检索结果-内蒙古大学图书馆

2019 IEEE International Conference on Artificial Intelligence and Computer Applications, ICAICA 2019

作者： Zhang, Yanyi Hao, Kuangrong Tang, Xuesong Wei, Bing Ren, Lihong Engineering Research Center of Digitized Textile Apparel Technology Ministry of Education College of Information Science and Technology Donghua University 201620 China

ISBN: (纸本)9781728112220

Applications of deep convolutional networks have achieved success in the field of video action recognition. However, there are still existing problems: 1) Most motion recognition only uses a single video segment as research object, which is difficult to represent the coherent process of the action in whole video because of the lack of ability to use the complementary information;2) Most studies have not specifically enhanced the ability to characterize movements as time goes on, just put temporal information in the same class as spatial information. A Long-term 3D Convolutional Fusion Network (LT3D-CFN) is proposed to aim at these problems. LT3D-CFN could be summarized as the following two aspects: CNN in two-stream network has been replaced by 3DCNN because of the ability of extracting features from both the spatial and the temporal dimensions of one video clip. In addition, long-term associations between clips of one motion video are established by adding deep LSTM network. The proposed architecture LT3D-CFN, is trained and evaluated on UCF-101 dataset where the proposed architecture achieves superior performers. © 2019 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Prediction of stock trading signal based on multi-indicator channel convolutional neural networks 8

Prediction of stock trading signal based on multi-indicator ...

引用

8th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2019

作者： Yang, Zhenhua Hao, Kuangrong Cai, Xin Chen, Lei Ren, Lihong Engineering Research Center of Digitized Textile Apparel Technology Ministry of Education College of Information Science and Technology Donghua University Shanghai China

ISBN: (纸本)9781728114545

Stock forecasting has always been a tempting and challenging problem in the field of financial research. Recently, convolutional neural networks have been used to classify trading signals of stock, but different indicator rankings will generate different images when generating data picture. A multi-indicator channel convolutional neural network (MICNN) is proposed to avoid the uncertainty of image generation. The test results are better than MLP and show that the proposed model has good classification performance, and the results of the simulated trading prove that the trading signals predicted by our method have practical value. © 2019 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Adaptive prototypical networks with label words and joint representation learning for few-shot relation classification

arXiv

引用

arXiv 2021年

作者： Xiao, Yan Jin, Yaochu Hao, Kuangrong Engineering Research Center of Digitized Textile & Apparel Technology Ministry of Education College of Information Science and Technology Donghua University Shanghai201620 China Department of Computer Science University of Surrey Guildford SurreyGU2 7XH United Kingdom

Relation classification (RC) task is one of fundamental tasks of information extraction, aiming to detect the relation information between entity pairs in unstructured natural language text and generate structured data in the form of entity-relation triple. Although distant supervision methods can effectively alleviate the problem of lack of training data in supervised learning, they also introduce noise into the data, and still cannot fundamentally solve the long-tail distribution problem of the training instances. In order to enable the neural network to learn new knowledge through few instances like humans, this work focuses on few-shot relation classification (FSRC), where a classifier should generalize to new classes that have not been seen in the training set, given only a number of samples for each class. To make full use of the existing information and get a better feature representation for each instance, we propose to encode each class prototype in an adaptive way from two aspects. First, based on the prototypical networks, we propose an adaptive mixture mechanism to add label words to the representation of the class prototype, which, to the best of our knowledge, is the first attempt to integrate the label information into features of the support samples of each class so as to get more interactive class prototypes. Second, to more reasonably measure the distances between samples of each category, we introduce a loss function for joint representation learning to encode each support instance in an adaptive manner. Extensive experiments have been conducted on FewRel under different few-shot (FS) settings, and the results show that the proposed adaptive prototypical networks with label words and joint representation learning has not only achieved significant improvements in accuracy, but also increased the generalization ability of few-shot RC models. © 2021, CC BY.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Abnormal Crowd Behavior Detection Based on Predictive Neural Network

Abnormal Crowd Behavior Detection Based on Predictive Neural...

引用

2019 IEEE International Conference on Artificial Intelligence and Computer Applications, ICAICA 2019

作者： Liu, Yue Hao, Kuangrong Tang, Xuesong Wang, Tong Engineering Research Center of Digitized Textile Apparel Technology Ministry of Education College of Information Science and Technology Donghua University 201620 China

ISBN: (纸本)9781728112220

In recent years, malignant crowd incidents that endanger public safety occur frequently, which alarms humans of the security in public areas. Focus on the detection of abnormal crowd behavior has been heightened in the field of computer vision. To solve this problem, the predictive neural network is innovatively applied to crowd anomaly detection by enlarging the differences between predictive frames and real frames in moving object regions. Firstly, aiming at the drawback of slow convergence speed of running Gaussian average model for object detection, an improved attenuation strategy based on learning rate is proposed. Then the processed foreground data set is put into the predictive neural network, and we define the degree of anomaly as the differences between predictive frames and real frames. By adjusting the threshold adaptively, the abnormal behavior in the crowd can be judged. The experimental results show that, compared with optical flow method and social force model, this method is not only fast in calculation, but also can detect crowd anomalies accurately and effectively. The accuracy rate of this method in UMN data set is up to 97.7%. © 2019 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Time series classification based on FCN multi-scale feature eensemble learning 8

Time series classification based on FCN multi-scale feature ...

