Mobile users can open program in new tab for better viewing.

Open program in new tab

Day 1 26/09/2020
Room #1

Welcome speech by the General Chair 08:00 - 09:00

Starts at 9:00 China standard time

Welcome message by Conference Manager 08:05 - 09:00

Welcome message by EAI Community Manager 08:10 - 09:00

Keynote 1: Dr. Khan Muhammad 08:15 - 09:00

Intelligent Video Summary Generation: Current Challenges and Future Directions

Keynote 2: Dr. Gautam Srivastava 08:20 - 09:00

The Future of Blockchain Technology

Coffee break 09:00 - 09:00

Session 1 09:00 - 09:00

09:00 - 09:00
Visual Nondestructive Rendering of 3D Animation Images Based on Large Data

In the visual non-destructive rendering of three-dimensional animation images, the traditional visual non-destructive rendering method is slow, so a visual non-destructive rendering method of three-dimensional animation images based on large data is proposed. The theoretical model of pixel-by-pixel time-domain denoising process is used to denoise, and GPU is used to achieve time-domain consistent processing according to the denoising results. The non-linear Kuwahara filter is used to smooth the three-dimensional animation image, and the first-order differential operator is used to highlight the dramatically changing pixels in the image, so as to detect the edge of the image. After obtaining the distinct contour of the three-dimensional animation image, the non-destructive rendering of the three-dimensional animation image vision is realized. In order to verify the effectiveness of this method, the average rendering speed of the proposed method is 83.2%, which is significantly higher than that of the traditional method. The experimental results show that the average rendering speed of this method is the highest, and the effectiveness of this method is verified.
Authors: Yang ZHANG (Liaoning Communication University), Xu ZHU (Liaoning Communication University),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Research on Collaborative classification of e-commerce multi-attribute data based on weighted association rule model

Because the association between multi-attribute data of e-commerce is not obvious, the traditional collaborative classification method of e-commerce multi-attribute data has the problem of low classification accuracy. Therefore, the weighted association rule model is introduced to realize the optimal design of collaborative classification method of e-commerce multi-attribute data. Firstly, the weighted association rule model is built, and the multi-attribute data is mined and cleaned under the e-commerce platform. Taking the processed e-commerce data as the sample, the multi-attribute data classification index of e-commerce is determined. Through setting project weight, e-commerce data attributes and calculating multi-attribute relevance, multi-attribute data collaborative classifier is obtained. In the weighted association rule model, the collaborative classifier is used to get the multi-attribute data collaborative classification results of e-commerce. Compared with the traditional collaborative data classification methods, it is concluded that the accuracy of collaborative data classification is improved under the e-commerce platform of clothing and food 24.22% 。
Authors: Yi-huo JIANG (Fuzhou University of International Studies and Trade),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Location and Path Planning of Cross-border E-commerce Logistics Distribution Center in Cloud Computing Environment

In order to solve the problem of high transportation cost in the range of transportation distance from 3.5km to 7.5km, this paper proposes a method of location and path planning for cross-border e-commerce logistics distribution center in cloud computing environment. Cross-border e-commerce logistics distribution center location model is established under the cloud computing environment to achieve cross-border e-commerce logistics distribution center location. Cross-border e-commerce logistics path planning is realized by constructing cross-border e-commerce logistics path planning model in cloud computing environment. The logistic path planning model of cross-border e-commerce includes time and event sequence sub-model, state variable quantum model, external information sub-model, state transfer sub-model, objective function and optimal strategy sub-model. In order to prove that the transportation cost of this method is lower in the range of 3.5km to 7.5km, two original methods are compared with this method. The experimental results show that the transportation cost of this method is much lower than that of the other two methods, and the cost is reduced successfully.
Authors: Yi-huo JIANG (Fuzhou University of International Studies and Trade),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Research on Key Performance Evaluation Method Based on Fuzzy Analytic Hierarchy Process

In order to effectively improve the data aggregation of key performance evaluation, a new method of key performance evaluation based on fuzzy analytic hierarchy process (FAHP) is proposed. Based on the three indicators of financial personnel's work efficiency, the utilization rate of financial funds and the overall operation efficiency of finance, the data flow of performance indicators is established according to the current situation of enterprises. Through the comprehensive application of data envelopment analysis and static tree analysis, a comprehensive analysis model is established. According to the boundary performance value, the data flow of indicators is sampled, and the weights of factors are calculated by using the idea of fuzzy hierarchy. Quantification, obtains the final fuzzy evaluation, and achieves the key performance evaluation. Experiments show that compared with traditional key performance evaluation methods, the designed key performance evaluation method improves the data aggregation degree by 29%, and the overall scientificity is stronger.
Authors: Shi-han ZHANG (Shenyang Institute of technology), Gang QIU (Department of Computer Engineering,Changji College/College of Computer Science and Technology,Shandong University),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Research on Data Optimization Method of Software Knowledge Base Operation and Maintenance Based on Cloud Computing

To improve the accuracy of data matching in software knowledge base operation and maintenance, a data optimization method based on cloud computing is proposed. In order to achieve the goal of accurate detection, the steps of anomaly detection of software knowledge base operation and maintenance data are improved, and the optimization of software knowledge base operation and maintenance data is completed. Finally, the experiment proves that the matching accuracy of the software knowledge base operation and maintenance data optimization method based on cloud computing is significantly improved compared with the traditional operation and maintenance method.
Authors: Gang QIU (Department of Computer Engineering,Changji College/College of Computer Science and Technology,Shandong University), Shi-han ZHANG (Shenyang Institute of technology),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Artificial intelligence-based wireless sensor network radio frequency signal positioning method

Aiming at the problem of low positioning accuracy of existing wireless sensor network node positioning methods, a distributed node positioning method based on radio frequency interference is proposed. Analyze the structure of the wireless sensor network, use two anchor nodes to form a radio frequency interference field, and use the movement of one of the anchor nodes to generate the Doppler effect, so that each node can obtain the instantaneous frequency indicated by its low frequency received signal field strength the angle information with the mobile anchor node, combined with the geographic location of the anchor node, the node merges multiple sets of positioning angle information to obtain the optimal position estimate. Simulation results show that the positioning accuracy of this method is significantly improved compared with other positioning methods.
Authors: Dan ZHAO (College of Mechatronic Engineering,Beijing Polytechnic), Ming-fei QU (College of Mechatronic Engineering,Beijing Polytechnic),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Signal collection method of wireless radio frequency gas sensor array based on virtual instrument

The traditional multi-dimensional array tactile sensor research and application can not have the characteristics of flexibility and multi-dimensional force measurement, so there is a big gap in the acquisition of sensor array signal, it is difficult to extract relevant information and make corresponding actions in complex environment. Based on this, a method of wireless RF gas sensor array signal acquisition based on virtual instrument is proposed. By mining the flexible three-dimensional force and temperature composite sensor array numerical characteristics of virtual instrument, the flexible sensitive value of sensor array is improved, and the flexible three-dimensional force sensor array signal acquisition and temperature compensation are designed, so as to effectively reduce the temperature to three-dimensional force detection The influence of measurement can improve the signal acquisition performance of wireless radio frequency gas sensor array. The experiment proves that compared with the traditional dedicated array acquisition method, the wireless RF gas sensor array signal acquisition method based on virtual instruments is easy to implement, flexible to use, and cost-effective, which can be used by researchers for reference.
Authors: Ya-ping Li (College of Mechatronic Engineering,Beijing Polytechnic), Dan ZHAO,
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Research on Feature Extraction Method of UAV Video Image Based on Target Tracking

