首页 > 最新文献

2020 2nd International Conference on Information Technology and Computer Application (ITCA)最新文献

英文 中文
Sales Forecasting Based on CatBoost 基于CatBoost的销售预测
Jingyi Ding, Ziqing Chen, Li Xiaolong, Baoxin Lai
Sales forecasting is a vital technology nowadays in the retail industry. With the help of advanced machine learning and deep learning algorithms, business owners can accurately predict the sales of thousands of products and make optimum decisions based on them. In this paper, we proposed a sales forecasting system based on CatBoosting. The algorithm is trained on the Walmart sales dataset, by far the largest dataset in this field. We performed effective feature engineering to boost prediction accuracy and speed. In the experiments, our model outperforms traditional machine learning methods like Linear Regression and SVM, reaching an RMSE of 0. 605. Our method doesn't need as much finetuning as other methods thus improving its generalization ability on other custom datasets, expanding its potential use.
销售预测是当今零售业的一项重要技术。借助先进的机器学习和深度学习算法,企业主可以准确预测数千种产品的销售情况,并据此做出最佳决策。本文提出了一种基于CatBoosting的销售预测系统。该算法是在沃尔玛销售数据集上训练的,这是该领域迄今为止最大的数据集。我们进行了有效的特征工程来提高预测的准确性和速度。在实验中,我们的模型优于传统的机器学习方法,如线性回归和支持向量机,RMSE达到0。605. 我们的方法不需要像其他方法那样多的微调,从而提高了它在其他自定义数据集上的泛化能力,扩大了它的潜在用途。
{"title":"Sales Forecasting Based on CatBoost","authors":"Jingyi Ding, Ziqing Chen, Li Xiaolong, Baoxin Lai","doi":"10.1109/ITCA52113.2020.00138","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00138","url":null,"abstract":"Sales forecasting is a vital technology nowadays in the retail industry. With the help of advanced machine learning and deep learning algorithms, business owners can accurately predict the sales of thousands of products and make optimum decisions based on them. In this paper, we proposed a sales forecasting system based on CatBoosting. The algorithm is trained on the Walmart sales dataset, by far the largest dataset in this field. We performed effective feature engineering to boost prediction accuracy and speed. In the experiments, our model outperforms traditional machine learning methods like Linear Regression and SVM, reaching an RMSE of 0. 605. Our method doesn't need as much finetuning as other methods thus improving its generalization ability on other custom datasets, expanding its potential use.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"75 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":"133351280","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}
引用次数: 5
Similarity search of graph database based on Fuzzy Logic Support vector machine (PSO-SVM) algorithm and computer application 基于模糊逻辑支持向量机(PSO-SVM)算法及计算机应用的图数据库相似度搜索
Tao Yu, Feng He
Support vector machine (SVM) has excellent learning performance, has become a popular research method in the field of machine learning, and has been successfully applied in many fields. In recent years, more and more modeling methods have been put forward by relevant scholars to solve problems such as classification identification, risk prediction, and effectiveness evaluation. This article briefly introduces the support vector machine (SVM), and expounds the algorithm of support vector machine in graph database similarity search and computer application for readers’ reference.
