最新刊期
卷 22 ， 期 7 ， 2023
- “在中医脑瘤诊治领域，周仲瑛教授医案知识图谱的构建与链接预测研究取得新进展，为临床经验总结与隐含知识挖掘提供新方案。”摘要：To summarize the clinical experience and implicit knowledge of traditional Chinese medicine practitioners in diagnosing and treating brain tumors， a knowledge graph was constructed based on medical cases from professor Zhou Zhongying. He is a renowned TCM master who specializes in treating brain tumors. The purpose of this research was to predict links within the knowledge graph. The process involved extracting entities and relationships from structured medical case data using Pandas tool. Then， Py2neo tools and Cypher query language were used to build a knowledge graph which was stored and visualized using Neo4j graph database. To compare three types of link prediction models through experiments， a real-world link prediction dataset based on the medical cases of renowned TCM practitioners in treating brain tumors was created. The experimental results showed that for small-scale but complex relationship-based brain tumor medical case knowledge graphs， tensor decomposition models can more accurately predict missing entities.关键词：knowledge graph;link prediction;brain tumor;medical records of TCM;NEO4J125|105|0更新时间：2023-07-24
- “在农产品社区团购领域，研究者提出了一种基于深度图神经网络的社交推荐模型GNN-R4A，通过编码用户与农产品特征空间，有效提升了推荐效果，为社区团购推荐系统提供了新思路。”摘要：Due to the social attributes of acquaintances in agricultural production in China and the increasing popularity of various community group buying， recommendation systems based on social relationships have become an indispensable component of emerging internet applications such as agricultural product community group buying. However， most existing research attempts to explore and quantify the correlation between user preferences and social relationships， neglecting the correlation between agricultural product features that may affect certain social relationship topologies （the phenomenon of like-minded friends）. Therefore， a social recommendation model based on deep graph neural networks （GNN-R4A） has been proposed. Firstly， the model abstracts the user and agricultural product feature space into two graph networks， which are encoded using graph neural network methods； Then， embed the two encoding spaces into the two hidden factors of the matrix decomposition to complete the missing scoring values in the user agricultural product scoring matrix； Finally， experiments were conducted on three datasets， using root mean square error， mean square error， and normalized cumulative loss gain as evaluation indicators to validate the effectiveness of the recommended method through ablation experiments. Experiments have shown that GNN-R4A has better recommendation performance compared to existing methods， and can provide reference for recommendation systems for community group buying.关键词：recommendation system;graph neural network;deep learning;community group buying89|61|0更新时间：2023-07-24
- “在方面级情感分析领域，研究者提出了HCDC-GCN模型，通过混合编码和双通道图卷积网络，有效融合了语义、词性、物理位置、语法距离和情感极性信息，实验结果表明其在Lap14、Rest14和Twitter数据集上具有显著优势。”摘要：The aspect-level sentiment analysis model HCDC-GCN based on hybrid coding and two-channel graph convolutional network is proposed to address the problem that the combination of lexical and physical location is neglected and only the syntactic structure of the sentence is considered， which lacks the mining of the deeper sentiment polarity of words， including sentiment polarity labels and sentiment polarity values. and feeds into the output of each layer of the network， then the two-channel graph convolutional network combines syntactic distance and sentiment polarity on a tree structure to obtain important information， and finally an attention mechanism is used to highlight the sentiment features of aspectual words. Experiments were conducted on three public datasets， Lap14， Rest14 and Twitter， with accuracy rates of 85.56%， 88.46% and 78.37% respectively， indicating that HCDC-GCN can better integrate semantic， lexical， physical location， grammatical distance and sentiment polarity information and has advantages in the area of aspect-level sentiment analysis.关键词：aspect-level sentiment analysis;graph convolutional network;hybrid coding;grammar distance;emotional polarity63|49|0更新时间：2023-07-24
- 摘要：The traditional collaborative filtering method has the problems of low recommendation accuracy and cold startup of users， recommendation system which only considers accuracy can no longer meet the needs of current enterprises and users. To solve the above problems， a recommendation method combining improved collaborative filtering and the integrated learning algorithm CatBoost is presented， and the diversity of the recommendation methods in different situations is discussed. The significant nearest neighbors （SNN） based on relative similarity index （RSI） are introduced， and the SNN method identifies the nearest neighbors for recommended prediction. Using the original dataset to train the CatBoost model， to make a second prediction of the recall generated by the improved collaborative filtering algorithm， and to make a prediction of the users who have cold start using the original dataset， can effectively alleviate the cold start problem. Finally， a comparative experiment is performed using an open dataset， Movie Lens， and the diversity of collaborative filtering algorithms when selecting different nearest neighbors and TopK values is discussed. The experimental results show that the improved collaborative filtering algorithm has achieved better precision performance than the traditional collaborative filtering algorithm in terms of Precision， Recall， and F1 measure. At the same time， the improved collaborative filtering recommendation method integrated with CatBoost has a certain diversity loss compared with the improved collaborative filtering recommendation method integrated with random forest and XGBoost， but it obtains better recommendation accuracy.关键词：recommendation method;collaborative filtering;CatBoost;33|73|0更新时间：2023-07-24
