检索结果-内蒙古大学图书馆

2019 International Conference on Security, Pattern Analysis, and Cybernetics, SPAC 2019

作者： Zhang, Bing Zhao, Shengjie Shi, Qingjiang Zhang, Rongqing Tongji University Key Laboratory of Embedded System and Service Computing of Ministry of Education Shanghai China Tongji University Sch. of Software Eng. the Key Lab. of Embedded System and Service Computing of Ministry of Education Shanghai China Tongji University School of Software Engineering Shanghai China

ISBN: (纸本)9781728159287

Thanks to the large-scale smart meters deployments around the world, non-intrusive appliance load monitoring (NILM) is receiving popularity. It aims to disaggregate the total electricity load of a home into individual appliances without resorting to any specific appliance power monitors. NILM is worthy of broad attention owing to its facilitation in energy savings. This paper regards NILM as a classification task and proposes a two-step method based on graph signal processing (GSP). In the first step, a smoothest solution is obtained by minimizing the regularization term. In the second step, gradient projection method, which uses the obtained minimizer as a start point, is adopted to optimize the while objective function, where NILM is regarded as a constrained nonlinear programming problem. The experiment results based on the open-access data set REDD clearly demonstrate that the proposed GSP-based method achieves improved performance compared with other state-of-the-art low-rate NILM approaches. © 2019 IEEE.

关键词： Signal processing

来源：评论

学校读者我要写书评

暂无评论

RBML: A Refined Behavior Modeling Language for Safety-Critical Hybrid Systems

RBML: A Refined Behavior Modeling Language for Safety-Critic...

引用

Asia-Pacific Conference on software engineering

作者： Zhangtao Chen Jing Liu Xi Ding Miaomiao Zhang Shanghai Key Lab of Trustworthy Computing East China Normal University Shanghai China AECC Aero-Engine Control System Institute Wuxi China School of Software Engineering Tongji University Shanghai China

As a widely used modeling language, AADL (Architecture Analysis and Design Language) plays an important role in designing safety-critical systems. It provides abundant components for describing system architecture and supports the early prediction and repetitive analysis of performance-critical attributes. However, the approach used by AADL to describe the system behavior is based mainly on automata theory; thus, encountering the state space explosion problem when modeling and verifying large and complex systems is inevitable. Furthermore, due to the lack of means to describe the behavior details, it is also difficult for AADL to support the accurate analysis and verification of functional and non-functional requirements. In this paper, we propose a language called RBML that supports refined behavior modeling to compensate for the behavior modeling and verification deficiencies of AADL. This new language is based on AADL but extends the ability to detail various behaviors and allows SMT (Satisfiability Modulo Theories) solvers to verify the constructed refined behavior model, thus alleviating the state space explosion problem to some extent. Experiments on Baidu Apollo are presented to demonstrate the feasibility of our proposed approach.

关键词： Analytical models Syntactics Mathematical model Tools Semantics Computational modeling Computer architecture

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Automated Reasoning Toward Machine Self-Awareness: A Case Study

Multi-Agent Automated Reasoning Toward Machine Self-Awarenes...

引用

Theoretical Aspects of software engineering (TASE)

作者： Zhenbing Zeng Jianlin Wang Zhengfeng Yang Department of Mathematics Shanghai University Shanghai China School of Computer and Information Engineering Henan University Kaifeng Henan Province China hanghai Key Lab. of Trustworthy Computing East China Normal University Shanghai China

In this paper, we present a study on building a special SAARA (Self-Aware Automated Reasoning Agent) system for solving Freudenthal's Sum and Product puzzle, aimed to train the "self-reflection" and "subjective experience" abilities as in the Three Wise Men test performed by the Nao robots in Rensselaer Polytechnic Institute in July 2015. We show the dynamic evolution of corresponding knowledge sets in the automated reasoning process for the Sum and Product puzzle.

关键词： Self-aware Robots Mathematics Intelligent agents Engines Multi-agent systems

来源：评论

学校读者我要写书评

暂无评论

Robustness Verification of Classification Deep Neural Networks via Linear Programming

Robustness Verification of Classification Deep Neural Networ...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition

作者： Wang Lin Zhengfeng Yang Xin Chen Qingye Zhao Xiangkun Li Zhiming Liu Jifeng He School of Information Science and Technology Zhejiang Sci-Tech University Shanghai Key Lab of Trustworthy Computing East China Normal University State Key Laboratory for Novel Software Technology Nanjing University Center for Research and Innovation in Software Engineering Southwest University

ISBN: (纸本)9781728132945

There is a pressing need to verify robustness of classification deep neural networks (CDNNs) as they are embedded in many safety-critical applications. Existing robustness verification approaches rely on computing the over-approximation of the output set, and can hardly scale up to practical CDNNs, as the result of error accumulation accompanied with approximation. In this paper, we develop a novel method for robustness verification of CDNNs with sigmoid activation functions. It converts the robustness verification problem into an equivalent problem of inspecting the most suspected point in the input region which constitutes a nonlinear optimization problem. To make it amenable, by relaxing the nonlinear constraints into the linear inclusions, it is further refined as a linear programming problem. We conduct comparison experiments on a few CDNNs trained for classifying images in some state-of-the-art benchmark-s, showing our advantages of precision and scalab.lity that enable effective verification of practical CDNNs.

