Transactions on Computer Science and Technologyhttp://www.ivypub.org/journal/RSS.aspx?J=CST&lang=enen-USCNN-based Traffic Sign Recognition2022-06<p class="abstract">CNN-based Traffic Sign Recognition</p><ul><li>Pages 1-7</li><li>Author Qingkun HuangAskar Mijit</li><li>Abstract Background: The rapid development of the automobile industry has led to an increase in the output and holdings of automobiles year by year, which has brought huge challenges to the current traffic management. Method: This paper adopts a traffic sign recognition technology based on deep convolution neural network (CNN): step 1, preprocess the collected traffic sign images through gray processing and near interpolation; step 2, automatically extract image features through the convolutional layer and the pooling layer; step 3, recognize traffic signs through the fully connected layer and the Dropout technology. Purpose: Artificial intelligence technology is applied to traffic management to better realize intelligent traffic assisted driving. Results: This paper adopts an Adam optimization algorithm for calculating the loss value. The average accuracy of the experimental classification is 98.87%. Compared with the traditional gradient descent algorithm, the experimental model can quickly converge in a few iteration cycles.</li></ul>/CST/paperinfo/56818.shtmlTransactions on Computer Science and Technology/CST/paperinfo/56818.shtmlResearch on Privacy Protection of Intelligent Applications2022-06<p class="abstract">Research on Privacy Protection of Intelligent Applications</p><ul><li>Pages 8-13</li><li>Author Shengdi ZhaoYanxin Ya</li><li>Abstract There are many privacy protection methods in the field of artificial intelligence. Firstly, this paper summarizes the related secure multi-party privacy computing methods, image retrieval privacy protection methods, and machine learning privacy protection methods. At present, edge computing provides many benefits for various intelligent applications, but at the same time, when end-to-edge distributed computing is carried out during the unloading process of edge computing, privacy disclosure will occur. In this paper, a distributed layout privacy protection strategy is proposed to ensure the two-way tasks of face attribute feature extraction and privacy feature hiding. The main purpose is to avoid the remote transmission of privacy information characters while transmitting the main tasks, and to eliminate the hidden processing on mobile devices as much as possible, so as to improve the effectiveness of privacy protection. From the final experimental results, it can be concluded that the network framework algorithm can effectively achieve the effect of privacy blanking.</li></ul>/CST/paperinfo/56823.shtmlTransactions on Computer Science and Technology/CST/paperinfo/56823.shtmlApplication Analysis of Computer Technology in Composite Mapping2022-06<p class="abstract">Application Analysis of Computer Technology in Composite Mapping</p><ul><li>Pages 14-19</li><li>Author Chao TangMeirong Tan</li><li>Abstract In the process of architectural composite drawing, due to its cumbersome process, the work efficiency of manual drawing alone is low, and the accuracy is difficult to ensure. By using computer technology to carry out composite drawing, we can not only improve the drawing accuracy, but also save a lot of manpower and material resources. At present, the commonly used computer composite drawing technologies include AutoCAD, 3ds max, BIM, etc. This paper analyzes these technology types in detail to provide reference for architectural composite drawing.</li></ul>/CST/paperinfo/57831.shtmlTransactions on Computer Science and Technology/CST/paperinfo/57831.shtmlResearch on Business Model Optimization of Artificial Intelligence Garbage Classification2022-06<p class="abstract">Research on Business Model Optimization of Artificial Intelligence Garbage Classification</p><ul><li>Pages 20-25</li><li>Author Siyu LiuJiaqi HouYaning L</li><li>Abstract In recent years, garbage classification and environmental protection are gradually becoming an important step in the construction of ecological civilization in China. However, the popularity and commercial value of the application of artificial intelligence trash cans in Beijing are not high at present. This article analyzes these problems one by one and propose solutions, hoping that the commercial value of artificial intelligence trash cans can be optimized and improved and to make the city greener. This paper uses the questionnaire method and the literature method to research and analyze the optimization of the business model of artificial intelligence in garbage classification.