- “在海上风电功率预测领域，研究者提出了一种融合双阶段注意力机制与CNN-LSTM-XGBoost的模型，通过贝叶斯优化和模型权重分配，显著提升了预测准确率，为并行预测提供了有效参考。”摘要：In order to solve the problem that the parallel effect of a single model for predicting the wind power of offshore wind farms is unstable and the initial parameters are too sensitive， a fusion model based on two-stage attention mechanism （DAM） and CNN-LSTM-XGBoost is proposed. First， a DAM-CNN-LSTM model with two-stage attention mechanism is established. Then， use Bayes to optimize the super parameters of XGBoost model. Finally， based on the model weight distribution principle， the prediction results of each model are weighted and combined to obtain the final prediction results. The experiment shows that the prediction accuracy of the proposed model is significantly increased compared with the traditional model， MAPE is reduced to 0.26%， RMSE， R2 and MAE are 156.75， 0.988 and 87.47 respectively， so as to provide reference for the parallel prediction of offshore wind power.关键词：dual stage attention mechanism;short and long term memory network;XGBoost;parallel prediction;weight distribution25|77|0更新时间：2023-07-24
- “在电机故障检测领域，研究者提出了一种基于改进1D-CNN的智能诊断模型，通过引入残差结构，显著提升了模型的诊断效率和准确率，为电机故障实时检测提供了高效解决方案。”摘要：As an important power equipment in production and life， the motor will cause huge losses if it fails. So the real-time detection of motor fault is of great significance. This paper proposed an intelligent diagnosis model of motor bearing fault based on the improved 1D-CNN. In this method， one-dimensional motor vibration signals are directly used as the input of the 1D-CNN without data reconstruction or other processes， which greatly improves the diagnostic efficiency of the model. At the same time， the residual structure is introduced into the 1D-CNN to improve the learning ability of the model， so as to make up for the defects in feature extraction of the 1D-CNN， which achieves the unity of real-time and high accuracy. This paper uses Case Western Reserve database to design simulation experiment. 10 working states of motor bearings are identified， which achieved a 99.3% accuracy， higher than many models based on 2D-CNN， but the diagnostic time is significantly less than that based on 2D-CNN. The experimental results show that the proposed model has excellent performance in real-time and precision.关键词：residual structure;motor;bearing fault;high accuracy;1D-CNN;real-time performance18|105|0更新时间：2023-07-24
- “在可再生能源领域，专家提出了犹豫模糊多属性决策方法，构建评价指标体系，为配电网可再生能源接纳潜力评估提供解决方案。”摘要：With the growth of the installed capacity of renewable energy， the distribution network， as the carrier of renewable energy， is facing severe challenges. In order to solve the evaluation problem of renewable energy accommodation potential in distribution network， a hesitant fuzzy multi-attribute decision-making method is proposed. Constructing the evaluation criteria system of renewable energy acceptance potential of distribution network， aiming at the uncertainty of the evaluation criteria evaluation， the hesitant fuzzy set is used to express the evaluation information. The decision-making method of measurement of alternatives and ranking according to compromise solution （MARCOS） is extended to the hesitant fuzzy environment， and a multi-criteria decision-making method combining hesitant fuzzy set and Marcos is proposed. Finally， taking Shanghai as a case， the renewable energy accommodation potential of distribution network in each district is analyzed. The results of comparative analysis and sensitivity analysis show that the proposed method is feasible， effective and stable.关键词：distribution network;renewable energy;hesitant fuzzy sets;MARCOS21|37|0更新时间：2023-07-24
- 摘要：In order to solve the problems of local optimization， slow rate of convergence and low convergence accuracy of carnivorous plant algorithm， a carnivorous plant optimization algorithm based on reverse learning and neighborhood mutation was proposed. Firstly， adding a reverse learning strategy during population initialization improves the initial population quality， allowing the population to converge to the global optimal solution more quickly； Then， when the population falls into a local optimum， a neighborhood mutation mechanism is added to improve population diversity， achieving the goal of jumping out of the local optimum. Finally， the proposed algorithm is compared with the 5 population intelligent optimization algorithm， and relevant experiments are conducted on the 10， 30， and 50 dimensions of 10 test functions. Experiments show that the proposed algorithm has better performance in solving accuracy and rate of convergence， which verifies the superiority of the algorithm， and provides reference for the optimization of carnivorous plant algorithm.关键词：carnivorous plant optimization algorithm;opposition-based learning;neighborhood mutation;swarm intelligence optimization;hybrid algorithm30|26|0更新时间：2023-07-24
- “在视频编码领域，针对TZSearch算法的高计算复杂度问题，专家提出了一种改进算法，通过提前终止策略显著降低运动估计耗时，同时保持视频质量。”摘要：Considering the high computational complexity and relatively long time consumption of the TZSearch standard algorithm within HM-16.14， an improved TZSearch algorithm based on early termination strategy is proposed to improve the efficiency of video coding. Firstly， the depth sorting of the coding unit， transform unit and prediction unit is calculated according to the performance of rate distortion， which can effectively decrease additional division depths. Secondly， two search methods， i.e. diamond search and hexagonal search， are employed within the initial grid search step of TZSearch in order to precisely find the best matching point according to the motion vector distribution. Finally， OARP raster search and fine search are used to acquire the motion estimation results. Compared with the standard algorithm， experimental results show that the proposed method reduces more than 60% motion estimation time consumption on average， yet keeps the similar video quality .关键词：TZSearch algorithm;early termination strategy;raster search;fine search;motion estimation16|44|0更新时间：2023-07-24
