qi , HE Manli , JIA Wenchang , ZHOU You

2020, 43(11):41-51. DOI: 10.11835/j.issn.1000-582X.2020.11.005

[Abstract](549) [HTML](559) [PDF 3.46 M](683)

Abstract:
With the rapid development of quantum computing technology, encryption technology based on computational complexity is facing a huge threat, and single firewall technology cannot completely prevent hackers from intruding and attacks from the Intranet. The strategy which combines the firewall and quantum private communication technology can solve the above problems effectively. This paper designs a file security system in LAN based on quantum key, using quantum key to encrypt the internal privacy files of the LAN and one-time-pad encryption method can effectively prevent the loss caused by file stolen. The system is composed of two parts:the client software with the file processing unit as the core, and the server with the encryption/decryption information management module as the core component. In order to increase the complexity of ciphertext, the security of key store and the calculation feasibility, this paper proposes three key processing methods:mixed ciphertext splicing, misplaced mixing of weak password and intelligent matching of quantum key, which effectively improve overall security of the system. The effectiveness, security and feasibility of the system are verified by the system function test and network simulation analysis.

6 Recommendation algorithm based on label auxiliary edge optimization

CAI Biao , CHEN Run

2020, 43(11):52-62. DOI: 10.11835/j.issn.1000-582X.2020.11.006

[Abstract](541) [HTML](1065) [PDF 1.97 M](892)

Abstract:
The traditional bipartite recommendation model only considers the historical interaction behavior of users and items. In order to provide more accurate, diverse and interpretable recommendations, it is necessary to fully consider the label auxiliary information and the calculation method of weights on the basis of user-item interactive modeling. This paper proposed a recommendation algorithm (LWV) based on natural language processing for tag similarity auxiliary edge optimization. This method combined user historical behavior and tag assistance information to generate new edges for node interaction between nodes through word2vec and constructed the weight of the edges to update the recommendation list of the basic recommendation algorithm. A comparison between this algorithm and the benchmark algorithm in six public evaluation standards on the public data set shows that the updated recommendation algorithm of LWV achieves a better balance in terms of accuracy, diversity and novelty than the original algorithm.

7 Multi-scale giant panda face detection based on the improved VGGNet architecture

HE Yuxin , ZHENG Bochuan , TAN Dailun , LIU Dan , CAI Qianzhou

2020, 43(11):63-71. DOI: 10.11835/j.issn.1000-582X.2020.11.007

[Abstract](711) [HTML](848) [PDF 8.05 M](1029)

Abstract:
Individual identification of giant pandas is very important for studying their population of them.. Giant panda face detection is the first key step of giant panda individual identification method based on facial images. To solve the problem that the precision of the existing giant panda face detection methods are low, a multi-scale giant panda face detection method based on improved VGGNet-16 architecture was proposed in this paper. Firstly, based on the VGGNet-16 network architecture, a new feature extraction backbone network was constructed through certain improvements such as adding the residual block and BN(Batch Normalization) layer, reducing the channel dimensionality of convolution layer and adopting LeakyRelu active function as well. Secondly, a 3-scale feature pyramid network structure was combined with SPP(Spatial Pyramid Pooling) structure for object detection. Finally, the conventional convolution architecture was replaced with the depwise separation convolution architecture. Experimental results show that the proposed method can achieve 99.48% mAP(mean average recision) in the test dataset, and the detection performance is better than YOLOv4(You Only Look Once Version 4).

8 Detection of gear tooth number and common normal length variation based on computer vision

WU Yongzuo , GE Dongyuan , LI Jian , ZHU Minling , XU Zhibin , YAO Xifan

2020, 43(11):72-83. DOI: 10.11835/j.issn.1000-582X.2020.11.008

[Abstract](812) [HTML](930) [PDF 6.00 M](1127)

Abstract:
Based on the computer vision system, the methods of measuring the teeth number and the length of common normal line of gear was put forward for the first time in gear detection. The polar coordinate transformation algorithm was first used to transform the preprocessed tooth profile sampling data. The tooth profile curve on the circumference was transformed into a horizontal state, and the obtained tooth profile regarded as a sinusoidal curve. The Fourier transform function in the Matlab toolbox was employed to get the fitting expression of the sine curve, and then the ratio of the total number of tooth profile sampling data (i.e., the number of columns) and the period of the fitting function was rounded to obtain the number of teeth of the detected gear. As for the dection of changes of common normal line length, first, the radius and modulus of the tooth tip circle were obtained to get the radius of the base circle, thereby obtaining midpoint and slope at the intersection of the base circle and the tooth profile. The tangent equation tangent to the base circle was obtained by using the point slope equation, and the length of the intersection of the tangent line and the tooth profile spanning k teeth was whose length of the common normal, the length variation whose was obtained according to the difference between the maximum value and the minimum value. By the methods proposed above, the non-contact accuracy detection of gear can be realized, whose accuracy can meet the needs of engineering practice.

