检索结果-内蒙古大学图书馆

2017 3rd Workshop on Advanced Research and technology in Industry Applications(WARTIA 2017)

作者： Xin Liu Rongbin Xu Yongliang Cheng Pengfei Zhang Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education School of Computer Science and Technology Anhui University Co-Innovation Center for Information Supply & Assurance Technology Anhui University

In recent years, along with the development of technologies for distributed computing such as big data and clouds workflow systems, efficiency of workflow scheduling has become very impotent. Hence sc

关键词：

来源：评论

学校读者我要写书评

暂无评论

Predicting lung nodule malignancies by combining deep convolutional neural network and handcrafted features

arXiv

引用

arXiv 2018年

作者： Li, Shulong Xu, Panpan Li, Bin Chen, Liyuan Zhou, Zhiguo Hao, Hongxia Duan, Yingying Folkert, Michael Ma, Jianhua Huang, Shiying Jiang, Steve Wang, Jing School of Biomedical Engineering Guangdong Provincial Key Laboratory of Medical Image Processing Southern Medical University Guangzhou510515 China Longgang District People's Hospital Shenzhen518172 China Department of Radiation Oncology University of Texas Southwestern Medical Center DallasTX75235 United States School of Computer Science and Technology Xidian University Xi'an710071 China School of Traditional Chinese Medicine Southern Medical University Guangzhou510515 China

To predict lung nodule malignancy with a high sensitivity and specificity, we propose a fusion algorithm that combines handcrafted features (HF) into the features learned at the output layer of a 3D deep convolutional neural network (CNN). First, we extracted twenty-nine handcrafted features, including nine intensity features, eight geometric features, and twelve texture features based on grey-level co-occurrence matrix (GLCM) averaged from five grey levels, four distances and thirteen directions. We then trained 3D CNNs modified from three 2D CNN architectures (AlexNet, VGG-16 Net and Multi-crop Net) to extract the CNN features learned at the output layer. For each 3D CNN, the CNN features combined with the 29 handcrafted features were used as the input for the support vector machine (SVM) coupled with the sequential forward feature selection (SFS) method to select the optimal feature subset and construct the classifiers. The fusion algorithm takes full advantage of the handcrafted features and the highest level CNN features learned at the output layer. It can overcome the disadvantage of the handcrafted features that may not fully reflect the unique characteristics of a particular lesion by combining the intrinsic CNN features. Meanwhile, it also alleviates the requirement of a large scale annotated dataset for the CNNs based on the complementary of handcrafted features. The patient cohort includes 431 malignant nodules and 795 benign nodules extracted from the LIDC/IDRI database. For each investigated CNN architecture, the proposed fusion algorithm achieved the highest AUC, accuracy, sensitivity, and specificity scores among all competitive classification models. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Variational neural discourse relation recognizer

Variational neural discourse relation recognizer

引用

2016 Conference on Empirical Methods in Natural Language processing, EMNLP 2016

作者： Zhang, Biao Xiong, Deyi Su, Jinsong Liu, Qun Ji, Rongrong Duan, Hong Zhang, Min Xiamen University Xiamen361005 China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou215006 China ADAPT Centre School of Computing Dublin City University Ireland Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China

ISBN: (纸本)9781945626258

Implicit discourse relation recognition is a crucial component for automatic discourse-level analysis and nature language understanding. Previous studies exploit discriminative models that are built on either powerful manual features or deep discourse representations. In this paper, instead, we explore generative models and propose a variational neural discourse relation recognizer. We refer to this model as VarNDRR. VarNDRR establishes a directed probabilistic model with a latent continuous variable that generates both a discourse and the relation between the two arguments of the discourse. In order to perform efficient inference and learning, we introduce neural discourse relation models to approximate the prior and posterior distributions of the latent variable, and employ these approximated distributions to optimize a reparameterized variational lower bound. This allows VarNDRR to be trained with standard stochastic gradient methods. Experiments on the benchmark data set show that VarNDRR can achieve comparable results against state-of-the-art baselines without using any manual features. © 2016 Association for Computational Linguistics

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

Transitioning conditional probability to discriminative classifier over inductive reasoning

Transitioning conditional probability to discriminative clas...

