As one of the core visual symbols of Chinese traditional culture,the communication history of auspicious cloud patterns on Central Plains ancient ceramics has great significance.Its contemporary value can be summarize...As one of the core visual symbols of Chinese traditional culture,the communication history of auspicious cloud patterns on Central Plains ancient ceramics has great significance.Its contemporary value can be summarized into four aspects,namely the carrier of cultural inheritance and national identity,the innovative resources of modern design,the media of international cultural exchange and the enlightenment of ecological philosophy.展开更多
The late Warring States Period (475 B.C-221 B.C)Caliber diameter:18.2 cm Bronze with inlaid silver The surfaces of the utensil body and the lid are decorated with cloud patterns by using the inlaid gold or silver fila...The late Warring States Period (475 B.C-221 B.C)Caliber diameter:18.2 cm Bronze with inlaid silver The surfaces of the utensil body and the lid are decorated with cloud patterns by using the inlaid gold or silver filaments and flakes. The decorative patterns are very slim and extremely exquisite.展开更多
Voids and complex cloud patterns have been observed in a radio frequency (rf) discharge dusty plasma system. The structures and behaviors of these patterns were investigated in two- and three-dimensions by shifting an...Voids and complex cloud patterns have been observed in a radio frequency (rf) discharge dusty plasma system. The structures and behaviors of these patterns were investigated in two- and three-dimensions by shifting an il- lumination laser sheet beam up and down. Two-dimensional (2D) circular voids, thin ring voids, and their coexistent voids were observed at the early stage of particle growth. The cor- responding three-dimensional (3D) structures were dome, shell, and their coexistent voids, respectively. The complex fluid-like cloud patterns occurred above the 3D dome voids. The origin and evolution process of the complex dust cloud patterns need a further theoretical explanation.展开更多
With the development of world heritage protection undertakings, dynamic inheritance of intangible cultural heritage has become a topic of great concern. This study explored the feasibility of integrating cloud-pattern...With the development of world heritage protection undertakings, dynamic inheritance of intangible cultural heritage has become a topic of great concern. This study explored the feasibility of integrating cloud-pattern brocade heritage and modern design and the innovation techniques, so as to provide new concepts for the inheritance and development of intangible cultural heritage.展开更多
Precipitation prediction(PP)have become one of the significant research areas of deep learning(DL)and machine vision(MV)techniques are frequently used to predict the weather variables(WV).Since the climate change has ...Precipitation prediction(PP)have become one of the significant research areas of deep learning(DL)and machine vision(MV)techniques are frequently used to predict the weather variables(WV).Since the climate change has left significant impact upon weather variables(WV)and continuously changes are observed in temperature,humidity,cloud patterns and other factors.Although cloud images contain sufficient information to predict the precipitation pattern but due to changes in climate,the complex cloud patterns and rapid shape changing behavior of clouds are difficult to consider for rainfall prediction.Prediction of rainfall would provide more meticulous assistance to the farmers to know about the weather conditions and to care their cash crops.This research proposes a framework to classify the dark cloud patterns(DCP)for prediction of precipitation.The framework consists upon three steps to classify the cloud images,first step tackles noise reduction operations,feature selection and preparation of datasets.Second step construct the decision model by using convolutional neural network(CNN)and third step presents the performance visualization by using confusion matrix,precision,recall and accuracy measures.This research contributes(1)real-world clouds datasets(2)method to prepare datasets(3)highest classification accuracy to predict estimated as 96.90%.展开更多
针对传统图像模式挖掘无法提取全局特征,不具备抽象能力,难以符合实际要求等问题,研究提出采用基于深度相关特征聚类算法来完成云平台用户界面智慧图像设计任务。并在此基础上,引入交叉熵损失、三元损失以及注意力机制来对该算法进行优...针对传统图像模式挖掘无法提取全局特征,不具备抽象能力,难以符合实际要求等问题,研究提出采用基于深度相关特征聚类算法来完成云平台用户界面智慧图像设计任务。并在此基础上,引入交叉熵损失、三元损失以及注意力机制来对该算法进行优化,使得改进后的算法在图像的视觉模式挖掘上能同时满足判别性与频繁性,获得最优解。实验结果显示,在UI Elements Dataset与CIFAR10数据集上,改进后模型的分类准确率分别为0.936和0.978,频率分别为0.464和0.514,且在应用于教育领域时,该模型可提供较好的学习体验。综合表明,研究所提模型能推动改善云平台用户界面智慧图像的视觉体验,为新质生产力的发展提供有力的技术支持。展开更多
基金Supported by Open Project of Henan Key Laboratory of Research for Central Plains Ancient Ceramics in 2018(ZYGTCXN2018-05).
