检索结果-内蒙古大学图书馆

2017 international conference on progress in informatics and computing(PIC)

作者： Junhao Zhou Weibin Chen Guishen Peng Hong Xiao Hao Wang Zhigang Chen computer science Macau university of science and technology computer science Politecnico Di Milano computer science Guangdong University of Technology computer science Norwegian University of Science and Technology

ISBN: (纸本)9781538619797;9781538619780

As the convolutional neural network(CNN) algorithm is proved to be uncomplicated in the image preconditioning and relatively simple train the original image, it has become popular in image classification. Apart from the field of image classification, CNN has been widely used in many scientific area, especially in the field of pattern classification. In this paper, we use CNN for handwritten numeral recognition. The basic idea of our method is to use the multi-process to process the training samples in parallel, to exchange the training results and to get the final weight parameters. Compared with the conventional algorithm, the training time is greatly reduced, and the result can be obtained more quickly. Besides, the accuracy of the algorithm is proved to be almost the same as that of the conventional algorithm with sufficient training testing samples.. This significantly improves the efficiency of CNN in the hand written numeral recognition. Finally, we also implemented our proposed method with parallel acceleration optimization based on Many Integrated Core Architecture(MIC) architecture of Intel and GPU architecture of Nvidia.

关键词： Convolutional Neural Network Handwritten Recognition Parallel Multi-Process MIC GPU

来源：评论

学校读者我要写书评

暂无评论

Playing Games with Reinforcement Learning via Perceiving Orientation and Exploring Diversity 5

Playing Games with Reinforcement Learning via Perceiving Ori...

引用

2017 international conference on progress in informatics and computing(PIC)

作者： Dong Zhang Le Yang Haobin Shi Fangqing Mou Mengkai Hu School of Automation Northwestern Polytechnical University School of Computer Science Northwestern Polytechnical University School of Electronics and Information Northwestern Polytechnical University School of Electronics Engineering and Computer Science Peking University

ISBN: (纸本)9781538619797;9781538619780

The reinforcement learning can guide the agents to perform optimally under various complex *** reinforcement learning has brought breakthrough for many domains, they are constrained by two bottlenecks: extremely delayed reward signal and the trade-off between diversity and speed. In this paper, we propose a novel framework to alleviate those two bottlenecks. For the delayed reward, we introduce a new term, named the orientation perception term, to calculate the award for each state. For a series of actions successfully leading to the target state, this term takes a difference to each state and assigns award to all states on the pathway, rather than only offers award to the target state. This mechanism allows the learning algorithm to percept the orientation information by distinguishing different states. For the trade-off between diversity and speed, we integrate the curriculum learning into the exploration process and propose the diversity exploration scheme. In the beginning, this scheme is prone to exploring the unexecuted action so as to discover the optimal action *** the learning process carrying on, the scheme gradually relays more on the acquired knowledge and reduces the random probability. Such randomicity to certainty diversity exploration scheme guides the learning scheme to achieve proper balance between strategy diversity and convergency speed. We name the complete framework OpDe Reinforcement Learning and prove the algorithm convergence. Experiments on a standard platform demonstrate the effectiveness of the complete framework.

关键词： reinforcement learning delayed reward orientation perception diversity exploration curriculum learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Anonymous Attribute-Based Encryption with Access Policy Hidden for Cloud computing 5

Efficient Anonymous Attribute-Based Encryption with Access P...

引用

2017 international conference on progress in informatics and computing(PIC)

作者： Chanying Huang Kedong Yan Songjie Wei Gongxuan Zhang Dong Hoon Lee School of Computer Science and Engineering Nanjing University of Science and Technology Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing University of Science&Technology Graduate School of Information Security Korea University

ISBN: (纸本)9781538619797;9781538619780

Cloud computing is a revolutionary information technology paradigm, which provides users with unlimited, scalale, low-cost and convenient resource services, but when data is outsourced to a semi-trusted cloud server, challenging security issues such as user privacy, access control, etc. still urgently need to be addressed. Attribute-based encryption（ABE） scheme can provide sufficient data security and fine-grained access control for cloud data. However, the limitation of ABE is that user’s privacy would be disclosed with the access policy（structure） stored in clear text. Some works sacrificed the computing efficiency, key length or ciphertext size for privacy concerns. To overcome these problems, this paper proposes an efficient anonymous attributebased encryption scheme with access policy hidden. Using the idea of Boolean equivalent transformation, the proposed scheme can achieve fast encryption and protect the privacy for both data owner and legitimate access user. In addition, the proposed scheme can satisfy constant secret key length and reasonable size of ciphertext requirements. We conduct theoretical security analysis, and carry out experiments to prove that the proposed scheme has good performance in terms of computational, communication and storage overheads.

关键词： CP-ABE access policy hidden anonymity privacy efficiency

来源：评论

学校读者我要写书评

暂无评论

Multimodal deep learning network based hand ADLs tasks classification for prosthetics control 5

Multimodal deep learning network based hand ADLs tasks class...

