检索结果-内蒙古大学图书馆

Improved CycleGAN for super-resolution of engineering drawings

MEASUREMENT SCIENCE AND TECHNOLOGY 2023年第7期34卷 077001-077001页

作者： Song, Zhiwei Yao, Hui Tian, Dan Zhan, Gaohui Xian Technol Univ Sch Mechatron Engn Xian 710032 Shaanxi Peoples R China

In intelligent manufacturing, the quality of machine translation engineering drawings directly affects manufacturing accuracy. Currently, most engineering drawing translation work is done manually, which greatly reduces production efficiency. This paper proposes an automatic translation method for welded structure engineering drawings based on the Cycle Generative Adversarial Network (CycleGAN). The CycleGAN model of unpaired transfer learning is used to learn the feature mapping of real welding engineering drawings to realize their automatic translation. U-Net and PatchGAN are used as the generator and discriminator, respectively. Based on the idea of removing the identity mapping function, a high-dimensional sparse network is proposed to replace the traditional dense network for the CycleGAN generator in order to improve noise robustness. It is found that increasing the residual block hidden layer increases the resolution of the generated graph. The improved and fine-tuned network models are experimentally validated by computing the gap between real and generated data. The results meet welding engineering precision standards and solve the problem of low drawing recognition efficiency in the welding manufacturing process. After training with our model, the peak signal-to-noise ratio, structural similarity and mean squared error of welding engineering drawings reach about 44.89%, 99.58% and 2.11, respectively, which are superior to the results achieved using traditional networks in terms of both training speed and accuracy.

关键词： engineering drawings deep learning CycleGAN image translation sparse algorithm

来源：评论

学校读者我要写书评

暂无评论

Visual saliency object detection using sparse learning

引用

IET IMAGE PROCESSING 2019年第13期13卷 2436-2447页

作者： Nasiripour, Reza Farsi, Hassan Mohamadzadeh, Sajad Univ Birjand Dept Elect & Comp Engn Birjand Iran

In many applications in order to recognise the relationship between user and computer, the position at which the user looks should be detected. To this end, a salient object should be extracted that is attracted to the attention of the viewer. In this study, a new method is proposed to extract the object saliency map, which is based on learning automata and sparse algorithms. In the proposed method, after decomposition of an image to its superpixels, eight features (namely three features in red-green-blue colour space, coalition, central bias, rotation feature, brightness, and colour difference) are extracted. Then the extracted features are normalised to zero mean and unit variance. In this study, K-means singular-value decomposition is used to integrate the extracted features. The performance of the proposed method is compared with that of 20 other methods by applying four new databases, including MSRA-100, ECSSD, MSRA-10K, and Pascal-S. The obtained results show that the proposed method has a better performance compared to the other methods with regard to the prediction of the salient object.

关键词： singular value decomposition object detection image colour analysis feature extraction object recognition image resolution visual saliency object detection sparse learning salient object red-green-blue colour space rotation feature colour difference zero mean unit variance sparse algorithm object saliency map extraction learning automata algorithm central bias K-means singular-value decomposition MSRA-100 ECSSD MSRA-10K Pascal-S

来源：评论

学校读者我要写书评

暂无评论

Intelligent Safe Driving Methods Based on Hybrid Automata and Ensemble CART algorithms for Multihigh-Speed Trains

引用

IEEE TRANSACTIONS ON CYBERNETICS 2019年第10期49卷 3816-3826页

作者： Cheng, Ruijun Yu, Wei Song, Yongduan Chen, Dewang Ma, Xiaoping Cheng, Yu Fuzhou Univ Coll Math & Comp Sci Fuzhou 350116 Fujian Peoples R China Beijing Jiaotong Univ State Key Lab Rail Traff Control & Safety Beijing 100044 Peoples R China Chongqing Univ Sch Automat Chongqing 400044 Peoples R China China Acad Railway Sci Inst Infrastruct Inspect Res Beijing 100081 Peoples R China

