Pub Date : 2023-02-03DOI: 10.1109/ECEI57668.2023.10105356
Chia-Jui Chang, Chih-Cheng Chen, Bing-Hong Chen
In modern industry, ball bearings are not prone to failure, once a failure occurs, the production of the factory will be shut down, which will cause economic losses. Therefore, it's crucial to research how to diagnose ball bearings. This research proposed an advanced fault diagnosis method: 1D-CNN-LSTM to classify ball bearing faults and use the ball bearing faults data from Case Western Reserve University (CWRU) to execute experiments, which is the raw one-dimensional vibration sequential data. In the experiment, the raw vibration data is first split into multiple subsequences, and input to one-dimensional convolutional neural network (1D-CNN) wrapped by TimeDistributed layer to extract features. The output of 1D-CNN is a sequence, which is input to long short-term memory (LSTM) for sequential processing. Finally, the class of bearing fault is output for diagnosis. The results indicate a good model fit and outstanding generalization and robustness on new validation data. The assessment of the training dataset indicates that it has achieved a perfect accuracy of 100%, while the validation dataset has achieved an accuracy of 99.99%, which is an exceptional outcome.
在现代工业中，滚珠轴承不容易发生故障，一旦发生故障，工厂的生产将停止，这将造成经济损失。因此，研究滚珠轴承的故障诊断方法至关重要。本研究提出了一种先进的故障诊断方法:1D-CNN-LSTM对球轴承故障进行分类，并利用凯斯西储大学(CWRU)的球轴承故障数据进行实验，该数据为原始的一维振动序列数据。在实验中，首先将原始振动数据分割成多个子序列，输入到timedidistributed层包裹的一维卷积神经网络(1D-CNN)中提取特征。1D-CNN的输出是一个序列，该序列被输入到LSTM (long - short memory)中进行顺序处理。最后输出轴承故障的类别进行诊断。结果表明，该方法对新的验证数据具有良好的拟合效果，具有较好的泛化和鲁棒性。对训练数据集的评估表明，它达到了100%的完美准确率，而验证数据集达到了99.99%的准确率，这是一个例外的结果。
{"title":"Bearing Fault Diagnosis Based on an Advanced Method: ID-CNN-LSTM","authors":"Chia-Jui Chang, Chih-Cheng Chen, Bing-Hong Chen","doi":"10.1109/ECEI57668.2023.10105356","DOIUrl":"https://doi.org/10.1109/ECEI57668.2023.10105356","url":null,"abstract":"In modern industry, ball bearings are not prone to failure, once a failure occurs, the production of the factory will be shut down, which will cause economic losses. Therefore, it's crucial to research how to diagnose ball bearings. This research proposed an advanced fault diagnosis method: 1D-CNN-LSTM to classify ball bearing faults and use the ball bearing faults data from Case Western Reserve University (CWRU) to execute experiments, which is the raw one-dimensional vibration sequential data. In the experiment, the raw vibration data is first split into multiple subsequences, and input to one-dimensional convolutional neural network (1D-CNN) wrapped by TimeDistributed layer to extract features. The output of 1D-CNN is a sequence, which is input to long short-term memory (LSTM) for sequential processing. Finally, the class of bearing fault is output for diagnosis. The results indicate a good model fit and outstanding generalization and robustness on new validation data. The assessment of the training dataset indicates that it has achieved a perfect accuracy of 100%, while the validation dataset has achieved an accuracy of 99.99%, which is an exceptional outcome.","PeriodicalId":176611,"journal":{"name":"2023 IEEE 6th Eurasian Conference on Educational Innovation (ECEI)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124203782","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-03DOI: 10.1109/ECEI57668.2023.10105308
Lulu C. H. Sun
In the research of big data, the technology and theory of artificial intelligence are increasingly improved, and its application fields are also extending, almost fitting into every aspect of life. We have to admit that the advancement of artificial intelligence is a key point leading every aspect to the forefront. Moreover, network education has been developed in society. Artificial intelligence has been a part of national strategy, and education has gradually moved toward the direction of intelligence. Thus, the use of artificial intelligence technology is analyzed and discussed in education with big data. First, the concepts of big data and artificial intelligence technology are described. Then, the impact of artificial intelligence education is analyzed to deeply discuss the factors that promote personalized services and build an artificial intelligence ecological environment.
