Top Read Articles
Published in last 1 year |  In last 2 years |  In last 3 years |  All
Please wait a minute...
For Selected: Toggle Thumbnails
Design of Driver Fatigue Recognition Algorithm Based on YOLOv8 and Face Key Points Detection
HE Zong-xi JIANG Ming-zhong XIE Ming-xia PANG Jia-bao CHEN Qiu-yan HU Yi-bo
Computer & Telecommunication    2023, 1 (11): 1-6.  
Abstract328)            Save
According to statistics, the accident rate caused by fatigue driving and mental inconcentration in traffic accidents accounts for 93%. To solve this problem, 68 key points of face are introduced in this paper. Based on deep learning and machine vision algorithm concepts, combined with YOLOv8 model and related fatigue driving judgment mechanism, PERCLOS algorithm, MAR algorithm, EAR algorithm and HPE algorithm are used to improve the accuracy and reliability of the system. A set of algorithms for recognizing tired driving behavior is successfully constructed.
Related Articles | Metrics
Leading by Ideological and Political Education, Integrating Industry and Education --Research on the Teaching Innovation of Computer Network Security
BAO Hai-yan
Computer & Telecommunication    2024, 1 (1): 4-7.   DOI: 10.15966/j.cnki.dnydx.2024.z1.001
Abstract110)            Save
With the rapid development of information technology, computer network security has become a focus of social attention. This article explores the teaching innovation and practice of Computer Network Security from the perspective of "ideological and po‐ litical guidance, integration of industry and education", aiming to cultivate outstanding talents with high awareness and skills of net‐ work security. The course utilizes Xuexi Tong APP to carry out blended online and offline teaching. Through the reconstruction of course content, improvement of teaching modes, innovation of teaching methods, integration of ideological and political elements, reform of teaching evaluation, and promotion of teaching effectiveness, the educational philosophy of "moral education first, studentcentered, integration of industry and education, and continuous improvement" is adopted to achieve the deep exploration of ideologi‐ cal and political elements in the course while imparting professional knowledge, integrate professional knowledge of network and se‐ curity with production practice, strengthen school enterprise cooperation, continue teaching reform, and build a learning community for teachers and students.
Related Articles | Metrics
Safety Helmet Detection Based on Lightweight YOLOv8
ZHANG Bi-chuan LIU Wei-dong MI Hao JING Ya-ning
Computer & Telecommunication    2024, 1 (1): 35-39.   DOI: 10.15966/j.cnki.dnydx.2024.z1.017
Abstract107)            Save
Helmet detection is a computer vision task with important application value, involving safety management in many fields such as construction sites, mines, and electric power. However, helmet detection also faces many challenges, such as large changes in target size and aspect ratio, rapid changes in target velocity, target occlusion, and background interference. In order to solve these problems, this paper proposes a safety helmet detection method based on YOLOv8, which uses the characteristics of high speed and high precision of YOLOv8 combined with the characteristics of safety helmets to achieve effective detection and identification of safety helmets.
Related Articles | Metrics
Research on Intelligent Financial System Based on OCR and Large Language Model
HUANG Zi-cong CHEN Dian-can OU Run-feng LUO Jing PENG Xin-dong
Computer & Telecommunication    2024, 1 (1): 1-3.   DOI: 10.15966/j.cnki.dnydx.2024.z1.005
Abstract92)            Save
With the rapid development of information technology and the growing demand for financial management and financial analyses, bookkeeping is no longer limited to ordinary handwriting or manual recording in software. In order to meet the needs and development of today's era, an intelligent financial system based on OCR and large language model is designed. The system is suit‐ able for mobile phones, with financial management functions as the starting point and simplified management operations as the pur‐ pose, and realizes a system that is mainly based on OCR recognition scanning and recording bookkeeping functions, supplemented by financial analysis functions of big language model, big data consumption classification trends, and multi-version switching of ver‐ sions suitable for people of different age groups. The system not only greatly improves the efficiency of people's bookkeeping, but also promotes the intelligent financial transformation of society.