Considering both the tracking safety of multi-HSTs and the operational efficiency of a single HST, intelligent safe driving methods (ISDMs) are proposed to obtain better speed-distance curves by integrating hybrid automata (HA) with data mining algorithms in this paper. To begin with, an intelligent safe distance controller is established by using HA to ensure the tracking safety of multi-HSTs' operation in real time. Then, data-driven intelligent driving methods based on ensemble algorithms (Bagging or Adaboost.R) and classification and regression tree (CART) are proposed to discover the potential driving rules from the field driving data. Furthermore, because of the continuous rise of HST's operation mileage, the driving data collected from HST has increased tremendously compared with the subways. So, an iterative pruning error minimization algorithm is designed to reduce the redundancy of the driving data and improve the computational speed of the learning process. Finally, compared with the automatic train operation (ATO) method, the energy consumption of B-CART, A-CART, and S-A-CART algorithms can be decreased by 3.32%, 3.80%, and 4.30%, respectively.

关键词： Automatic train operation (ATO) high-speed train intelligent train control machine learning algorithm sparse algorithm system safety

来源：评论

学校读者我要写书评

暂无评论

sparse algorithms of Random Weight Networks and applications

引用

EXPERT SYSTEMS WITH APPLICATIONS 2014年第5期41卷 2457-2462页

作者： Cao, Feilong Tan, Yuanpeng Cai, Miaomiao China Jiliang Univ Dept Informat & Math Sci Hangzhou 310018 Zhejiang Peoples R China

This paper studies sparse algorithms for training Random Weight Networks (RWN) and their applications. The proposed algorithms contain three principal steps: initialization of networks structure, simplification of RWN structure based on sparse coding, and relearning process with renewed nodes. A key of the algorithms is sparse coding of hidden layer neurons by adding an initialization process to simplify the networks structure. Specially, the new algorithms, to some extent, can avoid the over-fitting phenomenon efficiently. As applications, the algorithms are used to diagnose the fault of switch reluctance motor (SRM) and to recognize the human face. Compared with the traditional back-propagation (BP) and RWN algorithms, the experimental results show that the proposed algorithms have effective performances on the accuracy or time. These methodologies can also be conceived as support tools for the practical fault diagnosis of SRM and the human face pattern recognition. Crown Copyright (C) 2013 Published by Elsevier Ltd. All rights reserved.

关键词： Feedforward neural networks Random weights sparse algorithm Fault diagnosis Human face recognition

来源：评论

学校读者我要写书评

暂无评论

Equalizer Design Based on ATSC-M/H Protocol

Equalizer Design Based on ATSC-M/H Protocol

引用

2015 International Conference on Computer Information Systems and Industrial Applications(CISIA2015)

作者： T.Xu Z.H.Hu Z.F.Wang H.H.Song Shanghai Second Polytechnic University

ISBN: (纸本)9781510805750

This paper analyzes the channel model under mobile reception state firstly,then study the self-correlation characteristic of ATSC-Mobile DTV training *** with the mobile channel characteristic and selfcorrelation of training sequence,proposed a parallel channel estimation algorithm with multi-channel to reduce the channel estimation time and to improve the estimation ***,proposed a DFE equalizer structures based on sparse algorithm and validated the performance by simulation.

关键词： ATSC-M/H channel estimation sparse algorithm equalizer

来源：评论

学校读者我要写书评

暂无评论

FacetCube: a general framework for non-negative tensor factorization

引用

KNOWLEDGE AND INFORMATION SYSTEMS 2013年第1期37卷 155-179页

作者： Chi, Yun Zhu, Shenghuo NEC Labs Amer Inc Cupertino CA 95014 USA

Non-negative tensor factorization (NTF) has been successfully used to extract significant characteristics from polyadic data, such as data in social networks. Because these polyadic data have multiple dimensions (e.g., the author, content, and timestamp of a blog post), NTF fits in naturally and extracts data characteristics jointly from different data dimensions. In the traditional NTF, all information comes from the observed data, and therefore, the end users have no control over the outcomes. However, in many applications very often, the end users have certain prior knowledge, such as the demographic information about individuals in a social network or a pre-constructed ontology on the contents and therefore prefer the data characteristics extracting by NTF being consistent with such prior knowledge. To allow users' prior knowledge to be naturally incorporated into NTF, in this paper, we present a general framework-FacetCube-that extends the standard NTF. The new framework allows the end users to control the factorization outputs at three different levels for each of the data dimensions. The proposed framework is intuitively appealing in that it has a close connection to the probabilistic generative models. In addition to introducing the framework, we provide an iterative algorithm for computing the optimal solution to the framework. We also develop an efficient implementation of the algorithm that consists of several techniques to make our framework scalable to large data sets. Extensive experimental studies on a paper citation data set and a blog data set demonstrate that our new framework is able to effectively incorporate users' prior knowledge, improves performance over the traditional NTF on the task of personalized recommendation, and is scalable to large data sets from real-life applications.