关键词： linear programming Verification Robustness Neural network Scalab.lity

来源：评论

学校读者我要写书评

暂无评论

Τ-FPL: Tolerance-constrained learning in linear time 32

Τ-FPL: Tolerance-constrained learning in linear time

引用

32nd AAAI Conference on Artificial Intelligence, AAAI 2018

作者： Zhang, Ao Li, Nan Pu, Jian Wang, Jun Yan, Junchi Zha, Hongyuan Shanghai Key Laboratory of Trustworthy Computing MOE International Joint Lab of Trustworthy Software School of Computer Science and Software Engineering East China Normal University Shanghai China Institute of Data Science and Technologies Alibaba Group Hangzhou China IBM Research China Georgia Institute of Technology Atlante United States

ISBN: (纸本)9781577358008

In many real-world applications, learning a classifier with false-positive rate under a specified tolerance is appealing. Existing approaches either introduce prior knowledge dependent lab.l cost or tune parameters based on traditional classifiers, which are of limitation in methodology since they do not directly incorporate the false-positive rate tolerance. In this paper, we propose a novel scoring-thresholding approach, τ-False Positive Learning (τ-FPL) to address this problem. We show that the scoring problem which takes the false-positive rate tolerance into accounts can be efficiently solved in linear time, also an out-of-bootstrap thresholding method can transform the learned ranking function into a low false-positive classifier. Both theoretical analysis and experimental results show superior performance of the proposed τ-FPL over the existing approaches. Copyright © 2018, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Mathematical transformations

来源：评论

学校读者我要写书评

暂无评论

CNN-based Super-resolution Reconstruction for Traffic Sign Detection

CNN-based Super-resolution Reconstruction for Traffic Sign D...

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Fan Wang Jianqi Shi Xuan Tang Jielong Guo Peidong Liang Yuanzhi Feng College of Electrical Engineering and Automation Fuzhou university Fujian China Shanghai Key Lab for Trustworthy Computing School of Software Engineering East China Normal University Shanghai Putuo District Quanzhou Institute of Equipment Manufacture Haixi Institutes Chinese Academy of Sciences Quanzhou China Quanzhou HIT Research Institute of Engineering and Technology Quanzhou Fengze District China Henan University North Section of Jinming Avenue Kaifeng Longting District China

ISBN: (数字)9781728124858

ISBN: (纸本)9781728124865

Automatic identification for traffic signs is an important part of intelligent driving and traffic safety. Deep learning has already made a great achievement in traffic sign detection. However, the camera on a car may capture a low resolution and blurry image in certain environments, which make it inaccurate for traffic sign detection. Therefore, we propose a method based on image super-resolution reconstruction for improving the detection rate of traffic signs. Firstly, a low-resolution image is transformed by CNN-based super-resolution network into a high-resolution one. Then, to meet the requirements of on-line processing, we use the generated super-resolution image as input for the detection network with 16 filters in this layer. At last, we separately trained two CNNs for super-resolution reconstruction and traffic sign detection, which reduce the processing time. Experimental results demonstrate that our model can achieve better performance than the existing methods for traffic sign detection.

关键词： Image resolution Convolution Feature extraction Signal resolution Image reconstruction Object detection Machine learning

来源：评论

学校读者我要写书评

暂无评论

A New Energy Efficient VM Scheduling Algorithm for Cloud computing Based on Dynamic Programming 4

A New Energy Efficient VM Scheduling Algorithm for Cloud Com...

引用

4th IEEE International Conference on Cyber Security and Cloud computing, CSCloud 2017 and 3rd IEEE International Conference of Scalab.e and Smart Cloud, SSC 2017

作者： Zhang, Kepi Wu, Tong Chen, Siyuan Cai, Linsen Peng, Chao Shanghai Key Lab of Trustworthy Computing School of Computer Science and Software Engineering East China Normal University Shanghai China

ISBN: (纸本)9781509066438

As a new computing paradigm, cloud computing has significantly contributed to the rapid development of massive data centers. However, the corresponding energy issue becomes increasingly challenging. In this paper, we focus on the energy saving issue for virtual machine (VM) selections on an overloaded host in a cloud computing environment. We analyze the energy influencing factors during a VM migration, then design energy efficient VM selection algorithms based on greedy algorithm and dynamic programming method. We conduct experiments with CloudSim and results show that the proposed algorithm in this paper can effectively reduce energy consumption while satisfying the SLA constraints. © 2017 IEEE.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