Related Articles | Metrics
Design of SCN Facial Expression Recognition System Based on WeChat APP
YU Yan LIU Zhong-xu
Computer & Telecommunication    2024, 1 (1): 67-71.   DOI: 10.15966/j.cnki.dnydx.2024.z1.012
Abstract74)            Save
In view of facial expression recognition technology, the advantages of self-repair network (Self-Cure Network, SCN) fa‐ cial expression recognition algorithm model are used to realize the application of SCN on mobile terminal devices, using the trained model to build facial expression recognition system, and develop a wechat small program as the system platform.After the system test, the results show that the system has high expression recognition accuracy, convenient operation, smooth operation and complete functions.The SCN face expression recognition system based on wechat small program has a wide range of application prospects.
Related Articles | Metrics
A Named Entity Recognition Model Based on Rotational Attention
LAI Xiao-meng WEI Jia-yin
Computer & Telecommunication    2024, 1 (1): 21-25.   DOI: 10.15966/j.cnki.dnydx.2024.z1.011
Abstract64)            Save
Addressing the issue of inadequate classification accuracy in named entity recognition via entity word-to-relationship modeling, we propose a method using rotational attention. Firstly, the text is encoded using the BERT model and Bi-LSTM, fol‐ lowed by extraction of features from input text using convolutional neural networks. Subsequently, the extracted feature sequence is inputted into the rotational attention model for output probability calculations, and the MLP layer is used for output classification. The study's outcomes affirm the efficacy and feasibility of the technique proposed in this paper, as it successfully yields superior re‐ sults on mainstream English databases including CADEC, GENIA and CoNLL2003, for named entity recognition exercise. 
Related Articles | Metrics
Knowledge Graph Construction for Data Science and Big Data Technology
WANG Zi-ming XIAO Da-wei LIU Ya-nan
Computer & Telecommunication    2024, 1 (1): 32-34.   DOI: 10.15966/j.cnki.dnydx.2024.z1.007
Abstract61)            Save
Knowledge graph has been innovated in knowledge representation and management, and is widely used in fields such as intelligent search and question answering, but it has relatively few applications in the field of education and teaching. Based on knowledge graph and natural language processing technology, the main components of the course teaching plan are sorted out, the in‐ formation such as course entities, attributes and relationships are extracted from the talent training scheme and the course teaching plan, and the ontology model of the data science and big data technology professional course system is designed, which realizes the construction of the knowledge graph of the data science and big data technology professional course system.
Related Articles | Metrics
Prediction of Total Ionospheric Electron Content Based on Informer
MA Yan LIU Hai-jun HE Ren CUI Chun-jie WANG Gao-yuan YANG Yue-qiao
Computer & Telecommunication    2024, 1 (1): 17-20.   DOI: 10.15966/j.cnki.dnydx.2024.z1.008
Abstract59)            Save
Related Articles | Metrics
Practical Study on Empowering Program Design Teaching in Universities with OBE and Integration of Industry and Education
LI Dan
Computer & Telecommunication    2024, 1 (1): 26-28.   DOI: 10.15966/j.cnki.dnydx.2024.z1.019
Abstract55)            Save
In response to the requirements of the Ministry of Education for cultivating "Four New" composite applied talents in re‐ cent years, combining the disciplinary background of university program design courses to cultivate high-quality students with both professional and practical abilities has become a new research topic. This article relies on the advantages of school and enterprise co‐ operation and proposes a practical research on the teaching mode of university program design courses based on the concept of in‐ dustry education integration, and puts it into practice. By adopting a "363" teaching model and an OBE output oriented practical teaching strategy in the teaching of Python Programming, we aim to strengthen students' subject status in information technology empowerment education, in order to better enhance their computational and innovative thinking abilities under the new medical background, and provide reference for future program design teaching.
Related Articles | Metrics
Research of Java Teaching Mode Reform of Multiple Integration Based on OBE and PBL
LI Hui YANG Ling-xue YANG Li-na
Computer & Telecommunication    2024, 1 (1): 8-13.   DOI: 10.15966/j.cnki.dnydx.2024.z1.004
Abstract54)            Save
Aiming at the pain points of Java course teaching process, the teaching model of the course is reformed and innovated. The course deeply integrates PBL and OBE to build a teaching model of multiple integration based on Golden Class. O2O teaching platform is used to divide traditional classes into online and offline mixed teaching. According to the standard of "Golden Class", the innovation reform is carried out from the diversification of curriculum resources, teaching methods, assessment mechanism, curricu‐ lum ideology and politics. The curriculum naturally integrates with the curriculum ideology and politics with local characteristics in teaching, which not only pays attention to students' knowledge generation, but also pays more attention to students' practical ability. It has established a diversified examination mechanism, to strengthen the interaction between teachers and students, and cultivate stu‐ dents' computational thinking and innovation ability.
