检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Ma, Xingjun Niu, Yuhao Gu, Lin Wang, Yisen Zhao, Yitian Bailey, James Lu, Feng State Key Laboratory of VR Technology and Systems School of CSE Beihang University Beijing China School of Computing and Information Systems The University of Melbourne ParkvilleVIC3010 Australia Beijing Advanced Innovation Center for Big Data-Based Precision Medicine Beihang University Beijing China National Institute of Informatics Tokyo101-8430 Japan Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Cixi Instuitue of Biomedical Engineering Ningbo Institute of Industrial Technology Chinese Academy of Sciences Ningbo China

Deep neural networks (DNNs) have become popular for medical image analysis tasks like cancer diagnosis and lesion detection. However, a recent study demonstrates that medical deep learning systems can be compromised by carefully-engineered adversarial examples/attacks with small imperceptible perturbations. This raises safety concerns about the deployment of these systems in clinical settings. In this paper, we provide a deeper understanding of adversarial examples in the context of medical images. We find that medical DNN models can be more vulnerable to adversarial attacks compared to models for natural images, according to two different viewpoints. Surprisingly, we also find that medical adversarial attacks can be easily detected, i.e., simple detectors can achieve over 98% detection AUC against state-of-the-art attacks, due to fundamental feature differences compared to normal examples. We believe these findings may be a useful basis to approach the design of more explainable and secure medical deep learning systems. Copyright © 2019, 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

Hierarchical taxonomy-aware and attentional graph capsule RCNNs for large-scale multi-label text classification

arXiv

引用

arXiv 2019年

作者： Peng, Hao Li, Jianxin Gong, Qiran Wang, Senzhang He, Lifang Li, Bo Wang, Lihong Yu, Philip S. Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100083 State Key Laboratory of Software Development Environment Beihang University Beijing100083 China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing211106 China Department of Biostatistics and Epidemiology University of Pennsylvania PhiladelphiaPA19104 United States National Computer Network Emergency Response Technical Team Coordination Center of China Beijing100029 China Department of Computer Science University of Illinois at Chicago ChicagoIL60607 United States

CNNs, RNNs, GCNs, and CapsNets have shown significant insights in representation learning and are widely used in various text mining tasks such as large-scale multi-label text classification. However, most existing deep models for multi-label text classification consider either the non-consecutive and long-distance semantics or the sequential semantics, but how to consider them both coherently is less studied. In addition, most existing methods treat output labels as independent medoids, but ignore the hierarchical relations among them, leading to useful semantic information loss. In this paper, we propose a novel hierarchical taxonomy-aware and attentional graph capsule recurrent CNNs framework for large-scale multi-label text classification. Specifically, we first propose to model each document as a word order preserved graph-of-words and normalize it as a corresponding words-matrix representation which preserves both the non-consecutive, long-distance and local sequential semantics. Then the words-matrix is input to the proposed attentional graph capsule recurrent CNNs for more effectively learning the semantic features. To leverage the hierarchical relations among the class labels, we propose a hierarchical taxonomy embedding method to learn their representations, and define a novel weighted margin loss by incorporating the label representation similarity. Extensive evaluations on three datasets show that our model significantly improves the performance of large-scale multi-label text classification by comparing with state-of-the-art approaches. Copyright © 2019, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Feature extraction and evaluation of electricity load data with high precision

Feature extraction and evaluation of electricity load data w...

引用

IEEE International Conference on Cloud computing and big data Analysis (ICCCBDA)

作者： Jiangqi Chen Ting Zhao Yang Yang Di Zhang Advanced Computing and Big Data Technology Laboratory of SGCC Global Energy Interconnection Research Institute Beijing China School of Control and Computer Engineering North China Electric Power University Beijing China

ISBN: (纸本)9781509045006

This paper summarizes the characteristics of the electricity load data collected every 15 minutes of power users. The single-day load data of single power user is taken as a 96-length vector, and the single-day data of n users is taken as a 96-column set. Single-user monthly data and annual data are described as a 30 (31) × 96 matrix and a 365 (366) × 96 matrix respectively. By comparing the wavelet transforms of multiple wavelet basis functions, the Daubechies 4 wavelet basis function is chosen as the wavelet transform basis function of the electricity load data according to the Shannon entropy of the obtained wavelet coefficients. The difference between the inverse wavelet transformed data and the original data is compared under various characteristic wavelet coefficients. Besides, the number of the characteristic wavelet coefficients and the error of the wavelet transform are determined. The results show that there is a high redundancy in the original power load data, and the storage space can be greatly compressed by wavelet transform to achieve feature extraction and data desensitization. Therefore, the feature extraction technology of power load data based on wavelet transform in this paper has potential application value and popularization value, and can produce high economic efficiency.

