首页 > 最新文献

2021 International Conference on Computer Technology and Media Convergence Design (CTMCD)最新文献

英文 中文
Research on the Construction of Network-based Practice Teaching Platform for the Courses of Ideological and Political Theory 思想政治理论课网络实践教学平台建设研究
Wenjia Hao
Along with the development of informatization, there are numerous limitations of traditional practical teaching. Scholars start to pay attention to the network-based practical teaching of ideological and theory courses because of the network popularization. To build the ideological and political theory course practical teaching network platform, and to realize the network of practical teaching is becoming the future trend. In order to comply with the requirements of information age development and the needs of the reform of higher education, universities generally begin to explore network ideological and political education. Firstly, this paper states the idea about the network practical teaching platform construction of universities for ideological and political theory courses in the Big Data Era, and studies the educational reform brought by information network to traditional ideological and political education and teaching. Secondly, based on the theoretical and practical basis of constructing the practical teaching network platform on ideological and political theory course, this paper analyzes its necessity and feasibility and investigates its significance on socialist education. Finally, from the two aspects about system building and safeguard measure, this paper proposes the feasible path about the construction of politics theory class practice teaching network platform. And explores the network platform operation from the aspects on platform structure and content. This paper exerts the characteristics and functions of the network platform and reveals its superiority by a large data to construct the ideological education evaluation mechanism.
随着信息化的发展,传统的实践教学出现了许多局限性。随着网络的普及,思想理论课的网络实践教学开始受到学者们的关注。构建思想政治理论课实践教学的网络平台,实现实践教学的网络化正成为未来的趋势。为了适应信息时代发展的要求和高等教育改革的需要,高校普遍开始探索网络思想政治教育。本文首先阐述了大数据时代高校思想政治理论课网络实践教学平台建设的思路,研究了信息网络对传统思想政治教育教学带来的教育变革。其次,在构建思想政治理论课实践教学网络平台的理论和实践基础上,分析了构建思想政治理论课实践教学网络平台的必要性和可行性,探讨了构建思想政治理论课实践教学网络平台对社会主义教育的意义。最后,从制度建设和保障措施两个方面,提出了构建政治理论课实践教学网络平台的可行路径。并从平台结构和内容两个方面对网络平台运营进行了探讨。本文通过大数据构建思想政治教育评价机制,发挥网络平台的特点和功能,揭示其优势。
{"title":"Research on the Construction of Network-based Practice Teaching Platform for the Courses of Ideological and Political Theory","authors":"Wenjia Hao","doi":"10.1109/CTMCD53128.2021.00019","DOIUrl":"https://doi.org/10.1109/CTMCD53128.2021.00019","url":null,"abstract":"Along with the development of informatization, there are numerous limitations of traditional practical teaching. Scholars start to pay attention to the network-based practical teaching of ideological and theory courses because of the network popularization. To build the ideological and political theory course practical teaching network platform, and to realize the network of practical teaching is becoming the future trend. In order to comply with the requirements of information age development and the needs of the reform of higher education, universities generally begin to explore network ideological and political education. Firstly, this paper states the idea about the network practical teaching platform construction of universities for ideological and political theory courses in the Big Data Era, and studies the educational reform brought by information network to traditional ideological and political education and teaching. Secondly, based on the theoretical and practical basis of constructing the practical teaching network platform on ideological and political theory course, this paper analyzes its necessity and feasibility and investigates its significance on socialist education. Finally, from the two aspects about system building and safeguard measure, this paper proposes the feasible path about the construction of politics theory class practice teaching network platform. And explores the network platform operation from the aspects on platform structure and content. This paper exerts the characteristics and functions of the network platform and reveals its superiority by a large data to construct the ideological education evaluation mechanism.","PeriodicalId":298084,"journal":{"name":"2021 International Conference on Computer Technology and Media Convergence Design (CTMCD)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129772836","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
Flexible lane detection using CNNs 基于cnn的柔性车道检测
Lin Haixia, Lin Xizhou
To discuss the lane detection have a significant meaning in the autonomous driving research field, particularly, the research direction of path planning. At this stage, to achieve lane line detection, there are two ways, one is based on traditional machine learning methods, and the other is a hot deep learning model in recent years. The method based on traditional machine vision is greatly affected by environmental factors, and the cost is large. In recent years of research, more and more scholars have used deep learning to detect lanes and have achieved good results. The feature of this method is that the labeled data sets are often used to train models. The accuracy of this method is very good, but since the label is fixed, the scene for lane change is difficult to change and is not easy to expand. This paper proposes a method that uses a cascaded convolutional neural network structure for end-to-end lane detection. The whole system adopts the encoder and decoder structure. The lane boundary is instance segmented first, and then the lane classification is classified by the linear classifier.