Related Articles | Metrics
A Wireless Local Area Network Intrusion Signal Detection Method Based on GA-SVM Algorithm
Computer & Telecommunication    2024, 1 (1): 47-49.   DOI: 10.15966/j.cnki.dnydx.2024.z1.018
Abstract53)            Save
Conventional wireless local area network intrusion signal detection nodes are mostly set independently, resulting in low detection efficiency and high false detection rate of intrusion signal detection. Therefore, this article proposes a wireless local area network intrusion signal detection method based on GA-SVM algorithm. This method first uses correlation to extract intrusion sig‐ nal features, improve detection efficiency, set up correlation detection nodes, construct a GA-SVM intrusion signal detection model, and use location separation method to achieve signal detection processing. The test results show that for signal intrusion detection at the selected 300 sampling points, compared to the traditional distributed fiber optic network intrusion signal detection group and the traditional FastICA calculation network intrusion signal detection group, the GA-SVM calculation network intrusion signal detection group has a good detection error rate of less than 20%, indicating that with the assistance of the GA-SVM algorithm, the current de‐ sign has better detection results, stronger pertinence, and practical application value.
Related Articles | Metrics
Research on Upgrading Method of E-government Extranet Based on SPN and Super SIM Zero Trust Security Gateway
WANG Ning GUO Gong-hua
Computer & Telecommunication    2024, 1 (1): 56-61.   DOI: 10.15966/j.cnki.dnydx.2024.z1.006
Abstract51)            Save
Government extranet is an important infrastructure of e-government in China. In the new era, Guangdong Province pro‐ poses to build a new generation government extranet with "resilience, comprehensive integration and extensive coverage", which puts forward higher requirements for the coverage, stability and security of the network. Therefore, combining SPN technology and Super SIM zero trust security gateway technology, this paper discusses the planning, design and construction of a new generation of government extranet.
Related Articles | Metrics
Research on Introducing Educational Robots into C Language Programming Teaching
XIE Chang-ying WANG Chun-ling
Computer & Telecommunication    2024, 1 (1): 14-16.   DOI: 10.15966/j.cnki.dnydx.2024.z1.013
Abstract50)            Save
By analyzing the problems in the traditional teaching mode of C Language Programming, this paper discusses the teach‐ ing framework and implementation plan of applying educational robots to C Language Programming teaching, and discusses the transformation of teacher roles.By introducing educational robots, it is possible to stimulate students' interest in learning, mobilize their internal drive for learning, improve their problem-solving ability, strengthen their teamwork awareness and innovative spirit, and effectively improve teaching effectiveness.
Related Articles | Metrics
Whale Optimization Algorithm with Aquila Exploration Method
QI Xin YU Yan MA Ning WU Hao-qian
Computer & Telecommunication    2023, 1 (11): 7-13.   DOI: 10.15966/j.cnki.dnydx.2023.11.007
Abstract50)            Save
The Whale Optimization Algorithm (WOA) is an effective meta-heuristic. However, whale optimization algorithms tend to converge slowly and are prone to fall into local optimal solutions. Therefore, this paper proposes an algorithm based on the exploration idea of the Aquila Optimizer (AO) to solve global optimization problems. The improved algorithm is inspired by the exploration idea of the Aquila Optimizer. Firstly, Aquilas conduct exploration to expand the search range, thereby enhancing the global search capability and reducing the likelihood of getting trapped in local optima. Secondly, it incorporates the hunting behavior of whales to balance the exploration and exploitation phases of the algorithm. To validate the effectiveness of the algorithm, this study uses benchmark test functions as experimental objects and compares it with other popular metaheuristic algorithms. The experimental results demonstrate that the proposed algorithm in this study has shown good convergence speed, optimization accuracy, and stability.
