Pub Date : 2020-12-01DOI: 10.1109/ITCA52113.2020.00127
Panpan Zhang
In the current education model, in order to improve the teaching quality of teachers, the established teaching system can push the teaching data and conclusions to the teachers themselves or the school, which helps to understand the teaching situation in many ways, so as to improve the teaching methods of teachers in the classroom. Develop targeted solutions to the problems that arise. This paper is based on the particle swarm algorithm, combined with particle cluster calculation and feature intensive fusion, to analyze the teacher's behavior in the classroom scene, aiming to improve the accuracy of teacher behavior recognition, make full use of video resources to assist in the analysis of the teacher's overall behavior, thereby automatically generating teaching Ways to evaluate.
{"title":"Application of Particle Vector Model in Smart Teaching Management System","authors":"Panpan Zhang","doi":"10.1109/ITCA52113.2020.00127","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00127","url":null,"abstract":"In the current education model, in order to improve the teaching quality of teachers, the established teaching system can push the teaching data and conclusions to the teachers themselves or the school, which helps to understand the teaching situation in many ways, so as to improve the teaching methods of teachers in the classroom. Develop targeted solutions to the problems that arise. This paper is based on the particle swarm algorithm, combined with particle cluster calculation and feature intensive fusion, to analyze the teacher's behavior in the classroom scene, aiming to improve the accuracy of teacher behavior recognition, make full use of video resources to assist in the analysis of the teacher's overall behavior, thereby automatically generating teaching Ways to evaluate.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127001628","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 : 2020-12-01DOI: 10.1109/ITCA52113.2020.00142
Xiong Cong, L. Biao, Wang Hengyang
The inkjet printer is a kind of industrial printing and marking equipment, which mainly prints the corresponding identification pattern to the designated position of the product on the assembly line, in order to improve the management efficiency and mobile convenience of the inkjet printer and enhance the user experience, a mobile platform which is intergrated and based on embedded Android system is built. At the same time, we have researched and designed a set of management system software that can run on the above platforms and covers the basic functions required by the inkjet printer. Using Unicode code dot matrix font to draw text. The traditional button mode is eliminated, and apply the full touch method with friendly interaction to achieve efficient management, and work with the drive control module and mechanical module to complete the coding and real-time monitoring of equipment. Finally, some function samples of the management software are shown to verify the effectiveness of its design.
{"title":"Software Design of Inkjet Printer Management System Based on Android","authors":"Xiong Cong, L. Biao, Wang Hengyang","doi":"10.1109/ITCA52113.2020.00142","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00142","url":null,"abstract":"The inkjet printer is a kind of industrial printing and marking equipment, which mainly prints the corresponding identification pattern to the designated position of the product on the assembly line, in order to improve the management efficiency and mobile convenience of the inkjet printer and enhance the user experience, a mobile platform which is intergrated and based on embedded Android system is built. At the same time, we have researched and designed a set of management system software that can run on the above platforms and covers the basic functions required by the inkjet printer. Using Unicode code dot matrix font to draw text. The traditional button mode is eliminated, and apply the full touch method with friendly interaction to achieve efficient management, and work with the drive control module and mechanical module to complete the coding and real-time monitoring of equipment. Finally, some function samples of the management software are shown to verify the effectiveness of its design.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125850452","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 : 2020-12-01DOI: 10.1109/ITCA52113.2020.00091
Mei-Jing Sun, Chen-Xin Fang, Zhen-Hua Zhao
In this paper, we addressed the decomposition problem of electroencephalogram and the detection of sleep spindles and K-complexes. We propose an approach to decompose the electroencephalogram into three components, including transient, low-frequency, and oscillation. The decomposition problem can be attributed to the convex optimization. The objection function of the optimization included the 1 norm of the transient and the Fourier transform coefficient of the oscillation. Based on the methods of the Douglas-Rachford variable splitting and the Alternating Direction Method of Multipliers, the electroencephalogram is decomposed efficiently. The detection of sleep spindles and K-complexes is achieved by applying the Teager-Kaiser Energy Operator on the oscillation and the low-frequency signal, respectively. The performance of the proposed approach is tested using a human DREAMS dataset. The average spindle detection accuracy of our method is 0.97 and the F1 score is 0.69. The average K-complex detection accuracy of our method is 0.97 and the F1 score is 0.46.
