A Tally System Based on CNN and Block Chain Ni, Jinting; Chen, Xiaoyi; Yan, Yunyang ...
2018 17th International Symposium on Distributed Computing and Applications for Business Engineering and Science (DCABES)
Conference Proceeding
In order to design a reliable and convenient tally method, the emergence of a tally system solves the problem of high database maintenance costs, such as management of the site factory, telecom, ...power companies, etc. The novel phases, constituted of the Convolutional Neural Network (CNN) and the block chain, extracts character characteristics through the VGG network training character classification model. The principal component analysis(PCA) algorithm accelerates feature comparison efficiency by reducing the dimensions of the feature matrix. In terms of data storage, the consistency of the Practical Byzantine Fault Tolerance(PBFT) algorithm ensures the accuracy of the data. The experiment demonstrates that practicability of the system can catch the requirements of the automatic bookkeeping method in the construction site.
In order to design a three-dimensional WebGIS which describes the geographic information of a smaller region like Huaiyin Institute of Technology, a method for building WebGIS is proposed. In ...details, LocaSpace Viewer and SketchUp are used to draw maps, ArcGIS API for JavaScript is used to develop project and Tomcat, ArcGIS Server is used to load users requests. Experiments show that the application system obtains a very high efficiency. The results show as by proposed system architecture can satisfy the application requirements for the customers.
Intelligent Graph Review System Based on Knowledge Map Zhu, Liangsheng; Bian, Wenwen; Wu, Bin ...
2019 18th International Symposium on Distributed Computing and Applications for Business Engineering and Science (DCABES)
Conference Proceeding
In order to meet the background of the digital map review of the rapid development of information technology such as "Internet +", big data, machine learning, etc., a smart graph review system based ...on knowledge map is proposed. The system includes a data processing module, a knowledge map building module, and a comment recommendation module. At present, the knowledge map is constructed through the Neo4j database, and the accuracy of the entity recognition algorithm in this project reaches 95.7%. The survey results show that the application of the system can meet the requirements of intelligent review.
In order to solve problem of huge manpower demand in the construction industry and heavy drawing work, a construction primitive extraction system was designed. This system relieved pressure of the ...artificial building review and improved the reviewing efficiency of the reviewing experts. The system uses a Convolutional Neural Network (CNN) to extract drawing primitives using the Visual Geometry Group (VGG) network training model. Principal component analysis algorithm improves feature comparison efficiency by reducing the dimension of the matrix. Experiments show that the practicability of the system can meet the requirements of general construction primitive extraction.
In order to improve the use value of expert information, the Information technology experts Mining System is designed and realized which based on Mining Association. University website on the ...Internet, CNKI and Soopat patent website to provide expert information related data. Through the application system designed based on Web crawling, association mining model and page analysis, good results achieved by digging the expert information from universities and first-class hospitals in Jiangsu. According to the data mining from the database of Soo PAT and CNKI, correlation algorithm model of the technology experts mining system is designed and achieved 92% of the associated information accuracy and 97% of the expert information accuracy in experiment, which provided the data support for the system design. Available to the government departments or technology enterprises to browse, the system can meet the demands of the information of scientific and technological information of technology experts of government science and technology departments and science and technology enterprises.
There are many issues in traditional inland ship lockage operation, such as operation cumbersome, low-level efficiency and prone to waterway jam. In order to solve these problems, a relevant solution ...scheme based on Internet of Things technology is proposed in this paper. The ships used RFID tag can be identified automatically, wireless communication between readers and host machine can be realized by Zig Bee module, and short messages can be sent from host machine to the ship-owners using GPRS module. The proposed ship lockage management system which based on Internet of Things can realize ships identification, monitoring and paying automatically. The analyses show that using RFID, Zig Bee and GPRS technologies, the processes of ship lockage can be optimized, time can be reduced, and traffic capacity and management level will be improved efficiently.
As RS485 network has the character of simple construction, lower cost and easy extension, it has been widely applied to many application systems based on Radio Frequency Identification (RFID). In ...RS485 network the mainframe can access many readers. Aiming at the demand of a RFID application system in which the mainframe needs transmitting information to display terminal, this paper proposes a solution. Through connecting display terminal and readers into RS485 network, defining custom communication protocols between the mainframe and display terminal, the mainframe can access display terminal like the other readers. The implementation results show that the solution has achieved the anticipated target and run stablely and reliably.