- 摘要：A semi-supervised affinity propagation clustering algorithm based on Mahalanobis distance （SAPBM） is proposed to try to solve some problems， including that the limitations of the distance measurement of the affinity propagation （AP） clustering algorithm and the low accuracy of the clustering algorithm for some complex data sets. Considering that the Mahalanobis distance is not affected by the sample dimension， in the similarity measurement of samples， the SAPBM algorithm replaces the Euclidean distance with the Mahalanobis distance， reducing the mutual interference between samples due to the influence of sample dimension； combining pairwise constraint information to improve the similarity between the data， so that the obtained similarity matrix can more accurately reflect the relationship between the data. Experiments are carried out on the UCI standard data set， and the experimental results show that the SAPBM algorithm has better clustering performance than the traditional AP clustering algorithm and the SAP clustering algorithm that only uses pairwise constraint information.关键词：affinity propagation clustering;Mahalanobis distance;similarity measure;semi-supervised clustering;pairwise constraint information18|59|0更新时间：2023-07-24
- “在提高三相光伏逆变器并网效率和电流质量方面取得新进展，专家建立了两级三相电路拓扑结构，并通过SVPWM技术实现并网控制，为优化并网电流波形提供解决方案。”摘要：In order to improve the grid connected efficiency and current quality of three-phase photovoltaic inverter，a grid connected control strategy is proposed.Firstly，a two-stage three-phase circuit topology is established，through the park transform of the current and voltage，the AC quantity in the static coordinate system is transformed into the DC quantity in the synchronous rotating coordinate system，the grid voltage oriented vector control is used to control the active power and reactive power of grid connected inverter， and act on the output pulse of SVPWM to get the driving signal of grid connected inverter，and finally realize the grid connected control of inverter.Finally，the simulation model is established by using MATLAB/simulink to verify the feasibility of the circuit topology and the control strategy，which proves that the control strategy can stably track the grid voltage phase and output good grid current waveform.关键词：photovoltaic grid connection;inverter;Park's transformation;control strategy18|33|0更新时间：2023-07-24
- 摘要：The traditional short text matching algorithm based on bag-of-words model has high-dimensional sparseness in feature word space.Compared with long texts， the contextual semantic information of short texts is weak， which makes the semantic information of feature words ambiguous. Problems such as low matching accuracy are reflected. First， Semantic similarity between short texts is calculated by truncated singular value decomposition and cosine similarity. Secondly， the deep semantic discrimination of feature words is introduced by the information entropy and standard deviation of the semantic dimension of feature words. The best match is improved by deep semantic discrimination of feature words. The probabilistic relevance between short texts is calculated by the improved best match. Finally， short text matching is performed using the harmonic mean of semantic similarity and probabilistic relatedness. Experiments show that the algorithm proposed in this paper improves the matching accuracy by 11.22% and the F1 score by 10.5% compared with the traditional algorithm.关键词：TF-IDF;best matching;latent semantic analysis;truncated singular value decomposition;cosine similarity21|48|0更新时间：2023-07-24
- “在工业控制系统云服务领域，专家开发了运行时热点数据收集系统，优化了系统软件运行，为芯片设计和EDA工具提供了重要数据支持。”摘要：The computer that carries the cloud service of the industrial control system and the system software running on it are abstracted into a service under the guidance of the platform as a service （PaaS）. In order to improve computing efficiency and reduce hardware and operation maintenance costs， it requires the joint efforts of cloud service providers， chip designers and users.Therefore， for industrial control systems， the main business types provided by cloud service providers are collected， the optimization strategy of cloud services is expounded， the runtime hotspot data of industrial control systems is analyzed， and a runtime hotspot data collection system is developed. The runtime hotspot data collection system collects data such as the calling frequency and regularity of the interfaces and methods invoked by the business system， and these data assists the design of special computers and the optimization of system software runtime. In addition， the current EDA tools also rely heavily on these runtime data in architecture design， layout making， and process selection. The hotspot data collected by the system can help chip designers choose the optimal algorithm to be solidified in the chip.关键词：industrial control cloud;cloud service optimization;hot data;EDA;chip design53|32|0更新时间：2023-07-24
- “在软件开发领域，微服务容器化技术通过简化部署过程、降低运维难度，有效解决了传统开发框架的运维、部署、耦合度等问题。通过分析Kubernetes与Docker的优缺点，展示了微服务容器化在服务间通信与自动化运维方面的优势。同时，以开源社区服务应用为例，论述了微服务容器化在移动边缘计算领域的发展前景与应用实例。”摘要：With the increasing number of computer software application scenarios， software development is faced with many problems， and various development frameworks have gradually encountered difficulties in operation and maintenance， deployment， coupling， and framework design. In view of the above problems， it is proposed to realize the efficient deployment and automatic operation and maintenance of the overall architecture of the open source community through the containerization of microservices， and simplify the deployment process and the difficulty of operation and maintenance. By introducing the development history of microservices and containerization technology， key containerization technologies and open source tools， this paper focuses on the complementarity of microservices and container orchestration tools in inter-service communication and automated operation and maintenance， and analyzes and demonstrates the advantages of Kubernetes and the disadvantages of Docker， to demonstrate the benefits of microservice containerization. In terms of application deployment， taking a simple open source community service application as an example， the traditional monolithic architecture application is transformed into a microservice containerized service to discuss its advantages and characteristics， and the development of microservice containerization in the field of mobile edge computing is discussed later. Finally， the potential problems and future challenges of microservice containerization are summarized and discussed.关键词：microservices;open source community;containerization;moblie edge computing37|51|0更新时间：2023-07-24