支持向量机(SVM)具有优异的学习性能,已成为机器学习领域的热门研究方法,并已成功应用于多个领域。近年来,相关学者提出了越来越多的建模方法来解决分类识别、风险预测、有效性评价等问题。本文简要介绍了支持向量机(SVM),阐述了支持向量机在图数据库相似度搜索中的算法及计算机应用,供读者参考。
{"title":"Similarity search of graph database based on Fuzzy Logic Support vector machine (PSO-SVM) algorithm and computer application","authors":"Tao Yu, Feng He","doi":"10.1109/itca52113.2020.00027","DOIUrl":"https://doi.org/10.1109/itca52113.2020.00027","url":null,"abstract":"Support vector machine (SVM) has excellent learning performance, has become a popular research method in the field of machine learning, and has been successfully applied in many fields. In recent years, more and more modeling methods have been put forward by relevant scholars to solve problems such as classification identification, risk prediction, and effectiveness evaluation. This article briefly introduces the support vector machine (SVM), and expounds the algorithm of support vector machine in graph database similarity search and computer application for readers’ reference.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"20 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":"126002090","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}
引用次数: 1
An empirical analysis of the key factors affecting the inter school sharing of regional digital teaching resources 影响区域数字化教学资源校际共享关键因素的实证分析
Wei Wang
The regional digital teaching resources sharing among schools is becoming more and more popular, but restricted by some factors. It is of great practical significance to find out the key influencing factors to guide the regional digital teaching resources sharing among schools. In this paper, Suzhou International Education Park is taken as the empirical research object of the key influencing factors of regional digital teaching resources sharing between schools. Spss19.0 statistical software is used to process and analyze the collected information, find out the key influencing factors, and then carry out logistic regression analysis, finally forming the research conclusion
学校间区域数字化教学资源共享越来越受欢迎,但受到一些因素的制约。找出影响区域数字化教学资源共享的关键因素,对指导区域数字化教学资源共享具有重要的现实意义。本文以苏州国际教育园区为实证研究对象,研究区域数字化教学资源校际共享的关键影响因素。使用Spss19.0统计软件对收集到的信息进行处理和分析,找出关键影响因素,然后进行logistic回归分析,最终形成研究结论
{"title":"An empirical analysis of the key factors affecting the inter school sharing of regional digital teaching resources","authors":"Wei Wang","doi":"10.1109/ITCA52113.2020.00153","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00153","url":null,"abstract":"The regional digital teaching resources sharing among schools is becoming more and more popular, but restricted by some factors. It is of great practical significance to find out the key influencing factors to guide the regional digital teaching resources sharing among schools. In this paper, Suzhou International Education Park is taken as the empirical research object of the key influencing factors of regional digital teaching resources sharing between schools. Spss19.0 statistical software is used to process and analyze the collected information, find out the key influencing factors, and then carry out logistic regression analysis, finally forming the research conclusion","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"2 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":"130255672","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}
引用次数: 0
Research on the application of Minnan architectural pattern elements in ceramics cultural creation under the background of big data 大数据背景下闽南建筑图案元素在陶瓷文化创作中的应用研究
Xiaoping Zhou, Yanmin Liu, Liang Xiaobo, Peng Zixuan, Chen Zhihong
The architectural pattern of southern Fujian is an important expression carrier of southern Fujian culture. It embodies the traditional aesthetic concepts and feelings of the Chinese nation. It is widely used in all aspects of Chinese society, and the use of ceramic decoration is particularly eye-catching. The shape, pattern, color and other artistic characteristics of the architectural lines in southern Fujian reflect a very valuable aesthetic orientation, which is worth learning from and recreating. In different fields, the effective combination of Minnan architectural pattern elements and modern ceramic craftsmanship presents a new artistic style, which fully reflects its aesthetic value. Therefore, in the technology of big data analysis, this article analyzes the architectural style of southern Fujian, and interprets how the elements of southern Fujian architectural textures are cited in modern ceramics, and analyzes how the architectural patterns of southern Fujian can improve the development of ceramic culture and creativity. This paper shows the charm of southern Fujian architecture and promote the innovation and inheritance of southern Fujian culture.
闽南建筑格局是闽南文化的重要表现载体。它体现了中华民族传统的审美观念和情感。它广泛应用于中国社会的各个方面,陶瓷装饰的使用尤为引人注目。闽南建筑线条的造型、图案、色彩等艺术特征体现出非常宝贵的审美取向,值得借鉴和再创造。在不同的领域,闽南建筑图案元素与现代陶瓷工艺的有效结合呈现出新的艺术风格,充分体现了其审美价值。因此,本文运用大数据分析技术,对闽南建筑风格进行分析,解读闽南建筑肌理元素如何在现代陶瓷中被引用,分析闽南建筑纹样如何促进陶瓷文化创意的发展。展示闽南建筑的魅力,促进闽南文化的创新与传承。
{"title":"Research on the application of Minnan architectural pattern elements in ceramics cultural creation under the background of big data","authors":"Xiaoping Zhou, Yanmin Liu, Liang Xiaobo, Peng Zixuan, Chen Zhihong","doi":"10.1109/ITCA52113.2020.00093","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00093","url":null,"abstract":"The architectural pattern of southern Fujian is an important expression carrier of southern Fujian culture. It embodies the traditional aesthetic concepts and feelings of the Chinese nation. It is widely used in all aspects of Chinese society, and the use of ceramic decoration is particularly eye-catching. The shape, pattern, color and other artistic characteristics of the architectural lines in southern Fujian reflect a very valuable aesthetic orientation, which is worth learning from and recreating. In different fields, the effective combination of Minnan architectural pattern elements and modern ceramic craftsmanship presents a new artistic style, which fully reflects its aesthetic value. Therefore, in the technology of big data analysis, this article analyzes the architectural style of southern Fujian, and interprets how the elements of southern Fujian architectural textures are cited in modern ceramics, and analyzes how the architectural patterns of southern Fujian can improve the development of ceramic culture and creativity. This paper shows the charm of southern Fujian architecture and promote the innovation and inheritance of southern Fujian culture.","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":"129300313","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}
