This PDF file contains the front matter associated with SPIE Proceedings Volume 12599, including the Title Page, Copyright information, Table of Contents and Conference Committee lists.

Studying the influence of the central bank's digital currency on the payment system has important practical significance for the planning and construction of the payment system and surrounding services. By narrowing the research sample, analyzing the payment scenarios in university campuses, the different forms of campus payment systems from the elementary to the latest stages, and establishing payment system models based on the use of central bank's digital currency in different forms of payment systems. The payment efficiency model is established by integrating factors such as the efficiency of consumer payment, the efficiency of business capital withdrawal from merchants, the retention time of deposited funds in payment management institutions, and the loss ratio of funds in the transaction process. Using this payment efficiency model, combined with the comparative consideration of the length of the key path of payment transactions, analyze the positive role of central bank's digital currency in promoting the upgrade of the payment system and the improvement of payment efficiency.

With the gradual expansion of the power grid scale, the complexity of the power grid becomes higher and higher, and the stable operation and dispatching of the power grid become more and more difficult. The application of artificial intelligence to power grid dispatching can make the process of power grid dispatching simple and efficient. Moreover, it is an effective way to solve the difficulties of power grid dispatching. Taking the virtual dispatcher in the Lanzhou power grid system as an example, the application of artificial intelligence system in the power grid control was summarized. Combined with the actual situation of the Lanzhou power grid, the necessity and feasibility of the development of the power grid intelligent dispatching system were fully analyzed, and the concrete implementation steps and methods of the development of the power grid intelligent dispatching system were illustrated by examples. This work can provide a reference for the development of an intelligent dispatching system and intelligent upgrade of the power grid.

In this paper, a centralized collection and measurement system of energy is developed based on the requirements of intelligent substation for the development of electronic, integrated circuit and intellectualization of in-station metering equipment in combination with the main working mode of the terminal of energy collection in intelligent substation.

Aiming at the problems of data isolation in the current auto repair industry and the primitive data analysis and decision-making means in company, this paper adopts big data technology and data warehouse technology to analyze the business data of company, designs and implements an automobile service company operation decision support system based on distributed data warehouse. The specific solutions of the system are as follows: (1) According to the results of business analysis and demand investigation, the theme of data warehouse is determined, and the theme-oriented data warehouse model is designed and built; (2) Design and build a big data platform based on Spark computing engine; (3) Build a data transmission module by using big data transmission tools to collect and clean the multi-source heterogeneous data sources of automobile service company; (4) According to the needs of company apply the decision support system, and display the indicators visually for decision makers. The system supports the fusion analysis of different dimensions, which is convenient for decision makers to understand the data from the thematic point of view, which provide decision support for company.

The user growth system based on the power industry is an important service system to build a relationship with users in this industry. This research aimed to enhance the sense of belonging of power users, improve product adhesion and achieve precise marketing goals. Taking a provincial electric power company of the State Grid (referred to as a provincial electric power company) as an example, the author built and applied a user growth system centered on power customers on the basis of data resources such as power users' flow and their electricity consumption. After analyzing the current situation and existing problems of the power user growth system, the researcher comprehensively sorted out and constructed an overall framework of this system in a targeted manner, and then applied it to the omni-channel membership center of a provincial electric power company. Finally, the application effect of the user growth system is expounded, and the future application trend is prospected.

Accurate electricity price forecasting is of great importance to all participants in the market, which can provide powerful support for them to make wise decisions in the unpredictable market. In this paper, we propose to use the MLP-Mixer model as a new technique for electricity price forecasting. This model considers the various factors affecting electricity price fluctuations and can use the MLP-Mixer model for concise and practical feature extraction and information interaction, ultimately achieving more accurate electricity price forecasting. The effectiveness of the proposed model is verified by using data from ERCOT, Texas electricity market. Empirical results show that the proposed model can significantly improve the forecasting accuracy, and achieves the optimal results on four evaluation metrics, which fully demonstrates the model's effectiveness for electricity price forecasting.

Fintech is continuously driving the overall upgrade of payment methods. Technologies such as Big Data, the Internet of Things, and Artificial Intelligence continue to be applied in the payment field and significantly impact the payment industry. Based on the fusion of multiple machine-learning models, the problem of identifying potential default credit card customers is investigated in this paper. The customers are mined and classified based on their bill amount, education level, marital status and other characteristic information. The various models predict using the AutoML framework, then fused and optimized by bagging and stacking methods, and the models are evaluated using evaluation metrics such as F1 values. The test results show that the F1 value of the integrated model after multiple stacks reaches 54.3%, which is better than that of a single algorithm.

To solve the problem of strong subjectivity and low credibility of complaints, a new detection model of false information in environment complaints based on graph convolution was proposed. Firstly, the text of environment complaint is preprocessed: then the word in the complaint text and lexicon are used as nodes, the edges between words are constructed by point mutual information, the edges between text and words are constructed by term frequency-inverse document frequency, and the edges between text and text are constructed by text similarity. The edges between words, text-word relationship and text-text relationship are used to construct the text graph of environmental complaint based on word co-occurrence, text-word relationship and text-text relationship; finally, the node information is passed between nodes through graph convolution, and the coupling between complaint information is used to detect complaint false information. Through designing experiments, the model is compared with the methods of common classification models, and the experimental results show that the model has good performance. It is suitable to be applied in the task of environment-based false complaint detection.

In order to further strengthen the fire safety work in colleges and universities, and improve the degree of public property and personal safety of teachers and students, colleges and universities should actively take measures to improve the level and efficiency of fire safety management. This paper takes fire safety facilities as the research object, innovatively introduces WebGIS technology into daily management and maintenance, and combines ArcGIS Server application platform and Ajax technology to complete the construction of university fire safety facilities management information system in C# language environment. The whole system adopts B/S architecture, and the Web Server is built by ASP.NET framework. It can support the business logic control of functional modules such as user login, basic data management, fire control facilities management and automatic fire alarm, and can also control Oracle database to complete the storage and call of various data. With the help of JSP page and Openlayers framework of the system, the electronic map of campus fire protection produced by WebGIS is displayed, and the image and intuition of the map and the data of fire protection facilities are integrated, which can not only improve the efficiency of campus fire protection management, but also make an attempt for the informatization construction of campus fire safety.

Power communication is an important part of power system. The security requirements of power communication include identity authentication, access control, firewall, etc. The realization of these security requirements depends on security protocols. Security protocol is an interactive protocol based on cryptosystem, which is an important guarantee for the reliability of power communication system. Through the analysis of the three-layer structure platform, this paper uses the three-layer network to build the technical guarantee method of the power system security protocol to realize the effective guarantee of the platform information, so as to provide auxiliary decision-making support for the relevant departments.

In the digital intelligence era, users have higher requirements for machine aided learning environment experience. How to provide personalized learning support services based on users' different characteristics has become a hot topic for researchers. Intelligent learning system (ILS) is a learning support environment that can dynamically diagnose users' different learning needs and then provide personalized services. However, the current research on intelligent learning systems is still in the exploratory stage, and the research results need to be improved in the aspect of intelligent recommendation effect. Based on this, this paper will further explore the personalized recommendation technology solution of intelligent learning system on the basis of the analysis of relevant case results. In order to improve the recommendation accuracy of intelligent learning system, we will focus on the analysis of the system architecture, feature model construction method and recommendation process from the perspective of user feature model. The simulation experiment analysis shows that the research results have certain advantages in the personalized recommendation effect, which can dynamically provide the current user with a suitable personalized learning path to meet the user's learning needs.

At present, indoor human behavior recognition technology is widely used in the fields of video intelligent monitoring, intelligence elderly care and intelligent medical care, etc. The existing research methods are more focused on classifying human behavior and ignore the connection between objects in the scene and human behavior. In order to make full use of the association between the objects in the scene and indoor human behavior, this paper proposes an indoor human behavior recognition model based on deep learning and knowledge graph. Firstly, we use YOLOv5 target detection network to identify the objects in the scene, and also use human keypoint detection algorithm to locate the skeletal keypoints of human body, extract and analyze the spatial features of objects and keypoints to obtain the human behavior feature triad, construct the behavior detection knowledge graph and perform search and inference to realize human behavior recognition. The experimental results show that the recognition accuracy of the model is 94.9% on the homemade test set.

The high accuracy of deep learning in various computer vision tasks often relies on massive image data, but there is usually not enough image data to complete the task in actual project applications. Aiming at the problem that thermal infrared face images are few and difficult to obtain in the absence of light, this paper proposes a method to generate thermal infrared face images based on color face images to obtain more thermal infrared face image data. This method takes the conditional generative adversarial (CGAN) network as the framework and uses the deep high-resolution network and the Patch Net network as the generator and discriminator to build the network model. By verifying the network model on the two datasets, it can be proved that the proposed method is clearer, and the details of the facial features are more obvious than the thermal infrared face images generated by the traditional image generation methods. Compared with the FID values of the original generation method, the FID values of the generated image using this method were reduced by 136 and 92. Therefore. The unsupervised data augmentation method based on HRNet network as a generator can also be applied to other visual tasks such as object recognition and detection that lack image data.