- 摘要：An IoT-based control system lab teaching platform is constructed for automation and measurement and control majors ， in order to meet the needs of qualified and interdisciplinary talents’ training under the background of new engineering high education. The paper gives a detailed introduction about its design concept and basic functional modules. The innovative technology related to node-edge-cloud architecture of Iot is adopted and intelligent hardware are integrated into the platform and designed in a modular and reconfigurable way. These hardware modules include multi-core microcontroller development board， Iot gateway， DDC controller， input and output equipment， man-machine interface， etc.， which help students deepen the understanding of the theoretical knowledge about the Iot control system， as well as to help students master software development skills of Niagara industrial Iot software， embedded software and cloud platform software. Teaching practice shows that the course labs and project design based on the platform provide a support on the learning and development about intelligent nodes， embedded edge computing terminals， measurement and control technology in intelligent system， and effectively improve the students' ability to solve complex engineering problems.关键词：Internet of Things;control system;lab teaching platform;node-edge-cloud technology;Niagara23|73|0更新时间：2023-07-24
- “最新研究进展：房地产线上营销平台房源信息分析与房价预测。专家采用Scrapy框架采集数据，基于最小二乘法优化多元线性回归模型，开发Vue框架Web端系统，实现房源信息检索、比较及数据可视化，为购房者提供价格展示、分析及辅助决策服务。”摘要：The discrete distribution of housing data on online marketing platforms plays an important role in helping consumers correctly collect housing information， predict housing prices， and make purchasing decisions to improve purchasing efficiency. Taking the structured real estate information of the real estate online marketing platform as the research object， firstly， the web crawler technology Scrapy framework is used to collect and process data such as community information and housing source information， select the representative characteristics， establish and optimize the multiple linear regression model based on the least square method， and predict the real estate price； Then we developed a web end real estate information analysis and display system based on Vue framework. The back-end uses the SpringBoot framework to connect the relational database MySQL to store data. Finally， we realized the functions of house source information retrieval， comparison and data visualization， providing buyers with house source price display， analysis and purchase auxiliary decision-making services.关键词：Scrapy;Web spider;least square method;multiple linear regress;house price prediction52|73|0更新时间：2023-07-24
- 摘要：At present，traffic management departments have accumulated a large number of traffic accident data， but due to the limitations of data analysis， visual technology and other means， has not fully realized the application of a large number of accident data and the cause of the accident and accident prevention decision further research. So this paper adopts a new analysis mining way-web traffic accident visual analysis website. The back end of the website is developed using Django architecture， and the front end uses Echarts combined with Baidu Map API to carry out multi-dimensional data visualization， realizing multi-dimensional visual analysis functions such as time analysis， spatial analysis， dynamic analysis and accident prediction. Relational database MySQL is used to store data， and Redis database is used as system cache. Based on the logistic algorithm， training modeling is carried out on the date， month， quarter， weather， road section and other fields of historical traffic accident data， and the number of traffic accidents that may occur on a certain day and road section in the future is predicted. The results show that the system does not need to master complex data analysis methods， but only needs to combine related options through the function buttons on the interface to realize visual analysis of data， which greatly reduces the time and energy investment of transportation personnel in visual analysis technology learning.关键词：Django;traffic accidents;website;visual analysis81|39|0更新时间：2023-07-24
- “在情感计算领域，针对图像情感分析的不均衡数据问题，研究者改进Focal Loss损失函数，采用加权投票法策略，有效提升了图像情感多分类的准确率。”摘要：At present， image based affective analysis has become a research hotspot in the field of affective computing. The open data set commonly used in image emotion analysis is usually presented as multi category unbalanced data， and the single model has the problems of single feature extraction and weak generalization ability. First， the Focal Loss loss function is improved to make the model dynamically adjust the focus parameters following the training progress. Then， probability threshold parameters are set to determine the difficult samples， and the model avoids learning incorrect features by discarding the difficult samples. Next， select three convolutional neural network models with good classification performance as base classifiers， focusing on the local， color， and depth semantic features of the image. Finally， the weighted voting strategy is adopted， and information entropy is introduced to update the weights of multi classifier decisions. The experiment shows that the proposed method can improve the accuracy of image sentiment multi classification， and can provide reference for the research of image sentiment classification based on imbalanced data and ensemble learning.关键词：image sentiment analysis;unbalanced data;Focal loss function;difficult samples;weighted voting method20|20|0更新时间：2023-07-24