引用次数: 0
Multi dimensional data distribution monitoring based on OLAP 基于OLAP的多维数据分布监控
Yifan Mao, Shasha Huang, Shuo Cui, Haifeng Wang, Junyan Zhang, Wenhao Ding
With the rapid development of the Internet, society is gradually entering the information age, and various data in enterprises have become the most important strategic core resources of all enterprises. The operation and decision-making of enterprises all require a large amount of data analysis. Nowadays, many companies do not pay enough attention to the monitoring of data asset distribution. In addition, various internal systems such as financial management and ERP systems are relatively independent. Each system has its own data organization standard, which makes it difficult to conduct a unified management of data. This also directly leads to the one-sided and subjective problem of enterprise managers' distribution of data assets. With the construction of the data center of each enterprise, the data of each system is aggregated to the center through data integration technology. Therefore, all enterprises need to build a multi-dimensional data distribution monitoring model around data links to comprehensively monitor the status of various data distributions across the company's entire network, and improve data service capabilities and sharing capabilities as well as the company's operational capabilities. This article uses OLAP technology to construct a multi-dimensional data distribution monitoring model for the data link in the process of power enterprise data integration. This article first selects the dimensions and metrics that need to be monitored in the multidimensional data, and then constructs the conceptual model, logical model and physical model of the multidimensional data using on line analytical processing technology. Finally, an example analysis of OLAP system architecture based on B/S structure is realized. The overall data distribution of the enterprise can be grasped by analyzing the various dimensions of the data link, such as System type, location distribution, and time.
随着互联网的飞速发展,社会逐渐进入信息化时代,企业中的各种数据已经成为所有企业最重要的战略核心资源。企业的经营和决策都需要大量的数据分析。目前,很多企业对数据资产分布的监控不够重视。此外,财务管理、ERP系统等内部各系统相对独立。每个系统都有自己的数据组织标准,很难对数据进行统一管理。这也直接导致了企业管理者对数据资产分布的片面和主观问题。随着各企业数据中心的建设,各系统的数据通过数据集成技术汇聚到中心。因此,各企业都需要围绕数据链路构建多维度的数据分布监控模型,全面监控企业全网各种数据分布的状态,提升数据服务能力和共享能力,提升企业运营能力。本文利用OLAP技术构建了电力企业数据集成过程中数据链的多维数据分布监控模型。本文首先选取了多维数据中需要监控的维度和指标,然后利用在线分析处理技术构建了多维数据的概念模型、逻辑模型和物理模型。最后,对基于B/S结构的OLAP系统体系结构进行了实例分析。通过分析数据链的各个维度,如系统类型、位置分布、时间分布等,可以掌握企业整体的数据分布情况。
{"title":"Multi dimensional data distribution monitoring based on OLAP","authors":"Yifan Mao, Shasha Huang, Shuo Cui, Haifeng Wang, Junyan Zhang, Wenhao Ding","doi":"10.1109/ITCA52113.2020.00070","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00070","url":null,"abstract":"With the rapid development of the Internet, society is gradually entering the information age, and various data in enterprises have become the most important strategic core resources of all enterprises. The operation and decision-making of enterprises all require a large amount of data analysis. Nowadays, many companies do not pay enough attention to the monitoring of data asset distribution. In addition, various internal systems such as financial management and ERP systems are relatively independent. Each system has its own data organization standard, which makes it difficult to conduct a unified management of data. This also directly leads to the one-sided and subjective problem of enterprise managers' distribution of data assets. With the construction of the data center of each enterprise, the data of each system is aggregated to the center through data integration technology. Therefore, all enterprises need to build a multi-dimensional data distribution monitoring model around data links to comprehensively monitor the status of various data distributions across the company's entire network, and improve data service capabilities and sharing capabilities as well as the company's operational capabilities. This article uses OLAP technology to construct a multi-dimensional data distribution monitoring model for the data link in the process of power enterprise data integration. This article first selects the dimensions and metrics that need to be monitored in the multidimensional data, and then constructs the conceptual model, logical model and physical model of the multidimensional data using on line analytical processing technology. Finally, an example analysis of OLAP system architecture based on B/S structure is realized. The overall data distribution of the enterprise can be grasped by analyzing the various dimensions of the data link, such as System type, location distribution, and time.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"51 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":"129720602","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}
引用次数: 0
Application of computer image processing technology in Web Design 计算机图像处理技术在网页设计中的应用
Yue Ma, Dan Guangrong
Computer image processing technology is an important part of web design, which can effectively improve the appeal and artistic sense of web page. With the development of the times, the influence of the network in people’s life is more and more big, web design has also been widely concerned by people. The application of computer image processing technology in web page design can make the web page more beautiful and efficient. With the continuous improvement of the current society’s attention to network publicity, it provides favorable conditions for the combination of art and network development. The application of computer image processing in web design can increase the artistry and attractiveness of web pages, and achieve the purpose of network publicity through the stimulation of people’s interest, which can greatly promote the development of the industry. This paper analyzes the web design image processing knowledge and computer image processing technology in the application of web design, for reference only.
