Number Of Concurrent Users Research Articles

Intelligent Education Managemnt System Design for Universities based on MTCNN Face Recognition Algorithm

Face recognition technique has made significant advancements in security and attendance, but its application in teaching management is minimal. To address the issues of insufficient teacher resources and declining educational quality, the paper designs an intelligent education management system for colleges and universities based on improved Multi-task Cascaded Convolutional Neural Networks (MTCNN) face recognition. The purpose is to achieve accurate recognition of faces through improved facial recognition technology, thereby analyzing the attendance status of students, and improving the efficiency and quality of educational resource utilization. Firstly, an improved MTCNN facial recognition technology is adopted to achieve realtime monitoring of student status and attendance in the classroom through a B/S network structure. Secondly, through cluster deployment and load balancing, system stability and response speed can be improved. The results indicated that the improved MTCNN had better facial recognition accuracy and GPU utilization than traditional systems under different occlusion conditions. When there was no occlusion, recognition accuracy was 99.4%. However, when occlusion was presented at 10%, 20%, and 30%, the accuracy dropped to 92.3%, 84.25%, and 73.4%, respectively. Additionally, when the number of concurrent users was 1000, the maximum GPU utilization rate was 75%, which was 11% lower than traditional MTCNN systems. The use of an improved MTCNN facial recognition-based intelligent education management system in universities can effectively enhance the quality of classroom teaching and monitor the status of students. Further optimization of algorithm performance is needed in subsequent research to support larger-scale concurrent user usage while reducing hardware resource consumption.

In-memory database load balancing optimization for massive information processing of the Internet of Things

In order to improve the operation effect of the in-memory database for massive information processing of the Internet of Things, this paper combines the load balancing signal processing algorithm to carry out the load balancing optimization analysis of the in-memory database. According to the local transformation characteristics of non-stationary multi-component signals, an adaptive FSST algorithm is proposed in this paper. According to the signal separability condition, this paper uses the local Rayleigh entropy to estimate the window function parameters of the adaptive FSST and the adaptive FSST2. In addition, this paper adopts an adaptive window function to automatically match the local changes of the signal, so that the signal has the optimal energy aggregation in any part. The results show that when the number of concurrent users is the same, the time consumption, throughput and bandwidth of the proposed method are always higher than the method proposed in reference [10]. When the number of concurrent books is 97, the time of the proposed method is 45000ms, the time of the proposed method is 40000ms, the highest throughput of the proposed method is 2.30 MB/s, the highest bandwidth is 11.9MB/s, the highest throughput of the method proposed in reference [10] is 2.2 MB/s, and the highest bandwidth is 11.8MB/s. The load balancing optimization algorithm of the memory database for massive information processing of the Internet of Things has good results.

Performance analysis of 2D optical code division multiple access through underwater wireless optical medium

The performance of a two-dimensional optical code division multiple access (2D-OCDMA) system using an underwater wireless optical (UWO) medium is assessed in this work. The optical source is an LED with a working wavelength of 532 nm, and the optical detector is a p–i–n photodiode. When calculating the bit error rate (BER), the phase-induced intensity noise (PIIN), thermal noises, and shot sounds are taken into account. The user code address is set using 2D perfect difference (2D-PD) codes. Link distance, inclination angle, beam divergence angle, transmitter power, and the number of concurrent users are all taken into account when determining the BER performance. For various water media, such as pure sea water (PSW), clear ocean water (CLOW), and coastal ocean water (CSOW), the performance of the suggested system is examined.

Application of AI technology in personalized recommendation system for financial services

Abstract How to quickly and accurately retrieve the products that users are interested in from a huge amount of financial products has become a business pain point that financial institutions must solve. In this study, an interpretable EPRSA model for personalized financial service recommendations based on self-attention mechanisms is proposed by combining an LSTM model and an LDA topic model with AI technology support. A customized recommendation system for financial services is constructed by introducing the Nginx server into the Flask framework, and the design of the database and personalized recommendation module is interpreted. For the financial service personalized recommendation system proposed in this paper, its recommendation performance and system performance are tested, and the stock financial products are selected as the recommendation objects to explore its recommendation effect. It is found that the DNCG index of personalized recommendation of financial products of the EPRSA model is improved by 40.18%, the average response time of the system when the number of concurrent users is 1,000 is 1.96 s. The average quality of the personalized recommendation of the collection of stocks reaches 0.153. The customized recommendation of financial services using AI technology can select financial products based on the investor’s preference, help investors better understand the product returns, and improve the service quality of the financial industry.

