检索结果-内蒙古大学图书馆

2nd International Conference on Deep Learning Technologies, ICDLT 2018

作者： Wen, Yang Xu, An Liu, Wei Chen, Leiting Key Laboratory of Digital Media Technology of Sichuan Province Chengdu China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Dongguan Data Science Software Technology Co. Ltd Dongguan China Chengdu Vocational and Technical College of Industry Chengdu China Institute of Electronic and Information Engineering UESTC in Guangdong Dongguan China

ISBN: (纸本)9781450364737

Recurrent neural network (RNN) is a popular deep learning model for sentiment classification. Most RNN models benefit from the power of the depth of the deep learning network. However, training a sufficiently deep RNN using one word-embedding vector has a problem of feature reuse. In addition, deeper neural networks are more difficult to train. To overcome these problems, in this paper, we describe a sentiment classification model that combines a wide word embedding network architecture and a residual RNN. Firstly, more than one word-embedding vectors are pre-trained to obtain a larger feature space;Secondly, extend the RNN to be a deeper architecture, then employ a residual learning to ease the deep training of networks. Finally, experimental evaluations are conducted on two benchmarks, the results of the proposed networks demonstrate a good applicability for the sentiment classification problem. © 2018 ACM.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

A Multiple Layer Sercurity Architecture for Internet of Things into MVC Design

A Multiple Layer Sercurity Architecture for Internet of Thin...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Hongbo Chen Hongjun Dai Meikang Qiu School of Software Shandong University Jinan P.R. China College of Computer Science and Software Engineering Shenzhen University Guangdong China

Secure Layered architecture(SLA) has been become a widely used Architecture model. Each layer represents a kind of function. In the current process of software development, the most SLA is based on MVC: Model, View and Controller. Model is the layer that is used to communicate with database and provides the data for controller. Controller is the logical layer, it is responsible for handling the data provided from model and serve the layer of view. And the View is used to display the data. The Three tier architecture(TTA) is practical in most development. But In some project, whose business is more complex and the number of requests is bigger, the TTA has a little bad performance. For better development and better performance, The more secure multiple layer architecture(MMLA) is put forward. Besides the MVC, The MMLA splits the layer of model and controller. Based on the business logic and the service request, they are split into multiple layers for different business and different layer is put into the different server. This kind of layers can not only reducing coupling with modules and also improve the extensibility of the system. The way that the Different layer is in the different server can greatly improved the data security. Experiments show that The performance, the expansibility and the security can be greatly improved but also obtaining the satisfactory service with our proposed MMLA.

关键词： Servers computer architecture Business Databases software Computational modeling Data models

来源：评论

学校读者我要写书评

暂无评论

A regularization approach for instance-based superset label learning

arXiv

引用

arXiv 2019年

作者： Gong, Chen Liu, Tongliang Tang, Yuanyan Yang, Jian Yang, Jie Tao, Dacheng School of Computer Science and Engineering Nanjing University of Science and Technology Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University School of Software Faculty of Engineering and Information Technology University of Technology Sydney UltimoNSW2007 Australia Faculty of Science and Technology University of Macau Macau999078 China College of Computer Science Chongqing University Chongqing400000 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China School of Information Technologies Faculty of Engineering and Information Technologies University of Sydney J12/318 Cleveland St DarlingtonNSW2008 Australia

Different from the traditional supervised learning in which each training example has only one explicit label, Superset Label Learning (SLL) refers to the problem that a training example can be associated with a set of candidate labels, and only one of them is correct. Existing SLL methods are either regularization-based or instance-based, and the latter of which has achieved state-of-the-art performance. This is because the latest instance-based methods contain an explicit disambiguation operation that accurately picks up the groundtruth label of each training example from its ambiguous candidate labels. However, such disambiguation operation does not fully consider the mutually exclusive relationship among different candidate labels, so the disambiguated labels are usually generated in a nondiscriminative way, which is unfavorable for the instance-based methods to obtain satisfactory performance. To address this defect, we develop a novel Regularization approach for Instancebased Superset Label (RegISL) learning so that our instancebased method also inherits the good discriminative ability possessed by the regularization scheme. Specifically, we employ a graph to represent the training set, and require the examples that are adjacent on the graph to obtain similar labels. More importantly, a discrimination term is proposed to enlarge the gap of values between possible labels and unlikely labels for every training example. As a result, the intrinsic constraints among different candidate labels are deployed, and the disambiguated labels generated by RegISL are more discriminative and accurate than those output by existing instance-based algorithms. The experimental results on various tasks convincingly demonstrate the superiority of our RegISL to other typical SLL methods in terms of both training accuracy and test accuracy. Copyright © 2019, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Segmentation Guided HEp-2 Cell Classification with Adversarial Networks

Segmentation Guided HEp-2 Cell Classification with Adversari...