引用

International Conference on Awareness Science and technology (iCAST)

作者： Peng Mei Fuquan Zhang Lin Xu Hongyong Leng Lei Chen Guo Liu School of Software Beijing Institute of Technology Beijing China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China Innovative Information Industry Research Institute Fujian Normal University Fuzhou China

Overcome context-independent probabilities based reasoning, with decomposition of categories and predicates into features as non-stable predicates. With distinction between generative classifier and discriminative classifier, we purpose to use some discriminative classifiers such as dual-form perceptron and kernelized support vector machine to improve to result of reasoning process. With capability of dual-form perceptron and kernelized support vector machine, finding linear or non-linear decision boundary for similarity-like supporting predicate for reasoning process.

关键词： Cognition Classification algorithms Support vector machines Logistics Kernel Training Training data

来源：评论

学校读者我要写书评

暂无评论

Correction to: A whitelist and blacklist-based co-evolutionary strategy for defensing against multifarious trust attacks

引用

Applied Intelligence 2018年第7期48卷 1891-1891页

作者： Shujuan Ji Haiyan Ma Yongquan Liang Hofung Leung Chunjin Zhang Shandong Provincial Key Laboratory of Wisdom Mine Information Technology Shandong University of Science and Technology Qingdao China Shandong Provincial Key Laboratory of Novel Distributed Computer Software Technology Shandong Normal University Jinan China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong China Center of Network Shandong University of Science and Technology Qingdao China

The article A whitelist and blacklist-based co-evolutionary strategy for defensing against multifarious trust attacks, written by Shujuan Ji, Haiyan Ma, Yongquan Liang, Hofung Leung and Chunjin Zhang, was originally p...

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep learning models for EEG-based rapid serial visual presentation event classification

引用

Journal of information Hiding and Multimedia Signal processing 2018年第1期9卷 177-187页

作者： Zhang, Fu-Quan Mao, Zi-Jing Huang, Yu-Fei Xu, Lin Ding, Gang Yi Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China School of Software Beijing Institute of Technology Room A9-301 Juyuan Jinshan Jiyuan Fuzhou350008 China Department of Electronic Engineering University of Texas at San Antonio One UTSA Circle San Antonio Arrow Oaks 126 San AntonioTX78249 United States Innovative Information Industry Research Institute Fujian Normal University Fuqing Brunch of Fujian Normal University Campus County 1 Longjiang Road FuqingFuzhou350300 China School of Software Beijing Institute of Technology Room 611 Software Building 5 South Zhongguancun Street Haidian Beijing100081 China

We consider deep learning (DL) for event classification using electroencephalogram (EEG) measurements of brain activities. We proposed HDNN or hierarchical deep neural network, and CNN4EEG, a new convolution neural network (CNN). Both DL models are designed to improve the representation of spatial and local temporal correlations inherent in EEG data. These models were tested for image target prediction in a time-locked rapid serial visual presentation (RSVP) experiment. The performances were compared with the state-of-the-art RSVP classification algorithms including HDCA and XDAWN and with other popular machine learning algorithms. The results show that global spatial local temporal CNN (CNN4EEG) achieved a 13% improvement over the best competing non-DL algorithm and a 9% improvement over canonical CNN for image processing, and a 6% over deep neural network (DNN). Our results suggest that the unique design of temporal and spatial filters in CNN4EEG can improve the representation of EEG data, hence the prediction performance. © 2018, Ubiquitous International. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Research on face recognition method based on deep learning in natural environment

Research on face recognition method based on deep learning i...