In order to extract the key and useful features of the target in the UAV video image and strong marking ability, a feature extraction method for the UAV video image based on target tracking is proposed. The sparse beam method is used to adjust the splicing of UAV video images. Based on this, the pixel coordinates are obtained through the frame difference method to detect and locate the target. According to the target detection and positioning results, the video image of the target area is selected and preprocessed by the wavelet transform algorithm Target area video image, and extract the target area video image feature, through hierarchical particle filtering to achieve target tracking, to achieve the extraction of UAV video image feature. The experimental results show that: in the ORL database experiment, the average feature extraction percentage is 78.08%, and the average target tracking error is 1.16; in the COIL-20 database experiment, the average feature extraction percentage is 82.55%, and the average target tracking error is 1.20, which meets the needs of UAV video image feature extraction and target tracking.
Authors: Xin ZHANG (Beijing Polytechnic, College of Mechatronic Engineering), Zhi-jun LIU (Beijing Polytechnic, College of Mechatronic Engineering), Ming-fei Qu (Mechanical and Electronic Engineering School),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Research on abnormal data detection method of power measurement automation system

Aiming at the problems of long time consuming and low accuracy in traditional methods of abnormal data detection in power measurement automation system, this paper studies the methods of abnormal data detection in power measurement automation system.Design the data storage structure table of the electric power metering automation system database, and repair the missing data and denoise the data in the data table. Perform PAA calculation on the data to get the data feature sequence.After the P clustering algorithm pre-clusters the data, the iForest model is used to detect abnormal data to complete the research on the method.The experimental results show that the proposed detection method has the advantages of short detection time and high precision of 91.26-95.67%.
Authors: Ming-fei Qu (Mechanical and Electronic Engineering School), Nan CHEN (College of Mechatronic Engineering,Beijing Polytechnic),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Detection method of abnormal behavior of network public opinion data based on Artificial Intelligence

In order to improve the effect of network public opinion data abnormal behavior detection, an artificial intelligence-based network public opinion data abnormal behavior detection method is proposed. By constructing the network public opinion data model, recognizing the evolution rule of network public opinion data, locating the abnormal data area according to the behavior detection algorithm, and using the probability neural network under artificial intelligence to detect the abnormal data behavior. The experimental results show that the detection method proposed this time is 28.12% and 84.37% higher than the two traditional methods when detecting large-scale public opinion abnormal behavior data. It can be seen that the detection method based on artificial intelligence is not restricted by the volume of network data, and the detection effect is better.
Authors: Ying-jian Kang (Beijing Polytechnic), Lei MA (Beijing Polytechnic), Yan-ning ZHANG (Beijing Polytechnic),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Dynamic monitoring system of big data leakage in mobile network based on Internet of things

Aiming at the problem of large acquisition time synchronization error caused by data explosion in traditional monitoring systems, a dynamic monitoring system for mobile network big data leakage based on Internet of Things is designed. The wireless sensor network is arranged in the system, the multi-channel base station node is designed, and the sensors are arranged in different channels to achieve the purpose of data diversion. Ep3c16q240 chip is selected as the core control chip of the multi-channel base station node, Based on the above hardware design, cluster monitoring, node performance monitoring and job operation monitoring functions are designed to upload the big data status information of the mobile network for job operation monitoring step by step to meet the needs of dynamic monitoring of data leakage. So far the overall design of the system is completed. The experimental results show that: compared with the traditional monitoring system, the designed monitoring system based on the Internet of things has smaller acquisition time synchronization error and better data acquisition synchronization performance.
Authors: Yan-ning ZHANG (Beijing Polytechnic), Ying-jian Kang (Beijing Polytechnic),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Query optimization method for massive heterogeneous data of Internet of Things based on machine learning

In view of the problem that the traditional query optimization method of massive heterogeneous data of the Internet of things can not describe the data characteristics clearly, which results in the long execution time of data query, a query optimization method of massive heterogeneous data of the Internet of things based on machine learning is designed. It divides the massive heterogeneous data query level of the Internet of things, and extracts the data characteristics according to the hierarchical structure and the Dirichlet smoothing method in machine learning. The feature data is transformed into a query tree, and a dynamic data dictionary is constructed. The data dictionary is referred to the traditional query optimization method of massive heterogeneous data in the Internet of things. At this point, the query optimization method for massive heterogeneous data of the Internet of Things based on machine learning is designed. The test link of the construction method shows that the use effect of this method is better than the original method and the method based on artificial intelligence technology.
Authors: Yun-wei LI (Beijing Youth Politics College), Lei Ma (Telecommunication Engineering Institute,Beijing Polytechnic),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Research on host intrusion detection method based on big data technology

When the host runs a large number of applications at the same time under normal activities, the abnormal probability value of the host after the fusion of evidence is large, resulting in false alarms, resulting in a reduction in the final detection accuracy of the detection method. A host intrusion detection method based on big data technology.Using big data processing intrusion detection index weight, sliding window is introduced. According to the number of times of host resource availability anomaly in the time window, the value of anomaly probability is controlled, the index anomaly closed value is determined, and the availability anomaly threshold is set to realize host intrusion detection.The experiment builds a data collection platform and compares the two traditional detection methods with the detection methods studied in the paper. The results show that the detection accuracy of the detection method proposed in the paper is about 98%, and the detection of host intrusion behavior is more accurate.
Authors: Lei Ma (Telecommunication Engineering Institute,Beijing Polytechnic), Hong-xue YANG (Beijing Polytechnic),
Hide Authors & Abstract

Show Authors & Abstract

Lunch break 09:00 - 09:00

30 minutes

Session 2 09:00 - 09:00

09:00 - 09:00
Automatic recognition of tea bud image based on support vector machine

the existing recognition method of tea shoots is only to judge the single color or shape features, resulting in low recognition accuracy. Therefore, an automatic recognition method of tea shoots image based on support vector machine is designed. In this method, two kinds of image features, color and shape texture, are extracted from the tea bud image for discrimination. The RGB model is used to extract color features, and LBP / C operator is used to extract the shape and texture features of the bud. The extracted features are used as the feature vectors of the training samples, and support vector machine model training is carried out to obtain the support vector machine classifier, and the tea bud image is recognized. The results of comparative experiments show that the recognition rate, recall rate and comprehensive evaluation index of the designed method are higher than those of the traditional method, which proves that the designed method has higher recognition accuracy.
Authors: Wang LI (College of Big Data, TongRen University), Rong CHEN (College of Big Data, TongRen University), Yuan-yuan GAO (Changsha Medical College),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Simulation of multi-area integrated energy for cooling, heating and power based on large data analysis

