检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Liu, Xiwei Ma, Hailian Department of Computer Science and Technology Tongji University Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai201804 China

In this brief, we set up the finite time stability (FnTSta) theory for dynamical systems with bounded timevarying delays via aperiodically intermittent control (AIC) and quantized control (QC). A more general QC is designed in this brief. The bound of time-varying delay is required to be less than the infimum in AIC. Two-phases-method (2PM) is applied to solve the FnTSta for delayed system, i.e., it divides the whole proof process into two phases, one phase is that the process for the norm of system error evolving from initial values to 1, and the other is the process for the norm of system error evolving from 1 to 0. By proving that these two phases both use FnT to realize, the whole FnTSta for system is proved. We also design the adaptive rules and prove its validity rigorously. Furthermore, the obtained theories are used to discuss the finite time synchronization (FnTSyn) of neural networks as an application. Finally, some simulations are given to illustrate the effectiveness of our theoretical result. Copyright © 2020, The Authors. All rights reserved.

关键词： Dynamical systems

来源：评论

学校读者我要写书评

暂无评论

Global µ-stability and finite-time control of octonion-valued neural networks with unbounded delays✡

arXiv

引用

arXiv 2020年

作者： Wang, Jingzhu Liu, Xiwei Department of Computer Science and Technology Tongji University Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai201804 China

Octonion-valued neural networks (OVNNs) are a type of neural networks for which the states and weights are octonions. In this paper, the global µ-stability and finite-time stability problems for octonion-valued neural networks are considered under unbounded and asynchronous time-varying delays. To avoid the non-communicative and non-associative multiplication feature of the octonions, we firstly decompose the OVNNs into eight real-valued neural networks (RVNNs) equivalently. Through the use of generalized norm and the Cauchy convergence principle, we obtain the sufficient criteria which assure the existence, uniqueness of the equilibrium point and global µ-stability of OVNNs. By adding controllers, the criteria to ensure the finite-time stability for OVNNs are presented by dividing the analysis of finite-time stability process into two phases. Furthermore, we also prove the adaptive finite time stability theory of above networks. At last, the simulation results of specified examples is given to substantiate the effectiveness and correctness of the theoretical results. Copyright © 2020, The Authors. All rights reserved.

关键词： Timing circuits

来源：评论

学校读者我要写书评

暂无评论

Non-intrusive load disaggregation using semi-supervised learning method

Non-intrusive load disaggregation using semi-supervised lear...

引用

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

作者： Miao, Nan 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

With the emerging of smart metering around the world, there is a growing demand to analyse the residential energy usage. In this paper, we propose a Deep Neural Network (DNN)-based approach for non-intrusive load monitoring (NILM), which can achieve effective and efficient estimation of individual appliance usage according to a single main meter reading in a non-intrusive manner. Considering practical situations, two training methods are provided. The first training approach is fully supervised learning, which requires a ground truth of label, indicating the state of the appliance (ON/OFF), to build a prediction model. The second training approach is semi-supervised learning, leading to better performance by F-Measure metric while only requiring some more unlabelled training data. Experimental results on the low-sample rate REDD dataset demonstrate the superior performance of our proposed DNN-based method compared with Hidden Markov Model (HMM)based and Graph Signal Processing (GSP)-based approaches. © 2019 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Low-rate non-intrusive appliance load monitoring based on graph signal processing

Low-rate non-intrusive appliance load monitoring based on gr...

引用

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

Detecting Data-flow Errors Based on Petri Nets With Data Operations

引用

IEEE/CAA Journal of Automatica Sinica 2018年第1期5卷 251-260页

作者： Dongming Xiang Guanjun Liu Chungang Yan Changjun Jiang Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai 201804 China IEEE

In order to guarantee the correctness of business processes, not only control-flow errors but also data-flow errors should be considered. The control-flow errors mainly focus on deadlock, livelock, soundness, and so on. However, there are not too many methods for detecting data-flow errors. This paper defines Petri nets with data operations(PN-DO) that can model the operations on data such as read, write and delete. Based on PN-DO, we define some data-flow errors in this paper. We construct a reachability graph with data operations for each PN-DO, and then propose a method to reduce the reachability graph. Based on the reduced reachability graph, data-flow errors can be detected rapidly. A case study is given to illustrate the effectiveness of our methods.