{"title":"Pattern Recognition in Human Sleep Electroencephalogram Using Sparse Optimization","authors":"Mei-Jing Sun, Chen-Xin Fang, Zhen-Hua Zhao","doi":"10.1109/ITCA52113.2020.00091","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00091","url":null,"abstract":"In this paper, we addressed the decomposition problem of electroencephalogram and the detection of sleep spindles and K-complexes. We propose an approach to decompose the electroencephalogram into three components, including transient, low-frequency, and oscillation. The decomposition problem can be attributed to the convex optimization. The objection function of the optimization included the 1 norm of the transient and the Fourier transform coefficient of the oscillation. Based on the methods of the Douglas-Rachford variable splitting and the Alternating Direction Method of Multipliers, the electroencephalogram is decomposed efficiently. The detection of sleep spindles and K-complexes is achieved by applying the Teager-Kaiser Energy Operator on the oscillation and the low-frequency signal, respectively. The performance of the proposed approach is tested using a human DREAMS dataset. The average spindle detection accuracy of our method is 0.97 and the F1 score is 0.69. The average K-complex detection accuracy of our method is 0.97 and the F1 score is 0.46.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"93 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125977512","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 : 2020-12-01DOI: 10.1109/ITCA52113.2020.00133
Luo Hongqi, Liu Zhixin
High frequency of safety accidents in the process of mechanical production has brought great pressure and loss to the social economy. Relevant statistics show that the proportion of illegal operation of operators is the main factor. In order to reduce the occurrence of safety accidents, the computer vision research technology based on monitoring video is applied to the direction of mechanical safety behavior recognition. The content of abnormal behavior of mechanical operators is relatively broad. A foundation for the subsequent simulation analysis can be formed through extracting the characteristics of the actor, calculating the characteristic operator of human behavior, and debugging and modifying the threshold value of the characteristic operator for judging the abnormal behavior.
{"title":"Research on feature extraction of mechanical operators with abnormal behavior","authors":"Luo Hongqi, Liu Zhixin","doi":"10.1109/ITCA52113.2020.00133","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00133","url":null,"abstract":"High frequency of safety accidents in the process of mechanical production has brought great pressure and loss to the social economy. Relevant statistics show that the proportion of illegal operation of operators is the main factor. In order to reduce the occurrence of safety accidents, the computer vision research technology based on monitoring video is applied to the direction of mechanical safety behavior recognition. The content of abnormal behavior of mechanical operators is relatively broad. A foundation for the subsequent simulation analysis can be formed through extracting the characteristics of the actor, calculating the characteristic operator of human behavior, and debugging and modifying the threshold value of the characteristic operator for judging the abnormal behavior.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"1146 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126347899","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 : 2020-12-01DOI: 10.1109/ITCA52113.2020.00072
Sengoku Yu, Weizhen Zeng, Jingna Guo, Yueyuan Liu
To transfer the load of processing image data to embedded devices, a solution based on ZYNQ image processing and return system is presented. The platform achieves communication with the host computer by building the LwIP protocol stack, uses ZYNQ hardware and software co-design, and interacts with data through DMA transmission mechanism. The host computer sends image data to ZYNQ via Gigabit Ethernet for processing. The image processing can not only be displayed in real time on this platform, but also be returned to the host computer using Gigabit Ethernet. Experiments show that the design meets the requirements of high-resolution image data with large quantity and high data transmission rate.