- “在医学图像处理领域，研究者提出了一种新的肺结节分割方法DC-CBAM-UNet++，通过结合空洞卷积与注意力机制，显著提高了分割精度，为肺结节图像分析提供了有效解决方案。”摘要：To address the problems of small volume， irregular shape and blurred edges in lung nodule images， which lead to difficulty in feature extraction and low segmentation accuracy， propose a lung nodule segmentation method （DC-CBAM-UNet++） based on UNet++ combined with cavity convolution and attention mechanism. In order to obtain a larger sense field for the feature map， this method improves the traditional UNet++ network ， introducing the null convolution （DC-UNet++） on the original basis， and also introducing the attention mechanism to enhance the feature map to obtain more weighted occupancy. Experiments were conducted using the LIDC lung nodule public dataset for training and validation， and the accuracy， similarity coefficient and cross-merge ratio reached 94.98%，90.86% and 84.54%， respectively， demonstrating the effectiveness of the method and providing a new method for segmenting pulmonary nodule images.关键词：UNet++;dilated convolution;attention mechanism;image segmentation42|29|0更新时间：2023-07-24
- 摘要：To solve the problem of high computational complexity and time-consuming target image retrieval in smart agricultural monitoring systems， a video adaptive sampling algorithm is proposed. Firstly， adaptively adjust the sampling rate of video frames based on changes in similarity between adjacent frames to extract video keyframes， ensuring that the keyframes extracted by the algorithm can replace adjacent frames in target image retrieval calculations. Then， a video frame retrieval operator is constructed based on the time axis of the video keyframes， replacing the original video to participate in the target image retrieval calculation， thereby reducing a large number of repeated calculations when retrieving the target image in the video， and achieving the goal of improving retrieval efficiency. Experiments have shown that the adaptive sampling algorithm has a higher and more stable detection rate than the video frame retrieval operator constructed by fixed frequency sampling and minimum keyframe algorithms. On the basis of ensuring that all images are detected， using video frame retrieval operators to replace the original video in the calculation of target image retrieval has a significant optimization range， reducing time consumption by more than 60%， and is of great significance for improving the retrieval efficiency of target images in smart agricultural monitoring systems.关键词：adaptive sampling;image similarity;target image frame;video frame retrieval operators23|30|0更新时间：2023-07-24
- “在遥感船舶图像细粒度分类领域，专家提出了一种基于注意力机制的分类网络，通过CBAM注意力机制和数据增强方法，有效提升了分类精度。”摘要：The difficulty of fine-grained classification of remote sensing ship images is that the differences between classes are small and the differences within classes are large， and there are too few publicly available datasets in this field， and conventional data enhancement methods are inefficient and not effective enough. In order to solve the above problems， an attention mechanism-based remote sensing ship image classification network is proposed. Specifically， the CBAM attention mechanism is first used to generate the attention map of each training map to highlight the salient feature parts of the target， and then the data augmentation is carried out through attention-guided region clipping and attention-guided region deletion. Finally， the original images and the augmented images are inputted for training. The method is verified on the dataset FGSCR-42. The experimental results show that the method surpasses other existing models and effectively improves the accuracy of the fine-grained classification of remote sensing ship images.关键词：remote sensing images;fine-grained classification of ships;data augmentation;CBAM attention mechanism31|56|0更新时间：2023-07-24
- “介质阻挡放电技术在工业应用中取得新突破，通过可见光图像分析，成功评价放电空间均匀性，为提高工业效率提供新方案。”摘要：The efficient generation of low-temperature plasma through dielectric barrier discharge （DBD） is influenced by the discharge mode and level， which in turn affects the efficiency of practical industrial applications.A new method is used in to evaluate spatial uniformity of dielectric barrier discharge based （DBD） on visible light images. The spatial uniformity of DBD is evaluated by calculating the gray-level co-occurrence matrix （GLCM） of the discharge image under different discharge conditions， exposure time， and characteristic parameters. According to the establishment of distribution model of filamentary discharge with different uniform degrees， discharge levels can be determined by the characteristic parameters of GLCM of discharged images： evenly distributed discharge assigned to grade I， unevenly distributed discharge defined as grade II， and extremely uneven discharge classified as grade III. The results showed that the characteristic parameters of GLCM of discharge image is valid to evaluate the uniformity of DBD under the same exposure time and experimental conditions. These parameters well reflect the characteristics of the discharge image on a long-time scale， and can be used for further classification of the input of the classifier. The characteristic parameters vary greatly with the exposure time of the captured discharge image， which effectively reflect the spatial distribution of discharge in 0.3-1s. With the increase of voltage level， the discharge times of filamentary discharge increased， and the spatial uniformity was improved in the long-time scale.关键词：dielectric barrier discharge;uniformity evaluation;filamentous discharge;gray level co-occurrence matrix;image classification18|39|0更新时间：2023-07-24
- “在中小学人工智能教学应用领域，专家构建了基于期望确认理论和信息系统成功模型的持续性采纳影响因素理论模型。研究结果表明，有用性感知是中小学教师对人工智能教学应用持续性采纳最直接也是最主要的影响因素。”摘要：Currently，the application of AI in primary and secondary schools technology is constantly deepening，for the continuous adoption of AI teaching applications among primary and secondary school teachers， this study constructed a theoretical model of factors influencing continuance adoption based on expectation confirmation theory and information system success model. The results show that perceived usefulness has a significant direct effect on satisfaction and continuous behavioral intentions； expectation confirmation has a significant direct impact on satisfaction and perceived usefulness， it has an indirect impact on satisfaction and continuous behavioral intentions through perceived usefulness； content quality has a significant direct effect on perceived usefulness， and an indirect effect on continuous behavioral intentions through perceived usefulness； system quality has a significant direct effect on expectation confirmation， and an indirect effect on satisfaction through expectation confirmation； in addition， system quality has no significant effect on usefulness perception. Gender and age have moderating effects on perceived usefulness， satisfaction and continuous behavioral intentions. It is concluded that the perception of usefulness is the most direct and most important factor affecting the continuous adoption of artificial intelligence by primary and secondary school teachers.关键词：expectation confirmation theory;information system success model;influencing factors of continuous adoption;teaching application;artificial intelligence19|270|0更新时间：2023-07-24