From data to design: AI practice in design decisions

Abstract Facing the increasingly fierce market competition, enterprises need to make correct marketing decisions. Based on the decision support system, cloud server, and SOA framework, the article establishes an enterprise intelligent marketing decision-making system by combining the TCP/IP communication protocol and designing a data warehouse to store the marketing decision-making data. The Apriori algorithm in association rules is used to generate marketing rules to assist marketing decision-making, the marketing data is classified using the random forest algorithm, and the sparrow search algorithm optimizes the parameters of the random forest model. In practice, simulation experiments were designed to analyze the performance of the random forest model and the marketing decision-making system, and they were applied to the marketing decision-making example of the e-commerce platform. It was found that the AUC value obtained when the number of binary trees of the random forest model was 75 was 0.836, and the number of conflicts per second of the system was only 0.41 when the number of concurrent users was 5*104. The use of association rules resulted in eight marketing decisions, with the highest probability of user purchase prediction reaching 98.54%. Based on the intelligent marketing decision system, it can help decision-makers better analyze market changes and provide decision support for enterprises to develop scientific and reasonable marketing strategies.

Research on the method of fine-tuning teaching quality improvement in higher education under digital empowerment

Abstract With the rapid development of information technology, digital technology is also continuously applied to the teaching of higher education, and colleges and universities more and more emphasize the application of intelligent teaching guidance systems. A feature-weighted Bayesian algorithm is constructed in this study by assigning different weights to each attribute depending on its influence on the Bayesian classification results. On this basis, combined with the error-reversing BP neural network algorithm, it realizes refined intelligent instruction and develops an intelligent instruction system for higher education based on the ternary model. The transaction success rate reaches 98% when the number of concurrent users is below 4000, and the transaction success rate is 90% at 8000, and the system has good stability. The average classification accuracy of FWNB algorithm in this paper is 84.95%, which is larger than SWNB and HCWNB, and the average classification time is 3.17s, which is smaller than SWNB and HCWNB. The FWNB classifier achieves high classification accuracy at a low computational cost. The system in this paper can better mobilize learners’ enthusiasm, drive learners to study diligently and inspire learners to improve their learning ability, which leads to improved teaching quality.

Intelligent education management system design for universities based on MTCNN face recognition algorithm

Abstract This paper first constructs an intelligent education management system for universities according to their needs and explains its logical and technical architecture. Secondly, a multi-task convolutional neural network with MTCNN is used to detect faces, and different loss functions are selected to ensure recognition accuracy. Finally, the effectiveness of the application of intelligent education management systems in universities is verified through performance tests. The results show that the time consumed for face recognition detection using MTCNN is 524ms, and the response time of each function of the system does not exceed 500ms when the number of concurrent users is less than 500, which indicates that the intelligent education management system based on MTCNN face recognition algorithm has a good response speed and meets the requirements of intelligent education management in colleges and universities.

Big data-based digital management system for the whole process of financial reporting in SMEs

Abstract Based on big data technology, this paper designs a digital management system for the whole process of financial reimbursement and gives the automatic transformation process of digitalization of financial reimbursement claims and accounting documents. In the K-Means algorithm, the AHC algorithm idea is introduced to construct the DH-K-Means clustering algorithm, which in turn enables the financial reimbursement behavioral portrait of enterprise employees to be constructed. To confirm the effectiveness of the system application in this paper, performance testing and portrait analysis were carried out. The results show that the maximum memory utilization of the database server is 50.42% when the number of concurrent users is 100, and the average response time of the system reaches a maximum of 825.63ms when the number of concurrent users is 200. Based on big data, the whole process of financial reporting digital management system has good stability, which can make enterprises more aware of their financial situation and then develop appropriate financial reimbursement strategies.

An Exploration of the Practical Path of Internet Civic Education in Student Management in Colleges and Universities Based on K-means Clustering

Abstract This paper first analyzes the path of network ideological education to boost student management and constructs a student management platform that integrates network ideological education using big data technology. Secondly, K-means clustering analysis is used to mine students’ campus behaviors, and the DPC algorithm combined with the improved AdaBoost algorithm is used to detect students’ academic anomalies so as to help schools better realize student management. Finally, performance testing and application analysis were conducted to verify the effectiveness of the student management platform that integrates online ideological education. The results show that when the number of concurrent users is 5000, the CPU occupancy rate and response time of this platform are 10.34% and 0.52 s. It is able to analyze and detect abnormalities in students’ campus behaviors and academic situations and encourage universities to analyze students’ situations through visual reports. This shows that the student management platform integrating network ideological education in the era of big data can promote the level of student management in colleges and universities.