{"title":"Research on Application of Education Big Data Integrated with Artificial Intelligence Technology in Teaching Field","authors":"Lulu C. H. Sun","doi":"10.1109/ECEI57668.2023.10105308","DOIUrl":"https://doi.org/10.1109/ECEI57668.2023.10105308","url":null,"abstract":"In the research of big data, the technology and theory of artificial intelligence are increasingly improved, and its application fields are also extending, almost fitting into every aspect of life. We have to admit that the advancement of artificial intelligence is a key point leading every aspect to the forefront. Moreover, network education has been developed in society. Artificial intelligence has been a part of national strategy, and education has gradually moved toward the direction of intelligence. Thus, the use of artificial intelligence technology is analyzed and discussed in education with big data. First, the concepts of big data and artificial intelligence technology are described. Then, the impact of artificial intelligence education is analyzed to deeply discuss the factors that promote personalized services and build an artificial intelligence ecological environment.","PeriodicalId":176611,"journal":{"name":"2023 IEEE 6th Eurasian Conference on Educational Innovation (ECEI)","volume":"262 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132590937","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-03DOI: 10.1109/ECEI57668.2023.10105314
Jianing Yang, Meize Chen, Guangze Cao
Urban underground integrated pipe corridor is used for the water, electricity, gas, communications, and other pipelines into the underground space to effectively alleviate road traffic congestion, urban construction infrastructure, and other problems. After the completion of the corridor, the corridor inspection is a huge problem, as the underground space is complex and difficult to locate. For the need to detect the concentration of toxic and harmful gases inside the corridor, it is difficult to ensure the safety of the lives of the underground staff. With the development of artificial intelligence and digital twin, the corridor inspection robot gradually becomes the “perfect candidate” for inspection work. Thus, we present a system design of 3D LIDAR-based robot positioning and map building underground where GPS is not available.
{"title":"System Design of 3D LiDAR-based Underground Integrated Pipeline Corridor Inspection Robot for Positioning and Map Building","authors":"Jianing Yang, Meize Chen, Guangze Cao","doi":"10.1109/ECEI57668.2023.10105314","DOIUrl":"https://doi.org/10.1109/ECEI57668.2023.10105314","url":null,"abstract":"Urban underground integrated pipe corridor is used for the water, electricity, gas, communications, and other pipelines into the underground space to effectively alleviate road traffic congestion, urban construction infrastructure, and other problems. After the completion of the corridor, the corridor inspection is a huge problem, as the underground space is complex and difficult to locate. For the need to detect the concentration of toxic and harmful gases inside the corridor, it is difficult to ensure the safety of the lives of the underground staff. With the development of artificial intelligence and digital twin, the corridor inspection robot gradually becomes the “perfect candidate” for inspection work. Thus, we present a system design of 3D LIDAR-based robot positioning and map building underground where GPS is not available.","PeriodicalId":176611,"journal":{"name":"2023 IEEE 6th Eurasian Conference on Educational Innovation (ECEI)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134262633","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-03DOI: 10.1109/ECEI57668.2023.10105343
Danni Wang
With the development of Internet study, big data mining for Internet learners is forming a new research direction. Network higher education institutions offer higher education with distance learning for continuous learning. Based on the analysis of the learning diaries of the students in the network of Xi'an Jiaotong University, this study aims to reveal the learning situation of the students in the network of higher education institutions and probe the relationship between the typical Internet study abroad. Based on the statistical analysis of the log data, the aggregation analysis is carried out according to the number of main knowledge points mastered by learners and the realization rate of relevant main knowledge points, and the learners of Internet colleges and universities are classified. The Spearman correlation coefficient is used to analyze the relationship between various learning activities and the achievements of learners. The result provides an important basis for further improvement and a more accurate evaluation of online teaching in the future.