Publisher's Note: This paper, originally published 3 April 2023, was withdrawn on 12 June 2023 per contact author request.

Similarity measures play an important role in ambiguous environments. Fuzzy hypergraph theory can carry out relatively rich information description and operation in the process of dealing with uncertain problems. The dominance matrix of the fuzzy hypergraph describes the dominance relationship of the attributes of different objects in the information system composed of the fuzzy hypergraph. In this paper, by constructing the dominance matrix of fuzzy hypergraphs, the Euclidean distance is used to solve the similarity of the dominance relationship between the information systems constructed by different fuzzy hypergraphs. By discussing the relationship between fuzzy sets and fuzzy hypergraphs, an algorithm for solving the similarity of dominant relations between fuzzy hypergraphs is proposed. In order to test the efficiency and reliability of the method, this paper uses multiple examples and solves it with the proposed method, which proves the rationality and effectiveness of the proposed method.

Fault-generated traveling waves of one phase conductor is usually captured and used to locate the fault position in electrical distribution system because of the cost reduction of sensors installation. This method leads to additional location error because of the propagation speed variation in the fault location procedure. In this paper, the traveling wave-based fault location error is analyzed and discussed detailed when zero-mode, aerial-mode and phase traveling wavefronts are applied in the location procedure separately. In the meantime, the refraction and reflection of the fault generated traveling waves are also analyzed to reveal the propagation attention characteristics, which would also affect the wavefront arrival time identification. The results shown that aerial-mode traveling waves are suitable to be used in electrical distribution system to reduce the locate error, approximately less than 175 meters.

Digitization is an important way to realize the development, construction and operation of warship combat system in the future. The main purpose of this paper is to analyze the necessity and development measures of digitalization of warship combat system. This paper analyzes the origin and technical basis of digitalization of US military weapons and equipment, summarizes the main ways and development of digitalization of US surface ship combat system and submarine combat system. At last, this paper puts forward suggestions on system construction, development idea, technical path of digitalization of combat system, which is of great significance for guiding the subsequent development of combat system.

In order to solve many problems existing in enterprise performance management from formulation, promotion to evaluation, and make enterprise driving school management convenient, efficient and scientific, the author of this paper designs a lightweight enterprise performance online management system, which combines Web technology and computer technology, completes the construction of server side with JAVA language under J2EE specification, and realizes data support with MySQL database. The platform adopts B/S architecture, follows the MVC three-tier architecture design idea, and introduces SSH framework to complete the design and deployment of Web Server. It provides a set of efficient tools for enterprise performance management, stimulates employees' sense of ownership, and promotes the improvement of organizational and personal performance.

Blockchain is a distributed ledger technology where all nodes in a blockchain maintain the same ledger. The key to a blockchain is to ensure the uniqueness of the ledger. Therefore, different consensus protocols have been designed to cater for different applications. Consensus protocols such as pow and pos allow nodes to enter and leave at any time but still ensure convergence, while PBFT and Raft protocols can speed up convergence in licensed blockchains but are relatively less secure. We analyse consensus protocols from a database perspective and can think of consensus protocols as consistency. We analyze the characteristics of consistency and propose CChain blockchain system, which integrates the eventual consistency method (CRDT) into Fabric for the first time. Compared with the native Fabric, the throughput is improved by more than 16X.

In order to further improve the operation efficiency of the expressway automatic toll collection system, in this research, based on the radio frequency technology, integrated with the support of computer technology and artificial intelligence technology, the expressway automatic toll collection system based on radio frequency technology has been carried out in various aspects, including database, functional modules and other parts. On this basis, the design effect is tested through the test link. The test results show that the designed highway automatic toll collection system based on radio frequency technology has excellent overall performance, which proves that the design has achieved initial success.

With the development of modern education, the country pays more attention to the discipline training of experimental practice in science education, and high school laboratories become a high ground for students' science education and comprehensive quality education, while the current domestic laboratory management basically remains in the traditional manual management mode, with problems such as heavy management work, high repetition, low management efficiency, accuracy of information is difficult to guarantee, and easy to produce unnecessary property loss and waste of expenditure. In order to further improve the efficiency of laboratory management and enhance laboratory safety and security, this paper puts forward the concept of designing a school laboratory management system based on computer technology, providing convenient services and technical support for laboratory management through five modules: system management module, academic affairs management module, operation management module, safety management module and equipment management module, which greatly improve management efficiency and promote open teaching in schools.

UHV transmission and transformation projects in China are developing rapidly. However, the construction of UHV transmission and transformation projects has damaged the natural environment along the way, and soil erosion has intensified. The development of water and soil conservation monitoring system in China is slow, and it is urgent to develop fast and reliable water and soil conservation monitoring. In this paper, a real-time online monitoring system for water and soil conservation is designed. The system consists of hardware, cloud and software. The hardware part uses field layout 9 fiber monitoring data and data transmission. The cloud part uses online cloud center to store soil and water conservation monitoring data. The software part is used to receive cloud information and facilitate data processing. To achieve long-term, real-time UHV transmission and transformation project construction site environmental impact, environmental restoration of soil erosion status accurate, rapid and reliable monitoring. The system is now used in soil and water conservation monitoring of Baihetan-Jiangsu ± 800 kV UHV transmission and transformation project to monitor local soil erosion. Through data analysis, the system meets the needs of on-line monitoring of soil and water conservation in UHV transmission and transformation projects. The results can provide reference for the application of other UHV soil and water conservation monitoring systems.

In view of the situation that the existing dispatching automation system does not provide specialized automatic listing and recovering during primary equipment maintenance, the automatic listing system is proposed based on the dispatching automation system platform. By considering the factors related to the maintenance listing attribute and device status, design and implementing schemes are presented. This system provides the functions of OMS operation ticket extraction, communication across security zone of information, intelligent analysis of maintenance files, the automatic listing function, and visual management of maintenance information, which provides dispatchers with great convenience in listing function of dispatching automatic system.

In order to solve the problem that the existing printer cannot be remotely controlled and the printer is not intelligent enough, this paper makes a series of improvements and optimizations to the original printer system. First, the Linux operating system required for the operation of the printer is cut and developed; second, a remote web control interface system for the printer is designed using the javascript language as the programming framework, and the user can control the corresponding functions of the printer through the remote browser web page by entering the URL address of the printer system and verifying the pre-set login account using the browser; finally, a web server is built Boa, and a detailed introduction to the theory of CGI (Common Gateway Interface) technology; after experiments and debugging on the Samsung 4412 series ARM embedded development board, the results prove that the printer remote control system is easy to operate, responsive and more conducive to the development of modern industrial intelligence.

This paper uses the oil monitoring and diagnosis module to conduct diagnosis and early warning based on the change of oil indicators caused by the deterioration products generated after the deterioration of the oil, which can quickly and accurately output the equipment to which the fault belongs and diagnose the link of the problem. Along with the related remote management software for the top computer and the lower oil monitoring equipment, the system also includes the diagnosis technique statistically created by the aforementioned modules. The host computer's software then performs real-time statistical data screening and diagnostics once the monitoring and diagnosis module detects the change in oil quality indicators and transmits the information through the switch.

With the deepening of the concept of knowledge society, the traditional college Chinese education is undergoing profound changes, which has gradually changed to "learning centered". Therefore, deep learning, core literacy and other teaching concepts have become the focus of current higher education, which has gradually been integrated with new teaching methods, such as flipped classroom and Mu class. Through multi form teaching methods, the teaching mode of information technology and curriculum integration has become the pursuit of in-depth learning in Chinese teaching, which is a learning mode of pursuing more diversified learning objectives of students. Through in-depth learning, the learning process of college Chinese will be more engaged and participatory, which will help students' cognitive processing methods, mainly including the connection of new and old knowledge, critical understanding, information integration, etc. Deep learning will increase the level of students' input and participation in the learning process, which will better develop the core quality of long-term memory and transfer of knowledge. Therefore, the construction of college Chinese teaching system based on deep learning technology is very necessary. This paper first analyzes the current research on the application of deep learning technology. Then, this paper analyzes the data analysis model of deep learning process. Finally, this paper constructs the college Chinese teaching system and puts forward some suggestions, which can better construct the teaching system.