讨论车道检测在自动驾驶研究领域,特别是路径规划的研究方向具有重要意义。现阶段,要实现车道线检测,有两种方式,一种是基于传统的机器学习方法,另一种是近年来比较热门的深度学习模型。基于传统机器视觉的方法受环境因素影响较大,且成本较大。近年来的研究中,越来越多的学者将深度学习用于车道检测,并取得了良好的效果。该方法的特点是经常使用标记的数据集来训练模型。这种方法的准确性非常好,但是由于标签是固定的,变道的场景很难改变,也不容易扩展。本文提出了一种使用级联卷积神经网络结构进行端到端车道检测的方法。整个系统采用编码器和解码器结构。首先对车道边界进行实例分割,然后用线性分类器对车道分类进行分类。
{"title":"Flexible lane detection using CNNs","authors":"Lin Haixia, Lin Xizhou","doi":"10.1109/CTMCD53128.2021.00057","DOIUrl":"https://doi.org/10.1109/CTMCD53128.2021.00057","url":null,"abstract":"To discuss the lane detection have a significant meaning in the autonomous driving research field, particularly, the research direction of path planning. At this stage, to achieve lane line detection, there are two ways, one is based on traditional machine learning methods, and the other is a hot deep learning model in recent years. The method based on traditional machine vision is greatly affected by environmental factors, and the cost is large. In recent years of research, more and more scholars have used deep learning to detect lanes and have achieved good results. The feature of this method is that the labeled data sets are often used to train models. The accuracy of this method is very good, but since the label is fixed, the scene for lane change is difficult to change and is not easy to expand. This paper proposes a method that uses a cascaded convolutional neural network structure for end-to-end lane detection. The whole system adopts the encoder and decoder structure. The lane boundary is instance segmented first, and then the lane classification is classified by the linear classifier.","PeriodicalId":298084,"journal":{"name":"2021 International Conference on Computer Technology and Media Convergence Design (CTMCD)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129879100","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: 9
Image Noise Estimation Algorithm Based on Super-pixel Segmentation and Scale Invariance of Kurtosis 基于超像素分割和峰度尺度不变性的图像噪声估计算法
Mingliu Sun, Wenbo Li, Qiao Zhou
Noise estimation methods are widely utilized in many areas of image processing and detection, such as image deblurring, mosaic detection . Recently, many researchers tried to design the corresponding estimation algorithm from the three directions of image spatial domain, transform domain and image statistical properties. Based on the scale invariance of kurtosis and piecewise stationarity of natural image in band-pass domain, this paper proposes a noise estimation algorithm based on Super-pixel segmentation and K-means clustering considering the influence of dominant edge and texture on the statistical characteristics in the image space domain. In this algorithm, we use PCA filters to transform the noisy image to transform domain. Furthermore, we can transform the noise estimation problem into a nonconvex optimization problem by using scale invariance of kurtosis. Finally, a large number of experiments verify the reliability of the algorithm, and the results show that the effect of the algorithm acts as a counterweight to the recent state-of-the-art algorithms.