引用

Computing, Communications and Applications Conference (ComComAp)

作者： Hai Xie Yejun He Haijun Lei Jong Yih Kuo Baiying Lei Guangdong Engineering Research Center of Base Station Antennas and Propagation Shenzhen Key Lab of Antennas and Propagation College of Electronics and Information Engineering Shenzhen University China Guangdong Province Key Laboratory of Popular High-performance Computers School of Computer and Software Engineering Shenzhen University Computer Science and Information Engineering National Taipei University of Technology Taiwan China National-Regional Key Technology Engineering Laboratory for Medical Ultrasound Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging School of Biomedical Engineering Health Science Center Shenzhen University China

ISBN: (数字)9781728119731

ISBN: (纸本)9781728119748

The analysis of indirect immuno fluorescence (IIF) on human epithelial type 2 (HEp-2) cells is of paramount importance for the autoimmune diseases diagnosis. Essentially, accurate segmentation masks can generate rich boundary information, which is beneficial for improving the performance of the classification task For this reason, this paper proposes a novel segmentation guided HEp-2 cell classification method via generative adversarial networks (GANs), which employs the GANs as the segmentor to generate accurate masks for the subsequent classification task. Specifically, the proposed network architecture consists of three modules (i.e., the generator, discriminator and classifier). The first two modules constitute GANs model, which is trained to obtain better segmentation results via playing a min-max game. The segmentation masks and the corresponding original images are fed to the third module together to identify the category of the trained cell. Furthermore, the Xception and ResNet-50 model are used as the backbone of the segmentation and classification network, respectively. Besides, an improved classification loss function via Gaussian Mixture (GM) is proposed to optimize the classification network The proposed architecture can learn rich boundary information and well represent the class label of HEp2 cell images. Experimental results on the HEp-2 International Conference on Pattern Recognition (ICPR) 2016 task1 dataset demonstrate our proposed model achieves quite promising performance.

关键词： Image segmentation computer architecture Task analysis Microprocessors Gallium nitride Feature extraction Generators

来源：评论

学校读者我要写书评

暂无评论

Large Scale UAVs Collaborative Formation Simulation Based on Starlings’ Flight Mechanism

引用

Asia Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint Conference on Web and Big Data, APWeb-WAIM 2018

作者： Xie, Rong Gu, Cunfeng Liu, Li Chen, Lifei Zhang, Linyu School of Computer Science Wuhan University Wuhan430072 China Shanghai Electro-Mechanical Engineering Institute Shanghai200000 China School of Big Data & Software Engineering Chongqing University Chongqing401331 China College of Mathematics and Informatics Fujian Normal University Fujian350117 China

ISBN: (纸本)9783030012977

Combining the latest biological results of behavior of intensive flight of starlings, this paper presents topological formation structure and an improved particle swarm algorithm based on the flight mechanism of starlings and its application to the formation of UAV cluster. It also proposes an approach of controling formation behavior of UAVs based on the improved artificial potential fields method. Through simulation experiments, the comparative results are given for verifying the efficiency of formation missions of our methods, as well as simulation of cluster behavior of aggregation and dispersion. The results provide technical assistance for simulation of autonomous collaborative formation of large-scale UAV cluster. © 2018, Springer Nature Switzerland AG.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

COMPLEXITY CONTROL FOR HEVC INTER CODING BASED ON TWO-LEVEL COMPLEXITY ALLOCATION AND MODE SORTING

COMPLEXITY CONTROL FOR HEVC INTER CODING BASED ON TWO-LEVEL ...

引用

IEEE International Conference on Image Processing

作者： Jia Zhang Sam Kwong Tiesong Zhao Xu Wang Shiqi Wang Department of Computer Science City University of Hong Kong Hong Kong College of Physics and Information Engineering Fuzhou University Fuzhou China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

High coding complexity is an obstruction when promoting the HEVC standard. In this paper, we propose a complexity control scheme for HEVC, which improves our previous work by employing a finer-grained complexity allocation scheme and mode sorting. In CTU-level complexity allocation, the time budget is allocated to each CTU proportionally to its estimated complexity. Then, the time budget for a CTU is further allocated to each CTU quadtree depth according to its probability of being the dominant depth. At last, a subset of modes are selected to reach the target complexity based on mode sorting. Compared with our previous work of which the least supported complexity ratio is 40%, the proposed scheme further reduces the lower bound of the ratio range to 20%.

关键词： Complexity theory Encoding Resource management Erbium Standards Training Sorting

来源：评论

学校读者我要写书评

暂无评论

A Group Construction Algorithm Based on Density and Closeness Clustering in Mobile Communication Networks

A Group Construction Algorithm Based on Density and Closenes...

引用

International Conference on Mobile Ad-hoc and Sensor Networks, MSN

作者： Jie Li Yue Guo Tengfei Li Ruiyun Yu Xingwei Wang School of Computer Science and Engineering Northeastern University Shenyang China Software College Northeastern University Shenyang China

ISBN: (纸本)9781728105499;9781728105482

with the strong impact of OTT (Over The Top) business in the mobile Internet era, operators urgently need to discover the user value information from massive data to help them provide personalized accurate services and expand business customer services. The construction of social user groups based on mobile communication data can help operators to accurately analyze customer social structures, thus promoting quality service and improving marketing quality. In this paper, we design a set of social group construction algorithm based on user behavior characteristics excavated from massive user data in mobile communication network. Due to the huge volume of mobile communication data sets, a parallel design based on MapReduce is exploited. The experimental results show that the ADBLINKw algorithm performs well on the efficiency and community detection quality.