The debugging quality in the debugging stage of the digital production line directly affects its processing accuracy. Due to the rich and varied production scenes and complex equipment associations, the general production debugging plan has a long cycle. Therefore, this paper adopts digital twin technology to apply to the traditional assembly system design process, adopts NX, MCD, TIA and other design methods. Firstly, builds a digital virtual model of the assembly platform; Secondly, the application of electromechanical concept design module to achieve virtual simulation of the assembly process; In the TIA project environment, the logic control program of the PLC controller is written; Then, build a physical system based on a virtual model; Finally, virtual and real system integration is achieved through communication connections. The research results show that the traditional assembly system from design, debugging and application cost is higher, cycles are usually within three to five months, assembly platform based on the digital twin technology can significantly reduce the design cycle of assembly system and research and development costs.

With the development of information and intelligent technology and the continuous promotion of national policies, colleges and universities have entered the financial information age. However, there are still some problems in college financial informatization, such as insufficient intelligence in business processing, and low work efficiency. This paper takes S university as the research object, based on case analysis and field research, using DUE, image processing, two-dimensional code recognition, visual processing, RPA and other technologies, proposes and practices the construction scheme of intelligent finance in universities. Practice has proved that intelligent financial construction greatly releases financial manpower, improves efficiency and improves financial intelligent management level.

Aiming at the issues of massive data integration and weak visualization in the tunnel structural health monitoring (SHM) during operation period, a BIM-based tunnel structural health monitoring and data integration system is developed, which uses MySQL database to manage multi-source data, and establishes a data visualization plug-in on the top of the Revit platform. The system integrates tunnel basic and monitoring information, security evaluation and early warning, and report management into the Revit functional area, and realizes the functions of visual display, processing, analysis and early warning of monitoring data. With the help of the proposed system, engineers are able to grasp the health status of the tunnel structure timely and ensure safe operation of the tunnel structure.

The safe operation of the safety stability control system is an important means to ensure the safe and stable operation of AC and DC power grids. Aiming at the shortage of existing test methods that cannot perform closed-loop testing of field safety stability control systems, a remote closed-loop test method for safety stability control systems based on step-by-step implementation is proposed. Using the simulation results of real-time digital simulation system (RTDS) as the signal source, a remote test platform architecture integrating laboratory and field safety and stability control devices is designed, key modules such as platform management system, test master and test terminal are developed, specific solutions are given for platform communication, and a remote closed-loop test procedure is formulated. Finally, a pilot application is carried out with an actual power grid security and stability control system as an example, and the effectiveness of the proposed method is verified.

The popularization and application of Internet technologies accelerate digital transformation of new retail enterprises. Based on “People-Product-Place”, a marketing theory of China’s new retail, this paper designed a smart digital system for new retail through consumer digitization, channel digitization and terminal scene digitization. We deeply studied the digital transformation of new retail from the aspects of member label database, precision marketing and promotion, and drive consumer operation through the application of label database. The computer vision system with in-depth learning and training in store, shelf and display management can accurately identify the commodity information in the picture, automatically detect and send out early warning in real time. Then K-Means, RCM Model, F1 Score and Life Cycle Management (LCM) to the smart digital platform, open up the whole link with the help of cloud computing, Internet of Things (IoT), business intelligence (BI) and other technologies, and quickly push goods to the exact customers through proper channels.

Aiming at the problems of time-consuming, labor-intensive and large errors in the investigation and collection of agronomic traits of foxtail millet in the field, this paper designed and developed a foxtail millet phenotype investigation and collection system that is easy to operate on mobile phones and tablet computers. The system is developed based on C/S structure, takes Android Studio as the development plat form, adopts JSON data format, and realizes the communication between webpage and server through Android technology. The system architecture is divided into user layer, data layer and application layer. The user layer is the module grouping, inputting and uploading of phenotypic traits to the client APP and prepares for login and collection; the data layer provides reception, error correction and modification functions for data collection, and the application layer realizes the processing of foxtail millet phenotype data after collection. decision-making, etc. The field test results show that the mobile APP effectively solves the problems of low data entry efficiency and secondary data entry, and improves the efficiency of foxtail millet phenotypic trait data collection by 64.7% compared with manually entered data. The system is flexible in functional design, quick in data entry, and simple in operation. It is suitable for experiments that require field agronomic traits collection at all levels in the foxtail millet breeding process. At the same time, this system can be used as a collection template for other crop phenotype data.

In order to adapt to the development of railway logistics financial business under the situation of modernization and transformation of railway enterprises, an intelligent integrated operation mode of logistics, capital flow and information flow is designed and financial risks are evaluated to guide the financial operation of railway enterprises. Combined with the status of railway freight, logistics operation and financial institutions, we design the operation mode and establish 4 internal risk evaluate on indicators and 21 external risk evaluation indicators, and use the structural equation model to evaluate the risks faced by railway logistics enterprises in the process of financial operation. The simulation results show that the external risk is greater than the internal risk. In detail, the order of impact degree of risk factors from high to low is: regulatory institution risk, financing enterprise risk, legal risk, core enterprise risk, environmental risk, and capital platform risk. Among the internal risks, the order is: internal management risk, collateral risk, future development risk and technology application risk.

ICT in education has become a hot word in the field of education in recent years, which is the inevitable trend of the times and the result of the country's efforts to develop ICT in education. Education informatization is a strategic support made by the country at the top-level design level, and an indispensable and important measure to promote China's modernization. Classroom management, especially students' classroom management, has a great pressure on teachers' management, which often requires teachers to spend more time and energy to maintain normal classroom order. The introduction of information classroom management tools into students' classrooms is an inevitable requirement for improving management efficiency and teaching quality. Therefore, this research is based on the information classroom learning and explores the effectiveness of the application strategy of information classroom management tools in classroom management.

Icing of transmission lines has always been a pain point for grid companies. The economic and property losses caused by icing every winter are huge. How to make an effective prediction of transmission line icing is a difficult problem. Existing forecasting methods are often based on micro-meteorological and micro-topographic information. In the characteristic variables of micro-meteorology and micro-topography, there are often interdependencies and potential spatial correlations. However, existing icing prediction methods do not fully exploit the interactions among these characteristic variables. Therefore, this paper proposes a transmission line icing prediction model based on the feature map structure, which reveals the potential agnostic topological relationship between the feature variables by adaptively extracting the sparse adjacency matrix between the feature variables. In addition, while the dilated convolution can improve the receptive field, there is also a loss of information continuity due to the discontinuity of the convolution kernel of the dilated convolution. We propose a temporal capture module to improve the loss of information continuity through GRU and dilated convolution in parallel. End-to-end prediction is achieved by stacking a graph convolution module and a temporal capture module, and after conducting several experimental comparisons, the effective prediction of the proposed model is validated.

Changing the configuration of the runway and taxiway geometry is an effective measure to improve the airport operation efficiency. Increasing the number of parallel Entrance Taxiways (ET) which is connected to the runway is a general way of saving flights waiting times, but the actual take off length for runway is reduced. To overcome this problem, the new operation mode was applied by increasing the additional inclined ET besides vertical ET which were set at the end of the runway. However, the effect of the additional inclined ET to the airport operation efficiency is hang over. In this study, the physical model of all-day run multi-runway airport was built to study the influence of the additional inclined ET to airport operation efficiency by comparison of runway with vertical ET and with additional inclined ET. It is found that flight delay rate is reduced from 17% to 13.8% for the runway with additional inclined ET. The time of maximum flight delay and the number of delay flights are reduced while the runway is connected to the additional inclined ET. Air delay and taxiing delay are the major reason for the ground delay for arrival flights and departure flights, respectively. Taxiing delay for arrival flights is reduced while the additional inclined ET is operated. Runway capacity has little change by the operation of the additional inclined ET.

Due to the digitization of cultural heritage, there has been an increase in its protection and development and a renewed vitality to it. This article examines the digitalization of cultural heritage and the research results and progress in the fields at home and abroad. For visual processing and display, use Cite Space software to measure the research literature for 10 years of the CNKI database. By analyzing and organizing three major phenomena in digitalizing cultural heritage: (1) Study hotspots and direction "multi-bloom, diverse development". (2) Research institutions and personnel are more independent. (3) The trend of research into emerging digital technology is relatively obvious. Based on the overall analysis, the research status of the two major needs to be improved: (1) Strengthen the cooperation and connection between colleges and universities, cultural relics protection departments, and museums. (2) Grasp the internal connection in digitalizing emerging digital technology and cultural heritage.

In the process of formulating the standard for the determination of multi-element content in gold alloy jewelry by LA-ICP-MS, in order to conduct independent research on its precision requirements and facilitate the laboratory to carry out daily analysis, 20 elements at 4-6 levels in gold adornment alloys were repeatedly tested in 6 laboratories using different types of instruments. The precision requirements for the determination of multi-element content in gold adornment alloys by LA-ICP-MS were obtained after data statistics. The results showed that under repeatability / reproducibility conditions, the difference between the two independent test results obtained in the 95% confidence interval didn’t exceed the repeatability limit and reproducibility limit in the corresponding concentration range.