{"title":"Image Processing and Return System Based on ZYNQ","authors":"Sengoku Yu, Weizhen Zeng, Jingna Guo, Yueyuan Liu","doi":"10.1109/ITCA52113.2020.00072","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00072","url":null,"abstract":"To transfer the load of processing image data to embedded devices, a solution based on ZYNQ image processing and return system is presented. The platform achieves communication with the host computer by building the LwIP protocol stack, uses ZYNQ hardware and software co-design, and interacts with data through DMA transmission mechanism. The host computer sends image data to ZYNQ via Gigabit Ethernet for processing. The image processing can not only be displayed in real time on this platform, but also be returned to the host computer using Gigabit Ethernet. Experiments show that the design meets the requirements of high-resolution image data with large quantity and high data transmission rate.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124293933","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 : 2020-12-01DOI: 10.1109/ITCA52113.2020.00105
Yingqiu Zhou
We proposed and completed a real-life data mining problem, aka, text corpus classification. We extracted 15,500 medical documents relevant to ten different diseases and used the bag-of-words model to create a word occurrence vector for each document. The latent semantic analysis (LSA) method is then used to reduce the occurrence vector’s dimensionality to a feature vector of dimension 200. We selected a multilayer perceptron (MLP) neural network to do the final classification and report the performance comparison with the other six classifiers. We also completed the grid search for the best feature subspace dimensionality.
{"title":"An Introduction to Text Classification with Applications to Medical Records","authors":"Yingqiu Zhou","doi":"10.1109/ITCA52113.2020.00105","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00105","url":null,"abstract":"We proposed and completed a real-life data mining problem, aka, text corpus classification. We extracted 15,500 medical documents relevant to ten different diseases and used the bag-of-words model to create a word occurrence vector for each document. The latent semantic analysis (LSA) method is then used to reduce the occurrence vector’s dimensionality to a feature vector of dimension 200. We selected a multilayer perceptron (MLP) neural network to do the final classification and report the performance comparison with the other six classifiers. We also completed the grid search for the best feature subspace dimensionality.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123621403","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 : 2020-12-01DOI: 10.1109/ITCA52113.2020.00066
Bin Chen, Yiqun Zhao
The traditional approach for evaluating node importance is based on measurement of network performance change before and after a node fails. But it is not always an effective approach. Consequently, most of the existing typical indexes are actually abused. The reason is systematically illustrated. To solve the problem, a new approach is proposed for evaluating node importance based on measurement of the residual network performance after a node fails. Furthermore, a new index is presented for measuring network interconnectedness. At last, Kite network is adopted to verify the reasonableness and validity of the proposed approach as well as the proposed index.
{"title":"A new approach for evaluating node importance","authors":"Bin Chen, Yiqun Zhao","doi":"10.1109/ITCA52113.2020.00066","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00066","url":null,"abstract":"The traditional approach for evaluating node importance is based on measurement of network performance change before and after a node fails. But it is not always an effective approach. Consequently, most of the existing typical indexes are actually abused. The reason is systematically illustrated. To solve the problem, a new approach is proposed for evaluating node importance based on measurement of the residual network performance after a node fails. Furthermore, a new index is presented for measuring network interconnectedness. At last, Kite network is adopted to verify the reasonableness and validity of the proposed approach as well as the proposed index.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122222889","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 : 2020-12-01DOI: 10.1109/ITCA52113.2020.00149
Ding Fan, Gao Jixun, Hu Bingyi, Huang Quanzhen
The energy saving technology of wireless sensor networks in the Internet of Things (IoT) is to extend the life cycle of the network and solve the problem of network energy consumption optimization. In recent years, with the rapid development of IoT technology, wireless sensor network energy saving technology has also received extensive attention and research. Based on the development status of network energy saving technology, this article first describes the wireless sensor network model under the framework of the IoT. Secondly, it focuses on the five common algorithms such as ant colony algorithm, bee colony algorithm, low energy adaptive clustering hierarchy (LEACH) algorithm, fruit fly optimization algorithm, genetic algorithm, etc., and elaborates on each algorithm in detail, and further elaborates various algorithm improvements and strategies. In the end, it summarized the direction that the IoT energy saving technology needs to be improved and developed in the future.
