检索结果-内蒙古大学图书馆

作者： Ahmed, H.O.A. Nandi, A.K. Department of Electronic and Computer Engineering Brunel University London UxbridgeUB8 3PH United Kingdom The Key Laboratory of Embedded Systems and Service Computing College of Electronic and Information Engineering Tongji University Shanghai China

Rotating machines are widely used in industry. Unforeseen machine failures affect production schedules, product quality, and production costs. Therefore, condition monitoring of rotating machine can play an important role in machine availability. There is a growing number of methods for Machine Condition Monitoring (MCM). Yet, the performance of these methods is limited by the massive amounts of data need to be collected for MCM. This work proposes a computational method which can greatly reduce the high dimensional vibration dataset to a set of compressively-sampled measurements using Compressive Sampling (CS). Then, to learn fewer features from these compressively-sampled measurements we propose an effective multi-step feature learning algorithm that combines the advantages of Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), and Canonical Correlation Analysis (CCA). Finally, with these learned features, we use multi-class Support Vector Machine (SVM) to classify machine health conditions. Experiments on a roller element bearing fault classification task based on vibration signals are used to evaluate the efficiency of the proposed method. The most obvious finding to emerge from this study is that we are able to achieve high classification accuracy even from highly reduced vibration signal measurements. Moreover, the efficiency of our proposed method outperforms some recently published results. The proposed method offers better accuracy and has lower costs in time and storage requirements. © 2019, Springer Nature Switzerland AG.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

On iterative liveness-enforcement for a class of generalized Petri nets

On iterative liveness-enforcement for a class of generalized...

引用

2012 IEEE International Conference on Automation Science and Engineering: Green Automation Toward a Sustainable Society, CASE 2012

作者： Hou, Yifan Liu, Ding Zhou, Mengchu School of Electro-Mechanical Engineering Xidian University No. 2 South Taibai Road Xi'an 710071 China Department of Electrical and Computer Engineering New Jersey Institute of Technology Newark NJ 07102 United States Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai 200092 China

ISBN: (纸本)9781467304283

This work presents an iterative liveness-enforcing method for a class of generalized Petri nets, which can model flexible manufacturing systems. The proposed method checks the liveness of net models using mixed integer programming and controls the token allocations of resource places instead of siphons using a liveness and resource usage ratio-enforcing supervisor. The enumeration of a kind of special structures, which is required in the previous work, is avoided and the number of iterations is bounded by the number of shared resource places in the net model. All strict minimal siphons in the controlled systems are minimally controlled. Several explanatory examples are used to illustrate this method. © 2012 IEEE.

关键词： Petri nets

来源：评论

学校读者我要写书评

暂无评论

OpenDrift: Online Evolving Fraud Detection for Open-Category and Concept-Drift Transactions

OpenDrift: Online Evolving Fraud Detection for Open-Category...

引用

IEEE International Conference on Web services (ICWS)

作者： Cheng Wang Songyao Chai Hangyu Zhu Department of Computer Science and Technology Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Ministry of Education China Shanghai Artificial Intelligence Laboratory Shanghai China

The rapid growth of electronic commerce brings convenience to modern life but comes with security risks by various cybercrimes in online payment services. Most existing security methods for fraud detection depend on the static learning paradigm, which trains a model over a static training dataset and deploys the trained model for inference with the frozen model parameters under the i.i.d. assumption. Unfortunately, this paradigm becomes incommensurate with the increasingly complicated and varying fraud patterns due to the untimely and delayed responses in the offline environment. Without sensing the evolution of fraud timely, it is challenging to train and deploy targeted countermeasures. The emerging means of fraud are not only reflected in the openness of their category, but also in the drift of their superimposed risk features. The interweaving of open-category and concept drift accelerates the process of existing methods becoming powerless. In this paper, we propose EvoFD, an online evolving fraud detection framework to enable continual learning to cope with undercurrent surges of evolving fraud. The core idea of EvoFD is to weaken the bias caused by the anchoring effect on the learned information. It learns in an online streaming fashion by using instructive representations as anchors. Specially, we maintain the progressively updatable class anchors and optimize the representation network to embed features and class anchors into a unified normalized space, where the training and predicting can be conducted simultaneously or independently. In the framework, we preserve the balanced replay memory for each class to accumulate knowledge and avoid forgetting. The advantages of our method are validated by extensive experiments over the real-world dataset from a prestigious bank.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Rough Sets and Knowledge Technology: 9th International Conference, RSKT 2014, Shanghai, China, October 24-26, 2014, Proceedings 1

引用

丛书名： Lecture Notes in Computer Science 8818 Lecture Notes in Artificial Intelligence

2014年

作者： Duoqian Miao, Witold Pedrycz, Dominik Ślȩzak, Georg Peters, Qinghua Hu, Ruizhi Wang (eds.)