- “在工程教育领域，专家建立了以动态知识图谱为核心的教学模式，为持续改进教学过程和教育智能化提供解决方案。”摘要：The application of knowledge graph technology in the teaching process of universities， and even the implementation of teaching activities centered on knowledge graphs， has been recognized by the education and industry sectors. The rapid development of the times has led to the continuous emergence of new technologies and theories in engineering majors. In the concept of "continuous improvement" in engineering education certification， it is necessary to continuously update the teaching content and mode. A static knowledge graph cannot adapt well to the teaching process of "continuous improvement". Therefore， a dynamic teaching knowledge graph is proposed to carry out teaching management practices in computer science and technology majors. Research has shown that a teaching model centered on dynamic knowledge graphs can meet the "continuous improvement" needs brought about by engineering education certification and subject development， and provide data support for educational intelligence.关键词：engineering education certification;knowledge graph;education mode;continuous improvement;computer science24|22|0更新时间：2023-07-24
- 摘要：In order to improve students' in-depth understanding of the structure， operation mechanism and development of computers， four aspects of teaching content reform are proposed and actively explored. Through the partial reconstruction and in-depth understanding of the teaching content， this paper focuses on the non closure of the computer structure， the advancement of the computer composition， the consideration of the principle to the reality， and the systematicness of the computer composition and operation， and gives the necessary case analysis.In the meantime， it is proposed to innovate teaching methods and pay attention to the use of case teaching and flipped classroom teaching methods to improve teaching and learning effects. After more than 5 years of reform and practice， positive progress has been made in course grades and practical aspects， and students' learning outcomes have been significantly improved.关键词：computer hardware system;computer composition principle;system capacity;teaching content reform34|51|0更新时间：2023-07-24
- “在程序设计课程思政领域，专家通过混合教学模式实践研究，采用PBL教学方法，激发学生学习兴趣，培养自主学习能力、团队协作能力与创新实践能力，实现润物无声的思政教育，提高学生综合素养。”摘要：Adhering to the trinity education concept of "value creation， ability cultivation and knowledge imparting"， study the blended teaching mode in curriculum ideological and political education in the course of programming.In the implementation of blended teaching， online and offline teaching resources are combined， and programming teaching resources are combined with curriculum ideological and political resources. The problem-based PBL teaching method is adopted to give full play to the expressiveness of program design in data calculation and fully let the data "speak". By constantly improving the teaching design， stimulating students' interest in learning and cultivating students' autonomous learning， teamwork and innovative practice ability， realize the ideological and political education of "moistening things silently" in teaching and improve students' comprehensive quality.关键词：programming course;curriculum ideology and politics education;blended teaching mode;PBL37|34|0更新时间：2023-07-24
- “安徽理工大学物联网工程专业实践教学改革，通过创新平台建设、课程设计、综合实训等举措，有效提升学生实践创新能力，为新工科建设提供有力支撑。”摘要：Aiming at the typical problems existing in the practical teaching of Internet of Things and the requirements for creative and practical ability under the background of emerging engineering education， some measures and methods to improve the practical teaching effect of Internet of Things are proposed， which are combined with the practice of the specialty construction of Internet of Things in Anhui University of Science and Technology. They include the construction of creative practice teaching platform， the multi-level curriculum experimental content， the curriculum design integrated with the engineering problem， the comprehensive training deeply integrated with industries， the creative practice activities driven by the discipline competition and national college students' innovation and entrepreneurship training program. Three years of practical teaching reform and implementation have enhanced students' practical innovation ability and improved the effectiveness of practical teaching, and the reform initiatives of the practical teaching link can provide strong support for the construction of new engineering disciplines.关键词：emerging engineering education;Internet of Things engineering;practical teaching;teaching reform22|279|0更新时间：2023-07-24
- “在Web程序设计课程中，通过深入探索课程思政建设，实现了全面育人目标，为创新课程育人方式提供了新思路。”摘要：The curriculum is the micro carrier to implement the task of ideology and politics education， and the construction of first-class courses essentially undertakes the core task of comprehensive education and whole process education. By elaborating the exploration and practice of Web programming course in the process of first-class course construction on the construction of course ideology and politics， first of all， analyzed the close relationship between first-class courses and course philosophy， then sorted out the knowledge， ability and nurturing objectives of the course， designed the teaching process， the integration of philosophy elements and course teaching design. Finally， a few specific practices of the curriculum team are given. The organic integration of civic and political elements and engineering ability cultivation with project cases provides a new way of thinking for implementing comprehensive moral education and innovating the way of educating people in the curriculum.关键词：curriculum ideology and politics;first-class courses;project cases;curriculum education26|24|0更新时间：2023-07-24