1D-Convolutional capsule network for hyperspectral image classification

arXiv

引用

arXiv 2019年

作者： Zhang, Haitao Meng, Lingguo Wei, Xian Tang, Xiaoliang Tang, Xuan Wang, Xingping Jin, Bo Yao, Wei School of Software Liaoning Technical University Huludao125105 China Fujian Institute of Research on the Structure of Matter Chinese Academy of Sciences Fuzhou350002 China Shanghai Key Lab for Trustworthy Computing School of Computer Science and Software Engineering East China Normal University China Department of Land Surveying and Geo-Informatics Hong Kong Polytechnic University 181 Chatham Road South Hung Hom Kowloon Hong Kong

Recently, convolutional neural networks (CNNs) have achieved excellent performances in many computer vision tasks. Specifically, for hyperspectral images (HSIs) classification, CNNs often require very complex structure due to the high dimension of HSIs. The complex structure of CNNs results in prohibitive training efforts. Moreover, the common situation in HSIs classification task is the lack of lab.led samples, which results in accuracy deterioration of CNNs. In this work, we develop an easy-to-implement capsule network to alleviate the aforementioned problems, i.e., 1D-convolution capsule network (1D-ConvCapsNet). Firstly, 1D-ConvCapsNet separately extracts spatial and spectral information on spatial and spectral domains, which is more lightweight than 3D-convolution due to fewer parameters. Secondly, 1D-ConvCapsNet utilizes the capsule-wise constraint window method to reduce parameter amount and computational complexity of conventional capsule network. Finally, 1D-ConvCapsNet obtains accurate predictions with respect to input samples via dynamic routing. The effectiveness of the 1D-ConvCapsNet is verified by three representative HSI datasets. Experimental results demonstrate that 1D-ConvCapsNet is superior to state-of-the-art methods in both the accuracy and training effort Copyright © 2019, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Joint learning of discriminative low-dimensional image representations based on dictionary learning and two-layer orthogonal projections

arXiv

引用

arXiv 2019年

作者： Wei, Xian Shen, Hao Li, Yuanxiang Tang, Xuan Jin, Bo Zhao, Lijun Murphey, Yi Lu Fujian Institute of Research on the Structure of Matter Chinese Academy of Sciences China Technical University of Munich Germany and fortiss GmbH Munich Germany Shanghai Key Lab for Trustworthy Computing School of Computer Science and Software Engineering East China Normal University China School of Aeronautics & Astronautics Shanghai Jiao Tong University Shanghai200240 China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150006 China Department of Electrical and Computer Engineering University of Michigan-Dearborn DearbornMI48128 United States

This work investigates the problem of efficiently learning discriminative low-dimensional representations of multi-class large-scale image objects. We propose a generic deep learning approach by taking advantages of Convolutional Neural Networks (CNN), sparse dictionary learning, and orthogonal projections. CNN is not only powerful on feature extraction, but also robust to spatial variance and changes. Sparse dictionary learning is well known for disentangling nonlinear underlying discriminative factors in data. The orthogonal projection is a notable efficient tool to project multi-class data onto low dimensional discriminative subspace. The proposed procedure can be summarized as follows. At first, a CNN is employed to extract high-dimensional (HD) preliminary convolutional features. Secondly, to avoid the high computational cost of direct sparse coding on HD CNN features, we present to learn sparse representation (SR) in an orthogonal projected space over a task-driven sparsifying dictionary. We then exploit the discriminative projection on SR. The whole learning process is treated as a joint optimization problem of trace quotient maximization, which involves the CNN parameters, the orthogonal projection on CNN features, the dictionary and the discriminative projection on sparse codes. The related cost function is well defined on product manifold of the Stiefel manifold, the Oblique manifold, and the Grassmann manifold. It is optimized via a geometrical stochastic gradient descent algorithm. Finally, the quality of dictionary and projections learned by the proposed approach is further investigated in terms of image classification. The experimental results show that the approach can achieve a strongly competitive performance with state-of-the-art image classification methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

AdaRate: A rate-adaptive traffic measurement method in software defined networks

引用

International Journal of Performability engineering 2017年第6期13卷 937-944页

作者： Tang, Jixing Zhang, Yue Li, Yan MoE Engineering Research Center for Software/Hardware Co-Design Technology and Application East China Normal University Shanghai200062 China Shanghai Key Lab for Trustworthy Computing East China Normal University Shanghai200062 China

Traffic measurement is the basis of analysis and prediction of network traffic. Its accuracy directly affects the reliability of upper applications. This paper proposes a rate-adaptive traffic measurement method called AdaRate. It adjusts the polling period according to fluctuations of flow rates which is calculated with a sliding window queue. We noticed that some fluctuations of flow rates may be dropped in AdaRate while the polling period is too long. Then we propose RAdaRate. It adjusts the polling period according to AdaRate or sets the polling period to minimum randomly. We compared the performance of AdaRate and RAdaRate with SWT in CeMon and Payless in Mininet when monitoring those VBR flows with frequent and large fluctuation. The results show that the accuracy of RAdaRate is the best while the overhead of AdaRate is the least. The overhead of AdaRate is 68.75% less than periodic polling. © 2017 Totem Publisher, Inc. All rights reserved.

关键词： software defined networking

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：