</li></ul>/CST/paperinfo/57840.shtmlTransactions on Computer Science and Technology/CST/paperinfo/57840.shtmlAnalysis of Intelligent Waste Classification Technology2022-06<p class="abstract">Analysis of Intelligent Waste Classification Technology</p><ul><li>Pages 26-30</li><li>Author Yaning LiJiaqi HouSiyu Li</li><li>Abstract The application of artificial intelligence technology to the field of garbage classification can reduce labor costs and improve the efficiency of garbage classification. Under the background of the gradual promotion of compulsory classification of domestic waste, a large number of artificial intelligence products serving garbage classification have emerged. Most of these products are based on computer vision technology. main. At this stage, artificial intelligence in the field of garbage classification has shown trends such as whole-process integration, platform-based management, and diversification of technical solutions.</li></ul>/CST/paperinfo/57841.shtmlTransactions on Computer Science and Technology/CST/paperinfo/57841.shtmlPractice of PERT Technology in Software Project Management2022-06<p class="abstract">Practice of PERT Technology in Software Project Management</p><ul><li>Pages 31-34</li><li>Author Nan LiPeng Zhan</li><li>Abstract The process of software development is complex, which involves many fields of knowledge and is a comprehensive work. During the software development, the project schedule management is related to the success of the project. In order to solve the problems in traditional software project management, the software development project management methods should be deeply analyzed, and the PERT technique should be flexibly utilized. Then, with the aid of the network diagram of PERT featured by reasonable and beautiful, less cross of arrow lines, etc., the project schedule and plotting system can be established, which makes up for the defect of drawing and tracking control, thereby enhancing the level of software project management.</li></ul>/CST/paperinfo/58164.shtmlTransactions on Computer Science and Technology/CST/paperinfo/58164.shtmlResearch Needs and Applications of Machine Learning — Predicting Logistics Stress by Machine Learning2022-06<p class="abstract">Research Needs and Applications of Machine Learning — Predicting Logistics Stress by Machine Learning</p><ul><li>Pages 35-42</li><li>Author Bin Ya</li><li>Abstract Machine learning is the use of computers to learn the intrinsic laws and information contained in data through algorithms to gain new experience and knowledge, in order to improve the intelligence of computers, so that they can make decisions similar to those made by humans when faced with problems. With the development of various industries, the amount of data has increased and the efficiency of data processing and analysis has become more demanding, a series of machine learning algorithms have emerged. Machine learning algorithms are essentially steps and processes that apply a large number of statistical principles to solve optimisation problems. Appropriate machine learning algorithms can be used to solve practical problems more efficiently for a wide range of model requirements. This paper presents the interim state of a dynamic disruption management software solution for logistics, using machine learning methods to study the extent to which stress is predicted based on physiological and subjective parameters, to prevent physical and mental stress on workers in the logistics industry, to maintain their health, to make them more optimistic and better able to adapt to their work, and to facilitate more accurate deployment of human resources by companies according to the real-time requirements of the logistics industry.</li></ul>/CST/paperinfo/58165.shtmlTransactions on Computer Science and Technology/CST/paperinfo/58165.shtmlInnovative Design and Management in the Context of Virtual-Real Scenarios2022-06<p class="abstract">Innovative Design and Management in the Context of Virtual-Real Scenarios</p><ul><li>Pages 43-50</li><li>Author Yong WangTingting LiuJiang Zh</li><li>Abstract From virtual technology, the Internet to the meta-universe, around the creation of virtual and real isomorphism and immersive experience venues, an innovative integration model and innovative design concept integrating the three major fields of "science and technology + art + culture" have been opened, and the method of today's design industry management model has also been shaped. The author, ground on design originality and experience, intends to source feasible exhibition design tactics from the "presence" design and implementation project that integrates immersive display and performances. From this, efforts are invested in sorting specific innovative design patterns referring to ongoing cases of Metaverse, thereby charting course for prospective design projects.</li></ul>/CST/paperinfo/58170.shtmlTransactions on Computer Science and Technology/CST/paperinfo/58170.shtml