噪声估计方法广泛应用于图像去模糊、拼接检测等图像处理和检测领域。近年来,许多研究者尝试从图像空间域、变换域和图像统计属性三个方向设计相应的估计算法。基于自然图像在带通域峰度的尺度不变性和分段平稳性,考虑优势边缘和纹理对图像空间域统计特征的影响,提出了一种基于超像素分割和k均值聚类的噪声估计算法。在该算法中,我们使用PCA滤波器对带有噪声的图像进行变换以实现域变换。利用峰度的尺度不变性,将噪声估计问题转化为非凸优化问题。最后,通过大量的实验验证了该算法的可靠性,结果表明,该算法的效果可以抵消当前最先进的算法。
{"title":"Image Noise Estimation Algorithm Based on Super-pixel Segmentation and Scale Invariance of Kurtosis","authors":"Mingliu Sun, Wenbo Li, Qiao Zhou","doi":"10.1109/CTMCD53128.2021.00041","DOIUrl":"https://doi.org/10.1109/CTMCD53128.2021.00041","url":null,"abstract":"Noise estimation methods are widely utilized in many areas of image processing and detection, such as image deblurring, mosaic detection . Recently, many researchers tried to design the corresponding estimation algorithm from the three directions of image spatial domain, transform domain and image statistical properties. Based on the scale invariance of kurtosis and piecewise stationarity of natural image in band-pass domain, this paper proposes a noise estimation algorithm based on Super-pixel segmentation and K-means clustering considering the influence of dominant edge and texture on the statistical characteristics in the image space domain. In this algorithm, we use PCA filters to transform the noisy image to transform domain. Furthermore, we can transform the noise estimation problem into a nonconvex optimization problem by using scale invariance of kurtosis. Finally, a large number of experiments verify the reliability of the algorithm, and the results show that the effect of the algorithm acts as a counterweight to the recent state-of-the-art algorithms.","PeriodicalId":298084,"journal":{"name":"2021 International Conference on Computer Technology and Media Convergence Design (CTMCD)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130667285","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
An Optimized Cloudlet Scheduling Based Method for Tablets and Mobile Phones 一种基于平板电脑和手机的云调度优化方法
Alshamaileh Mohammad, L. Chunlin
The improvement in the communication technology incorporates sophisticated electronic gadgets that rely on wireless technique to support the signal transmission from the emitter to the receiver points. The cloudlet scheduling method relies on the environment and task type to accomplish the scheduling process in an algorithm supported by the visual machine programs. The paper captures the cloudlet network gains attributed to the increased use of cloudlet scheduling technique in tablets and mobile phones operated within the communication and data delivery platform. The system relies on improved storage space and processing speed with which the systems works with reference of minimizing power usage. The platform sustains efficient programming of tasks through the application of meta-heuristic algorithms. The paper focuses on AES algorithm and how it solves a given task at every instance while optimizing system efficiency. The beauty of the algorithm is efficient energy consumption in the data transfer platform that adopts the analysis in response to the task completion based on first-come-first-serve. The concept sustains the sequences of service delivery in the computing networks. The algorithm anchored in the cloudlet platform facilitates the use of the internet to support data transmission between different users and the server that rely on the same computing infrastructure.