Because the current power supply does not take into account the regional climate cold and hot issues, leading to some areas of power energy supply is greater than demand, waste a lot of unnecessary electricity, power utilization rate is low. To solve the above problems, a multi-area integrated energy dispatching method based on large data analysis is proposed. Firstly, the data warehouse method is used to integrate the supply and demand data of multi-region related comprehensive energy sources, then the integrated data is processed, and then the power demand level is divided based on fuzzy clustering. Finally, the multi-region power is reasonably supplied according to the level, and the comprehensive energy dispatch of cooling, heating and power is completed. The results show that the power supply decreases by 353.534 KW on average and the power utilization ratio increases after the application of the multi-area integrated energy dispatching method based on large data analysis.
Authors: Feng JI (Jiangsu Electric Power Company Research Institute), Shi-hai YANG (Jiangsu Electric Power Company Research Institute), Xiao-dong CAO (Jiangsu Electric Power Company Research Institute), Yong-biao YANG (Southeast University),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Intelligent Control method for load of Multi-Energy complementary Power Generation system

In order to reduce environmental pollution, the load of power generation system becomes an important basis for the balance of supply and demand of power system. Therefore, the intelligent control method of multi-energy complementary generation system load is studied. In the research process, the intelligent control scheme of multi-energy complementary generation system is formulated, the circuit principle of the control method is determined, and the frequency control parameters of the power network, the frequency regulation of the generator set and the control mode of the generator set are controlled. As a result, the whole method is realized through the load control of the load network. It can be proved by experiments that the intelligent control method of multi-energy complementary generation system load can effectively control the load of power generation system.
Authors: Shi-hai YANG (Jiangsu Electric Power Company Research Institute), Xiao-dong CAO (Jiangsu Electric Power Company Research Institute), wei-guo ZHANG (NARI technology Co.Ltd.), Feng JI (Jiangsu Electric Power Company Research Institute),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Dynamic data mining method of cold chain logistics in drug distribution under the background of cloud computing

Because of the huge volume of cold chain logistics data, the traditional data dynamic mining method can not mine the whole local drug circulation data, resulting in the lack of a large number of data mining results, reducing the integrity of the data. Therefore, in the context of cloud computing, a new dynamic mining method is proposed for the cold chain logistics data of drug circulation. Under the cold chain logistics model, the method is further developed by defining the drug circulation mode. The data mining uses cloud computing technology to extract the target data; uses data cleaning, data elimination, data supplement and data conversion to preprocess the target data; according to the association rules between the acquired data, realizes the dynamic mining of cold chain logistics data information. Experiments show that, compared with the traditional methods, the proposed mining method can find the target data in the huge cold chain logistics data, and achieve all the data mining. It can be seen that the data mining method proposed in this paper has higher data integrity.
Authors: Meng-li RUAN (Shandong Management University), Zhi-Yu ZHUO (Shandong Management University),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
An evaluation of the intervention effect of Autonomous English learning motivation based on Knowledge Map

In the past, the evaluation method of the intervention effect of Autonomous English learning motivation was not fluent because of the lack of correlation between autonomous learning ability and motivation factors. Therefore, this paper proposes an evaluation of the intervention effect of Autonomous English learning motivation based on knowledge map. Based on the different degree of connection, the knowledge map of self-learning ability and motivation factors is constructed. Combined with motivation intervention, the evaluation index of intervention effect is determined, the weight of different indexes is calculated, the comprehensive score is calculated for the index assignment, and the evaluation of intervention effect is realized by combining the intervention effect evaluation grade table. The experimental results show that compared with the traditional methods, the designed method based on knowledge map has better fluency.
Authors: Zhi-Yu ZHUO (Shandong Management University), Meng-li RUAN (Shandong Management University),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Hyperspectral recognition and early warning of rice diseases and insect pests based on convolution neural network

The traditional method of disease and pest recognition uses SVM to classify and recognize the image. Because of the large training convergence error, the recognition accuracy is not high. In view of the above problems, the paper studies the method of rice hyperspectral pest identification and early warning based on convolution neural network. By reducing the dimension of the collected spectral image, we can get more image information and extract image features. Based on alexnet, the structure of convolutional neural network is designed. The recognition database was established by collecting the spectrum images of rice diseases and insect pests, and the convolution neural network was trained by transfer learning, so as to realize the recognition and early warning of rice diseases and insect pests. The experimental results show that the convergence error of the method based on convolution neural network is small and the recognition accuracy is higher.
Authors: heng xiao (Sanya University), Cao-Fang LONG (Sanya University),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Online monitoring method of big data load anomaly based on deep learning

In the process of monitoring the abnormal load of big data in network behavior, more network traffic resources are consumed, which leads to the low efficiency of its operation. Therefore, an on-line monitoring method for the abnormal load of big data in network behavior based on deep learning is proposed. The online monitoring model of load anomaly is established, the network data distribution is analyzed, and the adaptive random link configuration is adopted to improve the channel balance and the positioning ability of the abnormal load. The load anomaly is identified through the load pattern and the online monitoring is completed. The experimental results show that the proposed method consumes about 50% of the traffic of the traditional method, which can effectively reduce the traffic consumption and improve the utilization rate of network resources. This method is more suitable for online monitoring of big data load anomalies in network behavior.
Authors: Cao-Fang LONG (Sanya University), heng xiao (Sanya University),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Simulation analysis of building energy consumption based on big data and BIM technology

In order to solve the problem of discrepancy between simulation results and measured results of building energy consumption simulation and analysis, a method based on big data and BIM technology is designed. The 3D building information model is constructed by BIM technology, and the factors affecting building energy consumption are obtained. The building energy consumption is simulated and predicted by heat balance method and Design Builder. Finally, data mining technology is used to modify the prediction results, and static energy analysis method is used to analyze the revised results. So far, the design of building energy consumption simulation and analysis method based on big data and BIM technology is completed. Compared with the original method, the simulation results of this method are close to the measured ones. In summary, the energy consumption simulation ability of this method is better than the original method.
Authors: Xiao MA (CCTEG Chongqing Engineering Co.,Ltd), Xin QIU (CCTEG Chongqing Engineering Co.,Ltd.),
Hide Authors & Abstract

Show Authors & Abstract

Coffee break 09:00 - 09:00

Session 2 (continued) 09:00 - 09:00

09:00 - 09:00
Research on intelligent investment prediction model of building based on support vector machine

In view of the imperfection of intelligent construction cost specification, the complexity of cost influencing factors and the lack of historical cost data, the expert system and support vector machine theory are combined to achieve knowledge acquisition and data integration. By using the expert system module, the regression calculation, the establishment of project cost prediction model and the model test of parameter setting and optimization are realized. In addition, the investment prediction speed of the model is faster. Finally, through the empirical data analysis, the accuracy and effectiveness of the model are verified, which provides the economic indicators and reference materials for the design stage of intelligent building projects.
Authors: Yuan-ling MA (CCTEG Chongqing Engineering Co.,Ltd.), Run-lin Li (CCTEG Chongqing Engineering Co.,Ltd.), Xiao MA (CCTEG Chongqing Engineering Co.,Ltd),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Online monitoring method for hazard source of power system network based on mobile internet