Related Articles | Metrics
Design and Implementation of Campus Ordering Backend System Based on Microservice
SU Bing
Computer & Telecommunication    2023, 1 (11): 23-28.   DOI: 10.15966/j.cnki.dnydx.2023.11.008
Abstract50)            Save
In order to alleviate the problem of seat tension in university canteens, it is urgent to develop a kind of software to solve this problem and improve the dining experience for students. This article discusses the use of the current mainstream microservice framework Spring Boot, combined with technologies such as MyBatis Plus and Vue.js, to design and implement a campus ordering system backend, which facilitates platform administrators and merchant administrators to manage dishes, packages, orders, etc., providing a solution for the problem of tight dining for college students.
Related Articles | Metrics
Aerial Vehicle Detection in Low Light Environment Based on Yolov5
XIN Bo-fu
Computer & Telecommunication    2024, 1 (1): 78-83.   DOI: 10.15966/j.cnki.dnydx.2024.z1.010
Abstract49)            Save
An improved algorithm is proposed to address the problem that yolov5 detects UAV aerial images with poor monitoring performance for low light background targets. Firstly, data normalization is performed on the target dataset visdrone2019 to improve the detection effect. Then the dynamic convolution kernel with Mish activation function and the C3_DSConv module using distrib‐ uted offset convolution to replace the C3 block are introduced, and the above two convolution structures are fused into the yolov5 network; the BiFormer attention mechanism is embedded to improve the accuracy of small target detection. In summary, the MODByolov5 model is finally obtained, and the experimental results prove that the model's mAP and recall are both improved, and the ac‐ curacy of detecting vehicles in shadows and dark environments is significantly increased, and the FPS is high, which ensures that the model can still be used for rapid detection or real-time monitoring.
Related Articles | Metrics
Exploration on the Training Mode of Electronic Information Talents in Local Colleges and Universities under the Background of New Engineering
LAI Yi-han WANG Qing-hui FU Zhi-he LIU Feng-lin
Computer & Telecommunication    2023, 1 (11): 33-36.   DOI: 10.15966/j.cnki.dnydx.2023.11.004
Abstract46)            Save
Under the background of new engineering, this paper analyzes the current situation and existing problems of talent cultivation of electronic information specialty in local undergraduate colleges and universities. Take the electronic information engineering specialty of Longyan University for example, this paper introduces the reform ideas of the professional talent training mode, with the educational concept of student-centered, output-oriented, continuous improvement, constructs a new professional curriculum system, innovates a new teaching reform mode, establishes a collaboration platform for innovative education of production, learning, research and school, and implements a diversified evaluation system, so that students' comprehensive application ability, engineering practice ability and innovation ability have been greatly improved.
Related Articles | Metrics
Educational Computing Network Solution Based on 5G Plus Three-level Cloud Architecture
GUO Gong-hua WANG Ning
Computer & Telecommunication    2024, 1 (1): 62-66.   DOI: 10.15966/j.cnki.dnydx.2024.z1.002
Abstract46)            Save
Smart campus is the mainstream in the field of education informatization. As its infrastructure, education private network has high requirements for network coverage, quality, time ductility, data security and other performance indicators. Integrating 5G slicing technology and edge computing technology, innovative solutions are proposed to build an educational computing network with 5G+ three-level cloud architecture. This network architecture can optimize the distribution of resources and realize the balanced development of education. Ensure network data security and access performance through dedicated slicing; Gradually replace WIFI with 5G to realize the interconnection of devices and everything; Provide construction conditions for new mobile services and appli‐ cations such as AR/VR teaching; Provide a customized converged network; Provides local access management. It implements classi‐ fied cloud network solutions for different types of schools. For new schools, new infrastructure concepts can be incorporated to re‐ duce repeated investment in wireless network resources. For the information pilot school, it can focus on satisfying the application innovation of computing power and the application demonstration of information education. For non-pilot schools, wireless network coverage can be optimized to reduce network construction costs. For remote schools, the goal is to balance educational resources and access the regional cloud nearby to achieve computing power sharing. Schools of different sizes can achieve an education private net‐ work of high safety, high stability, strong bearing capacity, easy expanding with the smallest construction cost. 