计算机图像处理技术是网页设计的重要组成部分,它可以有效地提高网页的感染力和艺术感。随着时代的发展,网络在人们生活中的影响越来越大,网页设计也受到了人们的广泛关注。将计算机图像处理技术应用于网页设计中,可以使网页更加美观、高效。随着当前社会对网络宣传关注度的不断提高,为艺术与网络的结合发展提供了有利的条件。在网页设计中应用计算机图像处理,可以增加网页的艺术性和吸引力,通过激发人们的兴趣来达到网络宣传的目的,可以极大地促进行业的发展。本文分析了网页设计中的图像处理知识以及计算机图像处理技术在网页设计中的应用,仅供参考。
{"title":"Application of computer image processing technology in Web Design","authors":"Yue Ma, Dan Guangrong","doi":"10.1109/ITCA52113.2020.00033","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00033","url":null,"abstract":"Computer image processing technology is an important part of web design, which can effectively improve the appeal and artistic sense of web page. With the development of the times, the influence of the network in people’s life is more and more big, web design has also been widely concerned by people. The application of computer image processing technology in web page design can make the web page more beautiful and efficient. With the continuous improvement of the current society’s attention to network publicity, it provides favorable conditions for the combination of art and network development. The application of computer image processing in web design can increase the artistry and attractiveness of web pages, and achieve the purpose of network publicity through the stimulation of people’s interest, which can greatly promote the development of the industry. This paper analyzes the web design image processing knowledge and computer image processing technology in the application of web design, for reference only.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"20 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":"127581519","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}
引用次数: 13
Efficient Algorithm for Mining Probabilistic Frequent Itemsets of Uncertain Data 不确定数据概率频繁项集挖掘的高效算法
Yuan Quan, Liu ZhiLong
At present, uncertain data has become a hot research topic for scholars. For the current mining algorithms, there are still many shortcomings in terms of time and memory. How to improve or find efficient mining algorithms and quickly mine them Information that is more valuable to people has also become a thorny problem for researchers. At present, the existing algorithms for mining frequent itemsets of uncertain data probabilities with pattern growth have many shortcomings in terms of memory. Aiming at the problem that the existing PUFP-Growth algorithm consumes too much memory, this paper proposes a HUFP-Growth algorithm. This algorithm adds a candidate item set judgment mechanism to the original algorithm, which can judge the item set in advance Is it necessary to do linking to save a lot of memory. At the same time, it can also save the time consumed when the itemsets in the original algorithm are connected, and to a certain extent, it also saves the running time of the algorithm. Finally, the effectiveness of the method is proved through experiments.