关键词： Wavelet transforms Load modeling Analytical models data models Entropy Monitoring

来源：评论

学校读者我要写书评

暂无评论

Stability Analysis and Hopf Bifurcation Research for DNA Strand Displacement with Time Delay

Stability Analysis and Hopf Bifurcation Research for DNA Str...

引用

Symposia and Workshops on Ubiquitous, Autonomic and Trusted computing, UIC-ATC

作者： Yanhong Liu Hui Lv Changjun Zhou Zhixiang Yin Xianwen Fang Zhonglong Zheng Qiang Zhang Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Dalian University Dalian China School of Mathematics and Big Data Anhui University of Science and Technology Huaian China College of Mathematics Zhejiang Normal University Jinhua China Department of Computer Science and Technology Dalian University of Technology Dalian China

ISBN: (纸本)9781538693810;9781538693803

In this paper, a nonlinear system with time delay mode for DNA strand displacement based on toehold exchange firstly is proposed. The boundedness of all the state variables of the DNA strand displacement system is proved. After that, local stability analysis is performed around the positive equilibrium point to obtain a necessary and sufficient condition for local stability, which depend on the coefficients of the characteristic equation corresponding to linearization of the system. In addition, the existence of the Hopf bifurcation is analyzed, which shows that the time delay parameter will guarantee that the system is stable within a certain range. However, Hopf bifurcation and chaos occur when the time delay parameter increases continuously and even exceeds the critical value. At last, numerical simulations have verified the correctness and validity of the DNA strand displacement studies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fault Range Analysis of Information and Communications Assets in Power Grid: A Graph data Perspective

Fault Range Analysis of Information and Communications Asset...

引用

2017 International Conference on Applied Mathematics, Modelling and Statistics Application（AMMSA2017）

作者： Bo Chai Siyan Liu Jiangpeng Dai Ting Zhao Aihua Zhou Kunlun Gao Advanced Computing and Big Data Laboratory Global Energy Interconnection Research Institute State Grid Corporation of China

In this paper, information and communication assets in the power grid are modeled as graph data. A graph database, Neo4j, is chosen to capturing the connections that could help to analyze fault ranges. Based on breadth-first search, recursion terminations are designed to obtain the fault range from the failed nodes. Two cases are given in the paper, and more cases will be further considered in the future work. In final, we provide the analysis results and shows the advantage of graph databases.

关键词： graph data fault range analysis Neo4j breadth-first search

来源：评论

学校读者我要写书评

暂无评论

Research on Loop Detection of Power Grid Equipment Based on Graph database

Research on Loop Detection of Power Grid Equipment Based on ...

引用

2017 2nd International Conference on Automation, Mechanical and Electrical Engineering (AMEE2017)

作者： Hongbin Qiu Aihua Zhou Kunlun Gao Jiangpeng Dai Bo Chai Bo Zhang Advanced Computing and Big Data Laboratory Global Energy Interconnection Research Institute State Grid Corporation of China

this paper presents a method of power grid loop detection based on graph database. The topology concept is introduced to extract the network relationship from the power grid equipment. The devices and power lines in the power grid correspond to the vertices in the topological graph, and the connection relation between the grid devices corresponds to the edges in the topological graph. The topological graph data model is generated by establishing the edges of connected vertices and stored in graph database. The loop detection of power grid equipment is divided into ordinary topological loop detection and multi-power loop detection, using the degree reduce algorithm and union-find sets to achieve the ordinary loop detection, and using the breadth first search algorithm to achieve the multipower loop detection. For large-scale power grid, the efficiency of power grid loop detection based on graph database can be 10 times higher than relational database.

关键词： topological graph graph database loop detection power grid

来源：评论

学校读者我要写书评

暂无评论

A Blockchain-Based Collocation Storage Architecture for data Security Process Platform of WSN

A Blockchain-Based Collocation Storage Architecture for Data...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Libo Feng Hui Zhang Liqi Lou Yong Chen State Key Laboratory of Software Development Environment Beihang University Beijing P.R. China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing P.R. China State Key Laboratory of Information Photonics and Optical Communications Beijing University of Posts and Telecommunications Beijing P.R. China

ISBN: (纸本)9781538614839

Wireless Sensor Networks (WSN) interconnects thousands of sensor nodes to support the services of Internet of Things (loT). However, data collected from sensor nodes may be tempered, forged and divulged. Traditional WSN data process platform handle the data centralized in terminal devices which is vulnerable to attacks and reduce the security of the system. Blockchain is a kind of distributed databases. It has been successfully applied in finance, securities, digital currency and other fields. We first propose a blockchain-based distributed collocation storage architecture for data security process platform of WSN with consensus protocol and asymmetric signature scheme. The security and efficiency are verified on the simulation to enable blockchain as a good solution.