Related Articles | Metrics
Research on the Transformation of Scientific and Technological Achievements in Software Quality Inspection Based on Visual Knowledge Graph
ZHAO Chang-ping XU Ying-mei KUANG Bi-qin
Computer & Telecommunication    2024, 1 (1): 72-77.   DOI: 10.15966/j.cnki.dnydx.2024.z1.009
Abstract46)            Save
This paper uses the CiteSpace tool and literature statistical methods to conduct a visual knowledge graph analysis of the literature on the transformation of scientific and technological achievements in software quality inspection for the past 10 years. The high-frequency keywords "information security"、"software testing" and "network security" are current research hotspots with strong centrality, and the future will shift to "data encryption" which prominence intensity is 2.71. To promote the transformation of scien‐ tific and technological achievements, third-party quality testing institutions should cooperate deeply with research and development institutions, and leverage the data advantages of market testing and practical capabilities of achievement transformation, and strengthen detailed research on different sub characteristics in the field of quality inspection, and conduct more specific and intuitive analysis of each sub feature at the software application, and establish standards for testing technology through big data analysis. At the same time, it can also rely on artificial intelligence for cross penetration of sub features, achieving the sharing and complementar‐ ity of research and development resources. This paper summarizes the research strength, hotspots and cutting-edge trends of soft‐ ware quality inspection, and provides some reference value for promoting the transformation of subsequent achievements.
Related Articles | Metrics
Construction of Production-Teaching Integration System for Web Application Development Course Group Based on Job Requirements 
LUO Shao-ye HU Wei-wei CHE Yan
Computer & Telecommunication    2024, 1 (1): 43-46.   DOI: 10.15966/j.cnki.dnydx.2024.z1.003
Abstract44)            Save
With the wide application of Web application development technology, many colleges and universities have set up related courses, and the training of Web application development talents is becoming more and more important. The demands for Web appli‐ cation development talents are collected by obtaining and analyzing job demand data from recruitment websites. According to these, a Web application development course group is constructed, which consists of basic courses, application technology courses and practical courses, and a job-demand-oriented production-education integration system scheme is proposed to provide support and help for the training of Web application development talents in colleges and universities.
Related Articles | Metrics
Research on the Diversified Curriculum System of Vocational Colleges under the Background of Industry and Education Integration
LI Rui-xia WANG Yan
Computer & Telecommunication    2024, 1 (1): 40-42.   DOI: 10.15966/j.cnki.dnydx.2024.z1.014
Abstract42)            Save
In order to improve the quality of talent cultivation and meet the personalized needs of students, it is necessary to reform and innovate the curriculum system under the background of industry and education integration. Take the computer application tech‐ nology major for example, this article analyzes the current status of the curriculum system in talent cultivation in vocational col‐ leges. Based on the personalized needs of students and the needs of society for talents, it proposes the construction ideas and plans of a diversified curriculum system based on“ big major and small direction”. Practice has proven that the construction of a diversified curriculum system greatly enhances students' practical skills and adaptability to professional positions, improves the quality of talent cultivation, meets students' individual needs, and cultivates high-quality applied talents that meet social needs. 
Related Articles | Metrics
Research on Channel UL Scheduler Application in 5G Telecommunication System
XU Xiao-tao
Computer & Telecommunication    2024, 1 (1): 29-31.   DOI: 10.15966/j.cnki.dnydx.2024.z1.015
Abstract42)            Save
The channel uplink scheduler scientifically calculates the relative signal strength parameters of the scheduling value, and processes the program area specified by two symbols in a standardized manner, and specifies the sub-parts of the PUSCH area from different angles. The regularized scheduling area allocated by PRB (the area where the uplink scheduling program starts from the PRB allocation) will be allocated to the cell based on the interference and noise power measured in the area, and finally the corre‐ sponding simulation data will be given to verify the operation of the channel uplink scheduling.
Related Articles | Metrics
Accurate Construction and Digital Management of 5G Base Stations
SONG Hui WAN Chan-chan
Computer & Telecommunication    2024, 1 (1): 50-55.   DOI: 10.15966/j.cnki.dnydx.2024.z1.016
Abstract39)            Save
In the era of digital transformation, Xinjiang Telecom has built a digital management platform for wireless network engi‐ neering construction, which is used to leave traces of key data in the process of wireless network engineering construction. Since the platform has been used, it has stored a large number of trace data. Playing the value of the data has become an important challenge for Xinjiang Telecom. To address this challenge, Xinjiang Telecom strengthens data-driven full process control, streamlines the pro‐ cess of wireless network planning, design, construction, and post evaluation, and constructs a refined management system for wire‐ less network from planning to post evaluation, guiding the optimization and investment management of wireless network engineer‐ ing construction.