{"title":"Clustering Research on Learning Behavior of Online Moral Education Course Based on K-Means Algorithm","authors":"Danni Wang","doi":"10.1109/ECEI57668.2023.10105343","DOIUrl":"https://doi.org/10.1109/ECEI57668.2023.10105343","url":null,"abstract":"With the development of Internet study, big data mining for Internet learners is forming a new research direction. Network higher education institutions offer higher education with distance learning for continuous learning. Based on the analysis of the learning diaries of the students in the network of Xi'an Jiaotong University, this study aims to reveal the learning situation of the students in the network of higher education institutions and probe the relationship between the typical Internet study abroad. Based on the statistical analysis of the log data, the aggregation analysis is carried out according to the number of main knowledge points mastered by learners and the realization rate of relevant main knowledge points, and the learners of Internet colleges and universities are classified. The Spearman correlation coefficient is used to analyze the relationship between various learning activities and the achievements of learners. The result provides an important basis for further improvement and a more accurate evaluation of online teaching in the future.","PeriodicalId":176611,"journal":{"name":"2023 IEEE 6th Eurasian Conference on Educational Innovation (ECEI)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134283596","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-03DOI: 10.1109/ECEI57668.2023.10105264
R. Xue
We study the language characteristics that change the writing quality of language users to enhance the accuracy of the existing automatic evaluation system for writing using integrated learning technology. The FCE test sample in Cambridge is used, and the object is filtered by vector regression and random forest algorithm to establish and evaluate the automatic scoring mode. Compared with the existing technology, the accuracy of the evaluation using the integrated method is improved. This method effectively evaluates the writing efficiency of English learners and is used to develop a writing self-help evaluation system for large-scale computer tests and online autonomous learning systems.
{"title":"Research on Intelligent Classification And Grading Algorithm of English Composition Based on Support Vector Machine","authors":"R. Xue","doi":"10.1109/ECEI57668.2023.10105264","DOIUrl":"https://doi.org/10.1109/ECEI57668.2023.10105264","url":null,"abstract":"We study the language characteristics that change the writing quality of language users to enhance the accuracy of the existing automatic evaluation system for writing using integrated learning technology. The FCE test sample in Cambridge is used, and the object is filtered by vector regression and random forest algorithm to establish and evaluate the automatic scoring mode. Compared with the existing technology, the accuracy of the evaluation using the integrated method is improved. This method effectively evaluates the writing efficiency of English learners and is used to develop a writing self-help evaluation system for large-scale computer tests and online autonomous learning systems.","PeriodicalId":176611,"journal":{"name":"2023 IEEE 6th Eurasian Conference on Educational Innovation (ECEI)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133533287","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-03DOI: 10.1109/ECEI57668.2023.10105416
Guilian Li, Lili Jiang
Using the random forest algorithm in machine learning, the problem of children's social phobia is transformed into a classification prediction problem. There are many reasons for social anxiety disorder in childhood (SADC). Thus, we study the influence of parents' socioeconomic attributes on SADC. Based on the data obtained from the questionnaire survey of children and their parents in an early education institution, we build a prediction model between SADC and parents' socioeconomic attributes with the bivariate correlation method, the logistic regression, and the random forest method. The study result shows that the parents' socio-economic attributes are strongly related to SADC, and the model can be applied to the personalized care and psychological intervention of this early education institution. The result also shows that the accuracy reaches 80.5%. The model can be applied to preschool prediction and screening of children's social phobia tendencies and provides a reference for teachers to give personalized care and psychological intervention to children with a high tendency in follow-up teaching activities.
{"title":"Random Forest Algorithm-based Modelling and Neural Network Analysis Between Social Anxiety Disorder of Childhood and Parents' Socioeconomic Attributes","authors":"Guilian Li, Lili Jiang","doi":"10.1109/ECEI57668.2023.10105416","DOIUrl":"https://doi.org/10.1109/ECEI57668.2023.10105416","url":null,"abstract":"Using the random forest algorithm in machine learning, the problem of children's social phobia is transformed into a classification prediction problem. There are many reasons for social anxiety disorder in childhood (SADC). Thus, we study the influence of parents' socioeconomic attributes on SADC. Based on the data obtained from the questionnaire survey of children and their parents in an early education institution, we build a prediction model between SADC and parents' socioeconomic attributes with the bivariate correlation method, the logistic regression, and the random forest method. The study result shows that the parents' socio-economic attributes are strongly related to SADC, and the model can be applied to the personalized care and psychological intervention of this early education institution. The result also shows that the accuracy reaches 80.5%. The model can be applied to preschool prediction and screening of children's social phobia tendencies and provides a reference for teachers to give personalized care and psychological intervention to children with a high tendency in follow-up teaching activities.","PeriodicalId":176611,"journal":{"name":"2023 IEEE 6th Eurasian Conference on Educational Innovation (ECEI)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134044874","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-03DOI: 10.1109/ECEI57668.2023.10105415
Kai Liu, Faqiang Cui
In the current situation of the accounting courses for the major of finance and economics and the problems faced by the limited teaching time, textbooks and their contents cannot catch up with the development of the Internet due to the limited conditions of teaching experiment environment and practical activities. Therefore, an efficient plan is proposed in this study to build a virtual reality-assisted teaching system based on computer networks that is compatible with conventional classroom teaching methods. A new model integrates teaching activities and extracurricular network interaction, theoretical learning and practical work, practical teaching activities, and online teaching activities. It guides learners to learn and carry out projects beyond the teaching activities and provide all-round technical support for the teaching activities of business computing and corresponding professional courses. Through the functions provided by the online auxiliary teaching system, the theoretical and practical simulation exercises and the practical operation of the application software system are connected to a whole teaching system.