-
Construction Practice of Practice Curriculum System of Big Data Management and Application Specialty AI导读
“北京联合大学大数据管理与应用专业在实践课程体系建设中，针对专业数据素养能力培养，提出实践教学建设整体思路，为提升学生专业核心能力奠定了基础。”摘要：At present， in professional construction， how to output talents that meet the needs of big data management and application capabilities to society， and how to improve students' core professional abilities guided by ability cultivation are the focus of teachers' attention. To this end， in response to the cultivation of professional data literacy abilities， the big data management and application major of Beijing Union University has identified problems in practical teaching of ability cultivation in the construction of the practical course system， proposed an overall approach to practical teaching construction， clarified the relationship between the course system and ability goals by sorting out professional ability goals， and determined a practical teaching system based on data literacy abilities. Taking the teaching content design of practical courses in the field of the Internet as an example， the discussion is conducted at different levels. Practice has shown that the construction of a practical teaching system based on data literacy ability has laid the foundation for improving students' core professional abilities and become an important guarantee for enhancing professional abilities.关键词：big data;management and application;capability objectives;practical teaching;curriculum system18|78|0更新时间：2023-07-24 -
Practice of "Mixed-source and Multi-mode" Teaching Mode in Postgraduate Software Testing Course AI导读
“在高校教育数字化建设领域，西北工业大学和扬州大学近5年研究生软件测试课程教学探索与实践，提出“混源多模”教学模式。该模式借助人工智能优化教学资源，结合“案例+研讨式”教学方法，实现教学模式的灵活授课。实践结果表明，该模式显著提升了教学效果，课程目标达成度和优秀率均有大幅提升，形成了以10万条开源缺陷报告为核心的教学案例知识库，为软件测试教学提供了新思路和方法。”摘要：To adapt to the rapid development of digital education in colleges and universities， a "mixed source and multi-mode" teaching model is proposed based on the teaching exploration and practice of the postgraduate course "software testing" of Northwestern Polytechnical University and Yangzhou University in the past five years. We select and optimize teaching resources with the help of artificial intelligence. The online teaching resources， open source project data， and students' ideological dynamics are comprehensively considered and the classical "case + discussion" teaching method are applied to adapt to "changes" and provide flexible teaching. At the same time， with the help of digital platforms， teaching evaluation feedback is established to form an iterative optimization mechanism for course teaching models. Practice has shown that the "mixed source and multi-mode" teaching model has significantly improved the teaching effect by integrating teaching resources and students' ideological dynamics. In the teaching years 2017-2021， some of our achievements include： the achievement degree of course goal rose from 0.73 to 0.87， and the excellent rate （comprehensive score>=90 points） reached 31%； a teaching case knowledge base with 100 000 open source bug reports and related project data was formed；we designed and implemented an automatic teaching case construction system； we gained rewards of excellent teaching book， online course， and student competitions of software testing， and published some papers on high-quality journals and conferences.关键词：postgraduate course teaching;software testing;mixed-source and multi-mode;intelligent assistance23|14|0更新时间：2023-07-24 - “在应用型本科院校操作系统课程改革领域，专家提出融入思政元素的教学设计与实践，通过转变观念、融合教学方式等，为提升课程效果提供新思路。”摘要：In view of the problems existing in operating system courses in application-oriented undergraduate colleges， such as emphasising knowledge imparting and ignoring value shaping， outdated content， monotonous teaching methods， and inability of evaluation methods to reflect students' learning effects，propose the reform ideas of operating system course taking the curriculum ideology and politics as the breakthrough point，and expounds the teaching design and practice process from four aspects： changing teaching concepts， condensing the ideological and political elements of the curriculum， integrating various teaching methods， and highlighting the learning effect orientation. Finally， the implementation effect of curriculum reform is analyzed and reflected through questionnaire survey.关键词：curriculum ideology and politics;operating system;teaching reform and practice17|40|0更新时间：2023-07-24
- “安徽师范大学计算机专业通过改革教学资源建设与教师能力提升，有效提升了学生的系统能力，成绩显著提高。”摘要：The characteristics of systematic ability training in some demonstrative universities is studied， and the common problems in the process of systematic ability training in non demonstrative universities are analyzed. The weakness of the system ability training of computer major at Anhui Normal University is investigated through a questionnaire， and the measures adopted by the school is also introduced，that the construction of teaching resources and the improvement of teachers' ability can be promoted by writing good books and earnest teaching .Statistical data show that these measures have produced obvious effects on the cultivation of students' systematic ability.关键词：system ability training;circuit design ability;demonstrative;teaching ability15|23|0更新时间：2023-07-24
- “在计算机网络原理教学领域，专家提出教学建设方案，重构课程目标，创新教学模式，提升教师能力，有效提高学生政治素养和工程能力。”摘要：In order to better play the value leading role of computer network principle course and its supporting role of knowledge， ability and quality in talent training， by combining with many years of teaching experience， proposed a construction scheme for the computer network principle course oriented to the requirements of engineering education certification and the idea of curriculum ideology and politics. This scheme is implemented from the aspects of course object reconstruction， contents design， teaching model innovation， and improvement of teachers' ability. According to the result of implementation， this scheme can improve significantly students' political literacy and engineering ability.关键词：engineering education certification;curriculum ideology and politics;course construction;teaching reform19|40|0更新时间：2023-07-24