ISBN: (数字)9783319117409

ISBN: (纸本)9783319117393;9783319117409

This book constitutes the thoroughly refereed conference proceedings of the 9th International Conference on Rough Sets and Knowledge Technology, RSKT 2014, held in Shanghai, China, in October 2014. The 70 papers presented were carefully reviewed and selected from 162 submissions. The papers in this volume cover topics such as foundations and generalizations of rough sets, attribute reduction and feature selection, applications of rough sets, intelligent systems and applications, knowledge technology, domain-oriented data-driven data mining, uncertainty in granular computing, advances in granular computing, big data to wise decisions, rough set theory, and three-way decisions, uncertainty, and granular computing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Novel Clustering-Based Approach for Local Outlier Detection

Novel Clustering-Based Approach for Local Outlier Detection

引用

IEEE Conference on Computer Communications Workshops

作者： Haizhou Du Shengjie Zhao Daqiang Zhang Jinsong Wu Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University School of Software Engineering Tongji University Department of Electrical Engineering Universidad de Chile

ISBN: (纸本)9781467399562

With the rapid expansion of data scale, big data mining and analysis have attracted increasing attention. Outlier detection as an important task of data mining is widely used in many applications. However, conventional outlier detection methods have difficulty handling large-scale datasets. In addition, most of them typically can only identify global outliers and are over sensitive to parameters variation. In this paper, we propose a novel method for robust local outlier detection with statistical parameters, which incorporates the clustering-based ideas in dealing with big data. Firstly, this method finds some density peaks of dataset by 3σ standard. Secondly, each remaining data object in the dataset is assigned to the same cluster as its nearest neighbor of higher density. Finally, we use Chebyshev's inequality and density peak reachability to identify local outliers of each group. The experimental results demonstrate the efficiency and accuracy of the proposed method in identifying both global and local outliers. Moreover, the method is also proved to be more stability analysis than typical outlier detection methods, such as LOF (Local Outlier Factor) and DBSCAN (Density-Based Spatial Clustering of Applications with Noise).

关键词： Outlier detection Big data Data mining Clustering-based

来源：评论

学校读者我要写书评

暂无评论

Associating semantic sensor web with domain ontology: The way to obtain meaningful sensor data

引用

International Journal of u- and e- service, Science and Technology 2014年第5期7卷 271-282页

作者： Ji, Chaoqun Liu, Jin Wang, Xiaofeng College of Info. Engineering Shanghai Maritime University Shanghai China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China

To realize the sharing and reuse of sensor data and improve interoperability, semantic sensor web(SSW)is proposed to add semantics information to existing sensor networksby utilizing domain, spatial and temporal anthologies and other related semantic *** these is seldom research on how to fully utilize the sensor data through a semantic way such as domain ontology based inference. This paperpresents stateofthe art of SSWin various aspects, and proposesthe method to associate data from semantic sensor web with domain ontology to realize the communication between different domain ontologies and SSW. In addition, this paperalso proposes a new calculation method of semantic similarity amongdifferent entities in different ontology. Experiments show that this method can effectively find the similar entitiesandrealize the knowledge sharing and ontologies reuse. © 2014 SERSC.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Implementation Analysis of Reachability Graph and Its Application in Net Learning

Implementation Analysis of Reachability Graph and Its Applic...

引用

Computer, Control and Robotics (ICCCR), International Conference on

作者： Mingjian Guang Chungang Yan Zihao Lu Rui Duan Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China School of Computer Science and Cyber Engineering Guangzhou University Guangzhou China

ISBN: (数字)9798350373141

ISBN: (纸本)9798350373158

Reachability represents the most fundamental dynamic property of Petri nets. The reachability graph serves as a crucial tool for analyzing reachability, and its generation algorithm has garnered widespread attention. However, most of the existing work has focused primarily on the accuracy of the generation algorithm, often overlooking computational and time costs. Therefore, this paper concentrates on the implementation of reachability graphs and proposes three implementation methods: definition-based (DB), matrix-based (MB), and a fast generation method without self-loops (FG). Through comprehensive experiments, we evaluate and analyze the running speed and applicable scenarios of these three methods. Furthermore, we have successfully applied the proposed methods in net learning.

关键词： Digital control Costs Accuracy Heuristic algorithms Petri nets Benchmark testing Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Virtual Source-Based Particle Swarm Optimizer for Multi-Source Location Using Mobile Swarm Robotics

Virtual Source-Based Particle Swarm Optimizer for Multi-Sour...

