检索结果-内蒙古大学图书馆

American Control Conference

作者： Chenguang Xi Qiong Wu Usman A. Khany Machine Intelligence Unit & Center for Soft Computing Research Indian Statistical Institute 203 Kolkata India Odessa National Academy of Telecommunications n.a. A.S. Popov Odessa Ukraine Dep. of Electrical Eng. & Computer Science Massachusetts Institute of Technology Cambridge MA USA

ISBN: (纸本)9781467386838

We develop a fast distributed algorithm, termed DEXTRA, to solve optimization problems when N agents reach agreement and collaboratively minimize the sum of their local objectives over the network, where the communications between agents are described by a directed graph. Existing algorithms, including Gradient-Push (GP) and Directed-Distributed Gradient Descent (D-DGD), solve this problem restricted to directed graphs with a convergence rate of O(ln k/{the square root of}k). Our analysis shows that DEXTRA converges at a linear rate O(ε~k) for some constant ε <;1, with the assumption that the objective functions are strongly convex. Simulation examples illustrate our findings.

关键词： Convergence Optimization Radio frequency Eigenvalues and eigenfunctions Symmetric matrices Linear programming Distributed algorithms distributed algorithms Symmetric matrix Eigenfunctions directed graphs radiofrequency linear programming Converge

来源：评论

学校读者我要写书评

暂无评论

An intelligent system for diabetes prediction

An intelligent system for diabetes prediction

引用

Mediterranean Conference on Embedded Computing (MECO)

作者： Zhilbert Tafa Nerxhivane Pervetica Bertran Karahoda Dep. of Computer Science University for Business and Technology Prishtina Kosovo

With the emerging increase of diabetes, that recently affects around 346 million people, of which more than one-third go undetected in early stage, a strong need for supporting the medical decision-making process is generated. A number of researches have focused either in using one of the algorithms or in the comparisons of the performances of algorithms on a given, usually predefined and static datasets that are accessible through the Internet. This paper focuses on the joint implementation of the support vector machine (SVM) and Naïve Bayes statistical modeling, in the dataset acquired from the medical examinations of 402 patients, in order to improve the computer-supported diagnosis reliability. The dataset contains some attributes that have not been previously used in computer-based evaluations. The results show that the joint implementation of two algorithms improves significantly the overall reliability of the system outcome, which is crucial in the computer-supported diabetes diagnostic process.

关键词： Diabetes Support vector machines Classification algorithms Accuracy Joints Machine learning algorithms Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

The tradeoff of accuracy with different landmarks with manifold learning

The tradeoff of accuracy with different landmarks with manif...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Zezhong Zheng Chengjun Pu Mingcang Zhu Zhiqin Huang Yong He Yicong Feng Yufeng Lu Zhenlu Yu Shengli Wang Shijie Yu Jiang Li Ministry of Land and Resources of the China Chengdu Univ. of Technology Chengdu Sichuan PRC State Key Laboratory of Water Resources and Hydropower Engineering Science Wuhan Univ. Wuhan Hubei PRC School of Resources and Environment Univ. of Electronic Science and Technology of China Chengdu Sichuan PRC Guangxi Key Laboratory for Spatial Information and Geomatics Guilin Guangxi PRC Land and Resources Dep. of Sichuan Province Chengdu Sichuan PRC Land and Resource Dep. of Sichuan Province Information Center Chengdu Sichuan PRC Sichuan Institute of Geo-Environment Monitoring Chengdu Sichuan PRC Dep. of Electrical and Computer Engineering Old Dominion Univ. Norfolk VA USA

ISBN: (纸本)9781509033331

High-dimensional data such as hyperspectral images contain abundant information of surface radiation. But the massive redundant information makes it complex to be utilized conveniently. To solve this problem, a manifold learning dimensionality reduction framework for hyperspectral image is proposed. Firstly, statistical sampling methods were used to sample a subset of data points as landmarks. A skeleton of the manifold was then identified basing on the landmarks. The remaining data points were then inserted into the skeleton by Locally Linear Embedding algorithm. At last, original data sets and data sets reduced with different manifold learning approaches were classified by KNN classifier to evaluate the performance of the proposed framework. The framework was tested on AVIRIS Salinas-A dataset. The experimental results showed that the tradeoff of accuracy with different landmarks is of great significant. Insufficient landmarks lead to low accuracy and excess landmarks may spend a considerable amount of time.

关键词： Manifolds Hyperspectral imaging Skeleton Algorithm design and analysis Training

来源：评论

学校读者我要写书评

暂无评论

A spectrum decomposition to the feature spaces and the application to big data analytics

A spectrum decomposition to the feature spaces and the appli...