引用

International Conference on Awareness Science and technology (iCAST)

作者： Jia Li Yan Longfei Zhang YuFeng Wu Penghui Guo Fuquan Zhang Shuo Tang Gangyi Ding Lin Xu Digital Performance and Simulation Key Laboratory Beijing Institute of Technology Beijing China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjing University Fuzhou China School of Software Beijing Institute of Technology Beijing China Innovative Information Industry Research Institute Fujian Normal University Fuzhou Fujian CN

In the present study, there are a number of recognition methods with high recognition accuracy, which are based on deep learning. However, these methods usually have a good effect in a restricted environment, but in the natural environment, the accuracy of face recognition has decreased significantly, especially in the case of occlusion, face recognition will appear inaccurate or unrecognized situation. Based on this, this paper presents a face recognition method based on the deep learning in the natural environment, hoping to achieve robust performance in the natural environment, especially in the case of occlusion. The main contribution of this paper is improving the method of multi-patches by using 4 areas' patches in the face. And in order to have a higher performance, we use a Joint Bayesian (JB) measure in face-verification. Finally, we trained the model by the set of CASIA-WebFace and test it in the Labeled Faces in the Wild (LFW).

关键词： Face Face recognition Feature extraction Training Databases Bayes methods Conferences

来源：评论

学校读者我要写书评

暂无评论

Trajectory data privacy protection based on differential privacy mechanism

引用

IOP Conference Series: Materials Science and Engineering 2018年第1期351卷

作者： Ke Gu Lihao Yang Yongzhi Liu Niandong Liao School of Computer and Communication Engineering Changsha University of Science and Technology Changsha 410114 China Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science and Technology Changsha 410114 China

In this paper, we propose a trajectory data privacy protection scheme based on differential privacy mechanism. In the proposed scheme, the algorithm first selects the protected points from the user's trajectory data; secondly, the algorithm forms the polygon according to the protected points and the adjacent and high frequent accessed points that are selected from the accessing point database, then the algorithm calculates the polygon centroids; finally, the noises are added to the polygon centroids by the differential privacy method, and the polygon centroids replace the protected points, and then the algorithm constructs and issues the new trajectory data. The experiments show that the running time of the proposed algorithms is fast, the privacy protection of the scheme is effective and the data usability of the scheme is higher.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysis of SET pulses propagation probabilities in sequential circuits

引用

IOP Conference Series: Materials Science and Engineering 2018年第1期351卷

作者： Shuo Cai Fei Yu Yiqun Yang School of Computer and Communication Engineering Changsha University of Science and Technology Changsha 410114 China Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science and Technology Changsha 410114 China

As the feature size of CMOS transistors scales down, single event transient (SET) has been an important consideration in designing logic circuits. Many researches have been done in analyzing the impact of SET. However, it is difficult to consider numerous factors. We present a new approach for analyzing the SET pulses propagation probabilities (SPPs). It considers all masking effects and uses SET pulses propagation probabilities matrices (SPPMs) to represent the SPPs in current cycle. Based on the matrix union operations, the SPPs in consecutive cycles can be calculated. Experimental results show that our approach is practicable and efficient.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A throughput aware with collision-free MAC for wireless LANs

引用

Science China(information Sciences) 2016年第2期59卷 240-242页

作者： Tingrui PEI Yafeng DENG Zhetao LI Gengming ZHU Gaofeng PAN Youngjune CHOI Hiroo SEKIYA College of Information Engineering Xiangtan University Key Laboratory of Intelligent Computing & Information Processing of Ministry of Education Xiangtan University School of Computer Science & Engineering Hunan University of Science and Technology School of Electronic and Information Engineering Southwest University Department of Information and Computer Engineering Ajou University Graduate School of Advanced Integration Science Chiba University

Dear editor,The Carrier Sense Multiple Access with Collision Avoidance(CSMA/CA)hybrid with the resource reservation approach from Time Division Multiple Address(TDMA)has been emerged as a promising method to solve collision problems in wireless LANs[1–6].In the hybrid method,a TDMA circle contains multiple slots for nodes to contend for the ***,it allows a

关键词： MAC CSCF free TDMA A throughput aware with collision-free MAC for wireless LANs

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：