引用

第33届中国过程控制会议

作者： JunQi Zhang YuXuan Lin Qi Kang Department of Computer Science and Technology the Key Laboratory of Embedded System and Service ComputingTongji UniversityMinistry of EducationShanghai Electronic Trans actions and Information Service Collaborative Innovation Center IEEE

Source location is an interesting topic in the field of swarm ***-source location is a vital branch of *** with a single-source location problem,the main difficulty for the multi-source location lies in that the number and distribution of sources are *** Swarm Optimizer(PSO) has been widely adopted for the single-source location ***,its performance deteriorates greatly when it faces multiple sources because it is designed to find the single global best solution,not multiple *** handle such a challenge,a virtual source mechanism is proposed to help PSO overcome this *** key idea of the virtual source mechanism is to divide the search area into multiple cells,each of which has a virtual *** virtual source leads the swarm to cover each cell such that particles can cover all cells in a search space before they *** results demonstrate that the virtual source mechanism-based PSO effectively locates multiple sources.

关键词： Particle swarm optimizer virtual source mobile swarm robotics multi-source location

来源：评论

学校读者我要写书评

暂无评论

Asymptotic bounds on lifetime of large scale clustering UWB sensor network

引用

Tien Tzu Hsueh Pao/Acta Electronica Sinica 2011年第10期39卷 2263-2268+2281页

作者： Xu, Juan Fang, Yu Xu, Hua-Jie School of Electronics and Information Engineering Tongji University Shanghai 200092 China Key Laboratory of Embedded System and Service Computing of the Ministry of Education Tongji University Shanghai 200092 China School of Computer and Electronic Information Guangxi University Nanning Guangxi 530004 China

Considering time hopping impulse radio ultra wide band (TH-IR UWB) sensor networks composed n sensor nodes which are placed according to a Poisson point process on a square and a Sink. The results demonstrate that the bounds on the lifetime of dense network increase with the increase of the number of nodes n, and that of extended network decrease with the increase of the number of nodes n. The results also indicate the bounds on the lifetime of clustering sensor networks is far more than that of non-clustering network, thus clustering can evidently improve network lifetime. Furthermore, the bounds on the lifetime of clustering TH-IR UWB sensor network which the nodes are distributed according to a Poisson point process are different from that of clustering network which the nodes are placed according to uniform distribution, thus the behavior of nodes deploying can remarkably affect the lifetime bound.

关键词： Energy dissipation

来源：评论

学校读者我要写书评

暂无评论

Identification of mild cognitive impairment using extreme learning machines model 11th

Identification of mild cognitive impairment using extreme le...

引用

11th International Conference on Intelligent computing, ICIC 2015

作者： Zhang, Wen Shen, Hao Ji, Zhiwei Meng, Guanmin Wang, Bing School of Electronics and Information Engineering Tongji University Shanghai201804 China The Advanced Research Institute of Intelligent Sensing Network Tongji University Shanghai201804 China The Key Laboratory of Embedded System and Service Computing Tongji University Shanghai201804 China Department of Clinical Laboratory Tongde Hospital of Zhejiang Province 234th Gucui Road Hangzhou310012 China

ISBN: (纸本)9783319221854

Alzheimer’s disease (AD) is very common disorder among the older people. Predicting mild cognitive impairment (MCI), an intermediate stage between normal cognition and dementia, in individuals with some symptoms of cognitive decline may have great influence on treatment choice and disease progression. In this work, a novel prediction model based on extreme learning machines algorithm was proposed to identify mild cognitive impairment using the information of some biomarkers, i.e., Position Emission Tomography (PET), Magnetic Resonance Imaging (MRI), and the cerebrospinal fluid (CSF). Firstly, each subject will be represented by three biomarkers using a vector with 201 dimensions after some essential pre-processing. Then, a prediction model based on extreme learning machine algorithm was trained to catch the difference between the patients and healthy persons. Finally, the model had been employed to identify identifying MCI participants from the normal people. Based on a dataset, including 99 MCI patients and 52 health controls, our proposed method achieved 70.86 % prediction accuracy with 67.68 % sensitivity at the precision of 76.92 %. Extensive experiments are performed to compare our method with state-of-the-art techniques, i.e., support vector machine (SVM) and SVM with fusion kernels. Experimental results demonstrate that proposed extreme learning machine is a powerful tool for predicting MCI with excellent performance and less time. © Springer International Publishing Switzerland 2015.

关键词： Support vector machines

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：