关键词： Correlation Mobile communication Clustering algorithms Over-the-top media services Business Time measurement Entropy

来源：评论

学校读者我要写书评

暂无评论

Privacy Protection with Dynamic Pseudonym-Based Multiple Mix-Zones Over Road Networks

引用

China Communications 2017年第4期14卷 89-100页

作者： Qasim Ali Arain Zhongliang Deng Imran memon Asma Zubedi Jichao Jiao Aisha Ashraf Muhammad Saad Khan Beijing University of posts and Telecommunication Beijing China College of Computer Science Zhejiang University Hangzhou 310027 China Department of Software Engineering Mehran UET Jamshoro

In this research we proposed a strategy for location privacy protection which addresses the issues related with existing location privacy protection techniques. Mix-Zones and pseudonyms are considered as the basic building blocks for location privacy; however, continuously changing pseudonyms process at multiple locations can enhance user privacy. It has been revealed that changing pseudonym at improper time and location may threat to user's privacy. Moreover, certain methods related to pseudonym change have been proposed to attain desirable location privacy and most of these solutions are based upon velocity, GPS position and direction of angle. We analyzed existing methods related to location privacy with mix zones, such as RPCLP, EPCS and MODP, where it has been observed that these methods are not adequate to attain desired level of location privacy and suffered from large number of pseudonym changes. By analyzing limitations of existing methods, we proposed Dynamic Pseudonym based multiple mix zone(DPMM) technique, which ensures highest level of accuracy and privacy. We simulate our data by using SUMO application and analysis results has revealed that DPMM outperformed existing pseudonym change techniques and achieved better results in terms of acquiring high privacy with small number of pseudonym change.

关键词： road network multiple mix-zones location privacy

来源：评论

学校读者我要写书评

暂无评论

PRMT: Predicting Risk Factor of Obesity among Middle-Aged People Using Data Mining Techniques

引用

Procedia computer science 2018年 132卷 1068-1076页

作者： Rifat Hossain S.M. Hasan Mahmud Md Altab Hossin Sheak Rashed Haider Noori Hosney Jahan Departmentof Software Engineering Daffodil International University Dhaka-1207 Bangladesh Departmentof Management Science and Engineering University of Electronic Science and Technology of China Chengdu-611731 China Departmentof Computer Science and Engineering Daffodil International University Dhaka-1207 Bangladesh College of Computer Science Sichuan University Chengdu-610064 China

Obesity is an anatomical condition characterized by an extreme growth of body fat. The obesity rate is increasing gradually; from prior research, obesity is the serious health disease in the globe. This study collected 259 data from specified urban and rural areas regarding different risk factor of our daily activities. The purpose of the study is to simulate the risk factor by using statistical tools (SPSS), which helpsto predict the major risk factor of obesity by testing the class level attribute according to cross-sectional study with other attributes. By analyzing the P-value (p<0.05), the outcome of this process Age (0.002), Height (0.002), Weight 0.000), Healthy lifestyle (0.000), Marital status (0.001), BMI (0.000), Economic (0.028), Sleep per day (0.011) has a significant relationship with our obesity class. This study proposed a risk mining technique (PRMT)that foretells a model to analyze the risk factor of obesity class using different data mining classifiers, using WEKA to estimate the accuracy and error measurement. The outcome of this process Naïve Bayes is the best classifier for the 10-fold cross-validation study. The proposed model collaborates to predict human factor who want to control and mitigate this major cardiovascular disease.

关键词： obesity riskmining datamining cardiovascular disease classification

来源：评论

学校读者我要写书评

暂无评论

Construction and optimization of a file distribution model for all-to-all comparison of big dataset

引用

Ingenierie des Systemes d'Information 2019年第3期24卷 337-342页

作者： Li, Leixiao Gao, Jing Wang, Hui Deng, Dan Lin, Hao College of Data Science and Application Inner Mongolia University of Technology Hohhot010080 China Inner Mongolia Autonomous Region Engineering and Technology Research Center of Big Data Based Software Service Hohhot010080 China College of Computer and Information Engineering Inner Mongolia Agricultural University Hohhot010018 China Inner Mongolia Autonomous Region Key Laboratory of big data research and application for agriculture and animal husbandry Hohhot010018 China

This paper probes into the all-to-all comparison of large dataset, and gives a formal mathematical description of the problem. Then, a multi-objective file distribution model was constructed based on the LP, aiming to localize the data, balance node storage and loads, minimize the storage occupation, and control the occupied storage within the storage limit of each node. To save storage space, the established model was further optimized, and the file distribution algorithm was designed for the distributed environment. Experimental results show that our model and algorithm successfully balanced the storage occupation and loads between computing nodes, and minimized the occupation of node storage. © 2019 International Information and engineering Technology Association. All rights reserved.

关键词： Linear programming

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：