{"title":"Application of Virtual Machine Technology in Teaching Mode of Financial Budget in Vocational Colleges","authors":"Kai Liu, Faqiang Cui","doi":"10.1109/ECEI57668.2023.10105415","DOIUrl":"https://doi.org/10.1109/ECEI57668.2023.10105415","url":null,"abstract":"In the current situation of the accounting courses for the major of finance and economics and the problems faced by the limited teaching time, textbooks and their contents cannot catch up with the development of the Internet due to the limited conditions of teaching experiment environment and practical activities. Therefore, an efficient plan is proposed in this study to build a virtual reality-assisted teaching system based on computer networks that is compatible with conventional classroom teaching methods. A new model integrates teaching activities and extracurricular network interaction, theoretical learning and practical work, practical teaching activities, and online teaching activities. It guides learners to learn and carry out projects beyond the teaching activities and provide all-round technical support for the teaching activities of business computing and corresponding professional courses. Through the functions provided by the online auxiliary teaching system, the theoretical and practical simulation exercises and the practical operation of the application software system are connected to a whole teaching system.","PeriodicalId":176611,"journal":{"name":"2023 IEEE 6th Eurasian Conference on Educational Innovation (ECEI)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123724589","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-03DOI: 10.1109/ECEI57668.2023.10105409
Shigang Wang, Kai Ma, Xianghua Liao, Guang-Xing Tan
To improve the control accuracy of the quadruped robot, a method to estimate and control the attitude of the quadruped robot is presented using a nine-axis IMU sensor and kinematics model. An extended Kalman filter (EKF) is designed to filter the real-time data obtained from sensors such as a gyroscope, accelerometer, and magnetometer. After extended Kalman filtering, the nine-axis data of IMU is fused to obtain a more accurate quaternion. The quaternion is converted into the attitude angle to obtain the roll angle, yaw angle, and pitch angle of the quadruped robot. The filtered attitude angle is obtained by inversion to perform attitude compensation so that the quadruped robot can return to the normal attitude. After calculating the attitude compensation matrix, we solve the inverse kinematics of the quadruped robot to obtain the joint angle and understand the control of the quadruped robot's standing posture. The simulation results show that this method can effectively process the IMU sensor data and obtain a high-precision robot attitude angle. We will apply the above research results to the teaching of robot mechanisms for graduate students. The effectiveness of the algorithm is verified by the joint simulation of Matlab and CopperiaSim, and students have a further understanding of the quadruped robot attitude and control.