关键词： Non-negative tensor factorization Polyadic data Prior knowledge Iterative algorithm sparse algorithm

来源：评论

学校读者我要写书评

暂无评论

sparse Support Vector Regression algorithm with Piecewise Loss Function

Sparse Support Vector Regression Algorithm with Piecewise Lo...

引用

2010 2nd IEEE International Conference on Information Management and Engineering(2010年IEEE第二届信息管理与工程国际会议 IEEE ICIME 2010)

作者： Gensheng Hu Department of Computer ScienceShangqiu Normal College Shangqiu China

Applying sparse algorithm can improve the prediction speed of support vector regression effectively. This paper solves sparse support vector regression with piecewise loss function based on iterative reweight method. By reducing support vector number, the length of regression function expansion and the prediction time of regression function for new samples are decreased. Comparing with sparse LSSVR, the method has the advantages of suiting different noise data;Steady prediction performance and good generalization performance.

关键词： support vector regression sparse algorithm Iterative Reweight Method

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Address Allocation algorithm for IPv6

A Hybrid Address Allocation Algorithm for IPv6

引用

3rd International Conference on Network Security and Applications

作者： Murugesan, Raja Kumar Ramadass, Sureswaran Univ Sains Malaysia Natl Adv Ctr NAv6 IPv6 George Town 11800 Malaysia

ISBN: (纸本)9783642144776

The scalability of the Internet routing system has caught much attention in the recent years as it affects the performance of the Internet greatly. IP address fragmentation is one main cause for routing scalability and existing address allocation practices are one major contributor to address fragmentation. Address fragmentation increases routing table size, hence IP look-up and routing efficiency. It also constraints the processing and memory capabilities of routers leading to failing routes if the burgeoning growth of the routing table size is not contained. A proper address allocation algorithm coupled with appropriate address allocation policies will help to scale the existing addressing and routing system. This research proposes a hybrid address allocation algorithm for IPv6 by combining some of the existing address allocation algorithms leveraging on their merits. The proposed hybrid address allocation algorithm would help in reducing address fragmentation to a greater extent compared to the existing address allocation schemes. This would facilitate in reducing routing table size, increase scalability and hence improve the performance of the Internet.

关键词： IPv6 sparse algorithm Rate-sparse algorithm GAP algorithm aggregation conservation routing scalability

来源：评论

学校读者我要写书评

暂无评论

Estimation of time-dependent origin-destination matrices for transit networks

引用

TRANSPORTATION RESEARCH PART B-METHODOLOGICAL 1998年第1期32卷 35-48页

作者： Wong, SC Tong, CO UNIV HONG KONG DEPT CIVIL & STRUCT ENGNPOKFULAM RDHONG KONGHONG KONG

In this paper, the estimation of time-dependent origin-destination (O-D) matrices for transit network based on observed passenger counts is given. The dynamic assignment framework is based on a schedule-based transit network model, which can help determine the time-dependent least cost paths between all O-D pairs, and for each of them the clock arrival times at the end nodes of all observed links (if any) in the transit network. An entropy-based approach is then employed to estimate the time-dependent O-D matrices based on the observed passenger counts at those observed links in the network. An efficient sparse algorithm is also proposed to solve the resulting mathematical programming problem. The estimation methodology is tested in a transit network from the Mass Transit Railway (MTR) system in Hong Kong which is one of the busiest railway systems in the world. Both cases with and without prior information of the O-D matrices are considered for this network. The predicted matrices are then compared with the true matrices obtained from a sophisticated electronic fare collection system of MTR. Good agreement between predicted and observed matrices are found. (C) 1998 Elsevier Science Ltd.

关键词： O-D matrix estimation schedule-based transit network dynamic transit assignment entropy maximisation sparse algorithm

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：