关键词： Business process modeling data-flow errors Petri nets reachability graph

来源：评论

学校读者我要写书评

暂无评论

An Accuracy-and-Diversity-based Ensemble Method for Concept Drift and Its application in Fraud Detection

An Accuracy-and-Diversity-based Ensemble Method for Concept ...

引用

IEEE International Conference on Data Mining Workshops (ICDM Workshops)

作者： Shujie Yin Guanjun Liu Zhenchuan Li Chungang Yan Changjun Jiang Key Laboratory of the Ministry of Education for Embedded System and Service Computing Shanghai Electronic Transactions and Information Service Collaborative Innovation Center Tongji University Shanghai China

ISBN: (数字)9781728190129

ISBN: (纸本)9781728190136

Concept Drift is one of the most challenging issues in various applications such as fraud detection, spam filtering and sensor networks, causing the performance degradation of learning algorithms which are dedicated to processing static data such as Naive Bayes, due to their poor adaptability to changes. Several techniques and algorithms have been proposed to address the concept drift problem, e.g. the ensemble methods that have already achieved great success. However, most of the ensemble methods consider either accuracy or diversity of a trained model when adapting to new concepts, and thus they can hardly deal with different types of drifts. This paper proposes a novel ensemble method that considers both accuracy and diversity. We linearly combine accuracy and diversity with different coefficients, and propose an entropy-based policy to compute these coefficients. Experiments on 10 synthetic datasets and 4 public datasets demonstrate that our method outperforms the state-of-the-art ones on dealing with different concept drifts. Our method is also applied to the electronic transaction fraud detection and achieves an excellent performance.

关键词： Degradation Adaptation models Filtering Design methodology Conferences Computational modeling Data mining

来源：评论

学校读者我要写书评

暂无评论

A hierarchical clustering strategy of processing class imbalance and its application in fraud detection 21

A hierarchical clustering strategy of processing class imbal...

引用

21st IEEE International Conference on High Performance computing and Communications, 17th IEEE International Conference on Smart City and 5th IEEE International Conference on Data Science and systems, HPCC/SmartCity/DSS 2019

作者： Zhang, Youjun Liu, Guanjun Zheng, Lutao Yan, Chungang Key Laboratory of the Ministry of Education for Embedded System and Service Computing Shanghai Electronic Transactions and Information Service Collaborative Innovation Center Tongji University Shanghai China

ISBN: (纸本)9781728120584

With the Internet and mobile communications becoming an indispensable part of people's daily lives, online transactions have become one of the most common payment methods. However, transaction fraud incidents also occur frequently, causing a larger number of economic losses. Therefore, transaction fraud detection is significant. The methods of machine learning are often used to detect fraudulent transactions from a larger amount of transaction data. However, the class imbalance problem reduces the performance of these methods. There are mainly four factors causing this problem: imbalanced class distribution, sample size, class separability and within-class concept. The existing improvement strategies for class imbalance mainly focus on the first factor but omit other three ones. This paper considers the four factors to propose a comprehensive model called clustering tree. Constructing a clustering tree includes two steps: 1) we first select a clustering algorithm considering the class separability;and then 2) we use this clustering algorithm to construct a tree that can be used to determine if an incoming transaction is illegal. The root node of this tree contains all samples, and we consider both the imbalanced class distribution and the within-class concept when samples are hierarchically divided into sub-nodes during the constructing process. We compare the proposed method with five state-of-the-art ones on two real transaction datasets, and the experimental results show that our method works better. © 2019 IEEE.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Generalized Visual Quality Assessment of GAN-Generated Face Images

arXiv

引用

arXiv 2022年

作者： Tian, Yu Ni, Zhangkai Chen, Baoliang Wang, Shiqi Wang, Hanli Kwong, Sam The Department of Computer Science City University of Hong Kong 999077 Hong Kong The Department of Computer Science & Technology Tongji University Shanghai 200092 China The Department of Computer Science & Technology Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai Institute of Intelligent Science and Technology Tongji University Shanghai 200092 China The City University of Hong Kong Shenzhen Research Institute Shenzhen518057 China