引用

2017 international conference on progress in informatics and computing(PIC)

作者： Li Zhengyi Zhou Hui Yang Dandan Xie Shuiqin School of Biomedical Engineering South-Central University for Nationalities Key Laboratory of Cognitive Science South-Central University for Nationalities College of Electronics and Information South-Central University for Nationalities

ISBN: (纸本)9781538619797;9781538619780

Natural control methods based on surface electromyography(sEMG) and pattern recognization are promising for hand ***, the control robustness offered by scientific research is still not sufficient for many activities of daily living(ADLs). Difficulty results from limited s EMG signals susceptible to interference in clinical practice, it needs to synthesize hand movement and s EMG to improve classification robustness. Human hand ADLs are made of complex sequences of finger joint movements, and capturing the temporal dynamics is fundamental for successful hand prosthetics *** research suggests that recurrent neural networks(RNN) are suited to automate feature extraction for time series domains, and dynamic movement primitives(DMP) can provide representation of hand kinematic primitives. We design a multimodal deep framework for inter-subject ADLs recognization, which:(i)implements heterogeneous sensors fusion;(ii) does not require hand-crafted features;and(iii) contains the dynamics model of the hand ADLs task control. We evaluate our framework on Ninapro datasets. Results show that our framework outperforms competing deep networks with single modal and some of the previous reported results.

关键词： human activity recognization sEMG multimodal deep learning dynamic movement primitives

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation for Tujia Brocade Cultural Coordinate Panorama Display System Based on Touch Screen 5

Design and Implementation for Tujia Brocade Cultural Coordin...

引用

2017 international conference on progress in informatics and computing(PIC)

作者： Zhao Gang Di Bingbing Zhu Wenjuan Li Yaxu He Hui Zan Hui School of Educational Information Technology Central China Normal University National Engineering Research Center for E-Learning Central China Normal University

ISBN: (纸本)9781538619797;9781538619780

To get rid of durance of distribution environment on Tujia Brocade dissemination and provide a more comprehensive and immersive learning environment of Tujia brocade, this paper designs a system on Tujia Brocade cultural coordinate panorama display based on touch screen, and establishes panoramic scenes which takes the birthplace of Tujia brocade named Lao Chehe village as the cultural coordinates of Tujia brocade. What’s more, the system has ten panoramic scenes, which completes following functions: viewpoint control, scenes shifting, hotspot information, touch operation and voice explanation. Users can have real-time interaction with ecological panorama of Tujia Brocade Laoche village in the scene, this will contribute to the digital protection and social dissemination of Tujia brocade.

关键词： Cultural Coordinate Tujia Brocade Panorama Display Touch Screen Interaction

来源：评论

学校读者我要写书评

暂无评论

Developing an EC Computer Policy, 1965-1974

引用

ieee ANNALS OF THE HISTORY OF computing 2010年第1期32卷 44-59页

作者： Van Laer, Arthe Univ Louvain Louvain Belgium Univ Louvain Namur Belgium

In the late 1960s, the European Community (EC) Commission tried to develop a common industrial policy to help Europe establish a competitive position in the informatics sector. Before the middle of the 1970s, only a few of its projects were realized, and the most important were abandoned. The lack of progress appears fundamentally due to the member states' reluctance to relinquish control of this key sector.

关键词： INDUSTRIAL policy international competition COMMITTEES COMPUTER industry ECONOMIC sectors TECHNOLOGY -- History 20TH century

来源：评论

学校读者我要写书评

暂无评论

A Heuristic Task Dispatching Algorithm in the Clouds 2

A Heuristic Task Dispatching Algorithm in the Clouds

引用

2nd ieee international conference on progress in informatics and computing (PIC)

作者： Luo, Fei Yi, Jianjun E China Univ Sci & Technol Sch Informat & Engn Shanghai 200237 Peoples R China PowerLeader Sci & Technol Grp Co Ltd Shenzhen Peoples R China E China Univ Sci & Technol Sch Mech & Power Engn Shanghai 200237 Peoples R China

ISBN: (纸本)9781479920303

Cloud computing is becoming a popular solution for storing data and executing applications, where task dispatching in the scheduling policy is significant to the overall performance in the Cloud systems. To minimize the makespan of the application consisting of many independent tasks, a heuristic task dispatching algorithm is proposed in this paper. Therein, the task is dispatched to the virtual machine with the least relative workload. Then combined with the local schedule strategy of the virtual machine, the performance of the task dispatching algorithm is analyzed and simulated in CloudSim, which indicate that the proposed algorithm can improve the performance of the clouds.

关键词： cloud computing task dispatching makespan least workload

来源：评论

学校读者我要写书评

暂无评论

Mineral Identification and Geological Mapping Using Near-Infrared Spectroscopy Analysis 5

Mineral Identification and Geological Mapping Using Near-Inf...