Related Articles | Metrics
Simulation Analysis of Race-hazard in Combinatorial Logic Circuit Based on Proteus
LI Zhen-dong HOU Zeng-tian HUANG Yong-mei
Computer & Telecommunication    2023, 1 (11): 14-.   DOI: 10.15966/j.cnki.dnydx.2023.11.002
Abstract34)            Save
In order to teach students more intuitively the phenomenon of race-hazard in combinational logic circuits, this study builds a simulation module circuit based on Proteus simulation software, and carries out simulation experiments to test the generation and elimination of circuit race-hazard. The simulation interface clearly displays the peak pulse of race-hazard, as well as the elimination results. Through this simulation module circuit, students not only observe the process of race-hazard more intuitively, but also can take different measures to eliminate circuit race-hazard. Teaching practice shows that the simulation module circuit provides a new scene for students to learn and understand the race-hazard phenomenon, thus improving the teaching effect.
Related Articles | Metrics
Reform and Practice of Computer Public Basic Education Model for Training Applied Talents in the Era of Big Data and Artificial Intelligence
LI Xin JIA Mei-juan LIU Chun MAO Kai-ji
Computer & Telecommunication    2023, 1 (11): 19-22.   DOI: 10.15966/j.cnki.dnydx.2023.11.001
Abstract30)            Save
The new technology and new concept in the era of digital intelligence have profoundly changed the way of operation, organization, production and decision-making in all walks of life. Under the impact of Big Data and Artificial Intelligence, the employment position has higher requirements for the computer skills and literacy of applied talents. The course of Computer Public Basic aims at cultivating students' computational thinking, computer technology and literacy, which plays an important role in improving the vocational skills of applied talents. Take Daqing Normal University, an application-oriented undergraduate university with characteristics in Heilongjiang Province, for example, this paper introduces the reform and practice of the education model of Computer Public Basic. On the basis of analyzing the computer ability required for application-oriented talents in the new era, this paper introduces the reform and practice path from four aspects: hierarchical curriculum system, mixed teaching mode, experimental teaching reform and innovation and entrepreneurship ability training.
Related Articles | Metrics
Computer & Telecommunication    2024, 1 (3): 93-.   DOI: 10.15966/j.cnki.dnydx.2024.03.017
Abstract29)            Save
Related Articles | Metrics
Prediction of Waterlogging Depth in Bridges and Culverts Based on PSO-SVR
XUE Zi-yun LI Zhong WANG Zhi ZHANG Li-li SONG Qing-chang
Computer & Telecommunication    2023, 1 (11): 29-.  
Abstract28)            Save
Urban waterlogging is an important urban disaster, and culvert ponding is one of the main manifestations of urban waterlogging, which can easily cause serious casualties and property losses. In order to improve the efficiency and accuracy of predicting the culvert ponding depth, a predicting model naming PSO-SVR is proposed, which the current meteorological data and waterlogging depth data are selected as input and output vectors respectively. Firstly, a support vector regression prediction model (SVR) for the culvert ponding depth is established, and then the particle swarm optimization algorithm (PSO) is used to optimize key parameters, which has the advantages of objectivity and simplicity. The experimental results indicate that the PSO-SVR model is effective in predicting the depth of culvert ponding. Compared with traditional prediction models of SVR and BP neural network, the PSOSVR model has higher fitting accuracy for waterlogging depth. This model can provide technical support for urban waterlogging warning and emergency rescue decision-making.
Related Articles | Metrics
CSI-based Indoor Localization Method Using IDW Interpolation and Amplitude-phase Fusion Network
RU Chun-rui DANG Xiao-chao
Computer & Telecommunication    2024, 1 (3): 1-6.  
Abstract25)            Save
To address the problem of poor localization performance caused by the small number of fingerprint points and the lack of representativeness of fingerprint features in the offline phase of fingerprint-based indoor localization, a CSI-based indoor localiza‐ tion method is proposed using Inverse Distance Weighted (IDW) interpolation and amplitude-phase fusion network. The IDW inter‐ polation algorithm is used to generate a large-capacity fingerprint library. Then, a parallel convolutional neural network (CNN) is used to process the amplitude and phase to obtain the positional fingerprint features. Finally, a novel integrated architecture fusing Random Forest (RF) and Multilayer Perceptron (MLP) is used for classification to obtain the estimated positions of the target loca‐ tion samples.