Recent years have witnessed the dramatically increased interest in face generation with generative adversarial networks (GANs). A number of successful GAN algorithms have been developed to produce vivid face images towards different application scenarios. However, little work has been dedicated to automatic quality assessment of such GAN-generated face images (GFIs), even less have been devoted to generalized and robust quality assessment of GFIs generated with unseen GAN model. Herein, we make the first attempt to study the subjective and objective quality towards generalized quality assessment of GFIs. More specifically, we establish a large-scale database consisting of GFIs from four GAN algorithms, the pseudo labels from image quality assessment (IQA) measures, as well as the human opinion scores via subjective testing. Subsequently, we develop a quality assessment model that is able to deliver accurate quality predictions for GFIs from both available and unseen GAN algorithms based on meta-learning. In particular, to learn shared knowledge from GFIs pairs that are born of limited GAN algorithms, we develop the convolutional block attention (CBA) and facial attributes-based analysis (ABA) modules, ensuring that the learned knowledge tends to be consistent with human visual perception. Extensive experiments exhibit that the proposed model achieves better performance compared with the state-of-the-art IQA models, and is capable of retaining the effectiveness when evaluating GFIs from the unseen GAN algorithms. Copyright © 2022, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A Cloudedge-Combined Data Placement Strategy Based On User Access Regions

A Cloudedge-Combined Data Placement Strategy Based On User A...

引用

International Conference on Big Data and Information Analytics (BigDIA)

作者： Eryang Cao Pengwei Wang Chungang Yan Changjun Jiang The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China School of Computer Science and Technology Donghua University Shanghai China

ISBN: (数字)9781665422321

ISBN: (纸本)9781665446662

To improve the availability of data in the cloud and avoid vendor lock-in risk, multi-cloud storage is attracting more and more attentions. However, accessing data from the cloud usually has some disadvantages such as higher latency and more bandwidth-consuming. Edge computing, which has become popular in recent years, could effectively solve the above problems while it usually reduces availability. Storage only in the cloud or edge environment is limited by many factors. To this end, we build mathematical model which is abstracted from real access mode of users in consideration of multi-cloud and edge. This paper presents a method combined NSGAII with multi-group method which has better ability of global search to help users determine cloud and edge services to store and access data object. A large number of experiments using real service provider information demonstrate that the proposed algorithm outperforms existing methods and effectiveness of it.

关键词： Cloud computing Data privacy Search problems Data models Delays Mathematical model Edge computing

来源：评论

学校读者我要写书评

暂无评论

ASBSO: An improved brain storm optimization with flexible search length and memory-based selection

arXiv

引用

arXiv 2021年

作者： Yu, Yang Gao, Shangce Wang, Yirui Cheng, Jiujun Todo, Yuki The Faculty of Engineering University of Toyama Toyama930-8555 Japan Key Laboratory of Embedded System and Service Computing Ministry of Education Department of Computer Science and Technology Tongji University Shanghai200092 China The School of Electrical and Computer Engineering Kanazawa University Kanazawa-shi920-1192 Japan

Brain storm optimization (BSO) is a newly proposed population-based optimization algorithm which uses a logarithmic sigmoid transfer function to adjust its search range during the convergent process. However, this adjustment only varies with the current iteration number, and lacks of flexibility and variety which makes a poor search efficiency and robustness of BSO. To alleviate this problem, an adaptive step length structure together with a success memory selection strategy are proposed to be incorporated into BSO. This proposed method, adaptive step length based on memory selection BSO, namely ASBSO, applies multiple step lengths to modify the generation process of new solutions, thus supplying a flexible search according to corresponding problems and convergent periods. The novel memory mechanism which is capable of evaluating and storing the degree of improvements of solutions is used to determine the selection possibility of step lengths. A set of 57 benchmark functions are used to test ASBSO's search ability, and four real-world problems are adopted to show its application value. All these test results indicate the remarkable improvement in solution quality, scalability and robustness of ASBSO. Copyright © 2021, The Authors. All rights reserved.

关键词： Swarm intelligence

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：