通信技术的改进包括依靠无线技术来支持信号从发射器到接收器的传输的复杂电子设备。cloudlet调度方法依赖于环境和任务类型,在可视化机器程序支持的算法中完成调度过程。这篇论文捕捉到了云调度技术在通信和数据传输平台内的平板电脑和移动电话中使用的增加所带来的云网络收益。该系统依赖于改进的存储空间和处理速度,系统以最小化功耗为参考。该平台通过应用元启发式算法来维持任务的高效编程。本文主要研究AES算法,以及它如何在优化系统效率的同时,在每个实例中解决给定的任务。该算法的优点在于,在采用先到先得的任务完成响应分析的数据传输平台上,节能效率高。这个概念维持了计算网络中服务交付的顺序。基于cloudlet平台的算法促进了互联网的使用,以支持依赖于相同计算基础设施的不同用户和服务器之间的数据传输。
{"title":"An Optimized Cloudlet Scheduling Based Method for Tablets and Mobile Phones","authors":"Alshamaileh Mohammad, L. Chunlin","doi":"10.1109/CTMCD53128.2021.00060","DOIUrl":"https://doi.org/10.1109/CTMCD53128.2021.00060","url":null,"abstract":"The improvement in the communication technology incorporates sophisticated electronic gadgets that rely on wireless technique to support the signal transmission from the emitter to the receiver points. The cloudlet scheduling method relies on the environment and task type to accomplish the scheduling process in an algorithm supported by the visual machine programs. The paper captures the cloudlet network gains attributed to the increased use of cloudlet scheduling technique in tablets and mobile phones operated within the communication and data delivery platform. The system relies on improved storage space and processing speed with which the systems works with reference of minimizing power usage. The platform sustains efficient programming of tasks through the application of meta-heuristic algorithms. The paper focuses on AES algorithm and how it solves a given task at every instance while optimizing system efficiency. The beauty of the algorithm is efficient energy consumption in the data transfer platform that adopts the analysis in response to the task completion based on first-come-first-serve. The concept sustains the sequences of service delivery in the computing networks. The algorithm anchored in the cloudlet platform facilitates the use of the internet to support data transmission between different users and the server that rely on the same computing infrastructure.","PeriodicalId":298084,"journal":{"name":"2021 International Conference on Computer Technology and Media Convergence Design (CTMCD)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134006418","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
Joint Design of Transmit and Receive Beamforming for Transmit Subaperturing Airborne MIMO Radar 发射亚孔径机载MIMO雷达发射与接收波束形成联合设计
Zhihui Li, Yunxiang Mao, C. Niu, Wei Han, Qingsong Zhou
This paper deals with the joint design of transmit and receive beamforming for airborne transmit subaperturing (TS) multiple-input multiple-output (MIMO) radar to improve moving target detection performance in the presence of signal-dependent clutter background. The considered system is referred to as an airborne TS-MIMO radar, whose transmit array is divided into several subarrays to form the steerable waveforms with directional gain. The joint design of transmit and receive beamforming problem is formulated by maximizing the signal-to-interference-plus-noise ratio (SINR) under the energy constraint. To resolve the resulting non-convex joint design problem, we devise a sequential optimization algorithm. Simulation results demonstrate that the proposed method is monotonically increasing and convergent, and exhibits superior property to compared methods in terms of moving target detection performance.
研究了机载发射子孔径(TS)多输入多输出(MIMO)雷达的发射和接收波束形成联合设计,以提高信号相关杂波背景下的运动目标检测性能。所考虑的系统被称为机载TS-MIMO雷达,其发射阵列被分成几个子阵列以形成具有方向增益的可操纵波形。在能量约束下,以最大信噪比(SINR)为目标,提出了发射和接收波束形成问题的联合设计。为了解决由此产生的非凸接头设计问题,我们设计了一种顺序优化算法。仿真结果表明,该方法具有单调递增性和收敛性,在运动目标检测性能方面优于其他方法。
{"title":"Joint Design of Transmit and Receive Beamforming for Transmit Subaperturing Airborne MIMO Radar","authors":"Zhihui Li, Yunxiang Mao, C. Niu, Wei Han, Qingsong Zhou","doi":"10.1109/CTMCD53128.2021.00061","DOIUrl":"https://doi.org/10.1109/CTMCD53128.2021.00061","url":null,"abstract":"This paper deals with the joint design of transmit and receive beamforming for airborne transmit subaperturing (TS) multiple-input multiple-output (MIMO) radar to improve moving target detection performance in the presence of signal-dependent clutter background. The considered system is referred to as an airborne TS-MIMO radar, whose transmit array is divided into several subarrays to form the steerable waveforms with directional gain. The joint design of transmit and receive beamforming problem is formulated by maximizing the signal-to-interference-plus-noise ratio (SINR) under the energy constraint. To resolve the resulting non-convex joint design problem, we devise a sequential optimization algorithm. Simulation results demonstrate that the proposed method is monotonically increasing and convergent, and exhibits superior property to compared methods in terms of moving target detection performance.","PeriodicalId":298084,"journal":{"name":"2021 International Conference on Computer Technology and Media Convergence Design (CTMCD)","volume":"570 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133875554","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
Research on the Network Platform for Innovative Ideological and Political Education in Universities in the Era of Big Data 大数据时代高校思想政治教育创新网络平台研究
Aiwa Huang
Colleges and universities are the focus of ideological and political education in China. The purpose of ideological and political education is to cultivate new people who are responsible for the great task of national rejuvenation. In the era of big data, the network has an important impact on the ways and methods of ideological and political education for college students, as well as the educational results. Using the network platform to carry out ideological and political education in colleges and universities is an important innovative means. How to give full play to the positive role of network and discard the negative influence is also the difficulty of ideological and political education in colleges and universities in China. On the basis of analyzing the situation of ideological and political education in colleges and universities in China, this paper analyzes the influence of network on ideological and political education in colleges and universities, and puts forward some Suggestions and measures to develop ideological and political education research in colleges and universities by exerting the role of network platform.