Related Articles | Metrics
Analysis of Public Sentiment in Libraries Based on Text Mining
WANG Long-jun WANG Jing LI Guang-hua CHEN Liang
Computer & Telecommunication    2024, 1 (3): 13-.   DOI: 10.15966/j.cnki.dnydx.2024.03.020
Abstract25)            Save
With the increasing influence of mobile Internet on young readers in university libraries, the proportion of new generation readers using QQ instant messaging software is increasing, text mining of library QQ group text information can be used to under‐ stand the public sentiment of the library, which can be used for library public sentiment warning and provide strong public sentiment response capabilities for library decision-makers. Web crawler technology is used to crawl chat records in QQ groups from Septem‐ ber 2022 to December 2022 as library public sentiment data, then performing data preprocessing operations such as deduplication and cleaning on the original public sentiment data. Then, Tsinghua University's Thulac segmentation technology is used to extract keywords and calculate their weights from the public sentiment data, and them the WordCloud library is used for visualization. Next, the spaCy library is used to to calculate specific emotional tendencies and scores for public opinion data, and finally the emotional tendencies of library public opinion are analyzed through experiments.
Related Articles | Metrics
Computer & Telecommunication    2024, 1 (3): 84-.   DOI: 10.15966/j.cnki.dnydx.2024.03.018
Abstract25)            Save
Related Articles | Metrics
Computer & Telecommunication    2024, 1 (3): 89-.   DOI: 10.15966/j.cnki.dnydx.2024.03.013
Abstract25)            Save
Related Articles | Metrics
A Fine-grained Network for Person Re-identification
WU Shu-li
Computer & Telecommunication    2024, 1 (3): 45-.   DOI: 10.15966/j.cnki.dnydx.2024.03.019
Abstract25)            Save
To solve the problem that the recognition efficiency of different types of attention mechanisms is too low in the person reidentification task, and the focus is too much on extracting single-granularity information, which makes it difficult to extend to realworld application scenarios, a fine-grained module based on local attention is proposed. The obtained coarse-grained feature repre‐ sentation is divided into multiple parts, guiding the network to extract finer-grained local clues. In addition, considering the short‐ comings of a single branch in extracting multi-granularity clues, a multi-branch fine-grained network is designed to further extract richer clues. Experimental results on mainstream datasets verify the effectiveness of the network proposed in this article
Related Articles | Metrics
The Literature Review about Sentiment Analysis in Network Public Opinion Research in China
YOU Dan-dan LUO Shao-ye
Computer & Telecommunication    2024, 1 (3): 64-.   DOI: 10.15966/j.cnki.dnydx.2024.03.006
Abstract24)            Save
With the popularization of the internet and social media, the impact of network public opinion on the social level cannot be underestimated, and sentiment analysis in network public opinion is of utmost importance. This paper collects, organizes, and summarizes relevant literature on sentiment analysis in network public opinion research in China, adopting bibliometric methods to analyze the quantity of literature, co-occurrence of high-frequency keywords, and evolution of theme keywords. Following the pro‐ cess of sentiment analysis in network public opinion research, this study analyzes the main research content, ideas, and methods in data collection, data processing, sentiment recognition(classification/tendency),sentiment evolution. Finally, this study points out fu‐ ture research directions, and gives the working directions of next steps.
Related Articles | Metrics
The Implementation of IPv6 Network Deployment and IPv4 Network Security Reinforcement for Web Application Systems Based on Intelligent DNS and Reverse Proxy
WU Guo-song
Computer & Telecommunication    2024, 1 (3): 7-.   DOI: 10.15966/j.cnki.dnydx.2024.03.001
Abstract24)            Save
Based on the core technology of the next generation Internet IPv6, which has the characteristics of large enough address space, higher security, better service quality and supporting mobile terminal equipment, the information development of universities is gradually promoting the IPv6 network deployment and IPv6 network application of information system. However, in the process of promoting IPv6 network deployment and access of application systems in universities, there are still some problems that some un‐ derlying network devices do not support IPv6 protocol, and security devices cannot achieve comprehensive control. In order not to change the current school network architecture, without affecting the current IPv4 network access, this paper puts forward the imple‐ mentation of IPv6 network deployment and access for college Web application system based on the intelligent DNS and reverse proxy. This technology has the characteristics of simple principle, strong stability, high security and easy maintenance. Through link‐ age deployment, IPv6 network access and IPv4 access security reinforcement of the school application system are realized, which provides reference practice for the deployment of IPv6 network application.
