Current Issue

20 March 2020, Volume 2 Issue 1

Previous Issue    Next Issue

Regular Papers

Research review and prospect of intelligent dynamic wireless charging system for electric vehicles

Hongye SU, Ze ZHOU, Zhitao LIU, Liyan Zhang

2020, 2(1):  1-9.  doi:10.11959/j.issn.2096-6652.202001

Asbtract ( 1053 )   HTML ( 159)   PDF (4720KB) ( 1134 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

In order to solve the problems of large volume of battery and mileage anxiety,and accelerate application of electric vehicles,dynamic wireless charging system (DWCS) was presented and studied.In this paper,the basic framework of intelligent DWCS for electric vehicles was introduced,and a detailed review of the research results for DWCS by the researchers in the world was described,including the circuit structure and system modeling,electric vehicle positioning,control strategy of DWCS and the interaction with smart grid,etc.Then the intelligent DWCS of electric vehicle was prospected,mainly including system structure and optimization,the integration with the driverless technology,the integration of technologies and the collaborative optimization strategy with power grid and traffic network.The research direction and development trend in the future were also analyzed in this paper.

A survey on vehicle re-identification

Kai LIU, Yidong LI, Weipeng LIN

2020, 2(1):  10-25.  doi:10.11959/j.issn.2096-6652.202002

Asbtract ( 2704 )   HTML ( 2013)   PDF (2568KB) ( 2505 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Given a vehicle image,vehicle re-identification aims to find the same vehicle caught by other cameras,it can be regarded as a sub-problem of image retrieval.In the real traffic surveillance system,vehicle re-identification can play a role in locating,supervising and criminal investigation of target vehicles.With the rise of deep neural networks and the release of large-scale dataset,improving the accuracy and efficiency of vehicle re-identification has become a research focus in the field of computer vision and multimedia in recent years.The vehicle re-identification methods from different perspectives were classified,and the overview,comparison and analysis in terms of feature extraction,design and performance were given in detail,and the challenges and future trends of vehicle re-identification were predicted.

Enhancing alignment with context similarity for natural language inference

Qianlong DU,Chengqing ZONG,Keh-Yih SU

2020, 2(1):  26-35.  doi:10.11959/j.issn.2096-6652.202003

Asbtract ( 388 )   HTML ( 30)   PDF (1252KB) ( 618 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Previous approaches generally use context information to improve the word representation but ignore the importance of context similarity in aligning tokens.Furthermore,most of them uniformly weight various local decisions during aggregation for the global judgment.However,local decisions related to various tokens can influence the final decision differently.In order to process these problems,an enhanced alignment mechanism was proposed,which jointly considers both token content and context similarity in computing the alignment weight for each token pair.Besides,a selection gate mechanism to weight local decisions differently was also proposed.Experimental results show that our performance is comparable to state-of-the-art approaches but better mimics human behavior,making it more interpretable.

Technical analysis of typical intelligent game system and development prospect of intelligent command and control system

Xiangang LI,Qiang LI

2020, 2(1):  36-42.  doi:10.11959/j.issn.2096-6652.202004

Asbtract ( 697 )   HTML ( 90)   PDF (549KB) ( 2247 )   Knowledge map   

References | Related Articles | Metrics

In the future era of intelligence,the massive and heterogeneous battlefield data and the widespread use of unmanned platforms will accelerate the expansion of the combat space from the physical and information domains to the cognitive domains,which will put forward higher requirements for the accuracy,timeliness and effectiveness of command and control,and the intelligence of command and control will become the general trend.Based on the analysis of typical foreign intelligent command and control system,the machine game technology development course was clarified,the challenge of applying machine game technology to intelligent command and control system was analyzed,the future intelligent command and control in combat training,operational innovation and prospective of system architecture and implementation was put forward,so as to provide reference and enlightenment for the future development of command and control system.

Industrial Internet platform based on data engine technology

Da LI,Song ZHENG

2020, 2(1):  43-52.  doi:10.11959/j.issn.2096-6652.202005

Asbtract ( 258 )   HTML ( 22)   PDF (11558KB) ( 534 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

In recent years,the development wave of industrial Internet has attracted great attention from academia and industry.At present,there are still some problems in the development of industrial Internet,such as weak equipment commonality and poor software dynamic reconstruction ability.Based on the above problems,an IAP industrial Internet common platform was designed,which is based on data architecture driving engine technology (data engine) and can achieve data isomorphism and dynamic processing in heterogeneous platforms.At the same time,a test bed for IAP was designed.Through a series of experiments,the characteristic advantages of this platform were demonstrated,which provided a new technical scheme for industrial Internet interconnection.