高校是中国思想政治教育的重点阵地。思想政治教育的目的是培养担负起民族复兴伟大任务的新型人才。在大数据时代,网络对大学生思想政治教育的方式、方法以及教育效果产生了重要影响。利用网络平台开展高校思想政治教育是高校思想政治教育的重要创新手段。如何充分发挥网络的积极作用,摒弃网络的消极影响,也是中国高校思想政治教育的难点。本文在分析中国高校思想政治教育现状的基础上,分析了网络对高校思想政治教育的影响,提出了发挥网络平台作用开展高校思想政治教育研究的建议和措施。
{"title":"Research on the Network Platform for Innovative Ideological and Political Education in Universities in the Era of Big Data","authors":"Aiwa Huang","doi":"10.1109/CTMCD53128.2021.00032","DOIUrl":"https://doi.org/10.1109/CTMCD53128.2021.00032","url":null,"abstract":"Colleges and universities are the focus of ideological and political education in China. The purpose of ideological and political education is to cultivate new people who are responsible for the great task of national rejuvenation. In the era of big data, the network has an important impact on the ways and methods of ideological and political education for college students, as well as the educational results. Using the network platform to carry out ideological and political education in colleges and universities is an important innovative means. How to give full play to the positive role of network and discard the negative influence is also the difficulty of ideological and political education in colleges and universities in China. On the basis of analyzing the situation of ideological and political education in colleges and universities in China, this paper analyzes the influence of network on ideological and political education in colleges and universities, and puts forward some Suggestions and measures to develop ideological and political education research in colleges and universities by exerting the role of network platform.","PeriodicalId":298084,"journal":{"name":"2021 International Conference on Computer Technology and Media Convergence Design (CTMCD)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124444134","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
Research on Online Practice Platform of University Accounting Major Course in Big Data Context 大数据背景下高校会计专业课程在线实践平台研究
Xuan Wang, Pinghe He
With the development of information technology, the application of big data has been popularized to all sectors of social development. As a highly applied and practical discipline, accounting major courses in colleges and universities undertake the responsibility of training accounting talents for the society. The construction and application of the network practice platform of big data can enrich accounting teaching resources, improve the interest and innovation of the course, increase the school-enterprise alliance, and promote the employment of students. This paper explores the construction and application of college accounting network practice platform under the background of big data, proposes a new model of accounting practice teaching in colleges and universities, and provides new possibilities for the reform and innovation of accounting in colleges and universities.