Exploration of Enterprise Financial Management Innovation Based on Accounting Informatization under the Background of Big Data

Abstract This paper first demonstrates an enterprise-intelligent financial management platform built on big data technology. Secondly, KPCA is used to preprocess financial data to improve the accuracy of financial data warnings and combined with the XGBoost algorithm to construct a financial warning model to analyze the enterprise’s economic crisis. Finally, the enterprise’s intelligent financial management platform underwent performance testing and prediction analysis. The results show that when the number of concurrent users is 100, the average response time of the platform is 1.94s, and the error rate of the system is about 0.5%. The platform can also predict and analyze financial data of the enterprise, which can help the enterprise better understand its financial situation and formulate a development plan. In summary, accounting automation can promote the development of enterprise financial management innovation. Intelligent financial management platforms can further realize enterprise accounting informatization to help enterprises achieve good economic development.

Research and Effectiveness Analysis of Innovative Teaching Models of Physical Education in Colleges and Universities under Convergent Network Architecture

Abstract In order to realize the innovation of sports teaching mode, this paper first combines the motion capture technology and three-dimensional modeling technology, based on the objectives and theories of sports teaching in colleges and universities, and constructs a college sports auxiliary teaching system under the fusion network architecture. Then, the three-dimensional modeling of sports action, the extraction of key sports action features, and the use of generalized discriminant analysis and hierarchical SVM construction method for the degradation and classification, respectively, to achieve the recognition of the sport in sports teaching. Finally, the effectiveness of the system and teaching model was tested and evaluated through the use of Loadrunner and SPSS software. The results show that the response time is 2s when the number of concurrent users is 100, the utilization rate of CPU is 64.2%, and the mastery of sports knowledge and movement skills of the experimental class is higher than that of the control class by 0.18 and 0.26, respectively. The innovative teaching mode of physical education in this study is effective.

A study on the improvement of student education management in universities based on depth-constrained Boltzmann machine

Abstract In this paper, a student education management platform is constructed using ASP.NET development technology. Secondly, a fast CD method is used to update the main parameters of RBM, and multiple restricted Boltzmann machines are used to jointly form a depth-constrained Boltzmann machine for the personalized recommendation of educational management methods. Finally, a performance test analysis was conducted to verify the platform’s effectiveness presented in this paper. The results show that when the number of concurrent users is 600, the maximum response times of student management, faculty management and education management functions are 2.79s, 2.95s and 2.81s, respectively, and the CPU occupancy rate is less than 20%. The education management platform with good performance can help improve and innovate student education management.

Scalable Computing Infrastructure for Online and Blended Learning Environments

With the growing popularity of online learning and blended learning, as well as the rapid development of cloud computing and big data technology, scalable computing infrastructure has become an indispensable part of building a modern education platform. Method: Five experiments were conducted to test the scalability and reliability of computing infrastructure based on online and blended learning environments. The experiments include the performance comparison of online learning platforms based on different virtualization technologies, the performance comparison of online and hybrid learning environments under different loads, the comparison of online learning experiences under different bandwidth constraints, the system stability test under different user numbers, and the comparison of access speeds in different regions. Result: The experimental results showed that on an online learning platform using the KVM (Kernel-based Virtual Machine) interface, when the number of concurrent users is 99, the response time is 100.9ms, and the CPU (Central Processing Unit) utilization rate is 60.9%. Under low load conditions, the concurrent access volume is 200; the response time is 50ms, and the throughput is 10.3. When accessing locally, the latency is 9.19ms; the download speed is 500.3KB/s; the network throughput is 399.8KB/s. Conclusion: Exploring the scalability, reliability, performance, stability, and access speed of online learning platforms is crucial for improving platform competitiveness and ensuring user experience.