文摘As one of the core visual symbols of Chinese traditional culture,the communication history of auspicious cloud patterns on Central Plains ancient ceramics has great significance.Its contemporary value can be summarized into four aspects,namely the carrier of cultural inheritance and national identity,the innovative resources of modern design,the media of international cultural exchange and the enlightenment of ecological philosophy.
文摘The late Warring States Period (475 B.C-221 B.C)Caliber diameter:18.2 cm Bronze with inlaid silver The surfaces of the utensil body and the lid are decorated with cloud patterns by using the inlaid gold or silver filaments and flakes. The decorative patterns are very slim and extremely exquisite.
文摘Voids and complex cloud patterns have been observed in a radio frequency (rf) discharge dusty plasma system. The structures and behaviors of these patterns were investigated in two- and three-dimensions by shifting an il- lumination laser sheet beam up and down. Two-dimensional (2D) circular voids, thin ring voids, and their coexistent voids were observed at the early stage of particle growth. The cor- responding three-dimensional (3D) structures were dome, shell, and their coexistent voids, respectively. The complex fluid-like cloud patterns occurred above the 3D dome voids. The origin and evolution process of the complex dust cloud patterns need a further theoretical explanation.
基金Sponsored by Education Science Youth Program of National Social Sciences Fund(CLA100169)
文摘With the development of world heritage protection undertakings, dynamic inheritance of intangible cultural heritage has become a topic of great concern. This study explored the feasibility of integrating cloud-pattern brocade heritage and modern design and the innovation techniques, so as to provide new concepts for the inheritance and development of intangible cultural heritage.
文摘Precipitation prediction(PP)have become one of the significant research areas of deep learning(DL)and machine vision(MV)techniques are frequently used to predict the weather variables(WV).Since the climate change has left significant impact upon weather variables(WV)and continuously changes are observed in temperature,humidity,cloud patterns and other factors.Although cloud images contain sufficient information to predict the precipitation pattern but due to changes in climate,the complex cloud patterns and rapid shape changing behavior of clouds are difficult to consider for rainfall prediction.Prediction of rainfall would provide more meticulous assistance to the farmers to know about the weather conditions and to care their cash crops.This research proposes a framework to classify the dark cloud patterns(DCP)for prediction of precipitation.The framework consists upon three steps to classify the cloud images,first step tackles noise reduction operations,feature selection and preparation of datasets.Second step construct the decision model by using convolutional neural network(CNN)and third step presents the performance visualization by using confusion matrix,precision,recall and accuracy measures.This research contributes(1)real-world clouds datasets(2)method to prepare datasets(3)highest classification accuracy to predict estimated as 96.90%.
文摘针对传统图像模式挖掘无法提取全局特征,不具备抽象能力,难以符合实际要求等问题,研究提出采用基于深度相关特征聚类算法来完成云平台用户界面智慧图像设计任务。并在此基础上,引入交叉熵损失、三元损失以及注意力机制来对该算法进行优化,使得改进后的算法在图像的视觉模式挖掘上能同时满足判别性与频繁性,获得最优解。实验结果显示,在UI Elements Dataset与CIFAR10数据集上,改进后模型的分类准确率分别为0.936和0.978,频率分别为0.464和0.514,且在应用于教育领域时,该模型可提供较好的学习体验。综合表明,研究所提模型能推动改善云平台用户界面智慧图像的视觉体验,为新质生产力的发展提供有力的技术支持。