目前,不确定数据已成为学者们研究的热点。对于目前的挖掘算法,在时间和内存方面还存在很多不足。如何改进或找到高效的挖掘算法,并快速挖掘出对人们更有价值的信息,也成为研究人员面临的棘手问题。目前,基于模式增长的不确定数据概率频繁项集挖掘算法在内存方面存在许多不足。针对现有PUFP-Growth算法占用内存过多的问题,提出了一种HUFP-Growth算法。该算法在原有算法的基础上增加了候选项集判断机制,可以提前判断项集,无需做链接,节省大量内存。同时,还可以节省原算法中项集连接时所消耗的时间,在一定程度上也节省了算法的运行时间。最后,通过实验验证了该方法的有效性。
{"title":"Efficient Algorithm for Mining Probabilistic Frequent Itemsets of Uncertain Data","authors":"Yuan Quan, Liu ZhiLong","doi":"10.1109/ITCA52113.2020.00017","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00017","url":null,"abstract":"At present, uncertain data has become a hot research topic for scholars. For the current mining algorithms, there are still many shortcomings in terms of time and memory. How to improve or find efficient mining algorithms and quickly mine them Information that is more valuable to people has also become a thorny problem for researchers. At present, the existing algorithms for mining frequent itemsets of uncertain data probabilities with pattern growth have many shortcomings in terms of memory. Aiming at the problem that the existing PUFP-Growth algorithm consumes too much memory, this paper proposes a HUFP-Growth algorithm. This algorithm adds a candidate item set judgment mechanism to the original algorithm, which can judge the item set in advance Is it necessary to do linking to save a lot of memory. At the same time, it can also save the time consumed when the itemsets in the original algorithm are connected, and to a certain extent, it also saves the running time of the algorithm. Finally, the effectiveness of the method is proved through experiments.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"113 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":"117249867","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}
引用次数: 0
Research on Text to Image Based on Generative Adversarial Network 基于生成对抗网络的文本到图像的研究
Li Xiaolin, Gao Yuwei
In recent years, Generative Adversarial Network (GAN) has quickly become the most popular deep generative model framework, and it is also the most popular topic in the current deep learning research field. Although the generative adversarial network has achieved remarkable results from text description to image generation, when a complex image containing multiple objects, the position of each object will be blurred and overlapped, and the edges of the generated image will be blurred and local textures will be unclear. Usually given text description can generate the corresponding rough image, but there are still some problems in the image details. In order to solve the above problems, on the basis of Stack GAN, a scene graph-based stacked generative confrontation network model (Scene graph stack GAN, SGS-GAN) is proposed, which converts the text description into The scene graph uses the scene graph as the condition vector and inputs the random noise into the generator model to obtain the result image. The experimental results show that the Inception store of the SGS-GAN model on the Visual Genome and COCO data sets reached 6.64 and 6.52, respectively, which were increased by 0.212 and 0.219 compared to Sg2Im. This proves that the diversity and vividness of the generated samples and the sharpness of the image are obviously improved after the number of times of training and the input of the scene graph.
近年来,生成对抗网络(Generative Adversarial Network, GAN)迅速成为最流行的深度生成模型框架,也是当前深度学习研究领域最热门的话题。虽然生成式对抗网络从文本描述到图像生成都取得了显著的效果,但是当一个复杂的图像包含多个物体时,每个物体的位置会被模糊和重叠,生成的图像的边缘会模糊,局部纹理会不清晰。通常给出的文字描述可以生成相应的粗糙图像,但在图像细节方面还存在一些问题。为了解决上述问题,在Stack GAN的基础上,提出了一种基于场景图的堆叠生成对抗网络模型(scene graph Stack GAN, SGS-GAN),该模型将文本描述转换为场景图,以场景图为条件向量,将随机噪声输入到生成器模型中,得到结果图像。实验结果表明,该模型在Visual Genome和COCO数据集上的Inception store分别达到6.64和6.52,比Sg2Im分别提高了0.212和0.219。这证明经过多次训练和场景图的输入后,生成的样本的多样性、生动性和图像的清晰度都有了明显的提高。
{"title":"Research on Text to Image Based on Generative Adversarial Network","authors":"Li Xiaolin, Gao Yuwei","doi":"10.1109/ITCA52113.2020.00077","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00077","url":null,"abstract":"In recent years, Generative Adversarial Network (GAN) has quickly become the most popular deep generative model framework, and it is also the most popular topic in the current deep learning research field. Although the generative adversarial network has achieved remarkable results from text description to image generation, when a complex image containing multiple objects, the position of each object will be blurred and overlapped, and the edges of the generated image will be blurred and local textures will be unclear. Usually given text description can generate the corresponding rough image, but there are still some problems in the image details. In order to solve the above problems, on the basis of Stack GAN, a scene graph-based stacked generative confrontation network model (Scene graph stack GAN, SGS-GAN) is proposed, which converts the text description into The scene graph uses the scene graph as the condition vector and inputs the random noise into the generator model to obtain the result image. The experimental results show that the Inception store of the SGS-GAN model on the Visual Genome and COCO data sets reached 6.64 and 6.52, respectively, which were increased by 0.212 and 0.219 compared to Sg2Im. This proves that the diversity and vividness of the generated samples and the sharpness of the image are obviously improved after the number of times of training and the input of the scene graph.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"2 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":"124547941","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}
引用次数: 1
A universal index for measuring network interconnectedness 一种衡量网络连通性的通用指标
Bin Chen, Yiqun Zhao
Traditionally, there were many indexes proposed for network interconnectedness measurement. But they were actually abused. These indexes were either for connected networks or for unconnected networks. There is still no index suitable for both connected networks and unconnected networks. To solve the problem, a new index is constructed for interconnectedness measurement by synthesizing the average shortest path length and the average number of disconnected node pairs. And the theory how to construct it and why it is correct is illustrated systematically. At last, a case is adopted to test and verify the validity of the proposed index.