Green Power Consumption Digital Identification System Based on Blockchain Technology

In China, the promulgation of a green power identification system has gradually shifted from electricity power generation to consumption. However, there is no mature digital identification system for green power consumption enterprises. Exploiting the open, transparent, and immutable characteristics of blockchains, this study establishes a digital identification system for green power consumption based on blockchain technology. This system uses expert scoring and the entropy weight method as the evaluation algorithm for the green power consumption chain, issues non-fungible tokens as digital identification for consumption enterprises, and realizes the automatic generation of identification through smart contracts. These functions guarantee the credibility of the certification process and the uniqueness of the generated identification. The results of the experiments show that, in the case of multi-user concurrent requests, the number of concurrent users that the system could handle at optimal processing efficiency was 500, and block generation was stable. The proposed system has high practicability and stability.

Design and Application of College Student Management System Based on Big Data Technology

In order to effectively manage the employment information of colleges and universities and improve the employment ratio of college graduates, the employment information management system of colleges and universities under the big data environment is designed. The graduate management platform in the system is used for graduates to edit personal information, understand employment-related information, and check recruitment information. The enterprise information management platform is used for enterprises to edit their own materials and publish recruitment information, so as to find graduates meeting the job requirements. The personalized recommendation platform uses the recommendation method based on users’ historical information to achieve offline employment recommendation and uses the recommendation method based on real-time user behavior data to achieve online real-time employment recommendation and improve the employment ratio. The employment information tracking management platform is responsible for recording graduates’ employment information and verifying the authenticity of recruitment information. The experimental results show that the system has a fast response time and low resource occupancy rate when the number of concurrent users is different. The employment rate of college graduates is effectively increased.

A Low-Power Remote Information Monitoring System of Cold Chain Logistic Based on NB-IoT

<p>With the development of information technology, cold chain logistics monitoring systems are widely used in transportation of fresh food to detect the quality parameters in real time. Poor network transmission performance, high packet loss rate and high maintenance cost are the main problems in the current cold chain logistics monitoring. To solve these problems, the paper presents a low-power monitoring system based on Narrow Band Internet of Things (NB-IoT). Considering the characteristics of the moving carriage, the polling mode of Bluetooth is proposed for the communication of one sink node to three sensor nodes. An improved working sequence is designed to reduce the power consumption of Bluetooth modules. Subsequently, analyzing the standard NB-IoT terminal state transition diagram, combining with the practical applications of cold chain logistics, an improved terminal state transition diagram is proposed and its terminal power consumption is analyzed. In the experimental test, the packet loss rate is less than 1% within 8 km. And the battery life of improved Bluetooth module is 143 times of that of traditional one. The power consumption of main service of NB-IoT is discussed, the formula is given which includes the transmission quality, random access times, number of concurrent users, sleep interval and other parameters. Through simulation and calculate, the battery life of terminal is up to 17 years. These improvements will greatly reduce the cost of cold chain logistics monitoring system. In addition, the packet loss rate test experiment proves the high reliability of the communication system.</p> <p> </p>

Augmented Reality Interactive Guide System and Method for Tourist Attractions Based on Geographic Location

With the increasing improvement of people’s living standards, more and more tourists choose to travel independently, which puts forward higher requirements for the existing tourist guide system of scenic spots. Augmented reality (AR) is a technology that integrates computer-generated virtual information into real scenes. It provides more interactive modes, allowing visitors to have a stronger sense of immersion in the real world. The interactive navigation system is an analysis and processing system that recommends algorithms for tourists through the back-end server by collecting the user’s registration information data. It provides tourists with reasonable travel itineraries. This can not only allow users to avoid the peak flow of people and save tourists’ time, but also reduce the hidden dangers of scenic spots and improve the turnover rate of passenger flow. This paper aims to study an interactive guide system combined with augmented reality technology to provide tourism services for tourists in tourist attractions based on geographic locations. This paper proposes an improved probabilistic algorithm model to accurately locate tourists. (Probabilistic algorithms are also called randomization algorithms. Probabilistic algorithms allow the random choice of the next computational step during execution. In many cases, when the algorithm is faced with a choice during the execution process, the random choice is time-saving compared to the optimal one. Therefore, the probabilistic algorithm can greatly reduce the complexity of the algorithm.) At the same time, the paper designs an AR scenic spot tour guide system. It tests the performance of the system. The results show that the initial response speed of the improved probability algorithm is 0.69 s, the average response time is 4 s when the number of concurrent users is finally increased to 600, and the growth rate is about 0.006 s. The improved algorithm can obviously enhance the response speed.