随着信息技术的发展,大数据的应用已经普及到社会发展的各个领域。高校会计专业课程作为一门应用性强、实践性强的学科,承担着为社会培养会计人才的重任。大数据网络实践平台的建设与应用,可以丰富会计教学资源,提高课程趣味性和创新性,增加校企联盟,促进学生就业。本文探讨了大数据背景下高校会计网络实践平台的建设与应用,提出了高校会计实践教学的新模式,为高校会计改革创新提供了新的可能。
{"title":"Research on Online Practice Platform of University Accounting Major Course in Big Data Context","authors":"Xuan Wang, Pinghe He","doi":"10.1109/CTMCD53128.2021.00029","DOIUrl":"https://doi.org/10.1109/CTMCD53128.2021.00029","url":null,"abstract":"With the development of information technology, the application of big data has been popularized to all sectors of social development. As a highly applied and practical discipline, accounting major courses in colleges and universities undertake the responsibility of training accounting talents for the society. The construction and application of the network practice platform of big data can enrich accounting teaching resources, improve the interest and innovation of the course, increase the school-enterprise alliance, and promote the employment of students. This paper explores the construction and application of college accounting network practice platform under the background of big data, proposes a new model of accounting practice teaching in colleges and universities, and provides new possibilities for the reform and innovation of accounting in colleges and universities.","PeriodicalId":298084,"journal":{"name":"2021 International Conference on Computer Technology and Media Convergence Design (CTMCD)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124491543","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 lip language recognition based on spark 基于spark的唇语识别研究
Yulong Zhen, Wang Nan
Aiming at the problems of long lip feature coding and model training time in lip reading research, a distributed deep learning model based on spark is proposed. Firstly, we introduce the Ch-LipNet model structure, and then turn the cyclic layer LSTM network of the Ch-LipNet model into a ConvLSTM network to train and recognize the improved model. Secondly, a deep learning framework based on the keras library in the spark environment is built, and then the Ch-LipNet model and the improved model are built separately. Finally, the training and recognition of distributed deep learning models are carried out. On the lip language dataset NSTDB, the improved model in this paper is compared with the Ch-LipNet model in the local environment, and the recognition accuracy is increased by 15.6%. At the same time, the two models were tested separately in the spark environment, and the results showed that the distributed deep learning model can effectively improve the accuracy and training efficiency of lip reading.
针对唇读研究中存在的长唇特征编码和模型训练时间问题,提出了一种基于spark的分布式深度学习模型。首先介绍Ch-LipNet模型结构,然后将Ch-LipNet模型的循环层LSTM网络转化为ConvLSTM网络,对改进后的模型进行训练和识别。其次,在spark环境下构建基于keras库的深度学习框架,并分别构建Ch-LipNet模型和改进模型;最后,对分布式深度学习模型进行训练和识别。在唇语数据集NSTDB上,将改进后的模型与Ch-LipNet模型在局部环境下进行了比较,识别准确率提高了15.6%。同时,在spark环境下对两种模型分别进行了测试,结果表明分布式深度学习模型能够有效提高唇读的准确率和训练效率。
{"title":"Research on lip language recognition based on spark","authors":"Yulong Zhen, Wang Nan","doi":"10.1109/CTMCD53128.2021.00030","DOIUrl":"https://doi.org/10.1109/CTMCD53128.2021.00030","url":null,"abstract":"Aiming at the problems of long lip feature coding and model training time in lip reading research, a distributed deep learning model based on spark is proposed. Firstly, we introduce the Ch-LipNet model structure, and then turn the cyclic layer LSTM network of the Ch-LipNet model into a ConvLSTM network to train and recognize the improved model. Secondly, a deep learning framework based on the keras library in the spark environment is built, and then the Ch-LipNet model and the improved model are built separately. Finally, the training and recognition of distributed deep learning models are carried out. On the lip language dataset NSTDB, the improved model in this paper is compared with the Ch-LipNet model in the local environment, and the recognition accuracy is increased by 15.6%. At the same time, the two models were tested separately in the spark environment, and the results showed that the distributed deep learning model can effectively improve the accuracy and training efficiency of lip reading.","PeriodicalId":298084,"journal":{"name":"2021 International Conference on Computer Technology and Media Convergence Design (CTMCD)","volume":"129 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122419182","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
Reconstructing the New Significance of Combining Graphic Language —— Hand-drawn Graphic Language with Computer Graphics Language 重构图形语言结合的新意义——手绘图形语言与计算机图形语言
T. Long
With the development of science and technology network in China, the development of language information is in a prosperous scene, a large number of information accelerates the spread of culture, and the language of images also presents a variety of expressions. The opportunity of image design industry is also increasing, the vision and form of art are constantly upgraded, and the integration of hand-drawn graphics language and computer graphics language will become a trend. Human beings are about to become a new future in the direction of artistic development, and in the process of exploration, they will face many problems to be explored. This paper studies the fusion of hand-drawn graphics language and computer graphics language, understands the communication mode in the process of language transmission, deeply studies the logical thinking of reconstructing graphics language, finds out the new art of beauty, and lets the graphic language pass on.