In the power system network, aiming at the low accuracy of traditional network hazard online monitoring method, an online monitoring method for hazard source of power system network based on mobile internet is proposed. Based on mobile internet, a power system network communication is constructed. The model uses this model to collect dangerous source data. After the hazard data is collected, the WAMS system is used to calculate the relative residuals of the hazard source data, and then the relative residuals are used to identify the hazard source parameters, and the branch with the hazard source parameters is present. The traveling wave positioning network is used to locate the dangerous source. After the hazard source is located, the hazard source is monitored online by the hazard source indicator. Under the condition that the experimental environment is the same, the method is compared with the online hazard source online monitoring method based on feature recognition technology and the online hazard source online monitoring method based on communication message parsing. The monitoring accuracy of these three methods is improved. The results are 41.1%, 68.8%, and 94.5%, respectively. The experimental results show that the monitoring accuracy of this method is higher than the traditional online hazard source online monitoring method, which proves the superiority of the method.
Authors: Jie-sheng ZHENG (Guangdong Power Grid Corporation Information Center), Bo-jian WEN (Guangdong Power Grid Corporation Information Center), Wen-bin LIU (Guangdong Power Grid Corporation Information Center), Guang-cai WU (Guangdong Power Grid Corporation Information Center), Shang Gao (Guangdong Power Grid Corporation Information Cente),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Analysis of Intelligent Monitoring Model of Network Security Situation Based on Grid Power Flow

In order to introduce the grid power flow model to intelligently monitor the network security situation, a model based on grid power flow is established.In the construction of the network security situation intelligent monitoring system, the hierarchical database is protected and managed, the attacks brought by the network security situation are changed, and the network security situation level protection system is improved and improved. On this basis, the network trend correction factor is introduced, and the network security situation is normalized according to the network security situation value. The network information flow is processed uniformly, and the intelligent monitoring model of network security situation based on power flow is built.Compared with the traditional network security situation intelligent monitoring model, the application of network security situation intelligent monitoring model can effectively solve the uncertainty and fuzziness of information provided by various network security devices.
Authors: Shang GAO (Guangdong Power Grid Corporation Information Center), Shou-ming CHEN (Guangdong Power Grid Corporation Information Center), Yun-de LIANG (Guangdong Power Grid Corporation Information Center), Yan-qian LU (Guangdong Power Grid Corporation Information Center), Jie-sheng ZHENG (Guangdong Power Grid Corporation Information Center),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
An Optimal Tracking Method for Moving Trajectory of Rigid-Flexible Coupled Manipulator Based on Large Data Analysis

The manipulator has dynamic characteristics, and the trajectory tracking system of the manipulator has non-holonomic constraints and various uncertainties, which makes tracking control of the mobile manipulator more difficult. There is a big error in tracking a rigid flexible coupling manipulator with a single neural network. A new method for trajectory optimization tracking of a rigid-flexible coupled manipulator based on big data analysis is proposed. This method takes neural network as the research object, introduces fuzzy control into neural network, optimizes a single neural network, forms a composite method of fuzzy neural network, and uses a hybrid method to track the trajectory of the manipulator. Experimental results show that the tracking error of this method is less than 0.035 rad, which improves the tracking efficiency and improves the tracking accuracy. The method can complete the operation faster and more accurately according to the predetermined trajectory, and has higher practical applicability.
Authors: Fu-Jian YANG (Guilin University Of Aerospace Technology), Tao WEI (Northwestern Polytechnical University),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Fast Recognition of Multi-Combination Target Features in Motion Image Based on Large Data Analysis

In order to overcome the low efficiency of traditional recognition technology, a fast recognition method of multi-combination features of moving images based on large data analysis is proposed.Based on feature extraction of multi-combination target, denoising of moving image and determination of Boolean correlation coefficient, fast recognition of multi-combination target feature of moving image under large data analysis is realized.The experimental data show that the proposed recognition method can not only effectively improve the efficiency of traditional recognition technology, but also make the recognition result more stable, and enhance the adaptability and flexibility of image recognition technology.
Authors: Tao WEI (Northwestern Polytechnical University),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Study on the dynamics of virus propagation in combination with big data and kinetic models

With the continuous development of science and technology, in the context of current big data, the research on the law of traditional virus propagation dynamics had been developed to the bottleneck. The traditional law of virus propagation dynamics was less sensitive and the mathematical model was not easy to operate. Therefore, it was proposed to study the dynamics of viral propagation based on the combination of big data and kinetic models. The model was established by using differential equations and so on, and the accurate prediction law of virus propagation dynamics was completed by experimental tracking control. A graph of the number of patients over time was obtained by bringing the problem into the model, and the changes in the model results were derived from this graph. In this way, corresponding countermeasures was drawn based on the changes in the results. Finally, through simulation experiments, it was proved that the combination of big data and kinetic model of viral propagation kinetics scientifically and accurately studied the laws of viral propagation dynamics. The established mathematical model was easy to operate and had a good guiding significance for practice.
Authors: Guo-bin ZENG (Haikou university of Economics), Yan-ni CHEN (Haikou university of Economics),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Research on Electricity Characteristic Recognition Method of Clean Heating Based on Big Data Model

Because the traditional coal-fired heating mode consumes a lot of energy and is harmful to the environment, it produces a clean heating mode using electric energy, which is realized by energy storage heating equipment.The operation of energy storage heating equipment needs to be planned according to the electricity characteristics of clean heating. Therefore, a method based on large data model is proposed to integrate the electricity characteristics of clean heating using Hadoop platform. Then, according to the integrated data, the electricity load characteristics, electricity consumption characteristics, electricity consumption cycle characteristics and regional characteristics are identified to complete the electricity characteristics of clean heating. Farewell.Through experimental demonstration, it is proved that this method can effectively identify the electrical characteristics of clean heating and accurately predict the future heating data.
Authors: Xin-lei WANG (State grid economic and technological research institute co. LTD), Jia-song LUO (State grid economic and technological research institute co. LTD), Tong XU (State grid economic and technological research institute co. LTD), Guo-bin ZENG (Haikou university of Economics),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Text classification feature extraction method based on deep learning for unbalanced data sets

In order to fully realize the classified search of text data information, a text classification feature extraction method for imbalanced data sets based on deep learning is proposed. With the help of trestle automatic encoder and depth confidence network, the preliminary definition of text semantic category conditions is completed, and the text semantic classification processing based on depth learning algorithm is realized. On this basis, pre-processing and debugging of text parameters are implemented, and the dimensionality reduction standards related to the text features of the data set to be extracted are established through the expression of the characteristic behavior. The experimental results show that with the application of the new classification feature extraction method, the number of correctly classified documents starts to increase substantially, which meets the practical application requirements for the classification and search of text data information.
Authors: Li LIN (School of Computer Engineering, Jimei University), Shu-Xin GUO (Jilin University of Finance and Economics),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Research on Voluntary Intelligent Reporting System of College Entrance Examination Based on Big Data Technology

The college entrance examination application is a complex system project, which needs to collect many kinds of information. Aiming at the deficiency of the system research based on the analysis of the domestic mainstream platform, the reference system and Sina simulation system of college entrance examination application, the intelligent application system of college entrance examination application is designed based on big data technology. Considering the scores of examinees, the enrollment plan of colleges and universities, the enthusiasm of application, the prospect of professional development and other factors, the hardware structure of the intelligent filling system for college entrance examination is constructed. Through big data analysis and data mining, a large amount of real and valuable information for college entrance examination filling can be provided for the majority of examinees. It can be seen from the experimental verification results that the system fills in accurate results and has an ideal filling effect, which helps the candidates to apply for the ideal school and improve the admission rate.
Authors: Shu-xin GUO (Jilin University of Finance and Economics), Li LIN (School of Computer Engineering, Jimei University),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Visual Reconstruction of Interactive Animation Interface based on Web Technology