In 2022, the Ministry of Education officially launched the "Strategic Action for Digital Education", and digital transformation has become the focus of inward growth and transformation in the field of education. This paper first analyzed the connotation of the digital transformation of education and the difficulties of data integration encountered by colleges in the process of digital transformation, and proposed the technical path of digital transformation of colleges from two aspects: building an iPaas based educational data integration data base and key promotion strategies for digital transformation. Finally, from the perspective of practice, the article showed the practical cases of Shandong Youth Political College's digital transformation based on iPaas, with a view to providing reference for colleges to carry out digital transformation.

Highway variable toll collection is an important means of traffic governance in modern society. A reasonable variable tolling scheme can adjust the traffic flow through price, and further develop the bearing capacity of highway on the basis of existing infrastructure to improve its traffic efficiency and service level. In the past, the formulation of variable tolling schemes is usually based on various assumed models, which belongs to the knowledge-driven method. In this paper, a data-driven variable tolling scheme is proposed, which uses the traffic flow prediction model integrating attention mechanism, recurrent neural network and graph neural network to mine the historical traffic information data on the road. In this paper, the traffic flow information on the future road is forecasted, and the information is used to replace some assumptions of bottleneck theory which are not completely in line with the actual situation. Taking the forecast information of traffic flow as the new constraint condition of dynamic congestion pricing in bottleneck theory can help us develop a more scientific and reasonable variable tolling scheme.

A single lamp controller based on Narrowband Internet of Things (NB-IoT) is designed to facilitate the problems of lack of intelligence and single control mode in the traditional street lamp control system. With MCU and NB-IoT communication module as the core, the controller realizes remote control and operation status detection of the lamp. With the combination of sensors and real-time clock (RTC) to achieve three control modes of manual control, light intensity based control and multi-period dimming control, the controller is suitable for a wide range of application scenarios. The controller's operating parameters are stored locally, thus avoiding loss of control of street lamps due to loss of operating data in the event of network disconnection or power-off recovery. The experimental results are shown to verify that the controller functions properly and can meet the needs for intelligent control for urban street lighting.

Based on SIR model, combined with the mode of COVID-19 epidemic spread in Wuhan, the SIR model of COVID-19 epidemic spread is constructed, which mainly includes three aspects: simulation of the average number of infected people in COVID-19, simulation of cross-infection in COVID-19 and simulation of contact infection in COVID-19. Using the results of these three simulations, we can predict the spread of COVID-19 epidemic in the region, and find out the methods to prevent and control the outbreak or spread of the epidemic.

Traditional craft is an important part of cultural confidence in the national cultural strategy, and cultural design is an industry with great development potential in the future. With the arrival of artificial intelligence, virtual reality technology and a new round of information technology on the Internet, the design industry has ushered in the information age, and the traditional processes are endowed with more diversified, scale and open attributes. In order to break the one-sided structure of the traditional craft products and give the modern bamboo weaving more three-dimensional space possibilities, the parametric technology can provide the changing logical structure of the new form construction of the bamboo weaving products through the parameters. This paper uses the digital transformation of traditional bamboo weaving technology to carry out the new innovative design thinking process of bamboo weaving process, Use the 3 D Rhino software combined with Grasshopper to adjust the parameters of the bamboo weaving product weaving patterns and bamboo weaving derivative products, and then fine-tune according to the specific requirements of the curve surface shape. Compared with the traditional bamboo weaving method, the parameter modeling method can make the bamboo weaving form more intelligent, and the constructed parametric structure can be more flexible and efficient for the bamboo weaving derivative and design, which provides a new design method and ideas for the development of bamboo weaving products.

With the promotion of urbanization in China, a large amount of construction waste materials are piled up. In order to solve the problem of idle construction waste materials, We takes construction waste glass as an example, and establishes a SVM multi-classification prediction model based on one-to-many from two perspectives of classification prediction accuracy and model sensitivity. The data of chemical composition content in waste glass is divided into training set test set according to the ratio of 8:2 to complete the training and validation of the model. The data were brought into the trained model, resulting in five categories. Finally the model was analysed for sensitivity by Monte Carlo simulation with an accuracy of 95.4%.

The issue of climate change has become a global hotspot, and more and more countries attach importance to it, especially those vulnerable countries need to master the impact of climate change on national vulnerability. The evaluation model is established to provide a quantitative analysis of vulnerability for most countries in the world. In order to make this article easier to understand, we only focus on the representative characters used in the model, while ignoring the profound mathematical theory. This paper uses 12 indicators to measure the four areas of national vulnerability. Through K-means cluster analysis of the total national vulnerability value and ranking of 180 countries in 2021, and finally, Regress function is used to establish a multivariate linear fitting model. The study found that without the impact of climate conditions and national vulnerability would be reduced. In countries with strong vulnerability, economic development and human resources are very limited to their national vulnerability. To sum up, research on national vulnerability and climate change in the region is conducive to national development and people's in-depth research on climate.

The evaluation indicator model of the scenario trigger mechanism is constructed and proposed in this paper. By analyzing the elements of the V2X early warning function scenario, five indicators, which includes time to collision, the headway, the safe distance, the lane crossing time, and post conflict vehicle entry time are employed for the comprehensive assessment. The result demonstrate the priority relationship among the total 27 scenarios. It could support to detect and identify corner traffic scenarios, to broadcast safety warnings, to improve the performance of driving assist functions.

During the period of taking the economic development as the center, our lakes face the serious ecological environment problem of water pollution. Cleaning up water pollutants is not only conducive to the protection of lake biodiversity, but also conducive to human production and life. Traditional cleaning methods mainly rely on artificial salvage, labor time is long, manpower and material resources consumption is also large. At present, the known lake cleaning machinery can only work on the water surface, and there are many problems such as poor cleaning effect and waste of resources. Therefore, we designed a bionic form of lake garbage cleaning robot to free the labor force, while using underwater operations to achieve high efficiency and high quality lake garbage cleaning, with simple structure, energy saving, environmental protection and other advantages.

Sensor technology is an important support for the development of intelligent manufacture, industrial Internet, smart city and other fields. As an important economic city in western China and the leader of Chengdu-Chongqing Economic Circle, Chengdu has long been planning and making arrangement in the sensor industry, which is supported by a large number of universities and scientific research institutes; This study searches “the laser radar in Chengdu” on incoPat patent analysis platform, and analyzes the application trend, applicants, technical field and patent operation data of the search results, so as to explore the advantages and disadvantages in the field of laser radar industry in Chengdu. Then it puts forward the corresponding strategies to promote the development of local sensor industry by improving the transformation and application of sensor achievements.

The construction of the UHV transmission line project will affect the surface ecological structure, significantly affect the vegetation and landform along the line, and further aggravate the soil and water loss. With the improvement of environmental protection awareness, it is more and more necessary to consider soil erosion monitoring in UHV project construction. In this paper, a soil erosion detection method is proposed, which uses the meteorological station to monitor the meteorological changes around the transmission line. The soil and water loss is determined through the analysis of monitoring data so as to provide data support for the restoration and protection of the surface environment along the transmission line. Compared with the traditional manual detection method, the detection method proposed in this paper can greatly improve monitoring accuracy and efficiency and save financial and material resources. The method proposed in this paper has been applied to soil and water loss monitoring of the Shaanxi Hubei ± 800 kV HVDC transmission project, and the effect is remarkable.

In order to improve the operation and maintenance efficiency of offshore wind power onshore and offshore and reduce the maintenance cost of wind turbines, on the basis of considering the onshore rising station and offshore wind turbine business as a whole, a logical framework of a safety production management platform including display layer, application layer, business support layer, data service layer, infrastructure layer, safety operation and maintenance system, and unified standard system is established[1]; the use of timing diagrams and flowcharts describes the software architecture of the safety production management platform and the business processes of each subsystem, and is implemented in Java language. The implementation of the platform will realize the intelligent management and refined management of the offshore wind power business, improve production efficiency and reduce production costs.

With the launch of the whole-process integrated digital management platform of infrastructure in various provinces in China, it is necessary to establish a set of project management evaluation methods for electric power infrastructure projects that adapt to digital management. In this paper, the evaluation method of electric power infrastructure project schedule management is proposed, and a project schedule control system, including project cost management and project schedule management, is constructed to make the schedule management of electric power infrastructure projects more adaptable to the digital management mode, so that the schedule management can make full use of the digital management features and advantages to enhance the automation and intelligence level of management.