关键词： Wireless sensor networks Encryption Distributed databases Public key Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Inland port location planning based on user equilibrium 17

Inland port location planning based on user equilibrium

引用

17th COTA International Conference of Transportation Professionals: Transportation Reform and Change - Equity, Inclusiveness, Sharing, and Innovation, CICTP 2017

作者： Wei, Jingyi Tian, Daxin Rong, Hui Guo, Peng Wang, Wenyang Gong, Jinfeng Wang, Yunpeng Liu, He Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang Univ. Beijing100191 China Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control School of Transportation Science and Engineering Beihang Univ. Beijing100191 China Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies Nanjing210096 China Automotive Engineering Research Institute China Automotive Technology and Research Center Tianjin300300 China Quartermaster Equipment Institute of the General Logistics Dept. Of CPLA Beijing100010 China

ISBN: (数字)9780784480915

ISBN: (纸本)9780784480915

With stable development of container transportation in shipping industry, the transit shipment from road to railway of inland ports plays a significant role in multimodal transport. This paper presents the method of inland port location planning based on user equilibrium. In the study, the virtual connection simulating the process of transfer in inland ports is conducted to measure the fitness of inland port location through the cargo volume on virtual connection. At last, the methodology was applied into practical experiment with the results showing that the method can locate the suit inland port location. © ASCE.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Forecasting transportation network speed using deep capsule networks with nested LSTM models

arXiv

引用

arXiv 2018年

作者： Ma, Xiaolei Li, Yi Cui, Zhiyong Wang, Yinhai School of Transportation Science and Engineering Beijing Key Laboratory for Cooperative Vehicle Infrastructure System and Safety Control Beihang University Beijing100191 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China Department of Civil and Environmental Engineering University of Washington Seattle98195 United States

Accurate and reliable traffic forecasting for complicated transportation networks is of vital importance to modern transportation management. The complicated spatial dependencies of roadway links and the dynamic temporal patterns of traffic states make it particularly challenging. To address these challenges, we propose a new capsule network (CapsNet) to extract the spatial features of traffic networks and utilize a nested LSTM (NLSTM) structure to capture the hierarchical temporal dependencies in traffic sequence data. A framework for network-level traffic forecasting is also proposed by sequentially connecting CapsNet and NLSTM. On the basis of literature review, our study is the first to adopt CapsNet and NLSTM in the field of traffic forecasting. An experiment on a Beijing transportation network with 278 links shows that the proposed framework with the capability of capturing complicated spatiotemporal traffic patterns outperforms multiple state-of-the-art traffic forecasting baseline models. The superiority and feasibility of CapsNet and NLSTM are also demonstrated, respectively, by visualizing and quantitatively evaluating the experimental results. Copyright © 2018, The Authors. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Low-resolution face recognition in the wild via selective knowledge distillation

arXiv

引用

arXiv 2018年

作者： Ge, Shiming Zhao, Shengwei Li, Chenyu Li, Jia Institute of Information Engineering Chinese Academy of Sciences Beijing100095 China Institute of Information Engineering Chinese Academy of Sciences School of Cyber Security at University of Chinese Academy of Sciences China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China

Typically, the deployment of face recognition models in the wild needs to identify low-resolution faces with extremely low computational cost. To address this problem, a feasible solution is compressing a complex face model to achieve higher speed and lower memory at the cost of minimal performance drop. Inspired by that, this paper proposes a learning approach to recognize low-resolution faces via selective knowledge distillation. In this approach, a two-stream convolutional neural network (CNN) is first initialized to recognize high-resolution faces and resolution-degraded faces with a teacher stream and a student stream, respectively. The teacher stream is represented by a complex CNN for high-accuracy recognition, and the student stream is represented by a much simpler CNN for low-complexity recognition. To avoid significant performance drop at the student stream, we then selectively distil the most informative facial features from the teacher stream by solving a sparse graph optimization problem, which are then used to regularize the fine-tuning process of the student stream. In this way, the student stream is actually trained by simultaneously handling two tasks with limited computational resources: approximating the most informative facial cues via feature regression, and recovering the missing facial cues via low-resolution face classification. Experimental results show that the student stream performs impressively in recognizing low-resolution faces and costs only 0.15MB memory and runs at 418 faces per second on CPU and 9, 433 faces per second on GPU. Copyright © 2018, The Authors. All rights reserved.

关键词： Students

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：