- “心血管疾病诊断领域取得新进展，专家回顾电子听诊器及智能听诊算法研究，为提高诊断准确率提供建议，推动了该领域发展。”摘要：Cardiovascular disease （CVD） has become one of the greatest threats to human health， so accurate detection of early disease conditions is crucial for reducing the mortality rate of cardiovascular disease. With the normalization of the COVID-19， the demand for electronic auscultation， remote auscultation and intelligent auscultation is increasing. Through a retrospective study of the research and application of electronic stethoscope and intelligent auscultation algorithms in the diagnosis of heart disease at this stage， a more comprehensive list of existing electronic stethoscope and heart sound databases is given， and some key technologies that need to be solved urgently in the intelligent auscultation of heart sounds are summarized， providing suggestions on algorithms to improve the accuracy of intelligent auscultation， Suggestions are also provided on the development direction of electronic auscultation and intelligent auscultation.关键词：heart disease;heart sound;intelligent auscultation;electronic stethoscope;deep learning;machine learning19|322|0更新时间：2023-07-24
- “在图像修复领域，基于深度学习的技术快速发展，成为主流。本文全面梳理了卷积神经网络、生成式对抗网络和Transformer网络三大类修复方法，深入分析了它们的特点和不足，并在多个公开数据集上进行了系统的实验验证和分析。这为图像修复技术未来的发展提供了新方向。”摘要：Inpainting aims to use artificial intelligence and other technologies to automatically complete the pixel information of the damaged area in the image. It is extensively used in the fields of public security criminal investigation， cultural relic inpainting and so on. In recent years，inpainting technology based on deep learning has developed rapidly and gradually become the mainstream. Comprehensively summarize the image inpainting methods based on deep learning， including three categories of inpainting methods based on convolutional neural network， generative adversarial network and Transformer， deeply analyzing the characteristics and shortcomings of these methods，and conducts systematic experimental validation and analysis on several public datasets. Finally， the possible future directions of image inpainting techniques are given.关键词：image inpainting;deep learning;convolutional neural network;generative adversarial network;attention network38|65|0更新时间：2023-07-24
- “最新研究进展显示，固件漏洞检测技术在静态和动态分析领域取得显著成果，为解决安全问题提供新方案。”摘要：Firmware vulnerability detection technology can be divided into static detection and dynamic detection. Static detection relies on binary program of firmware image， which mainly includes two analysis methods： vulnerability function similarity comparison by extracting features and vulnerability detection by symbolic execution； Dynamic detection requires dynamically running firmware， simulating the firmware running environment， and combining software vulnerability detection technology to detect firmware vulnerabilities. Provide a detailed interpretation of the advanced static and dynamic analysis methods in the field of firmware vulnerabilities in recent years， while also analyzing the challenges faced by existing technologies.关键词：Internet of Things;firmware;vulnerability detection;static analysis;dynamic analysis24|87|0更新时间：2023-07-24
- “在计算机软件系统更新迭代领域，专家深入分析了数据迁移的热点与难点，建立了高效、高质量的迁移方法体系，为解决数据迁移问题提供了解决方案。”摘要：The updating and iteration of computer software system is accelerating day by day， and the available software modules and data existing in the legacy system play a decisive role in the research， development and start-up of the target system， so the data migration is widely used in the software update iteration area， because it can save the development time and reduce the development cost. At present， there are many problems in data migration research， such as missing of legacy system development documents， inconsistent data quality and low data migration efficiency. How to transfer program modules and data effectively and with high quality by means of available methods has become a hot and difficult topic in current research. This paper sorts out the influence of data quality on data migration， the basic architecture of data migration and data migration methods， analyzes the currently available architectures and methods， comprehensively evaluates the commonly used architecture models and methods， and summarizes the different migration methods for different models. Finally， the current problems and future research work in this field are summarized to provide ideas for further research.关键词：data migration;data quality;migration architecture;migration method31|139|0更新时间：2023-07-24
- “新一代信息技术为教学评价带来新突破，315篇文献揭示研究热点和趋势。大数据、人工智能等技术与教学深度融合，推动教学评价从理论走向应用。”摘要：The new generation of information technology develops rapidly，providing important technology support for teaching evaluation. Collect 315 articles on the teaching evaluation supported by the new generation of information technology using CNKI database， mainly adopts the methods of bibliometrics， and explores the related research hotspots and research trends. The research shows that the teaching evaluation research supported by the new generation of information technology has formed three major research themes： the current situation of teaching evaluation and response strategies， construction of teaching evaluation model and framework， innovation of teaching evaluation technology. Research hotspots mainly focus on big data， artificial intelligence， online teaching and formative evaluation. Research has gradually transitioned from theoretical research to both theoretical and applied research， and various technologies have been integrated with teaching in a deeper way. The paper is summarized to draw a summary and outlook of the research related to teaching evaluation supported by new generation information technology.关键词：new generation of information technology;teaching evaluation;research hotspots;research trends23|186|0更新时间：2023-07-24
- Technical support is provided by Beijing Founder electronics co., LTD 鄂ICP备18021494号-4
鄂公网安备42010602004949号 - It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
- Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
0