This paper aims at the problems of unclear scheduling model and low intelligence in the scheduling technology of bulk cargo terminals, analyzes the business process and characteristics of bulk cargo terminals based on the current situation and demand of the scheduling business of bulk cargo terminals, according to the actual scheduling characteristics and use rules of the berths and yards of bulk cargo terminals, and combined with the characteristics of complex coordination factors between the berths and yards of bulk cargo terminals, A multi resource collaborative scheduling model of bulk cargo terminal based on particle swarm optimization algorithm is proposed, and the algorithm is analyzed. This paper also proposes an optimization scheme for bulk cargo terminal scheduling.

Through the effect evaluation system of coal and gas co-extraction, gas extraction pipeline monitoring system, gas disaster warning system, ventilation monitoring and decision-making system, etc., the effect evaluation of coal seam extraction can be realized, and the comprehensive parameters such as gas concentration, flow rate, temperature and pressure of each main, trunk and branch pipelines can be monitored online in real time. Online early warning analysis of underground coal mine gas, geological structure, coal seam occurrence, ventilation and management, and online dynamic monitoring and abnormal alarm of wind speed, air volume, wind direction and other parameters in each wind location, to ensure efficient and precise extraction of gas and efficient coal mining in the fourth and fifth panels.

In view of the characteristics of mountain torrent, such as sudden, frequent, destructive, and difficult prevention and control, an advanced method of grid accurate early warning based on refined rainfall forecast data and measured rainfall data, multi rainfall forecast product optimization, combined with the survey and evaluation results of mountain torrents, can accurately predict the risk of mountain torrents 1 to 3 hours in advance, and effectively improve the timeliness and accuracy of mountain torrents early warning.

The urban road access is an important connecting section for vehicles to enter or leave urban roads from buildings, and is also the location where traffic conflicts are easily to occur especially when pedestrians passing on the sidewalk. This paper sums up several types of traffic organization of urban road access, summarizes the principles of traffic organization optimization. On this basis, builds evaluation index system, uses Analytic Hierarchy Process to evaluate how about of the traffic organization at an urban road access, and analyzes the key points of optimization which include defining the traffic space and path of various traffic modes, clearing traffic guidance, and important safety protection measures. For the common types of road access, the detailed methods and examples of traffic organization at road access are given.

With the continuous development of construction projects, people have higher and higher requirements for project quality. Project quality inspection is the basis for measuring whether the project meets the construction standards, and a qualified project quality inspection and evaluation system can play an important role in the full-cycle inspection and management of project quality and supervising enterprises to regulate construction. However, today's engineering quality inspection has problems such as unclear assessment criteria, unintuitive data and slow processing speed, leading to a decrease in the authority of engineering quality inspection, inaccurate assessment and a significant decrease in public trust in quality inspection parties. Therefore, this paper adopts a new data sampling and strict analysis and evaluation, and researches and designs an engineering quality inspection and evaluation system, which is conducive to improving the supervision and management of engineering quality, facilitating engineering quality inspection, and thus reducing construction costs and enhancing the credibility of the quality inspection team. In addition, the design of the system effectively guarantees the quality of the project, avoids construction risks, greatly improves construction safety, and brings a positive impact on the healthy and sustainable development of the construction industry.

Aiming at the slow movement and small displacement of dairy cows in the pasture breeding process, but the target scale changes significantly, a SURF-KCF dairy cow teat tracking algorithm is proposed. The original KCF algorithm needs to locate the target before tracking, and the tracking frame cannot be adaptive with the scale of the target. The SURF feature detection is introduced to provide target features for the KCF algorithm to achieve automatic target matching; and the scale estimation strategy is used to achieve scale adaption of cow teat targets. The experimental results show that the proposed improved algorithm achieves cow teat target matching and localization as well as scale adaption of the target area, and long-term stable tracking. Finally, in the laboratory environment, the improved algorithm is applied to the three-degree-of-freedom robotic arm automatic milking robot to realize the cow teat positioning and tracking experiment. When the cow's teat is detected, the robotic arm can automatically move to the position of the cow's teat. Good results have been obtained after testing, which shows the feasibility and effectiveness of the cow teat positioning system.

Under the promotion of national vigorous development of port logistics construction, the construction of port distribution centre will become the top priority of future development. Before the port distribution centre is newly built, reasonable site planning is of great practical significance to enhance the competitiveness of port logistics services. In this context, this paper analyses the characteristics of port distribution centres and studies the site selection problem of new distribution centres in ports. Combining the salient features of the port distribution centre site selection problem, this paper considers all the influencing factors in the process of container freight station - port distribution centre - customer enterprise, determines the site selection objectives, and establishes a two-layer planning model for site selection; the upper layer realizes the main decision objective of optimal cost of port distribution centre, and the lower layer realizes the auxiliary decision objective of optimal customer; according to the decision objective of site selection and the characteristics of the two-layer planning model, the genetic algorithm is used to solve the problem, and reasonable cases are designed and solved by software to verify the effectiveness of the model and algorithm.

In the design of new lines and reconstruction of existing lines, there is current lack of accurate and effective simulation methods for the operation interval of express/local trains, and it cannot meet the needs of pre-computing the design effect of express/local trains operation organization plans. For the CBTC (Communication Based Train Control) system that has been applied widely, operation interval simulation method for express/local trains in urban rail transit is proposed by adopting the whole-process operation data analysis of multiple type trains running on the same path and the comprehensive operation interval determination strategy of the associated area. The simulation method can be applied to the mixed running of trains with different speed and different lengths, and has been applied to the operation interval calculation of key stations in the early-stage express/local trains operation plan of Shanghai Rail Transit Line 21. And the operation interval simulation analysis of express/local trains in various operation scenarios in the up and down direction of some stations provides key quantitative support for design decisions such as the design of subsequent station wiring, the number of trains allocated, exploiting the potential of operation capacity, and operation routing optimization.

The indoor vibration of a high-rise frame structure office building near the subway is studied using the method of field test. The research results show that the average value of the vibration acceleration effective value of outdoor point is 0.003893 m/s2 , and with the rise of the floor, the indoor vibration of the building shows a fluctuation law, and the vibration is amplified in the middle and high floors. The vibration outdoor is mainly distributed in 50Hz~80Hz, and the peak frequency is 63Hz, and the indoor vibration is significantly reduced above 40Hz, while amplified below 35Hz.

This paper discusses how to study the current situation of ship fault prediction and maintenance support through performance-based support, primary and secondary contractor support, localization support center, and military civilian integration under the mode of war zone of operations and military arms construction after the military reform, put forward the warship equipment failure prediction and health management mode under the background of military-civilian integration. This model not only enables the original military maintenance and support units to continue to play their original role in the new military struggle, can also actively introduce local qualified external forces into the equipment support, it can also encourage contractors to take guaranteed performance as a primary consideration, effectively promote the comprehensive performance of ship equipment, So as to enhance the combat effectiveness of the service.

Manufacturing transformation and upgrading are the keys for enterprises to seize the high end of the value chain and maintain global competitiveness. Digital resources promote the digital transformation of manufacturing enterprises in technology, products, business models, and other aspects. This paper first discusses the historical development and rich connotation of the digitalization of manufacturing enterprises. Secondly, new technologies in product research and development and manufacturing in the digital transformation of enterprises are introduced. Finally, the actual cases of these new technologies in enterprises are discussed. Through the summary, we hope to introduce the connotation, current situation, application status, and future development trend of digital transformation of manufacturing enterprises, to provide a reference for the research and application of digital transformation of enterprises in the future.

The decreasing characteristic size of transistors leads to a large increase in the Soft Error Rate of circuits. In view of the Single Event Transient generated by the combined circuit, this paper proposes a Triple Modular Redundancy structure Flip-Flop with filtering function to replace the standard Flip-Flop, and the Flip-Flop to be replaced is divided according to the soft error sensitivity. At the same time, aiming at the problem of automatic equalization of various indicators of the generated circuit in the replacement process, this paper explores an optimization architecture based on the "BP-NSGA-III" algorithm, which can automatically determine the position, number and radiation level of the Flip-Flop to be replaced in the circuit, and achieve the comprehensive optimization of the three design indicators of radiation hardening performance, area and power consumption.

Objective: The posterior parietal cortex (PPC) is involved in cognitive attentional activity, according to neuroimaging research. Its specific role in the brain network responsible for attention need to be further identified. Approach: In this study, an attention network test (ANT) was designed. 1-Hz low-frequency repeated transcranial magnetic stimulation (rTMS) was performed over the right PPC. Behavioral and EEG data were analyzed before and after stimulation. Main results: The behavioral results showed that the frontoparietal network was directly connected to spatial orientation and executive functions. Low-frequency TMS produced an inhibitory effect in opposition to the learning effect, which persisted 24 hours after stimulation and was most pronounced under spatial cues. Event-related potentials (ERP) results showed that the stimulation inhibited the posterior parietal brain neural activity, and in particular, had a significant inhibitory effect on spatial attention. Significance: PPC is crucial in attentional orienting and executive functions. Exploring ways to intervene in brain activity has significant implications for people to recover attentional function.