The human perception that more than 80% of the external information is visually acquired, therefore, in the interactive animation interface design, the visual effect is very important. In this background, an interactive animation interface visual reconstruction method based on Web technology is proposed. The method is mainly described by two aspects, firstly, the related description is carried out on the Web technology, and then the visual reconstruction of the interactive animation interface is realized by using the technology, and the method comprises the visual feature extraction, the visual feature matching and the visual feature 3D reconstruction. The results show that, after the visual reconstruction, the visual effect of the interactive animation interface is improved, and the visual existence in the design of the interactive animation interface is solved. The problem.
Authors: Xu ZHU (Liaoning Communication University), Yang ZHANG (Liaoning Communication University),
Hide Authors & Abstract

Show Authors & Abstract
Day 2 27/09/2020
Room #1

Session 3 09:00 - 09:00

09:00 - 09:00
Mobile Communication Network Channel Allocation Method Based on Big Data Technology

Aiming at the problems of inaccurate allocation results and high bit error rate of traditional channel allocation methods, a channel allocation method based on big data technology is proposed and designed. This method makes use of the advantages of big data technology to discretize the channel data of mobile communication network. According to the requirements of the channel discretization standard and allocation algorithm of mobile communication network, it optimizes the channel allocation algorithm and realizes the effective channel allocation of mobile communication network. The validity of big data channel allocation method is confirmed by experimental demonstration and analysis. In the mobile communication network channel allocation, the allocation accuracy is high, and the allocation error is almost zero, which is better than the traditional method. It shows that this method can realize the effective allocation of mobile network channel, and the allocation result is very reliable, which can guarantee certain network security.
Authors: Feng JIN (Information and Communcition College National University of Defense Technology), Bing LI (Information and Communcition College National University of Defense Technology), Ying LI (Information and Communcition College National University of Defense Technology), Shi WANG (crrc qingdao sifang co.,ltd),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Research on Electric Drive Control Method Based on Parallel Computing

In order to solve the problems of low control accuracy and poor stability existing in the traditional electric drive control method, the electric drive control method based on parallel calculation is proposed. According to the selected motor parameters , make the parameters equal to the load ratio of the load distribution motor, and use parallel calculation to complete. The load distribution; generate an air gap magnetic field inside the motor, use coordinate transformation and space vector concepts to control the motor vector, and complete the Electric drive control . The experimental results show that the control accuracy of the proposed method is high. It can effectively reduce the position tracking error and improve the control accuracy.
Authors: Lin-ze GAO (Guilin University Of Electronic Technology),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Design of big data control system for electrical automation

The traditional big data control system is limited by hardware and software resources, which leads to low efficiency of data access and calculation. Therefore, a big data control system for electrical automation is designed.The system is mainly designed from two aspects of hardware and software. The hardware mainly designs a digital acquisition circuit, selects the model of each part in the overall working module of the acquisition board, and designs a pseudo dual-port RAM to store data, which is convenient for the processing of massive data and Control; in software design, according to the needs of the system, light MySQL and distributed HBase are used to jointly design the ER diagram and database table of the database user database to make the database performance more optimized. In the control algorithm of the system, the butterfly operation is used and optimized Calculate the speed, obtain the operation error through the operation and correct it to ensure the efficiency of the system operation.The experimental results show that the performance of the designed system is better than the traditional system in data insertion speed, access speed and calculation speed, which fully verifies the application value of the system.
Authors: Lin-ze GAO (Guilin University Of Electronic Technology),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Research on Dynamic Assignment of Distributed Tasks Based on Improved Contract Network Protocol

This paper introduces the basic idea and operation mechanism of contract network. In view of its shortcomings, it introduces an agent mental model and proposes a distributed task allocation algorithm based on improved contract network protocols. The algorithm improves the bidding process and the bidding process, reduces the system communication volume and fully considers the status information of the drone itself. Finally, a simulation experiment is designed to compare and analyze the advantages of the improved contract network over the traditional contract network.
Authors: Jinglong Wan (School of Aeronautics, Northwestern Polytechnic University), Zhili Tang (School of Aeronautics, Northwestern Polytechnic University),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Target tracking algorithm for multi-channel information transmission in large data environment

The traditional single channel information transmission algorithm neglects the real-time control of the transmission data, which leads to the low accuracy of signal transmission. For this reason, a target tracking algorithm for multi-channel information transmission in large data environment is proposed. The algorithm solves the echo signal of each point, determines the transmission range of multi-channel information, optimizes decoding algorithm by using interruption mechanism, and obtains the location of each point data by classifier classification, so as to realize multi-channel information transmission target tracking. Experiments show that the multi-channel information transmission target tracking algorithm has high information transmission efficiency in large data environment.
Authors: Xiao-gang ZHU (NanchangUniversity School Of Software), Zhi-wei YU (State Grid Jiangxi Electric Power Co., Ltd.), Tao LEI (South China Normal University),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Research on Adaptive Segmentation Algorithm of Image Weak Target Based on Pattern Recognition

Based on the comprehensive research of image segmentation technology, an adaptive segmentation algorithm based on pattern recognition for image weak targets is proposed. By systematically designing the image segmentation algorithm by analyzing the algorithm requirements and principles, the modules such as image preprocessing, weak target detection, image feature extraction and adaptive threshold selection are designed and implemented according to the algorithm implementation flow. In order to verify the experimental performance of the algorithm, the experimental analysis shows that the adaptive image segmentation algorithm is used to preserve the details of the image and improve the quality of the segmented image.
Authors: Tao LEI (South China Normal University), Xiao-gang ZHU (NanchangUniversity School Of Software),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Research on Real-time Monitoring Method of Communication Network Blocking Based on Cloud Computing

Aiming at the problems that the traditional method has long response time to communication network congestion monitoring and the detection effect is not ideal, a real-time monitoring method based on cloud computing for communication network blocking is proposed.Firstly, the communication network monitoring point is established, and the communication data collection process is completed by the radio-frequency receiver. On this basis, the real-time traffic calculation of the collected data is performed to determine the existence of abnormal blocking status in the communication network link, and the precise positioning of the blocking point is obtained. The information thus generates an alarm message to obtain a monitoring result.The real-time and accuracy of the monitoring method are analyzed experimentally. It is found that the monitoring method can control the delay time within 0.2 seconds and the monitoring error rate is low. It can be seen that the monitoring algorithm has high performance.
Authors: Wei-yan LI (College Of Information Science And Engineering,Shandong Agricultural University), Kui GAO (College Of Information Science And Engineering,Shandong Agricultural University), Yu LI (College Of Information Science And Engineering,Shandong Agricultural University), Pei-ying WANG (Tianhe College of Guangdong Polytechnical Normal University),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Deployment optimization of perception layer nodes in the Internet of Things based on NB-loT Technology

The traditional deployment optimization method of perception layer nodes in the Internet of Things has the drawbacks of poor optimization performance. Therefore, this paper proposes a research on deployment optimization of perception layer nodes in the Internet of Things based on NB-loT technology. The genetic algorithm is used to code the nodes in the perception layer of the Internet of Things, and the initial population is determined. Based on the coding of the nodes in the perception layer and the initial population, the fitness function is designed, and the NB-loT technology is used to optimize the deployment of the nodes in the perception layer of the Internet of Things. Experiments show that the average coverage of the proposed method is 24% higher than that of the traditional method, which shows that the proposed method has better optimization performance.
Authors: Rui LIU (STATE GRID LIAONING ELECTRIC POWER SLWPLY CO.LTD), Jie-ran SHEN (STATE GRID LIAONING ELECTRIC POWER SLWPLY CO.LTD), feng JIAO (STATE GRID LIAONING ELECTRIC POWER SLWPLY CO.LTD), Ming-hao DING (Department of computer and software technology, Tianjin Electronic Information College),
Hide Authors & Abstract

