Pub Date : 2020-12-01DOI: 10.1109/ITCA52113.2020.00160
H. Mengmeng, Liu Fang, Yao Aihuan, Meng Xianfa
SAR target recognition has a solid theoretical foundation and broad application prospects in both civil and military fields. Model-based target recognition generally includes feature extraction and classifiers. The recognition speed is faster and the recognition effect is better under limited sample conditions. However, it needs to rely on feature analysis and designe manual features. On the high-dimensional logic, feature selection and feature combination are also difficult. Recognition methods based on deep learning generally include convolutional neural networks, deep belief networks, encoders, etc. and have high recognition accuracy. However the methods are highly dependent on the amount and distribution of data. In the existing research, part of the research involves the combination of methods based on model and methods based deep learning. This article analyzes and reviews the existing hybrid model combining the two methods on SAR target recognition.
{"title":"Review of Hybrid Model Used in SAR Target Recognition","authors":"H. Mengmeng, Liu Fang, Yao Aihuan, Meng Xianfa","doi":"10.1109/ITCA52113.2020.00160","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00160","url":null,"abstract":"SAR target recognition has a solid theoretical foundation and broad application prospects in both civil and military fields. Model-based target recognition generally includes feature extraction and classifiers. The recognition speed is faster and the recognition effect is better under limited sample conditions. However, it needs to rely on feature analysis and designe manual features. On the high-dimensional logic, feature selection and feature combination are also difficult. Recognition methods based on deep learning generally include convolutional neural networks, deep belief networks, encoders, etc. and have high recognition accuracy. However the methods are highly dependent on the amount and distribution of data. In the existing research, part of the research involves the combination of methods based on model and methods based deep learning. This article analyzes and reviews the existing hybrid model combining the two methods on SAR target recognition.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"14 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":"123125041","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/ITCA52113.2020.00038
Qin Ying
The relevance of modern international trade and business English is studied based on computer software analysis system. Combined with the characteristics of computer software analysis system, a forgetting law model is proposed based on business English knowledge learning. Based on the characteristics of modern international trade development, BP neural network prediction model is established to analyze the export goods data to promote the wide application of business English. Finally, the algorithm is used to test the subject. The results show that the program can obviously overcome the forgetting of words and improve the vocabulary level of students. Modern international trade not only promotes the development of the national industrial economy, but also promotes the application of business English in modern international trade.
{"title":"The Correlation between Modern International Trade and Business English Based on Computer Software Analysis System","authors":"Qin Ying","doi":"10.1109/ITCA52113.2020.00038","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00038","url":null,"abstract":"The relevance of modern international trade and business English is studied based on computer software analysis system. Combined with the characteristics of computer software analysis system, a forgetting law model is proposed based on business English knowledge learning. Based on the characteristics of modern international trade development, BP neural network prediction model is established to analyze the export goods data to promote the wide application of business English. Finally, the algorithm is used to test the subject. The results show that the program can obviously overcome the forgetting of words and improve the vocabulary level of students. Modern international trade not only promotes the development of the national industrial economy, but also promotes the application of business English in modern international trade.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"24 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":"116676220","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}
This paper firstly describes present situation of Aerospace engineering application and Space TT&C Network in brief, in which the business process of Space mission is analyzed and the problem why it is weak at the command control of the command center at all levels is pointed out. Then the functional requirement including six aspects: resource management, comprehensive situation, task planning, command control, analysis evaluation, is studied, and the command control system architecture of space TT&C network with five layers and two vertical layers is designed.