While big data technology accelerates the development of campus intelligence and informatization, it also makes traditional campus security defense methods difficult to meet the needs. Massive data and the complexity of operation and maintenance management also affect the informatization construction of smart campus, bringing many security risks. Research the distributed management of data based on SDN, and use the new address hopping technology to achieve the active defense of the target, and build the architecture of the security platform considering the data type. Test and verify the architecture design proposed in the study. The results show that the security platform based on SDN and active defense technology performs well in network delay improvement and throughput, and its maximum CPU load difference with the fixed port reaches 9%. The anti attack time response changes are relatively stable, the accuracy of data transmission is more than 97%, and the root mean square error of data processing is small, It improves the protection level while ensuring data security.

In order to meet the power demand of low-voltage users and reduce the power cost, a low-voltage user demand response management platform based on blockchain technology is proposed. Based on the blockchain structure, the overall architecture of the demand response management platform is designed, including the response layer, the main chain layer and the decision-making layer. The platform hardware mainly includes the consensus mechanism module and the orderly power consumption management module of the low-voltage user demand response chain. The platform software part calculates the power supply cost of the power terminal and the power consumption cost of the low-voltage user, and constructs the objective function according to the cost calculation result. The reverse induction algorithm is used to calculate the optimal power consumption of low-voltage users, and the demand impact management problem of low-voltage users is transformed into a single objective solution problem. By solving the objective function, the demand response management of low-voltage users is completed. The experimental results show that the platform can play a good peak shaving effect, and can effectively improve the safety of the platform and the safety of low-voltage users.

Due to the strong nonlinearity of navier stokes equation, it is difficult to solve the hydrodynamics simulation problem. As a century problem, it is still a major difficulty in the academic community. With the improvement of computer ability and the development of data platform, some new changes have taken place in the research direction and content of turbulence model. The data-driven machine learning method is different from the traditional approximate equation solving method in physics, and shows its application potential in highly complex flow fields. In this study, convolution cyclic hybrid neural network is used to predict the complex flow field, and the generated confrontation network is used to generate the simulated flow field.

In the energy Internet integration mechanism, any abnormal data behaviour may affect the operation security of the network system. In order to accurately detect the abnormal transmission behaviour of data stream samples, this paper studies the abnormal detection method of the large data streams in energy Internet based on high-order statistical features. According to the principle of higher-order statistics, this paper defines statistical indicators. Combined with the characteristic function expression, the range of phase space parameters is determined, and the verification of abnormal large data stream information is realized. Hadoop distributed detection framework is set, and the accurate calculation result of abnormal scheduling coefficient is obtained by solving the vector of the high-dimensional large data stream, and the design of abnormal detection method for large data stream of energy Internet based on high-order statistical characteristics is completed. The experimental results show that under the high-order statistical principle, the detection accuracy of abnormal information of data stream samples by energy Internet hosts is improved, which has outstanding value in maintaining the running security of the network system.

Brain-computer interface (BCI) is a technology that enables direct communication with machines through brain signals. As BCI technology evolves into new applications, the need for robust feature extraction technology will only continue to increase. In BCI tasks with small amplitude variations, such as low-contrast oddball classification, classification and recognition of EEG signals are challenging. Inspired by fine-grained classification in the field of image classification, this study innovatively uses and integrates some fine-grained classification strategies based on convolutional neural networks to improve the classification performance of the system through feature learning and feature fusion at part-level and multi-scale. Ten subjects were recruited to perform the subthreshold low-contrast Oddball task. The results showed that Fine-grained EEG CNN had a better performance in small-difference EEG signal classification compared with the classical EEG convolution neural network. Therefore, we provide a valuable new strategy for improving the classification performance of small-difference EEG signals.

Aiming at the issues that the current Generative Adversarial Network (GAN) used for image super-resolution reconstruction is easy to produce false details and the mapping dependence is not flexible enough, a One-to-many Generative Adversarial Network (OTMGAN) based on Enhanced Super Resolution Generative Adversarial Network (ESRGAN) was proposed. First, the model uses one-to-many constraints to allow the estimated patches to dynamically seek the best supervision during training, instead of the one-to-one constraint from low-resolution (LR) images to high-resolution (HR) images, thus improving the loss function of the model. Then, a new region-aware adversarial learning strategy is used to distinguish between flat regions and textured regions, so that the model can adaptively generate more realistic details for textured regions during training. Finally, the experimental consequences of image super resolution reestablishment on the public datasets BSDS100, Set5, Set14 and DIV2K show that the new model is significantly superior to the classical models such as ESRGAN in terms of Peak Signal-to-Noise Ratio (PSNR), Structural Similarity (SSIM), and Learning Perception Image Patch Similarity (LPIPS).

A way of incorporating landmark information matrix QR to affect the global path planning algorithm is proposed for the use of landmarks in robot localization and navigation. It is also investigated how this method affects the pace at which the original algorithm solves problems. The reward and punishment items in this technique include dangerous locations with lots of obstacles around them, landmarks with location information connected to the ground, and the two combined. Three representative common robot path planning algorithms are also imposed as influences. Through MATLAB simulation experiment, find the optimal path planning algorithm that is appropriate for applying reward and punishment by comparing the quality of the robot's driving path and the algorithm solution speed before and after the reward and punishment. According to the simulation results, the reward and punishment approach is practical and efficient. The heuristic search algorithm is better suited for reward and punishment, and both its path quality and speed of solution have greatly increased.

With the acceleration of economic globalization, the importance of translation services has gradually manifested. The machine translation technology has a long and glorious history from statistical machine translation to neural machine translation, At present, machine translation software is emerging, mostly following the rules of natural language processing. In order to achieve quality and efficiency in translation, the various ambiguities in the language should be processed accurately and the speed of translation should be increased, while the anthropomorphism of machine translation should be enhanced and the machine's knowledge of human language should be constantly improved. Therefore, it is important to strengthen the research of machine learning technology, and to insist on the research on machine analogy translation technology based on machine learning is an important research topic.

In order to prevent the TT&C antenna from having a significant impact on the aerospace measurement and control work due to the unexpected shutdown of the transmission chain, this paper collects vibration, noise, and rotational speed signals in real time, and obtains the characteristics of the traditional antenna system based on the physical model of the antenna transmission chain (reduction box, motor). After removing the random impact interference in the original vibration signal, the diagnosis can be made by analyzing the gear meshing frequency, meshing frequency multiplier and its variable frequency band of the vibration signal under multiple working conditions (the intervals of the side-band frequencies are equal, all of which are the rotation frequency of the gear shaft). The bearing characteristic frequency is obtained by resonance demodulation, and the fault type is judged according to the characteristic frequency. For the first time, the fault diagnosis and degradation trend analysis of the antenna transmission chain based on the physical model was completed, which solved the problem that the abnormal noise of the servo mechanism could not be clearly distinguished by the post personnel during the operation and maintenance process, and realized intelligent fault diagnosis and prognosis.

The current performance management systems in process manufacturing are built on a centralized architecture. In the event of a single point of failure in the system, the entire system network is easily exposed to attackers. Secondly, as the amount of data increases, centralized storage will also increase the burden on the system, and opaque information will also lead to trust problems within the enterprise. In response to the above problems, this paper designs a performance management platform based on blockchain, which aims to provide a secure and reliable service platform for enterprises, which has the characteristics of access control and data transparency, traceability and non-tampering. This paper gives the overall framework, hierarchical structure, and system architecture design scheme, and designs a smart contract that automates data acquisition and calculation. Finally, this paper uses blockchain technology to build a performance management system in process manufacturing, and verifies the feasibility of the system by testing the throughput of the system.

With the rise of short video platforms, video recording and automatic editing technology has become increasingly important to the development of short video, artificial intelligence algorithms can use massive video data to understand the content of time-series video, providing a technical basis for video recording and editing, specifically, video recording and automatic editing methods based on artificial intelligence algorithms already have the corresponding data base, technical basis and application basis In particular, AI algorithm-based video recording and automatic editing methods have the corresponding data, technical and application bases. Therefore, this paper discusses the method of video recording and automatic editing based on artificial intelligence algorithms. This paper firstly describes the automatic video editing process and the extraction of temporal action features, then designs the automatic editing system and the video recording and coding system, and finally analyses the detection speed of the system. The research results demonstrate that the AI algorithm-based automatic editing system passed the concurrency test with good performance and the AI retrieval scheme has a fast detection speed to meet the user's editing needs.