传统的网络连通性度量指标有很多。但他们实际上受到了虐待。这些索引既适用于已连接的网络,也适用于未连接的网络。目前还没有同时适用于已连接网络和未连接网络的索引。为了解决这一问题,通过综合平均最短路径长度和平均断开节点对数,构造了一个新的互连度度量指标。并系统地阐述了该理论如何构建及其正确性。最后,通过实例验证了所提指标的有效性。
{"title":"A universal index for measuring network interconnectedness","authors":"Bin Chen, Yiqun Zhao","doi":"10.1109/ITCA52113.2020.00086","DOIUrl":"https://doi.org/10.1109/ITCA52113.2020.00086","url":null,"abstract":"Traditionally, there were many indexes proposed for network interconnectedness measurement. But they were actually abused. These indexes were either for connected networks or for unconnected networks. There is still no index suitable for both connected networks and unconnected networks. To solve the problem, a new index is constructed for interconnectedness measurement by synthesizing the average shortest path length and the average number of disconnected node pairs. And the theory how to construct it and why it is correct is illustrated systematically. At last, a case is adopted to test and verify the validity of the proposed index.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"543 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":"123375585","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}
引用次数: 0
Rapid elimination of noise in 3D laser scanning point cloud data 三维激光扫描点云数据噪声的快速消除
W. Weijie, Xue Hera, Z. Yanqing, Yang Tong
When using a hand-held 3D laser scanner to collect target object data, due to factors such as personnel operation, collection environment and equipment itself, a large number of external noise points are often produced. This will seriously affect the processing and reconstruction accuracy of later point cloud data. According to the data analysis, these external noise points are divided into two categories: flying points and cluster points. Aiming at this phenomenon, a point cloud model noise removal algorithm combining statistical filtering and pass-through filtering is proposed. Firstly, the flying points are eliminated by statistical filtering, and then the remaining large area cluster points are removed by through filtering. The experimental results show that the algorithm can quickly and accurately identify external noise points and eliminate them completely.
在使用手持式三维激光扫描仪采集目标物体数据时,由于人员操作、采集环境、设备本身等因素,往往会产生大量的外部噪声点。这将严重影响后期点云数据的处理和重建精度。根据数据分析,将这些外部噪声点分为飞行点和聚类点两类。针对这一现象,提出了一种结合统计滤波和透传滤波的点云模型去噪算法。首先通过统计滤波去除飞行点,然后通过滤波去除剩余的大面积聚类点。实验结果表明,该算法能够快速准确地识别并完全消除外部噪声点。
{"title":"Rapid elimination of noise in 3D laser scanning point cloud data","authors":"W. Weijie, Xue Hera, Z. Yanqing, Yang Tong","doi":"10.1109/itca52113.2020.00071","DOIUrl":"https://doi.org/10.1109/itca52113.2020.00071","url":null,"abstract":"When using a hand-held 3D laser scanner to collect target object data, due to factors such as personnel operation, collection environment and equipment itself, a large number of external noise points are often produced. This will seriously affect the processing and reconstruction accuracy of later point cloud data. According to the data analysis, these external noise points are divided into two categories: flying points and cluster points. Aiming at this phenomenon, a point cloud model noise removal algorithm combining statistical filtering and pass-through filtering is proposed. Firstly, the flying points are eliminated by statistical filtering, and then the remaining large area cluster points are removed by through filtering. The experimental results show that the algorithm can quickly and accurately identify external noise points and eliminate them completely.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"116 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":"124136927","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}
引用次数: 0
期刊
2020 2nd International Conference on Information Technology and Computer Application (ITCA)
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1