Show Authors & Abstract

Coffee break 09:00 - 09:00

Session 3 (continued) 09:00 - 09:00

09:00 - 09:00
Design of Short-term Network Congestion Active Control System Based on Artificial Intelligence

In order to solve the problem that the total amount of the congestion data is large and the distribution of the main control nodes is not uniform, the short-term network congestion active control system based on the artificial intelligence is designed. In that congestion control frame, the network motor and the congestion control node are connecte, and the hardware operation environment of the system is built. On the basis of this, a good artificial intelligence node control strategy is used to determine the congestion process and to improve the logic control standard, and the software running environment of the system is set up and combined, and the design of the short-term network congestion active control system based on the artificial intelligence is completed. The experimental results show that the short-term network based on artificial intelligence is applied in comparison with the common control technology. After the design of the congestion active control system, the total amount of congestion data decreases obviously, and the master node presents an idealized uniform distribution state.
Authors: Shuang-cheng JIA (Alibaba Network Technology Co., Ltd), Feng-ping YANG (Alibaba Network Technology Co., Ltd.),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Efficient Feature Selection Algorithm for High-Dimensional Non-Equilibrium Big Data Set

When the traditional algorithm is used to calculate the feature classification of high-dimensional non-equilibrium and large data set, it is easy to appear the problem of low accuracy and recall rate of feature selection. Therefore, a feature selection algorithm based on granular fusion is designed. By using the regularization feature of the data, the original big data aggregate is transformed into a small-scale data subset. On the basis of this, the feature selection function of the data particle is obtained. Finally, the weight fusion calculation of each feature subset is carried out. The feature classification of high-dimensional non-equilibrium big data set is realized. The experimental results show that the feature selection algorithm based on granular fusion can realize the feature selection and recall of high dimensional unbalanced data sets. The accuracy of the method is higher than that of the traditional method, which shows that the method is feasible and effective.
Authors: Shuang-cheng JIA (Alibaba Network Technology Co., Ltd), Feng-ping YANG (Alibaba Network Technology Co., Ltd.),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Design of 3D image feature point detection system based on artificial intelligence

Aiming at the problems of low efficiency and accuracy in the traditional 3D image feature point detection system, an efficient 3D image feature point detection system based on artificial intelligence is designed. Firstly, the whole frame of the system is designed. Then the hardware system is designed, including the development board, peripheral equipment and interface, basic engineering reconstruction and feature point detection unit. Then the software system is designed, including image collection module, image feature point display module. Image feature point processing module, image feature point extraction module, image feature point description module, and using the combination of hardware system and software system to achieve three based on artificial intelligence Dimension image feature point detection system. Finally, the effectiveness of the 3D image feature point detection system based on artificial intelligence is verified by experiments, and the detection efficiency and accuracy are much higher than the traditional methods. This study lays a foundation for the further study of images.
Authors: Peng HE (Center of Engineering Practice Training, Tianjin Polytechnic University),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Design of Urban Air Quality Monitoring System Based on Big Data and UAV

In order to effectively evaluate China's air quality and provide technical support for maintaining a good atmospheric environment, the design scheme of urban air quality monitoring system based on big data and drone is studied. In the research process, a system hardware environment including a drone platform, an air quality sensor and anti-jamming equipment was constructed, which provided the basis and support for the development of system software. In the software design, the monitoring terminal program and the air quality information acquisition module are designed according to the system requirements, and the data received by the drone is restored, analyzed and stored and managed by the data multi-thread receiving module. The experimental results prove the effectiveness of the urban air quality monitoring system based on big data and drone. Applying the system to actual monitoring is beneficial to better analysis of the atmospheric environment and better maintenance of the atmospheric environment.
Authors: Ying ZHAO (Nanchang Institute of Science and Technology), Peng-yao SHI (Nanchang Institute of Science and Technology /Nanchang Key Laboratory of VR Innovation Development and Application), Wen-hao GUO (Suzhou University of Science and Technology, Business School),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Null Value Estimation of Uncertainty Database Based on Artificial Intelligence

Due to the complexity of the objective world, information loss and uncertainty are common. As a tool to express the real world, database uses null values to express the problem of information missing. Aiming at the problem of null value in uncertain database, an artificial intelligence based null value estimation algorithm is proposed. Firstly, the characteristics of uncertain database are analyzed, then the lost information retrieval model is constructed, and the empty value estimation of database is completed by feature selection and data transformation, artificial intelligence clustering, influence degree calculation, empty value step estimation and other methods. Finally, it analyses the time complexity of the algorithm, and improves the problem of poor evaluation effect of traditional algorithms. Supported by experimental data and environment, the results show that the proposed algorithm has higher accuracy than the traditional algorithm. It shows that this algorithm can effectively estimate the null value in the uncertain database, and has high practical application value, and can provide theoretical reference value for related research.
Authors: Shuang-cheng JIA, Feng-ping YANG (Alibaba Network Technology Co., Ltd.),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Research on Fuzzy Clustering Algorithms for Large Dimensional Data Sets under Cloud Computing

With the rapid development of modern computer technology, the Internet technology based on computer technology has also been remarkably developed, which has made great progress in modern information technology. Every day, people will produce and obtain a large amount of data information. The management and effective application of these large-scale data has become the main trend of the development of modern society. In order to improve the ability of fast processing and recognition of large data, data clustering analysis is needed. Aiming at the problems existing in traditional fuzzy clustering algorithm, this paper proposes a design of fuzzy clustering algorithm for high-dimensional and large data sets under cloud computing. Through data classification and data processing classification, the design of fuzzy clustering algorithm for high-dimensional large data sets is realized, and compared with the traditional algorithm through experiments. The simulation results show that the method is easy to calculate and fast in the fuzzy clustering of high-dimensional and large data sets. The clustering effect is good, and the clustering algorithm of high-dimensional and large data sets is well realized.
Authors: Shuang-cheng JIA, Feng-ping YANG (Alibaba Network Technology Co., Ltd.),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Statistical analysis of catalytic removal of soot particles based on big data

Different temperature, power, flow rate and other factors have different effects on the removal of soot particles in the tail gas of simulated diesel vehicles, and the removal effect of each kind of soot particle catalytic removal method is also different. In order to further improve the effect of soot particle catalytic removal, a statistical analysis method of soot particle catalytic removal method based on big data is designed. Using large data technology to extract catalytic removal methods of soot particles, detailed analysis of each method was carried out, and the soot combustion performance of soot particles catalytic removal method was compared. The results showed that the removal of soot particles based on perovskite catalyst was more effective than that of soot particle removal method based on sol-gel preparation method, and that soot particles were catalyzed by low temperature plasma. The combustion performance of the removal method is better, and the catalytic removal performance is more superior.
Authors: Xiu-hong MENG (Guangdong University of Petrochemical Technology), Ping YANG (Guangdong University of Petrochemical Technology), Hui-bo QIN (Guangdong University of Petrochemical Technology), Lin-hai DUAN (Guangdong University of Petrochemical Technology),
Hide Authors & Abstract