引用

8th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2019

作者： Zhou, Wenshuo Hao, Kuangrong Tang, Xuesong Xiao, Yan Wang, Tong Engineering Research Center of Digitized Textile Apparel Technology Ministry of Education College of Information Science and Technology Donghua University Shanghai201620 China

ISBN: (纸本)9781728114545

Time series classification problem (TSC) is of great significance in the fields of finance, health care and environment. The full convolutional network is prominent in the classification of time series, but the feature length of the original data extracted by the network is fixed. Since the highly distinguishable local features in time series may have different scales, this paper proposes a multi-scale feature ensemble full convolutional network (MFCN) to extract different scale features and improve the classification accuracy of the network. Finally, 11 excellent time series classification models were compared on 44 UCR data sets, and the results showed that the proposed method obtained the minimum classification accuracy error in 16 data sets, and the average accuracy was also the highest, reaching 87.7%. © 2019 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Fabric defect detection based on faster RCNN

Fabric defect detection based on faster RCNN

引用

Artificial Intelligence on Fashion and textiles Conference, AIFT 2018

作者： Wei, Bing Hao, Kuangrong Tang, Xue-Song Ren, Lihong Engineering Research Center of Digitized Textile and Apparel Technology Ministry of Education College of Information Sciences and Technology Donghua University Shanghai201620 China

ISBN: (纸本)9783319996943

Considering that the traditional detection of fabric defect can be time-consuming and less-efficient, a modified faster regional-based convolutional network method (Faster RCNN) based on the VGG structure is proposed. In the paper, we improved the Faster RCNN to suit our fabric defect dataset. In order to reduce the influence of input data for Faster RCNN, we expanded the fabric defect data. Meanwhile, by taking the characteristics of the fabric defect images, we reduce the number of anchors in the Faster RCNN. In the process of training the network, VGG16 can extract the feature map through the 13 conv layers in which the activation function is Relu, and four pooling layers. Then, the region proposal network (RPN) generates the foreground anchors and bounding box regression, and then calculates the proposals. Finally, the ROI Pooling layer uses the proposals from the feature maps to extract the proposal feature into the subsequent full connection and softmax network for classification. The experimental results show the capability of fabric defect detection via the modified Faster RCNN model and indicate its effectiveness. © Springer Nature Switzerland AG 2019.

关键词： Anchors

来源：评论

学校读者我要写书评

暂无评论

Design, Simulation and Measurement of Metapocket: An All-textile Reflective Metasurface for On-body Smartphone Radiation Improvement

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Zhai, Menglin Tian, Wandai Pei, Rui Xu, Chen Leach, Mark Lim, Eng Gee Wang, Zhao Wang, Jingchen Hua, Qiang Akinsolu, Mobayode Liu, Bo Huang, Yi the College of information science and technology Donghua University Shanghai201620 China Engineering Research Center of Digitized Textile and Fashion Technology Ministry of Education Shanghai China the School of Advanced Technology Xi’an Jiaotong Liverpool University Suzhou215123 China vivo mobile Communication Co. Ltd. China Department of Engineering and Technology School of Computing and Engineering University of Huddersfield HuddersfieldHD1 3DH United Kingdom the Faculty of Arts Science and Technology Wrexham University WrexhamLL11 2AW United Kingdom the James Watt School of Engineering University of Glasgow GlasgowG12 8LU United Kingdom the Department of Electrical Engineering and Electronics University of Liverpool LiverpoolL69 3BX United Kingdom

A polarization-independent all-textile reflective metasurface – the metapocket, is presented in this paper. This design aims at enhancing gain, and radiation efficiency and reducing the Specific Absorption Rate (SAR) of a smartphone antenna when it is placed inside a jacket pocket close to the human body. During the design process, the state-of-the-art smartphone structure, the impact of varying unit cell numbers on reflectivity and the nature of textile materials have been taken into consideration. Also, an AI-driven antenna design algorithm is employed. Full wave simulations with a voxel human body model and real measurement with smartphone vivo iQOO validate the effectiveness of the metapocket. The effect of applying the metapocket is quantified with an anechoic chamber radiation pattern measurement and a reverberation chamber radiation efficiency measurement. Results reveal a 3.17 dB realized gain increase, 34.37% radiation efficiency improvement, and a more than 85% SAR reduction are achieved in the on-body scenario. The proposed design has a high potential for improving smartphone communication with various Internet of Things (IoT) and wearable devices. © 2025 IEEE. All rights reserved,

关键词： Reverberation

来源：评论

学校读者我要写书评

暂无评论

Spatial Dynamics of the Public Goods Game with Probabilistic Participation

Spatial Dynamics of the Public Goods Game with Probabilistic...