引用

2017 international conference on progress in informatics and computing(PIC)

作者： Xiu Liancun Zheng Zhizhong Chen Chunxia Gao Yang Nanjing Center China Geological Survey Key Laboratory of R&D of Spectrum Detection Geological Instrument China Geological Survey Jiangsu Provincial Key Laboratory of Spectral Imaging and Intelligent Sensing

ISBN: (纸本)9781538619797;9781538619780

In recent years, the near-infrared spectroscopy measurement technology in China has made considerable progress;it has been widely used in the fields of agriculture, chemistry, geology, and medicine measurement. The nearinfrared spectroscopy is very sensitive to the characteristics of CH(methyl, a methylene group, a methoxy group, a carboxyl group, an aryl group, etc.), hydroxy O-H, mercapto S-H, and amino N-H. So, it can distinguish the crystallinity of single mineral(clay minerals, chlorite, serpentine, etc.), containing hydroxy silicate minerals(epidote, amphibole, etc.), sulfate minerals(alunite, pyritepotassium alum, gypsum, etc.), and carbonate minerals(calcite, dolomite, etc.) in the layered silicate. The character of near-infrared spectroscopy is one of the important guarantees for the instrument development of the small portable near-infrared mineral analyzer, and for its fast, accurate identification of rock samples. In this paper, we focus on the near-infrared spectral characteristics, identification method, and quantitative analysis method for the low-temperature alteration minerals;at the same time, a portable near infrared spectrometer and its principle were presented. In the experiment, spectral parameters were acquired from the characteristic spectra of altered minerals, and the relationship between altered minerals and ore-forming were established. The measured spectral data from the drilling rock cores in Zijinshan Mine in Fujian province was used as an example to illustrate the credibility of the proposed method.

关键词： Near-Infrared Spectrum Altered Mineral Qualitative Analysis Quantitative Analysis Alteration Mineral Mapping

来源：评论

学校读者我要写书评

暂无评论

Detection of coordinated attacks using alert correlation model

Detection of coordinated attacks using alert correlation mod...

引用

2010 1st ieee international conference on progress in informatics and computing, PIC 2010

作者： Alserhani, Faeiz Akhlaq, Monis Awan, Irfan U. Cullen, Andrea J. Informatics Research Institute University of Bradford BD7 1DP United Kingdom

ISBN: (纸本)9781424467860

Alerts correlation techniques have been widely used to provide intelligent and stateful detection methodologies. This is to understand attack steps and predict the expected sequence of events. However, most of the proposed systems are based on rule -based mechanisms which are tedious and error prone. Other methods are based on statistical modeling;these are unable to identify causal relationships between the events. In this paper, an improved "requires/provides" model is presented which established a cooperation between statistical and knowledge-based model, to achieve higher detection rate with the minimal false positives. A knowledge-based model with vulnerability and extensional conditions provide manageable and meaningful attack graphs. The proposed model has been implemented in real-time and has successfully generated security events on establishing a correlation between attack signatures. The system has been evaluated to detect one of the most serious multi-stage attacks in cyber crime - Botnet. Zeus Botnet is analyzed within the realm of simulated malicious activities normally used by cyber criminals. ©2010 ieee.

关键词： Botnet

来源：评论

学校读者我要写书评

暂无评论

Efficient Pose Machine Based on Parameter-Sensitive Hashing 5

Efficient Pose Machine Based on Parameter-Sensitive Hashing

引用

2017 international conference on progress in informatics and computing(PIC)

作者： Shangchi Lin Bowen Liu Yang Wen Anum Masood Bin Sheng Ping Li Xin Liu Haoyang Yu Weiyao Lin Department of Computer Science and Engineering Shanghai Jiao Tong University Department of Mathematics and Information Technology The Education University of Hong Kong Faculty of Information Technology Macau University of Science and Technology Shenzhen Tencent Computer System Co.Ltd. Department of Electronic Engineering Shanghai Jiao Tong University

ISBN: (纸本)9781538619797;9781538619780

In this paper, we propose an efficient pose machine using Parameter-Sensitive Hashing(PSH) techniques. Based on the original pose machine, which is a sequential prediction framework, we employ the Convolutional Neural Network(CNN)to extract features. To handle the high dimensional feature vectors and conduct similarity search efficiently, we use the Parameter-Sensitive Hashing Function(PSHF) to map the feature vectors into binary values. The property of the PSHF ensures that the collisions happen when two vectors are near to each other and the search can be completed in a fractional power time. We apply our approach to the popular datasets including LSP and FLIC and make a comparison with previous methods based on a criterion of strict Percentage of Correct Parts(PCP).Experimental results reflect that our approach outperforms previous methods in accuracy.

关键词： Human pose estimation convolutional neural network parameter-sensitive hashing example-based method parameter estimation

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：