During the COVID-19 coronavirus epidemic, people usually wear masks to prevent the spread of the virus, which has become a major obstacle when we use face-based computer vision techniques such as face recognition and face detection. So masked face inpainting technique is desired. Actually, the distribution of face features is strongly correlated with each other, but existing inpainting methods typically ignore the relationship between face feature distributions. To address this issue, in this paper, we first show that the face image inpainting task can be seen as a distribution alignment between face features in damaged and valid regions, and style transfer is a distribution alignment process. Based on this theory, we propose a novel face inpainting model considering the probability distribution between face features, namely Face Style Self-Transfer Network (FaST-Net). Through the proposed style self-transfer mechanism, FaST-Net can align the style distribution of features in the inpainting region with the style distribution of features in the valid region of a face. Ablation studies have validated the effectiveness of FaST-Net, and experimental results on two popular human face datasets (CelebA and VGGFace) exhibit its superior performance compared with existing state-of-the-art methods.

In the modern security system, material support in emergency is an important part. In order to ensure the supply of necessary living materials and proprietary materials in wartime, major natural disasters and emergency epidemics, all countries have introduced corresponding measures. Emergency logistics system is a necessary condition to ensure the smooth and timely distribution of emergency supplies. This paper applies the complex network theory to study the main statistical characteristics of the three-layer emergency logistics system considering the material needs, material manufacturer and raw material resource supplier, which can provide a reference for optimizing the resource allocation and anti destruction ability of the emergency logistics system.

Focusing on the strategic goal of "Safe China", we will build a technical system for modernizing the theory and governance capacity of a smart society, and solve the problems of lagging theoretical innovation in resolving multiple conflicts and disputes, insufficient systematization of intelligent auxiliary technology for risk control and management, and poor coordination and linkage of governance. Enhance the ability to prevent and resolve major systemic risks, enhance scientific supervision and service capabilities, and provide scientific and technological support to promote the modernization of social governance system and governance capacity and build a smart society. Need to build a platform for analysis and control of conflicts and disputes and evaluation of their resolution effects. The platform aims to address the main problems in the resolution of multiple conflicts, build assessment indexes for the impact of conflicts and disputes, design intervention norms, multiple resolution mechanisms and policy tools synergistic model, build a large- scale dynamic knowledge map in the field of conflicts and disputes integrating the characteristics of the times, build an intelligent platform for the whole process of conflicts and disputes disposal, build a platform for psychological risk assessment and early warning, psychological assistance and automated psychological intervention, build The platform for analysis and control of contradictions and disputes and evaluation of the effectiveness of their resolution will be demonstrated and applied.

(Named Entity Recognition, NER) and (Relation Extraction, RE) are two basic tasks in Natural LanguageProcessing, NLP). Due to the indistinguishable boundaries between entities in Chinese and the lack of obvious formal signs, Named entity recognition has always been a difficult point in the Chinese field. Although it has made good progress in Chinese, it still lacks the semantic understanding ability in special fields and the effect is not ideal. In this paper, the algorithm of deep learning and self-attention mechanism are deeply studied. By improving LatticeLSTM model and integrating self-attention mechanism, the ability to understand Chinese semantics is improved, and a small amount of labeled data is expanded by data enhancement to build a data set in a special field to complete the task of named entity recognition.

To solve the problem of difficult feature extraction and low recognition rate of radar signal under low signal-to-noise ratio, this paper proposes a radar signal recognition method based on time-frequency feature extraction and convolutional neural network. This method uses short-term Fourier transform (STFT) to obtain two-dimensional time-frequency images of radar signals, and then sends the images to convolutional neural networks for deep feature extraction, and realizes the classification and recognition of radar signals through convolutional neural network classifiers. The simulation results show that for different intra-pulse modulated radar signals, when the signal-to-noise ratio is -5dB, the overall recognition accuracy of the proposed model can reach more than 93%, which effectively solves the problem of low radar signal recognition rate under low signal-to-noise ratio.

To realize an intelligent and automatic way to test the ability of the metasurface to control electromagnetic (EM) waves, we first design an element with a certain structure, which is loaded with active devices (PIN diodes) and is controlled by the digital bias voltage. Thus, the phase responses of the unit can vary according to the bias voltage. So, we can switch the functionality of the element easily by just controlling the bias voltage. After designing the cell, the corresponding metasurface is created, and its function is simulated under CST microwave studio. At last, an experiment scheme is put forward based on an automatic scanning rack and MATLAB software project, both physically and virtually, reducing the workload to obtain data on EM properties.

To meet the speed and accuracy requirements of road semantics segmentation algorithm scenarios, a lightweight semantics segmentation model, MADNet, based on MobileNetV2, is presented, which effectively reduces the computational load of convolution neural network. The feature enhancement module uses a pooled pyramid of empty space convolution. In the deep and shallow part of the MADNet network, attention mechanism is added to compensate for the decline in feature extraction accuracy of MobileNetV2. Finally, the data enhancement algorithm is used to train the identification task in rain and snow weather, road depression and automobile dataset scenarios. The results of ablation test and algorithm comparison test verify that the algorithm proposed in this paper can achieve a better effect and faster speed for road depression and fast semantic segmentation of vehicles in rain and snow weather.

This study aims to reveal the spatial correlation effects of the digitization of regional industries. This study uses machine learning and text quantification to construct a digital index of listed companies in China's traditional industries, and to perform regional clustering. Based on the industrial digital development index from 2008 to 2021, this study choose representative annual features to fully demonstrate the spatial aggregation of digital industrial development. The findings of this paper provide the digital core position and the cohesive subgroups in different regions of China. Beijing, Shanghai, and their surrounding provinces are in the total core area of the spatial connection network of digital industrial development, while most of the provinces in the western region are in the absolute edge area, forming a typical distribution trend of "strong in the east and weak in the west."

We systematically carried out a comparative study of 12 kinds of tree-based models for the task of rolling bearing fault diagnosis, using the publicly available XJTU-SY bearing dataset as an example. The results show that the ensemble tree models including random forest (RF), extremely randomized trees (ETs), and deep learning tree model (multi-Grained Cascade Forest, i.e. gcForest) are high-precision and strong robust models suiting industrial application of this task, which have better-performing detecting accuracy and stability than conventional machine learning and single tree models (decision tree and extremely randomized tree). gcForest achieves 99.37% test accuracy using only 3% of the training samples, while RF and ETs also exceed 98%, which outperform eXtreme Gradient Boosting (XGB), Light Gradient Boosting Machine (LGBM), categorical boosting (CatBoost), and neural tree models, i.e. Neural Network with Random Forest (NNRF) and TabNet. RF and ETs are better suited for real-time industrial detection tasks in terms of time consumption. This study provides a scientific basis for the rational selection of rolling bearing fault diagnosis methods.

Today, hacking attacks have affected countless Internet companies and users. Especially DDos attacks. Such attacks are long-lasting and cheap to launch. Currently, such defense mechanisms are not perfect, so DDos attacks have become one of the biggest threats to the global Internet environment. In response to this situation, researchers have proposed some new DDos defense mechanisms to make up for the previous vacancy. Through the experiments of the researchers, it was concluded that the performance of the newly proposed algorithm and mechanism was better than that of the previous ones. In addition, the researchers also proposed solutions based on human solvers to bypass the captcha problem. According to the research objects and research methods, this paper analyzes and classifies the collected relevant literature, aiming at summarizing and discovering possible innovation points. The experimental analyzes and reports of these literatures are then provided. In the final part of this survey, we summarize all the literature and propose research directions and recommendations.

With the rapid development of remote sensing technology, remote sensing registration plays an important role in the assessment of various natural disasters, especially earthquakes. However, multi-temporal remote sensing images for the assessment have some characteristics, e.g. large-scale and rotation, resulting in challenges of remote sensing registration. In order to better register remote sensing images, we propose a new image registration method with a deep learning feature matching strategy. We first extract the pre-match point sets M and S by using SIFT-FLANN (SIFT-Fast Library for Approximate Nearest Neighbors). Second, we filter out the correct matching point pairs from M and S by using a multiscale neighborhood information network and a dual-path ConvNeXt network with self-attention-guided local information enhancement. Thirdly, we register multi-temporal remote sensing images by solve the model parameters of the spatial transformation. Finally, we evaluate our proposed method using a variety of remote sensing images with different phases, including visible light images with different illumination, scale and geometry changes. On the remote sensing image dataset containing images of pre- and post-earthquake, we compare our method to existing state-of-the-art methods and provide the results with the evaluation indexes such as Root Mean Square Error (RMSE). The results show that our method for multi-temporal remote sensing registration has a higher registration accuracy and more robustness.