{"title":"Overview of Energy Saving Technologies for Wireless Sensor Networks in the Internet of Things","authors":"Ding Fan, Gao Jixun, Hu Bingyi, Huang Quanzhen","doi":"10.1109/ITCA52113.2020.00149","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00149","url":null,"abstract":"The energy saving technology of wireless sensor networks in the Internet of Things (IoT) is to extend the life cycle of the network and solve the problem of network energy consumption optimization. In recent years, with the rapid development of IoT technology, wireless sensor network energy saving technology has also received extensive attention and research. Based on the development status of network energy saving technology, this article first describes the wireless sensor network model under the framework of the IoT. Secondly, it focuses on the five common algorithms such as ant colony algorithm, bee colony algorithm, low energy adaptive clustering hierarchy (LEACH) algorithm, fruit fly optimization algorithm, genetic algorithm, etc., and elaborates on each algorithm in detail, and further elaborates various algorithm improvements and strategies. In the end, it summarized the direction that the IoT energy saving technology needs to be improved and developed in the future.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129666850","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 : 2020-12-01DOI: 10.1109/ITCA52113.2020.00083
L. Cheng, L. Sheng
In modern communication systems, optical fiber transmission is widely used because of its low power consumption and wide frequency band. At the same time, by using the SFP (Small Form-factor Pluggable) module, the video transmission system will quickly build. Therefore, this paper uses the FPGA-integrated GTX (Gigabyte Transceiver) serial high-speed transceiver as the transmission and forwarding medium. The image is captured through the camera, then transmitted by the GTX transceiver and SPF fiber interface, and finally the video image is displayed by the HDMI interface. By the analysis of Vivado, the requirements of timing and layout that could be met.
{"title":"Design and FPGA Implementation of Optical Fiber Video Image Transmission","authors":"L. Cheng, L. Sheng","doi":"10.1109/ITCA52113.2020.00083","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00083","url":null,"abstract":"In modern communication systems, optical fiber transmission is widely used because of its low power consumption and wide frequency band. At the same time, by using the SFP (Small Form-factor Pluggable) module, the video transmission system will quickly build. Therefore, this paper uses the FPGA-integrated GTX (Gigabyte Transceiver) serial high-speed transceiver as the transmission and forwarding medium. The image is captured through the camera, then transmitted by the GTX transceiver and SPF fiber interface, and finally the video image is displayed by the HDMI interface. By the analysis of Vivado, the requirements of timing and layout that could be met.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129846040","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 : 2020-12-01DOI: 10.1109/ITCA52113.2020.00031
Xianyi Zeng, Donggui Liang, Zhehui Liang, Guanghui Chen, Yong’en Li
With the breakthrough of the application of deep learning technology in computer vision and natural language processing tasks, the application of deep learning to intelligent dialogue robots has become a new research hotspot. As a novel way of human-computer interaction, intelligent dialogue robots are becoming one of the entrances of mobile search and services, and are increasingly being paid attention to by enterprises and society. However, there are still some problems in the current dialogue robot, such as insufficient use of multi-modal information and weak emotional expression ability. In this paper, a multi-modal intelligent reply generation model based on seq2seq + attention is proposed by using deep learning algorithm, which can effectively use multi-modal information such as text, picture and video to interact. At the same time, on the basis of considering the contextual content information, the model further integrates the emotional transfer change information of the dialogue text. Experimental evaluation results show that the combination of emotional intelligence can make text response generation more emotionally expressive and more vivid response generation results.
{"title":"Research on the Application of Deep Learning Technology in Intelligent Dialogue Robots","authors":"Xianyi Zeng, Donggui Liang, Zhehui Liang, Guanghui Chen, Yong’en Li","doi":"10.1109/ITCA52113.2020.00031","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00031","url":null,"abstract":"With the breakthrough of the application of deep learning technology in computer vision and natural language processing tasks, the application of deep learning to intelligent dialogue robots has become a new research hotspot. As a novel way of human-computer interaction, intelligent dialogue robots are becoming one of the entrances of mobile search and services, and are increasingly being paid attention to by enterprises and society. However, there are still some problems in the current dialogue robot, such as insufficient use of multi-modal information and weak emotional expression ability. In this paper, a multi-modal intelligent reply generation model based on seq2seq + attention is proposed by using deep learning algorithm, which can effectively use multi-modal information such as text, picture and video to interact. At the same time, on the basis of considering the contextual content information, the model further integrates the emotional transfer change information of the dialogue text. Experimental evaluation results show that the combination of emotional intelligence can make text response generation more emotionally expressive and more vivid response generation results.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"140 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130909706","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：