Show Authors & Abstract

Lunch break 09:00 - 09:00

30 minutes

Session 4 09:00 - 09:00

09:00 - 09:00
Design of temperature measurement and control system of chemical instrument based on Internet of things

The traditional temperature measurement and control system of chemical instruments can not accurately grasp the basic condition of temperature data, resulting in low efficiency of measurement and control. Therefore, a temperature measurement and control system of chemical instruments based on the Internet of things is designed. According to the relevant performance of the hardware components of the system, the system information of the control center is studied, and the correlation of the internal system is studied. Based on this, the command of hardware mode transformation is executed. After the hardware design is realized, the system software design is realized on the premise of hardware data. Combined with the measurement and control algorithm, the measurement and control mode of the center is continuously studied, the data difference between the systems is adjusted, and the contradiction between the measurement and control data is avoided Complete the overall system design operation. The experimental results show that the design of temperature measurement and control system of chemical instrument based on Internet of things has higher measurement and control efficiency and shorter measurement and control time.
Authors: Xiu-hong MENG, Shui CAO (Guangdong University of Petrochemical Technology), You-hua ZHANG (Guangdong University of Petrochemical Technology), Lin-hai DUAN (Guangdong University of Petrochemical Technology),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Design of Intelligent lifting system for Real-time Monitoring data expansion in Distribution Station area

In view of the fact that the monitoring data in large-scale distribution network has the characteristics of quantifiable, real-time, dynamic and so on, and the data storage capacity is insufficient, this paper puts forward the design of the real-time monitoring data expansion intelligent upgrading system in the distribution station area. Realizes the monitoring data expansion capacity intelligence enhancement. Through designing the hardware module of expanding capacity and installing the data acquisition interface, the hardware design of intelligent upgrading of monitoring data expansion capacity is realized. On this basis, the hierarchical extended storage mechanism is used to store the data node information. The real-time reading and querying function of the data is realized, and the capacity ratio of the monitoring data is calculated. Finally, the intelligent upgrading system of the real-time monitoring data expansion capacity is realized.
Authors: Xin-jia LI (Jiangsu Fangtian Power Technology Co., Ltd), Cheng-liang WANG (Jiangsu Fangtian Power Technology Co., Ltd.), Yong-biao YANG (Southeast University), Song SHU (Changjiang Polytechnic),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Intelligent Authentication method for trusted access of Mobile nodes in Internet of things driven by Cloud Trust

In order to solve the problem that traditional cloud trust-driven mobile nodes in the Internet of Things lack credible authentication, a cloud trust-driven intelligent authentication method for trusted access of mobile nodes in the Internet of Things is proposed. The mobile nodes in the Internet of Things are determined based on cloud trust-driven, relying on the processing of mobile nodes in the Internet of Things and the intelligent authentication of trusted access of mobile nodes in the Internet of Things. The cloud trust-driven Internet of Things migration is realized. Mobile node trusted access intelligent authentication. The experimental data show that the proposed intelligent authentication method can not only improve the credibility of the traditional authentication method, but also simplify and standardize the authentication process. It enhances the adaptability and flexibility of trusted access authentication of Internet of things driven by cloud.
Authors: Song SHU (Changjiang Polytechnic), Xin-jia LI (Jiangsu Fangtian Power Technology Co., Ltd),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Micro image surface defect detection technology based on machine vision big data analysis

The traditional micro image surface defect detection system had slower running speed and less detection precision, which made the detection system operate inefficient and could not meet the requirements of small image surface defect detection. To this end, the optimization design of the micro image surface defect detection system based on machine vision-based big data analysis was carried out. The system design was optimized with MATLAB 7.0 programming environment; MATLAB technology was used to process small images to visualize calculation results and programming; The filtering of the micro image was detected by the method of spatial domain filtering to complete the detection task of the surface defect of the micro image. The design method was validated and the test data showed that the micro image surface defect detection system ran faster and the detection was more precise. The detection accuracy was 92% and the detection quality was high.
Authors: Chao SU (Qingyuan Power Supply Bureau of Guangdong Power Grid Co.,Ltd.), Jin-lei HU (Qingyuan Power Supply Bureau of Guangdong Power Grid Co.,Ltd.), Dong HUA (Guangdong Jun & hua Energy Technology Co., Ltd.), Pei-yi CUI (Guangdong Jun & hua Energy Technology Co., Ltd), Guang-yong JI (Yantai Vocational College of culture and Tourism),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Research on Structural Optimization of Reinforced Concrete Frame Based on Parallel Cloud Computing

In order to solve the problems of excessive wear and poor bearing capacity of reinforced concrete frame, the optimization of reinforced concrete frame structure is studied with cloud computing method. The bearing capacity and related parameters of reinforced concrete structure are calculated by cloud computing method, and the support degree and potential structural wear displacement range of reinforced concrete frame structure are obtained. According to the calculation results, load parameters of building concrete structure are regulated and adjusted. The reinforced concrete frame with X-type braces is strengthened by combining with the standard parameters, and the reinforced concrete frame connection is established. The orthogonal intersection model of the bearing capacity of the structure can effectively complete the optimization study of the reinforced concrete frame structure. Finally, the experiment proves that the research of RC frame structure optimization based on parallel cloud computing has better bearing capacity and anti-wear performance than the traditional RC frame structure, and fully meets the research objectives.
Authors: qiansha LI (School of Civil Engineering and Hydraulic Engineering Xichang University), Qian HE (School of Civil Engineering and Hydraulic Engineering Xichang University,),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Research on Active Disturbance Rejection Method of Mobile Communication Network Nodes Based on Artificial Intelligence

With the increasingly complex network environment and the interference of various other radio waves, the quality of mobile communication network is seriously affected. Aiming at the above problems, this paper studies an auto-disturbance rejection method for mobile communication network nodes based on artificial intelligence. According to artificial intelligence, an interference identification analysis model is constructed, which is used to identify and analyze the interference factors of mobile communication network nodes. Based on the recognition results, the characteristics of different interference types are summarized, and the interference problem is accurately judged. Then, the anti-interference work of mobile communication network nodes is completed by checking and processing the results. The experimental results show that the user is more satisfied with the quality of the mobile communication processed by this method than the traditional method of UAI participating in the identification and analysis of interference factors, which proves that this method is effective in anti-jamming and can meet the needs of users.
Authors: Bing LI (Information and Communcition College National University of Defense Technology), Feng JIN (Information and Communcition College National University of Defense Technology), Ying LI (Information and Communcition College National University of Defense Technology),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Design of Intelligent Monitoring System for Air Visibility Data Based on UAV

UAV has the advantages of small size, low cost and strong performance. How to use UAV to realize the intelligent monitoring of atmospheric visibility data has become one of the research hotspots. Therefore, an intelligent monitoring system of visibility data based on UAV is designed. Through the overall design of the system, the requirements for the collection, processing, transmission, display, monitoring and positioning of atmospheric visibility data are realized. The airborne air visibility sensor module is used to collect gas data, the microprocessor is used to process data, the global positioning system is used to complete monitoring and positioning, and the general packet wireless service is used to complete data transmission and data display of the ground terminal. The experimental results show that the air visibility data intelligent monitoring system based on the UAV has good accuracy and high monitoring efficiency It can meet the requirements of data monitoring system.
Authors: Jun ZHANG (College of electrical engineering,Zhengzhou University of Science and Technology), Jun-jun LIU (Department of Information Engineering Information Engineering,Zhengzhou University of Science and Technology),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Decentralized Control Method for UAV Arriving Simultaneously Based on Large Data Analysis