引用

第三十九届中国控制会议

作者： Xiaofeng Wang Weijian Kong Department of Automation School of Information Science & TechnologyDonghua University Engineering Research Center of Digitized Textile & Apparel Technology (Donghua University) Ministry of Education

We consider the stochasticity of individuals' behavior on participating in the spatial public goods games by endowing cooperators and defectors with two different participating probabilities, and study its effects on the evolution of cooperation. By investigating the dependence of the potential cooperator density on the participation probabilities of cooperators and defectors,we show that cooperation can be promoted in the most parameter space of these two parameters. In particular, full cooperation can be achieved if both participation probabilities are not large. We also find that, by comparing the equilibrium fraction of potential cooperators in an infinitely well-mixed population with that on the square lattice, spatial structure has a sort of double-edged sword effect on the evolution of cooperation in the coexistence dynamic regime;whereas in other dynamic regions spatial structure is beneficial for cooperation. Interestingly, it is shown that cooperation may be unexpectedly inhibited with the increment of the enhancement factor in the spatial public goods game with probabilistic participation. These results can help better understand how cooperation evolves in the structured population where individuals probabilistically participate in the interactions depending on their strategy choices.

关键词： Probabilistic Participation Spatial Effects Cooperation Public Goods Game Evolutionary Game Theory

来源：评论

学校读者我要写书评

暂无评论

Review on the 3-D simulation for weft knitted fabric

引用

Journal of Engineered Fibers and Fabrics 2021年第16期16卷

作者： Sha, Sha Geng, Anqi Gao, Yuqin Li, Bin Jiang, Xuewei Tao, Hui Luo, Lei Yuan, Xiaohong Ke, Huizhen Hu, Xinrong Deng, Zhongmin Chen, Zhi State Key Laboratory of New Textile Materials and Advanced Processing Technologies Key Laboratory of Textile Fiber Product Ministry of Education Wuhan Textile University WuhanHubei China Wuhan Textile and Apparel Digital Engineering Technology Research Center School of Fashion Wuhan Textile University WuhanHubei China Engineering Research Center of Hubei Province for Clothing Information Wuhan Textile University WuhanHubei China Fujian Key Laboratory of Novel Functional Textile Fibers and Materials Engineering Research Center of Textile and Clothing Fujian Province University Minjiang University Fuzhou China

There are different kinds of geometrical models and physical models used to simulate weft knitted fabrics nowadays, such as loop models based on Pierce, piecewise function, spline curve, mass-spring model, and finite element analyses (FEA). Weft knitting simulation technology, including modeling and yarn reality, has been widely adopted in fabric structure designing for the manufacturer. The technology has great potentials in both industries and dynamic virtual display. The present article is aimed to review the current development of 3-D simulation technique for weft knitted fabrics. © The Author(s) 2021.

关键词： Knit fabrics

来源：评论

学校读者我要写书评

暂无评论

An adaptive immune algorithm for service-oriented agricultural Internet of Things

引用

Neurocomputing 2019年 344卷 3-12页

作者： Yang, Zhen Ding, Yongsheng Hao, Kuangrong Cai, Xin Engineering Research Center of Digitized Textile & Apparel Technology Ministry of Education College of Information Science and Technology Donghua University Shanghai China College of Information Engineering Huzhou University Huzhou China

Internet of Things (IoT) has the characteristics of multi-source, multi-type and unequal amount of task. Considering multiple requests at stochastic moment in the agricultural IoT service, an optimization model of minimum service cost is built in this paper, and an adaptive immune algorithm with endocrine regulation (AIE) is proposed to solve the problem of dynamic service for multiple requests. Based on this model, two service providing strategies are put forward, i.e. single service and collaborative service. The former means that one request task is completed by one service provider, while the latter means that one request task is collaboratively completed by multiple service providers. The service cost and service time are respectively evaluated under two service providing strategies. The simulation results verify the feasibility and effectiveness of the proposed AIE through comparison to the immune algorithm without endocrine regulation. Meanwhile, it is demonstrated that the proposed AIE can obtain more excellent performance than genetic algorithm and particle swarm optimization. © 2019

关键词： Agricultural Dynamic service Immune algorithm Internet of Things (IoT) Multiple requests

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：