{"title":"Demand Analysis of Command Control System of the Space TT&C Network","authors":"Yibing Dong, Yuanyuan Li, Junchao Chen, Mingkun Zhang, Yiming Jiang","doi":"10.1109/ITCA52113.2020.00057","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00057","url":null,"abstract":"This paper firstly describes present situation of Aerospace engineering application and Space TT&C Network in brief, in which the business process of Space mission is analyzed and the problem why it is weak at the command control of the command center at all levels is pointed out. Then the functional requirement including six aspects: resource management, comprehensive situation, task planning, command control, analysis evaluation, is studied, and the command control system architecture of space TT&C network with five layers and two vertical layers is designed.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"104 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":"127148213","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/itca52113.2020.00156
Xiaofang Huang, Qiuxin Wang, Zhibing Zhong
With the rapid development of information technology, online counseling plays a more and more important role, which has effectively carried out the crisis intervention of public health events in this epidemic. Online counseling is the development trend of future psychological consultation and the inevitable choice in the era of information society and big data. This paper generalizes the advantages and disadvantages of online counseling from various aspects, drawing the conclusion that video counseling can effectively solve the limitations of online counseling. However, it still need to be constantly improved. This paper also gives the corresponding development suggestions to provide a reference for future research and development of online counseling.
{"title":"The advantages and disadvantages of online counseling under the rapid development of information technology","authors":"Xiaofang Huang, Qiuxin Wang, Zhibing Zhong","doi":"10.1109/itca52113.2020.00156","DOIUrl":"https://doi.org/10.1109/itca52113.2020.00156","url":null,"abstract":"With the rapid development of information technology, online counseling plays a more and more important role, which has effectively carried out the crisis intervention of public health events in this epidemic. Online counseling is the development trend of future psychological consultation and the inevitable choice in the era of information society and big data. This paper generalizes the advantages and disadvantages of online counseling from various aspects, drawing the conclusion that video counseling can effectively solve the limitations of online counseling. However, it still need to be constantly improved. This paper also gives the corresponding development suggestions to provide a reference for future research and development of online counseling.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"34 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":"127454225","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/ITCA52113.2020.00012
Zhaoming Tian, Huiyong Liu
Aiming at the problems of sparse scoring matrix and low recommendation accuracy of traditional collaborative filtering algorithms, this paper proposes a collaborative filtering recommendation algorithm based on improved denoising auto encoder. First of all, this topic adds a balance matrix to the encoding and decoding process of the denoising auto encoder to compress the high-dimensional and sparse user behavior vector into a low-dimensional and dense user feature vector. Then, the user similarity is calculated in the process, celebrity factors are considered to obtain user similarity based on celebrity effect. Finally, a program recommendation list is generated based on the final user similarity. Experimental results show that the algorithm enhances the performance of scoring prediction, and improves the accuracy and recall rate of recommendation results.
{"title":"Collaborative filtering recommendation algorithm based on improved denoising auto encoder","authors":"Zhaoming Tian, Huiyong Liu","doi":"10.1109/ITCA52113.2020.00012","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00012","url":null,"abstract":"Aiming at the problems of sparse scoring matrix and low recommendation accuracy of traditional collaborative filtering algorithms, this paper proposes a collaborative filtering recommendation algorithm based on improved denoising auto encoder. First of all, this topic adds a balance matrix to the encoding and decoding process of the denoising auto encoder to compress the high-dimensional and sparse user behavior vector into a low-dimensional and dense user feature vector. Then, the user similarity is calculated in the process, celebrity factors are considered to obtain user similarity based on celebrity effect. Finally, a program recommendation list is generated based on the final user similarity. Experimental results show that the algorithm enhances the performance of scoring prediction, and improves the accuracy and recall rate of recommendation results.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"60 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":"125869024","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/ITCA52113.2020.00141
Zili Tang, Aishan Maoliniyazi, Jian Cao
Recent years have observed the rapid development of astronomy observation devices, hence leveraging a large amount of observation data to automatically detect flare has become an emerging research topic. Previous studies on the flare detection task focus on using hand-drafted astronomy features or time-series analysis to capture the abnormal values in the luminosity data. However, these approaches heavily rely on domain expertise and are difficult to transfer into other stars or special phenomena. In this paper, we consider adopting deep learning technology into this task. To enhance the transferability and build an effective model, we propose a novel task, namely a masked difference prediction task to learn the enhanced representations of each luminosity difference and the whole sequence. The learned representations can be transferred into conventional RNN and CNN models with simply fine-tuning on the original flare detection task. Experiments show that our approach can bring improvement to CNN and RNN models.