Related Articles | Metrics
Teaching Reform and Practice on Compiling Principle for Ability Training of Computer System
HU Li-hua ZHANG Ji-fu LIU Ai-qin
Computer & Telecommunication    2023, 1 (11): 42-44.   DOI: 10.15966/j.cnki.dnydx.2023.11.003
Abstract23)            Save
As a core course of computer system in computer science and technology, the teaching result of Compiling Principle directly affects the students' theoretical knowledge ability and practical ability of computer system. In order to improve the students' knowledge and practical ability of computer system, take the school Taiyuan University of Science and Technology for example, some reform measures such as optimizing the content of classroom teaching, strengthening the process of comprehensive practice, selecting reasonable textbooks and reference books are adopted into the course. Taking the students of grade 2015 as the object of implementation, it is verified that the reform measures can effectively improve the students' theoretical knowledge of computer system and enhance their practical ability of computer system.
Related Articles | Metrics
Computer & Telecommunication    2024, 1 (3): 65-.   DOI: 10.15966/j.cnki.dnydx.2024.03.015
Abstract23)            Save
Related Articles | Metrics
Design of Intelligent Sleep Massage Pillow System Based on Brainwave Monitoring
JIANG Jian-ting DENG Wen-qiang ZENG Teng-xiang DAI Zhen-hua
Computer & Telecommunication    2024, 1 (3): 31-.   DOI: 10.15966/j.cnki.dnydx.2024.03.005
Abstract23)            Save
This study designs an intelligent sleep massage pillow system, aiming to provide users with effective sleep protection. The system adopts TGAM brain wave detection, temperature and humidity control, massage control, Bluetooth, WIFI and other module technologies to control smart sleep products in real time. It is a highly intelligent and fully automated process. In addition, the Sleep Care APP also has a sleep staging algorithm, automatically generates sleep depth analysis reports, and provides users with personal‐ ized sleep plans. It also uses an AI smart assistant to analyze users’ sleep conditions in real time, helping users improve their sleep experience more scientifically.
Related Articles | Metrics
Robot Path Planning Based on Improved DQN Algorithm
MA Hao-dong CHEN Ling-ling JIN Xiao-hang
Computer & Telecommunication    2023, 1 (11): 37-41.   DOI: 1008 - 6609 (2023) 11 - 0037 - 05
Abstract22)            Save
To address the issues of slow convergence and low success rate in robot path planning associated with the DQN algorithm, this study introduces an enhanced version of the DQN algorithm named MDQN. This enhancement involves modifying the configuration of the state space to more accurately distinguish different states, resulting in a more realistic observation space. Additionally, by altering the reward function, the algorithm is capable of obtaining more reward values, thereby improving learning efficiency. Experimental evaluations conducted on grid maps demonstrate that the improved algorithm, when compared to the traditional DQN algorithm and other related approaches, offers advantages such as higher success rates, faster convergence, and shorter paths.
Related Articles | Metrics
Collaborative Communication Scheme Based on Generalized Carrier-indexed Differential Chaotic Shift Keying
YANG Bo-han
Computer & Telecommunication    2024, 1 (3): 36-.  
Abstract21)            Save
With the development of communication technology, chaotic communication technology has attracted the interest of many researchers for its resistance to multipath fading and strong confidentiality, among which Differential Chaos Shift Keying (DCSK) is the most widely studied non-coherent digital modulation scheme. Generalized Carrier Index Differential Chaos Shift Key‐ ing (GCI-DCSK) is the integration of the index modulation technique on the basis of DCSK, which further improves the system per‐ formance. In this paper, the GCI-DCSK modulation scheme is combined with the relay collaboration technique to extend the cover‐ age of the communication network and improve the communication quality.
Related Articles | Metrics
Computer & Telecommunication    2024, 1 (3): 72-.   DOI: 10.15966/j.cnki.dnydx.2024.03.010
Abstract21)            Save
Related Articles | Metrics
Copyright © Computer & Telecommunication, All Rights Reserved.
Powered by Beijing Magtech Co. Ltd