Construction of Educational Resource Metadata Management Platform Based on Service-Oriented Architecture

The existing cloud sharing system of educational resources is in the form of centralized management, which has the problems of small number of concurrent users and low score of resource retrieval results and cannot meet the current needs of implicit educational resource sharing. Therefore, a cloud sharing system of college implicit educational resources based on service architecture is proposed. At present, the sharing of educational resources mainly includes network teaching, distance education, and other methods. These schemes alleviate the sharing problem of educational data resources to a certain extent. However, the sharing and rational integrated utilization of educational application software are still under exploration, and there is no mature solution at present. At present, there is a lack of unified planning for the construction of the educational resource database of the management cadre college, and there are problems such as repeated construction, complex quantity, and nonstandard form, which directly leads to the failure of effective dissemination of resource information in the network distance education system, which is an urgent problem to be solved in the distance education system of the management cadre college. This paper first understands some domestic and foreign standardization and development of educational resources. Then, it introduces the ontology theory and the basic theory of metadata. At present, the construction of educational resource database in colleges and universities in China lacks unified planning, and there are problems such as repeated construction, complex quantity, and nonstandard form, which makes the resource information in the network distance education system unable to be shared and disseminated effectively. In order to improve the utilization of online educational resources and share the data of resource databases with different structures, a metadata management platform model of educational resources is designed. As a new architecture idea, service-oriented architecture can package existing assets and reuse existing assets. It can also minimize the impact of demand changes. This paper puts forward the process of metadata management under the service architecture and independently develops a metadata management platform suitable for the development and use of service mode. It is combined with automatic testing and continuous integration to effectively improve the data quality and development efficiency of service development.

Design of Personalised English Distance Teaching Platform Based on Artificial Intelligence

In the application of the existing distance education platform, the server load is often unbalanced, which increases the response time of the platform. This paper designs a personalised English distance teaching platform based on artificial intelligence. Put forward the overall architecture of the platform, and design the platform on this basis. In order to realise the personalised course resource recommendation function, a collaborative filtering personalised recommendation algorithm is designed to get the best course recommendation results. Using artificial intelligence technology to set up multipoint control unit, the task balance is allocated to multiple operation units, and the reasonable allocation of curriculum resources is realised. According to the functional requirements of the platform design, the composition of functional modules is further set to realise the scheduling and management of curriculum resources. The experimental results show that, under the condition of the same number of concurrent users, the average response time of this design platform is less than that of the existing distance teaching platform, which shows that it has certain advantages in server load balancing and resource scheduling, which can improve the rapid response ability of the platform and enhance the stability of the platform.

Modeling Performance of Microservices Systems with Growth Theory

ContextThe microservices architectural style is gaining momentum in the IT industry. This style does not guarantee that a target system can continuously meet acceptable performance levels. The ability to study the violations of performance requirements and eventually predict them would help practitioners to tune techniques like dynamic load balancing or horizontal scaling to achieve the resilience property.ObjectiveThe goal of this work is to study the violations of performance requirements of microservices through time series analysis and provide practical instruments that can detect resilient and non-resilient microservices and possibly predict their performance behavior.MethodWe introduce a new method based on growth theory to model the occurrences of violations of performance requirements as a stochastic process. We applied our method to an in-vitro e-commerce benchmark and an in-production real-world telecommunication system. We interpreted the resulting growth models to characterize the microservices in terms of their transient performance behavior.ResultsOur empirical evaluation shows that, in most of the cases, the non-linear S-shaped growth models capture the occurrences of performance violations of resilient microservices with high accuracy. The bounded nature associated with this models tell that the performance degradation is limited and thus the microservice is able to come back to an acceptable performance level even under changes in the nominal number of concurrent users. We also detect cases where linear models represent a better description. These microservices are not resilient and exhibit constant growth and unbounded performance violations over time. The application of our methodology to a real in-production system identified additional resilience profiles that were not observed in the in-vitro experiments. These profiles show the ability of services to react differently to the same solicitation. We found that when a service is resilient it can either decrease the rate of the violations occurrences in a continuous manner or with repeated attempts (periodical or not).ConclusionsWe showed that growth theory can be successfully applied to study the occurences of performance violations of in-vitro and in-production real-world systems. Furthermore, the cost of our model calibration heuristics, based on the mathematical expression of the selected non-linear growth models, is limited. We discussed how the resulting models can shed some light on the trend of performance violations and help engineers to spot problematic microservice operations that exhibit performance issues. Thus, meaningful insights from the application of growth theory have been derived to characterize the behavior of (non) resilient microservices operations.