{"title":"Improving Flare Detection via Masked Difference Prediction","authors":"Zili Tang, Aishan Maoliniyazi, Jian Cao","doi":"10.1109/ITCA52113.2020.00141","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00141","url":null,"abstract":"Recent years have observed the rapid development of astronomy observation devices, hence leveraging a large amount of observation data to automatically detect flare has become an emerging research topic. Previous studies on the flare detection task focus on using hand-drafted astronomy features or time-series analysis to capture the abnormal values in the luminosity data. However, these approaches heavily rely on domain expertise and are difficult to transfer into other stars or special phenomena. In this paper, we consider adopting deep learning technology into this task. To enhance the transferability and build an effective model, we propose a novel task, namely a masked difference prediction task to learn the enhanced representations of each luminosity difference and the whole sequence. The learned representations can be transferred into conventional RNN and CNN models with simply fine-tuning on the original flare detection task. Experiments show that our approach can bring improvement to CNN and RNN models.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"23 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":"125432087","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/ITCA52113.2020.00148
Sun Simo, Yang Hui, Yang Guanghui, Pi Jinxiu
Based on the two-party Game model between the government and the supplier, or between suppliers, a three-group Game income model of government, suppliers and consumers is constructed; the evolutionary dynamics of government incentives, low-price supply from suppliers, and consumer purchases are analyzed. ESS (Evolutionary Stable Strategy) of the three-group Evolutionary Game under different parameter values is solved; and the numerical simulation is used to verify the parameter conditions for the stability of the main subject strategy of the three-group Game. The research results show that the three groups of government, enterprises and consumers differ in their willingness of participation in the supply of public goods, and enterprises are more sensitive to government incentives, consumers more rational in purchasing public goods, and the government incentive strategies more reasonable.
{"title":"The Application Study on Evolutionary Game Theory and Dynamics Based on the Three-Group Supply of Public Goods","authors":"Sun Simo, Yang Hui, Yang Guanghui, Pi Jinxiu","doi":"10.1109/ITCA52113.2020.00148","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00148","url":null,"abstract":"Based on the two-party Game model between the government and the supplier, or between suppliers, a three-group Game income model of government, suppliers and consumers is constructed; the evolutionary dynamics of government incentives, low-price supply from suppliers, and consumer purchases are analyzed. ESS (Evolutionary Stable Strategy) of the three-group Evolutionary Game under different parameter values is solved; and the numerical simulation is used to verify the parameter conditions for the stability of the main subject strategy of the three-group Game. The research results show that the three groups of government, enterprises and consumers differ in their willingness of participation in the supply of public goods, and enterprises are more sensitive to government incentives, consumers more rational in purchasing public goods, and the government incentive strategies more reasonable.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"25 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":"114930492","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/ITCA52113.2020.00074
Wen Kai, Zhou Lingyu
For Chinese automatic summarization, most of the generation methods are extractive, and the generative summary is not smooth, incoherent, and covers incomplete information. Compared with the traditional sequence-to-sequence model, Generative Adversarial Network (GAN) uses a reinforcement learning strategy The use of discriminator to guide generation has achieved good results in text generation. This paper proposes a pre-training method based on Bidirectional Encoder Representation from Transformers (BERT) and combined with LeakGAN model to generate abstracts. Firstly, using the bidirectional encoding characteristics of the BERT model, it can retain the original information well, and has a better effect when extracting features of words in the context to generate high-quality word vectors; secondly, for the current supervised generative model Both have the training problem of maximum likelihood estimation. This article uses the LeakGAN model that can decompose the task into different levels of sub-strategies, and uses hierarchical reinforcement learning to solve the characteristics of sparse rewards and generate a more accurate summary.