9 Constrained fractional-order PSO with self-adaptive neighbors and differential mutators

SU Shoubao , LI Zhi , HE Chao

2020, 43(11):84-98. DOI: 10.11835/j.issn.1000-582X.2020.11.009

[Abstract](532) [HTML](742) [PDF 3.92 M](836)

Abstract:
Fractional order particle swarm optimization (FOPSO) is an improved particle swarm optimization algorithm with trajectories memory. In the multimodal constrained optimization problem, a neighborhood adaptive constrained fractional order particle swarm optimization (NAFPSO) method was proposed to solve the problem that FOPSO was easy to premature and sensitive to the initial parameters. In the algorithm, the positions and velocities of particles in the swarm were updated by the neighborhood topologies adjusted dynamically according to the evolution state of particles, so as to improve the global optimizing ability and convergence speed. Meanwhile, the penalty function with penalty factor was employed to force the particles to approach the feasible area. The differential mutation strategy was designed to increase the swarm diversity and enhance the particle ability to escape from local optimum. 9 constrained benchmarks were used to test the effectiveness and convergence performance of the proposed algorithm, and then it was applied to 2 constrained engineering design problems. Comparison analysis shows that the proposed algorithm has higher optimization ability, faster convergence, higher accuracy and better stability, and can be applied to solve complex constrained engineering design optimization problems effectively.

10 A pattern-based personalized service customization method

CHEN Chunrong , HE Ting , LIAO Yongxin , LI Haibo , XU Hanchuan

2020, 43(11):99-110. DOI: 10.11835/j.issn.1000-582X.2020.11.010

[Abstract](441) [HTML](729) [PDF 0.00 Byte](704)

Abstract:
In the service Internet environment, different requirements may be made simultaneously by different users. It is a great challenge to structure composite service quickly and effectively to fulfill personalized requirements.This paper presented a personalized service customization method based on patterns.The requirement patterns and service patterns from historical service request and service solutions were identified, and the matching relationship between the requirement patterns and service patterns were established. An algorithm called LPSC was proposed to deal with personalized requirements by which personalized requirements were classified according to the similarity between requirements and virtual requirements were constructed to replace them. Then each virtual requirement could be replaced by a limited number of requirement patterns.Through the matching relationship established between requirement patterns and service patterns,we could find optimal service pattern set that suited the requirement patterns. Finally, service solutions could be obtained by the composition of service patterns.Experimental results prove the effectiveness of the proposed algorithm.

11 Study on type analysis and identification of Ethereum Ponzi scheme

YU Wenqiang , ZHANG Yanmei , LI Ziyu , NIU Wa

2020, 43(11):111-120. DOI: 10.11835/j.issn.1000-582X.2020.11.011

[Abstract](1489) [HTML](1960) [PDF 1.62 M](1805)

Abstract:
As the number of investors in the blockchain investment field increases, the impact of Ponzi schemes hidden in smart contracts becomes worse. Although some researchers have begun to pay attention to the Ponzi scheme in the blockchain, most of them remain at the level of detection. This paper will conduct further research on the basis of the existing Ethereum Ponzi scheme detection method, and propose a novel Ethereum Ponzi scheme type identification method. The method is based on the source code and transaction record of the smart contract. By analyzing the extracted keywords, we match the keywords with the source code of the contract to be tested, then combine the logic of the transaction record, and performe a secondary analysis to determine which type of scam the contract belongs to. Experiments on the real dataset of Ethereum show that the classification accuracy of the method can reach 80% compared with the results of manual classification. This study will help researchers and investors better understand the nature of ethereum smart contract ponzi scheme.

12 Three-dimensional interactive decoration design and customization service platform for ceramic products

HU Kaihua , HUANG Hua , ZHANG Yilai , ZHANG Yujing

2020, 43(11):121-136. DOI: 10.11835/j.issn.1000-582X.2020.11.012

[Abstract](565) [HTML](604) [PDF 19.44 M](641)

Abstract:
Now personalized customization has become a fashion and trend, and it has upgraded the brand quality and culture of enterprises.In the new economic era led by big data, enterprises will take the initiative in the new economy if they can timely obtain and meet the personalized needs of different consumers.This paper took the acquisition of users' personalized and customized requirements for ceramic products through the network as case study, in which the components of ceramic products was digitized and stored in the cloud server, realizing online free 3D composite design of ceramic products by Web3D technology. At the same time, the cloud decoration pattern library resources or online independent design of decorative patterns were used for pattern decoration on ceramic products, and the mathematical model of correlation degree between pattern resources and shape was established to help ordinary users to improve the beauty of ceramic product design works. The interactive object model provided by Fabric. js on Canvas element was employed in online interactive decorative pattern design to realize the generation and editing of decorative patterns, and image filter transformation was realized by convolution operation in pattern editing. By establishing the mapping relationship between the design pattern canvas and the ceramic 3D model, the virtual display of ceramic 3D model with strong sense of reality was generated.The research results can be used for online 3D interactive customization and display promotion of ceramic products, which can not only meet consumers' requirements for personalized customization of ceramic products, but also create a new marketing mode for the current ceramic market, so as to achieve the growth of sales.

Home

Volume 43,Issue 11,2020 Table of Contents

Current Issue

Volume

Issue

Most Read

Most Cited

Most Downloaded