Due to the limitation of the control method during the conventional simultaneous arrival control drone, a certain deviation is caused. In order to solve such problems, a research on the decentralized control method of simultaneous arrival drone based on big data analysis is proposed. Fusion of decentralized information is achieved through information filtering. Based on this, decentralized coordination of formations is controlled. The optimal path and convergence speed are calculated by calculation. Decentralized control methods are implemented through communication delay constraints. The proposed method is used for simulation experiments and it is found that the method can effectively reduce the error, which fully proves the feasibility of the control method.
Authors: Jian-jun ZHU (College of electrical engineering,Zhengzhou University of Science and Technology), Jun ZHANG,
Hide Authors & Abstract

Show Authors & Abstract

Coffee break 09:00 - 09:00

Session 4 (continued) 09:00 - 09:00

09:00 - 09:00
Study on probability statistics of unbalanced cloud load scheduling

Aiming at the problem of unstable equilibrium probability in modern load scheduling applications, a statistical method of unbalanced probability in cloud load scheduling is proposed. The weights and anti-saturation factors are calculated, the servers are grouped, the fuzzy cyclic iterative control of dynamic network resources is realized, and the network packet cloud load scheduling is designed. By comparing with the common methods, it is proved that the method designed in this paper can guarantee high equilibrium probability and good stability in a certain program.
Authors: Shuo-yu ZENG (School of Mathematics and Statistics,Nanyang Institute of Technology), Yu-jun NIU (School of Mathematics and Statistics,Nanyang Institute of Technology), Hong-e WU (School of Mathematics and Statistics,Nanyang Institute of Technology),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Analysis of energy saving method for multiple relay nodes in wireless volume domain network

In order to solve the problem that the transmission link of wireless volume domain network is likely to be interrupted and consume unnecessary energy, this paper introduces probability statistics and proposes a research on energy saving of wireless volume domain network multi-relay nodes based on probability statistics. The energy consumption of network is analyzed and the formula of total energy consumption per bit network is derived. The simulation results show that compared with the traditional multi-path multi-relay node forwarding method, this method can greatly reduce the overall energy consumption of the network. Consumption also plays a role. This method can reduce the overall energy consumption of the network and prolong the life cycle of the network. When the optimal relay node is used for transmission, the transmission power is greatly increased.
Authors: Tian-bo DIAO (School of Mathematics and Statistics,Nanyang Institute of Technology), Hong-e WU (School of Mathematics and Statistics,Nanyang Institute of Technology), Shuo-yu ZENG (School of Mathematics and Statistics,Nanyang Institute of Technology),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Community Discovery algorithm based on parallel recommendation in Cloud Computing

In an interpersonal network, each node represents a person, and the contact between a person and a person is represented by an edge, and the network organized by this way is called a social network. With the emergence of social networking sites, such as Facebook and Twitter, the communication between people and people is becoming more and more frequent, and the networks they form become more complex and bulky. In social networks, communities can help people better understand the structure of social networks, understand individual relationships and behaviors and evolving trends within the community, and thus control information retrieval, recommendation systems, and information dissemination, such as public safety event control, provide strong support. Under the cloud computing environment, the traditional classification algorithm is low in stability, the information is wasted, the overlapping community and the expansibility are not high, the ideal calculation effect can not be achieved, and a social network community finding algorithm based on the parallel recommendation is proposed and designed. Experiments show that the LER algorithm improves the accuracy and stability of the social network community discovery algorithm, and has good effectiveness and stability.
Authors: Jian-li ZHAI (Huali College Guangdong University of Technology), Fang MENG (Huali College Guangdong University of Technology),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Heterogeneous big data Intelligent clustering algorithm in complex attribute Environment

In order to improve the stability of heterogeneous big data mining operations in complex attribute environment, such as data analysis and cleaning, a heterogeneous big data intelligent clustering algorithm is established. The data cleaning classification method is applied to clean the parameter space in complex attribute environment, and the regular term of sparse subspace clustering is introduced to eliminate the irrelevant and redundant information of heterogeneous big data, and the intelligent clustering index of heterogeneous big data is obtained. By measuring the clustering results, the design of heterogeneous big data intelligent clustering algorithm in complex attribute environment is completed. The experimental results show that the heterogeneous big data intelligent clustering algorithm in complex attribute environment has strong stability in the process of data analysis and cleaning.
Authors: Yue WANG (Software college&Nanyang Institute of Technology), Jian-li ZHAI (Huali College Guangdong University of Technology),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Intelligent performance evaluation method of assembly construction project management based on Cloud Computing Technology

In order to better evaluate the performance of construction project management in Jinzhou, an intelligent evaluation method based on cloud computing technology is proposed. Combined with the practice of construction project management, the performance evaluation index system of construction project is established. Using the formula of relative membership degree to standardize the data, using linear programming to determine the weight of index factors, vector projection formula to find the approach degree between the actual evaluation value and the target evaluation value to evaluate the construction project management performance. Finally, it is proved by experiments that the performance intelligent evaluation method of assembly construction project management based on cloud computing technology has higher accuracy and timeliness in the practical application process, and fully meets the research requirements.
Authors: Qiu-yi LI (Fuzhou University of International Studies and Trade),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Risk prediction pattern matching method of construction project management system in big data Era

In view of the influence of the scale of pattern information set on the pattern matching of risk prediction, aiming at improving the performance of pattern matching of risk prediction, this paper puts forward the method of pattern matching of risk prediction of construction project management system in the era of big data. In the era of big data, the central idea of risk prediction pattern matching algorithm is analyzed. Based on the description of risk prediction pattern matching algorithm, the specific implementation steps of risk prediction pattern matching algorithm are designed, the design of risk prediction pattern matching algorithm is completed, and the risk prediction pattern matching process of construction project management system is combined to achieve the risk prediction pattern matching. The experimental results show that, under different experimental platforms, compared with other risk prediction pattern matching methods, the accuracy of risk prediction pattern matching method of construction project management system in the era of big data is higher.
Authors: Qiu-yi LI (Fuzhou University of International Studies and Trade),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Research on big data classification algorithm of disease gene detection based on complex network technology

In order to improve the accuracy of the classification of the big data of disease gene detection, an algorithm for the classification of the big data of disease gene detection based on the complex network technology was proposed.On the basis of complex network technology, a distance-based membership function is first established. Considering the distance between the sample and the class center, the membership function of sample compactness is designed to complete the establishment of membership function of complex network.Combined with the design of the classification algorithm flow of the big data of disease gene detection, the design of the data classification algorithm was completed, and the classification of the big data of disease gene detection was realized.The experimental results show that the proposed algorithm is more accurate than the other two classification algorithms in the big data sets of different disease genes.
Authors: Yuan-yuan GAO (Changsha Medical College), Ju XIANG (Changsha Medical College), Yan-ni TANG (Changsha Medical College), Miao HE (Changsha Medical College), Wang LI (College of Big Data, TongRen University),
Hide Authors & Abstract

Show Authors & Abstract