{"title":"Research on Text Summary Generation Based on Bidirectional Encoder Representation from Transformers","authors":"Wen Kai, Zhou Lingyu","doi":"10.1109/ITCA52113.2020.00074","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00074","url":null,"abstract":"For Chinese automatic summarization, most of the generation methods are extractive, and the generative summary is not smooth, incoherent, and covers incomplete information. Compared with the traditional sequence-to-sequence model, Generative Adversarial Network (GAN) uses a reinforcement learning strategy The use of discriminator to guide generation has achieved good results in text generation. This paper proposes a pre-training method based on Bidirectional Encoder Representation from Transformers (BERT) and combined with LeakGAN model to generate abstracts. Firstly, using the bidirectional encoding characteristics of the BERT model, it can retain the original information well, and has a better effect when extracting features of words in the context to generate high-quality word vectors; secondly, for the current supervised generative model Both have the training problem of maximum likelihood estimation. This article uses the LeakGAN model that can decompose the task into different levels of sub-strategies, and uses hierarchical reinforcement learning to solve the characteristics of sparse rewards and generate a more accurate summary.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"108 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":"122328910","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/ITCA52113.2020.00042
Dingsheng Deng
With the rapid development of information science and technology, image recognition technology plays an increasingly important role in the field of information security. However, in practical application, image recognition is easily affected by factors such as illumination, occlusion, background and other non-ideal conditions, so it is of great practical significance to seek robust image recognition technology. Sparse representation and collaborative representation can capture the essential features of face image, and obtain better recognition effect in image recognition. Therefore, this paper proposes an image recognition algorithm based on information fusion of sparsity and synergy. Experiments are carried out on the problems of collaborative representation classification and single sample image recognition. Experimental results show that, compared with sparse representation classification, collaborative representation classification achieves higher classification accuracy. When part of the pixel value image is occluded by 10%, the recognition rate of sparse representation algorithm is 99.1%, and the recognition rate is very good. Both algorithms have achieved very good recognition results in image recognition. Experiments show that sparse representation algorithm and collaborative representation algorithm improve the recognition rate of images.
{"title":"Image Recognition Algorithm Based on Information Fusion Combining Sparsity and Synergy","authors":"Dingsheng Deng","doi":"10.1109/ITCA52113.2020.00042","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00042","url":null,"abstract":"With the rapid development of information science and technology, image recognition technology plays an increasingly important role in the field of information security. However, in practical application, image recognition is easily affected by factors such as illumination, occlusion, background and other non-ideal conditions, so it is of great practical significance to seek robust image recognition technology. Sparse representation and collaborative representation can capture the essential features of face image, and obtain better recognition effect in image recognition. Therefore, this paper proposes an image recognition algorithm based on information fusion of sparsity and synergy. Experiments are carried out on the problems of collaborative representation classification and single sample image recognition. Experimental results show that, compared with sparse representation classification, collaborative representation classification achieves higher classification accuracy. When part of the pixel value image is occluded by 10%, the recognition rate of sparse representation algorithm is 99.1%, and the recognition rate is very good. Both algorithms have achieved very good recognition results in image recognition. Experiments show that sparse representation algorithm and collaborative representation algorithm improve the recognition rate of images.","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":"122879493","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/ITCA52113.2020.00058
Guanlin Liu
The application of machine vision in the modern industry makes intelligent manufacturing possible. At present, circuit board related fault detection, such as broken wires, missing solder joints, and other problems frequently occur, the manual recognition speed is slow and the false detection rate is high. In response to this problem, this research proposes an image noise reduction processing method that combines deep dictionary learning and elastic thresholds, which can serve computer image processing, thereby greatly improving the detection speed of printed circuit boards, and ultimately serving the processing and production of modern electronic products.
{"title":"Image Denoising Method Based on Hybrid Deep Dictionary Learning and Elastic Threshold","authors":"Guanlin Liu","doi":"10.1109/ITCA52113.2020.00058","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00058","url":null,"abstract":"The application of machine vision in the modern industry makes intelligent manufacturing possible. At present, circuit board related fault detection, such as broken wires, missing solder joints, and other problems frequently occur, the manual recognition speed is slow and the false detection rate is high. In response to this problem, this research proposes an image noise reduction processing method that combines deep dictionary learning and elastic thresholds, which can serve computer image processing, thereby greatly improving the detection speed of printed circuit boards, and ultimately serving the processing and production of modern electronic products.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"63 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":"129763977","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：