Process stability modeling and attack protection of industrial control system based on reverse cloud algorithm model

Junhao LIN,Dongqin FENG

2020, 2(1):  53-61.  doi:10.11959/j.issn.2096-6652.202006

Asbtract ( 209 )   HTML ( 17)   PDF (6725KB) ( 365 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Compared with traditional network security defense methods,industrial system security protection research based on process flow has become an important research direction in the field of industrial security.An improved backward cloud algorithm based on first order absolute central moment (BC-1stM) non-deterministic reverse cloud method was proposed,which was modeled by the time series and the normal state of the process flow.The security protection detection and alarm based on the process attack mode in the industrial system was realized,and Tennessee Eastman chemical process platform was adopted to validate the algorithm.The results show that the model had a high precision in the detection of attack behavior and detection of attack points,and improved the security protection capability of industrial systems.

Wind speed-power data cleaning of wind turbine based on improved bin algorithm

Xin WANG,Zhengxia WANG

2020, 2(1):  62-71.  doi:10.11959/j.issn.2096-6652.202007

Asbtract ( 437 )   HTML ( 34)   PDF (9540KB) ( 522 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Wind power is an important indicator of the generating performance of wind turbines,which is of great significance to the operation and management of wind farms.The wind-speed and power data were collected through the monitoring and control (SCADA) system installed in the wind farm.There are a lot of noises in the original data,which brings great challenges to the subsequent application research.Based on the spatial distribution characteristics of wind-speed and power data,wind-speed and power data was divided into three categories,the data preprocessing method bin algorithm was improved,and the method and process of abnormal data identification and cleaning based on district bin(dbin) algorithm were proposed.The experimental results show that the dbin algorithm proposed in this paper is more efficient than the traditional algorithm in identifying abnormal data,and has strong universality.

Research on valid depth data extraction and correction for ToF camera

Xin QIAO,Chenyang GE,Pengchao DENG,Yanhui Zhou,Huimin Yao

2020, 2(1):  72-79.  doi:10.11959/j.issn.2096-6652.202008

Asbtract ( 420 )   HTML ( 27)   PDF (11931KB) ( 405 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

An algorithm was proposed to extract the valid depth information and correct the values of flying pixels with depth map and confidence map for time-of-flight camera.Firstly,the depth map was segmented adaptively based on kernel density estimation and connected component labeling.Then edge detection was performed by using a modified structure tensor to recognize the invalid pixels and the flying pixels.At last,the values of flying pixels were corrected with the bi-cubic interpolation and that of the invalid pixels were deleted by voting.Meanwhile,using augmented confidence,the pixels with wrong depth values were removed.Experimental results show the effectiveness of the proposed algorithm.Comparing with the conventional methods,the proposed algorithm can remove more invalid pixels and remain more valid depth data.Also,the proposed method is more robust to noise.

Stability analysis of commutative quaternion valued neural network with time varying delays

Dongyuan LIN,Xiaofeng CHEN,Wentao SUN,Weikai LI,Yannan XIA

2020, 2(1):  80-87.  doi:10.11959/j.issn.2096-6652.202009

Asbtract ( 310 )   HTML ( 19)   PDF (925KB) ( 549 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Because the traditional quaternion multiplication does not meet the commutative law,a kind of commutative quaternion was introduced,and a commutative quaternion valued neural network (CQVNN) was established,and the asymptotic stability of the CQVNN was studied.In the course of research,the CQVNN were decomposed into four real-valued neural networks.Then,through the topological degree theory,the traditional Lyapunov stability theory and the inequality theory,the conditions for the existence and uniqueness of the equilibrium point of CQVNN and the linear matrix inequality (LMI) conditions for the asymptotically stable of equilibrium point were obtained.Finally,a numerical example was given to verify the validity of the conclusion.

The evaluation of the control measures for COVID-19 based on ACP approach

Liang MA,Mei YANG,Chuan AI,Zhengqiu ZHU,Hailiang CHEN,Mengna ZHU,Wei DUAN,Xiaogang QIU,Xin LU,Bin CHEN

2020, 2(1):  88-98.  doi:10.11959/j.issn.2096-6652.202010

Asbtract ( 376 )   HTML ( 41)   PDF (4713KB) ( 560 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

It is theoretical and practical significance for epidemic prevention and control to evaluate epidemic control measures using information technology so as to guide the implementation of epidemic control measures.Based on ACP approach and statistical data,a platform of computation experiment for artificial city was constructed,from which artificial models were established for three typical places,namely community,school and factory,to support the evaluation of specific epidemic control measures.The control measures of COVID-19 were evaluated through the computational experiments.The results showed that the control measures of quarantine and self-protection could only delay the peak of the number of infected people in the epidemic,but had no obvious effect on reducing the total number of infected people.Only the isolation measure with huge economic cost could significantly inhibit the development of the epidemic.The effect of the isolation measures showed that effectively blocking the “person-to-person”transmission chain was the key to the epidemic control.Therefore,it was recommended to adopt comprehensive means involving inspection and quarantine,big data,artificial intelligence and so on to accurately screen the patients and potential infected people.