随着中国科技网络的发展,语言信息的发展呈现出一片欣欣向荣的景象,大量的信息加速了文化的传播,图像语言也呈现出多种多样的表现形式。形象设计行业的机会也在不断增加,艺术的视觉和形式也在不断升级,手绘图形语言和计算机图形语言的融合将成为一种趋势。人类即将在艺术发展的方向上成为一个新的未来,在探索的过程中,将面临许多有待探索的问题。本文研究手绘图形语言与计算机图形语言的融合,了解语言传播过程中的传播方式,深入研究重构图形语言的逻辑思维,找出新的美的艺术,让图形语言传承下去。
{"title":"Reconstructing the New Significance of Combining Graphic Language —— Hand-drawn Graphic Language with Computer Graphics Language","authors":"T. Long","doi":"10.1109/CTMCD53128.2021.00008","DOIUrl":"https://doi.org/10.1109/CTMCD53128.2021.00008","url":null,"abstract":"With the development of science and technology network in China, the development of language information is in a prosperous scene, a large number of information accelerates the spread of culture, and the language of images also presents a variety of expressions. The opportunity of image design industry is also increasing, the vision and form of art are constantly upgraded, and the integration of hand-drawn graphics language and computer graphics language will become a trend. Human beings are about to become a new future in the direction of artistic development, and in the process of exploration, they will face many problems to be explored. This paper studies the fusion of hand-drawn graphics language and computer graphics language, understands the communication mode in the process of language transmission, deeply studies the logical thinking of reconstructing graphics language, finds out the new art of beauty, and lets the graphic language pass on.","PeriodicalId":298084,"journal":{"name":"2021 International Conference on Computer Technology and Media Convergence Design (CTMCD)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131181385","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 construction of English teaching platform under the background of big data 大数据背景下英语教学平台建设研究
Yang Mei
The development of information technology provides a new development direction and mode for college education and teaching. The application of big data not only changes the traditional college education and teaching mode, but also provides more opportunities for resource sharing. The construction of college English teaching platform can break through the limitation of time and space in traditional English teaching and provide a broader space for English teaching. This paper will conduct an in-depth study on the construction of English teaching platform under the background of big data, and explore the mode and existing problems of the construction of English teaching platform under the background of big data through the combination of theory and practice.
信息技术的发展为高校教育教学提供了新的发展方向和模式。大数据的应用不仅改变了传统的高校教育教学模式,也为资源共享提供了更多的机会。大学英语教学平台的建设可以突破传统英语教学的时间和空间限制,为英语教学提供更广阔的空间。本文将对大数据背景下的英语教学平台建设进行深入研究,通过理论与实践的结合,探索大数据背景下英语教学平台建设的模式及存在的问题。
{"title":"Research on the construction of English teaching platform under the background of big data","authors":"Yang Mei","doi":"10.1109/CTMCD53128.2021.00018","DOIUrl":"https://doi.org/10.1109/CTMCD53128.2021.00018","url":null,"abstract":"The development of information technology provides a new development direction and mode for college education and teaching. The application of big data not only changes the traditional college education and teaching mode, but also provides more opportunities for resource sharing. The construction of college English teaching platform can break through the limitation of time and space in traditional English teaching and provide a broader space for English teaching. This paper will conduct an in-depth study on the construction of English teaching platform under the background of big data, and explore the mode and existing problems of the construction of English teaching platform under the background of big data through the combination of theory and practice.","PeriodicalId":298084,"journal":{"name":"2021 International Conference on Computer Technology and Media Convergence Design (CTMCD)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124399513","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
2021 International Conference on Computer Technology and Media Convergence Design (CTMCD)
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