High-precision optoelectronic tracking platforms deployed in the form of pods onto carriers like UAVs and capable of isolating external disturbance and maintaining stability in inertial space are referred to as airborne optoelectronic platforms. The development of today's society is requiring an airborne photoelectric stabilization platform with longer communication distances, faster speeds, clearer images, stronger anti-interference capabilities, and higher accuracy due to the ongoing improvement of the requirements in the field of reconnaissance. The photoelectric platform's visual axis stability control system is a crucial component. It will be impacted by various internal and external disturbances during the tracking and detecting process, such as carrier movement, mechanical vibration, various interfering moments, and measurement noise, which will reduce measurement accuracy. In view of the friction torque interference caused by the photoelectric platform in the work, the active disturbance rejection control technology which is easy to realize in engineering is applied to the speed ring for compensation test. The simulation and comparison experiments of the active disturbance rejection controller and the traditional PID controller are carried out to verify the compensation effect of the designed active disturbance rejection controller on the photoelectric platform. Through the established model and simulation curve, it can be seen that compared with the traditional PID control algorithm, the tracking response performance of the active disturbance rejection controller designed in this paper has been significantly improved, indicating that this research basically achieved the goal.

This paper proposes an improved wireless sensor network node location algorithm to locate terminal nodes of ZigBee wireless network in soybean farmland. The Gaussian data screening model was used to modify the measured distance of the received signal intensity, and the strategy of introducing variogram was adopted on the basis of standard particle swarm optimization. The advantage of each variogram was applied to the population in the process of algorithm search, so that the particles could jump out of the local optimal, ensure the global search traversal ability, and obtain the precise location of sensor nodes. The comparison between the standard particle swarm positioning algorithm without correction distance and the improved positioning algorithm in this paper shows that the improved positioning method has higher accuracy.

In order to improve the interactivity of industrial robot, this paper has designed a hand gestures recognition system for industrial robot control. The system contains two MPU6050 modules, Arduino Uno, computer and a ABB IRB 120 industry robot. Two MPU6050 modules collects the human hands movement signals which will be transmitted to Arduino Uno to process. The upper computer can receive signals processed and send commands through serial port. Also, the upper computer can send signals which include the robot movement mode parameters , speed parameters , direction parameters and so on to ABB IRB 120.Thus, the movements of the robot can be controlled by the movement of both hands where the prototypes were worn . The experimental results show that the correct rate of gesture recognition of the system higher than is 99% and the system works well, which achieves the expected purpose.

This paper aims to develop a new diagnosis and treatment platform for autism spectrum disorder based on artificial intelligence in view of the difficulties in the autism diagnosis and treatment industry in the market, such as a mix of institutions, shortage of talents and high treatment costs, as well as the shortcomings of related diagnosis and treatment digital platforms with single functions and low differentiation. The platform is mainly presented in the form of websites, apps and small programs. It integrates the functions of autism diagnosis, autism intervention, prognosis monitoring and other functions. It quantifies and visualizes the diagnosis data of autism through artificial intelligence technology, and provides an intelligent "stethoscope" for autism diagnosis, with a view to further advancing the diagnosis age of children. To achieve early detection, intervention and treatment of autism, so that children with autism have a better prognosis. Families will be connected with professional resources through artificial intelligence, and services between people will be connected through science and technology, allowing professional intervention from organizations to enter families.

As a kind of clean energy, natural gas is widely used and has achieved great development. However, natural gas enterprises are facing some difficulties now, such as difficulty in payment, maintenance of pipeline network, safety of gas use, and distribution of natural gas consumption. This paper studies that the use of IoT technology to establish an ecosystem in the natural gas industry can effectively solve those problems. In this paper, the advantages brought by the ecosystem for the digital transformation of natural gas are introduced firstly. Then this paper introduces how to establish an ecological model of the natural gas industry. The tasks undertaken by relevant stakeholders in the construction of the ecosystem, the process of data collection by taking the pipeline pressure as an example, and some intelligent applications of the ecosystem are presented. The problems existing in the current ecosystem construction process and future research directions are given finally. The research results of this paper can be used not only for the construction of natural gas industry ecosystem, but also as a reference for other industries to establish ecosystems.

Aiming at the problem that there are many factors affecting the comprehensive energy service level and it is difficult to quantitatively analyze them, this paper proposes a comprehensive evaluation method of the comprehensive energy service level based on ANP． Firstly, a comprehensive evaluation index system of comprehensive energy service level is constructed from five aspects: management level, economic benefit, operation effect, social impact and sustainable development level. Secondly, in order to achieve comprehensive evaluation, ANP method is used to solve the corresponding weight of the proposed comprehensive energy service level evaluation index. Through case analysis, important indicators are obtained. so as to provide reference for the operation and development of future integrated energy service providers

Smart cities apply Internet of Things equipment and communication technology to closely connect with citizens, collect and analyze a variety of data in the city to optimize the efficiency of urban operations and social services, and provide convenience for citizens in daily life. The realization of a smart city needs the help of various advanced technical means. The ServiceGIS model can be dragged and set up reasonably in the form of components when the platform is running to customize the thematic application system, which can basically meet the customization of the thematic application system in the component-based sharing mode. But in the customization process, the component objects are frequently created when being dragged. The memory occupation is large, so the platform performance is not high, and the component-based sharing effect is not good. To ensure the accuracy of multi-source data exchange, based on the data processing process of smart city data sharing and exchange platform, through the application functions of GIS such as spatial analysis and the data analysis ability of Logistic model, the process of data exchange and sharing is designed as a micro-service. Each function of the system is constructed as a single micro-service. Different data services and governance solutions can be configured according to application scenarios. Services can be deployed independently. Resources between micro-services can be isolated, and the functions of a single micro-service can be better maintained. The application of micro-service architecture patterns in practical projects can realize the decoupling of system modules, thus improving the flexibility and scalability of the system.

With the development of information technology and intelligence in power grid enterprises, more and more power terminals such as smart meters and centralized collectors are being accessed remotely through various networks, especially wireless public networks, making the use of marketing terminals to launch network attacks increasing day by day. Usually, marketing terminals are deployed in uncontrolled user sites, and once deployed, they are used for long periods of time, exposing them to the serious threat of illegal counterfeit terminals and theft of legitimate terminals to attack the main power marketing system in the information intranet of the power grid enterprise. This paper proposes a zero-trust access control mechanism for power networks based on service reputation assessment, using real-time reputation values within a cycle and historical reputation values obtained from the previous test cycle to obtain a comprehensive reputation value of the service. Experimental results show that continuous trust assessment can be accurately performed based on its runtime reputation value, ensuring the continuous trustworthiness of the endpoint identity.

In order to improve the stability and safety of unmanned ship navigation, this paper proposes an unmanned ship measurement and control system based on FPGA as the core controller. The shore-based control terminal sends control commands to the unmanned ship through the DTU communication module, and outputs commands to control the unmanned ship's ignition, flameout, and gear switching after data analysis by the FPGA controller in the ship. At the same time, AD conversion sensors and differential GPS are used Sensors, temperature and humidity sensors, linear displacement sensors and other sensors detect the real-time status of the unmanned ship, send the real-time status parameters of the unmanned ship to the shore-based control terminal through the DTU communication module, and display the received data on the LCD On the screen, so as to realize the function of real-time control and data monitoring. After testing, the results show that this system can perform real-time control and data monitoring on unmanned ships.

With the continuous deepening of the power market reform, the contradiction between the priority assurance electricity of the power generation side and the consumption side and the free competition market trading electricity is gradually prominent, which affects the power plan balance management and market organization design of market managers. Under this background, considering multiple kinds of constraints such as unit maintenance, electricity assurance, contracts execution, actual generation deviation, and taking maximizing the electricity guarantee at the generation side as the objective, this paper constructs a modified matrix factorization model based on the two-way horizontal-vertical intersection of power generation priority, and designs an engineering practical management mechanism that meets the two electricity balance management needs of annual balance and rolling balance, and verifies its effectiveness and adaptability by practical examples, which provide important support for market management and system stability in the power market development.

With the continuous development of science and technology, the combination of ship transportation and computer technology is the development trend of the future shipping industry. Most of the traditional dangerous goods stowage segregation verification is limited to manual verification, which is time-consuming and laborious, and the accuracy is difficult to guarantee. Based on this, the intelligent core carrying platform of dangerous goods container is designed. The platform is designed with HTML technology, database technology and Java programming language. It is a container cargo management platform that integrates ship drawing generation, cargo management, regulation inquiry, law and regulation editing and inquiry, to help relevant inspectors improve work efficiency and realize electronic management of dangerous goods information.

To solve the problem of backward warehouse management, low operation efficiency and incomplete information management, this paper introduces passive RFID technology, designs the Passive RFID Technology Warehouse Management System (PRWMS). The system includes four layers of architecture, integrating the information resources of perception, access, platform and application, which can effectively improve management segmentation. This paper also studies the characteristics of passive RFID technology in factory warehouse scene, and explores the application of PRWMS in key businesses such as asset management, stock-taking, inbound and outbound management, providing a new idea for smart warehouse management. The experiment results show that the system can improve the accuracy and efficiency of factory inventory operations, and help to realize scenarios such as automated asset taking and unmanned inbound and outbound management.