{"title":"Quadruped Robot Attitude Control Algorithm and its Application in Graduate Education","authors":"Shigang Wang, Kai Ma, Xianghua Liao, Guang-Xing Tan","doi":"10.1109/ECEI57668.2023.10105409","DOIUrl":"https://doi.org/10.1109/ECEI57668.2023.10105409","url":null,"abstract":"To improve the control accuracy of the quadruped robot, a method to estimate and control the attitude of the quadruped robot is presented using a nine-axis IMU sensor and kinematics model. An extended Kalman filter (EKF) is designed to filter the real-time data obtained from sensors such as a gyroscope, accelerometer, and magnetometer. After extended Kalman filtering, the nine-axis data of IMU is fused to obtain a more accurate quaternion. The quaternion is converted into the attitude angle to obtain the roll angle, yaw angle, and pitch angle of the quadruped robot. The filtered attitude angle is obtained by inversion to perform attitude compensation so that the quadruped robot can return to the normal attitude. After calculating the attitude compensation matrix, we solve the inverse kinematics of the quadruped robot to obtain the joint angle and understand the control of the quadruped robot's standing posture. The simulation results show that this method can effectively process the IMU sensor data and obtain a high-precision robot attitude angle. We will apply the above research results to the teaching of robot mechanisms for graduate students. The effectiveness of the algorithm is verified by the joint simulation of Matlab and CopperiaSim, and students have a further understanding of the quadruped robot attitude and control.","PeriodicalId":176611,"journal":{"name":"2023 IEEE 6th Eurasian Conference on Educational Innovation (ECEI)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125542017","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-03DOI: 10.1109/ECEI57668.2023.10105410
Tao Liu
In order to accurately identify and evaluate tennis movement, a method of tennis movement recognition and evaluation based on ResNet is proposed by combining computer vision with tennis movement-related knowledge. Firstly, the pose estimation model is used to detect the human target in a tennis video and extract the key points of the skeleton. Then, the ResNet model is trained using the video data set collected on the professional tennis court. The model can classify the sub-actions of tennis. A dynamic time-warping algorithm is used to evaluate the classified actions. A large number of experiments are carried out based on the collected video data set. The results show that the accuracy of the proposed ResNet-based tennis motion recognition method for the classification of 6 types of tennis sub-movements can reach 90.8%. Compared with methods based on graph convolution networks such as AGCN and ST-GCN, it has a stronger generalization ability. The proposed scoring algorithm based on dynamic time regulation gives the evaluation scores of corresponding actions in real time and accurately after the action classification, thus reducing the work intensity of tennis teachers and effectively improving the quality of tennis teaching.
{"title":"Resnet-Based Intelligent Recognition Algorithm and Evaluation of Students' Tennis Movement in Teaching Video","authors":"Tao Liu","doi":"10.1109/ECEI57668.2023.10105410","DOIUrl":"https://doi.org/10.1109/ECEI57668.2023.10105410","url":null,"abstract":"In order to accurately identify and evaluate tennis movement, a method of tennis movement recognition and evaluation based on ResNet is proposed by combining computer vision with tennis movement-related knowledge. Firstly, the pose estimation model is used to detect the human target in a tennis video and extract the key points of the skeleton. Then, the ResNet model is trained using the video data set collected on the professional tennis court. The model can classify the sub-actions of tennis. A dynamic time-warping algorithm is used to evaluate the classified actions. A large number of experiments are carried out based on the collected video data set. The results show that the accuracy of the proposed ResNet-based tennis motion recognition method for the classification of 6 types of tennis sub-movements can reach 90.8%. Compared with methods based on graph convolution networks such as AGCN and ST-GCN, it has a stronger generalization ability. The proposed scoring algorithm based on dynamic time regulation gives the evaluation scores of corresponding actions in real time and accurately after the action classification, thus reducing the work intensity of tennis teachers and effectively improving the quality of tennis teaching.","PeriodicalId":176611,"journal":{"name":"2023 IEEE 6th Eurasian Conference on Educational Innovation (ECEI)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125038629","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-03DOI: 10.1109/ECEI57668.2023.10105318
Lijing Wang
In order to quickly select a book from a large number of books, a comprehensive method is proposed with an implicit semantic model based on matrix analysis and time effect according to the cognitive characteristics of university readers in different learning periods. This method uses the random gradient descent method to calculate the customer-project evaluation matrix. In the method, a new treatment method is provided for cold start. The absolute error (MAE) and the mean square relative error (RMSE) of the evaluation index are used to test the correctness of the information provided by the proposed method. The feasibility and effectiveness of this method are confirmed by the actual data.
{"title":"Research on Intelligent Personalized Recommendation of Library Based on Matrix Decomposition Implicit Semantic Model","authors":"Lijing Wang","doi":"10.1109/ECEI57668.2023.10105318","DOIUrl":"https://doi.org/10.1109/ECEI57668.2023.10105318","url":null,"abstract":"In order to quickly select a book from a large number of books, a comprehensive method is proposed with an implicit semantic model based on matrix analysis and time effect according to the cognitive characteristics of university readers in different learning periods. This method uses the random gradient descent method to calculate the customer-project evaluation matrix. In the method, a new treatment method is provided for cold start. The absolute error (MAE) and the mean square relative error (RMSE) of the evaluation index are used to test the correctness of the information provided by the proposed method. The feasibility and effectiveness of this method are confirmed by the actual data.","PeriodicalId":176611,"journal":{"name":"2023 IEEE 6th Eurasian Conference on Educational Innovation (ECEI)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115042067","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：