引用

IEEE International Symposium on Information Theory

作者： Shao-Lun Huang Lizhong Zheng Dep. of Electrical & Computer Eng Massachusetts Institute of Technology Cambridge MA

In this paper, we investigate how to efficiently extract informative features of high-dimensional data through noisy channels. Specifically, we decompose the feature space of the data into a sequence of score functions with decreasing information volumes, such that different scores are uncorrelated. From this decomposition, the features of the data become a sequence of score functions such that the most informative lowdimensional feature can be selected as the first few scores. This greatly simplifies the feature selection problem. In addition, we apply this spectrum decomposition to data with high-dimensional structures, i.e., the hidden Markov model (HMM). We show that in HMM, it is desirable to consider a particular class of score functions called as the node scores, which allows us to efficiently extract informative features of the hidden variables by applying the spectrum decomposition approach. Finally, we develop efficient algorithms to extract such features from node scores, and present an example to illustrate the performance of the node scores.

关键词： Feature extraction Hidden Markov models Joints Principal component analysis Data mining Noise measurement Kalman filters

来源：评论

学校读者我要写书评

暂无评论

An Improved Energy Efficient Chain Based Routing in Wireless Sensor Networks

An Improved Energy Efficient Chain Based Routing in Wireless...

引用

International Conference on Computing, Communication and Security

作者： Zanele Mahlobogwane S. M. Ngwira T. Zuva Dept. of Computer Systems Eng Tshwane University of Technology Dep. Computer Systems Eng Tshwane University of Technology

ISBN: (纸本)9781467393553

Wireless Sensor Networks (WSNs) consists of sensor nodes that are battery powered, these nodes are often dep.oyed in remote areas and left unattended for long periods between battery charges. According to the studies, over sixty percent of energy is consumed during the transmission and reception process of the network. Due to the reason stated above, protocols and algorithms have been designed to manage energy, to make sure that the life span of the network is prolonged. This study proposes the improvement of the Energy Efficient Chain Based Network protocol (ECBSN). This protocol has challenges in a way it forms the chains using fixed number of nodes per chain instead of varying the number of nodes in a chain at different levels. This cause the chain furthest to the Base Station (BS) to die faster if it's Cluster Head (CH) is the chosen leader which has to relay all aggregated data to the sink just like in the Improved Energy Efficient Chain Based Network (IEBSN). We then propose the Improved Energy Efficient Chain Based Routing (IECBR) in WSNs. This study will consider varying the number of nodes at different levels, that is more nodes will be assigned to the chain closest to the BS and the further you are to the BS few nodes will be assigned. It will also consider the level of the energy and the distance of the node which is the CH to the BS. The simulation results showed a great improvement in the lifespan of the nodes in the network as compared to ECBSN.

关键词： Wireless Sensor Networks Sensor Nodes Energy Efficient Hierarchical Clustering

来源：评论

学校读者我要写书评

暂无评论

The manifold learning for dimensionality reduction with hyperspectral image

The manifold learning for dimensionality reduction with hype...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Zezhong Zheng Pengxu Chen Mingcang Zhu Zhiqin Huang Yong He Yicong Feng Yufeng Lu Zhenlu Yu Shijie Yu Shengli Wang Jiang Li Ministry of Land and Resources of the China Chengdu Univ. of Technology Chengdu Sichuan PRC State Key Laboratory of Water Resources and Hydropower Engineering Science Wuhan Univ. Wuhan Hubei PRC School of Resources and Environment Univ. of Electronic Science and Technology of China Chengdu Sichuan PRC Guangxi Key Laboratory for Spatial Information and Geomatics Guilin Guangxi PRC Land and Resources Dep. of Sichuan Province Chengdu Sichuan PRC Land and Resource Dep. of Sichuan Province Information Center Chengdu Sichuan PRC Sichuan Institute of Geo-Environment Monitoring Chengdu Sichuan PRC Sichuan Institute of Geo-Environment Monitoring Chengdu China 610081 Dep. of Electrical and Computer Engineering Old Dominion Univ. Norfolk VA USA

Hyperspectral remote sensing image (HSI) consists of hundreds of bands that contain rich space, radiation and spectral information. The high-dimensional data can also lead to the curse of dimensionality problem making it difficult to be used effectively. In this paper, we proposed a manifold learning algorithm to reduce the dimensionality for HSI data. For high dimensional datasets with continuous variables, it is often the case that the data points are arranged along with low dimensional structures, named manifolds, in the high dimensional space. Manifold learning aims to identifying those special low dimensional structures for subsequent usage such as classification or regression. However, many manifold learning algorithms perform an eigenvector analysis on a data similarity matrix whose size is N×N, where N is the number of data points. The memory complexity of the analysis is at least O(N 2 ) that is not feasible for a regular computer to compute or storage for very large datasets. To solve this problem, we used statistical sampling methods to sample a subset of data points as landmarks. A skeleton of the manifold was then identified based on the landmarks. The remaining data points were then inserted into the skeleton by Locally Linear Embedding (LLE). We tested our algorithm on AVIRIS Salinas-A data set. The experimental results showed that the HSI dataset could be reduced to a lower-dimensional space for land use classification with good performance, and the main structure was preserved well.

关键词： Manifolds Hyperspectral imaging Skeleton Principal component analysis Classification algorithms Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Understanding thermal fluxes in and around pune city using remotely sensed data 36

Understanding thermal fluxes in and around pune city using r...

引用

36th Asian Conference on Remote Sensing: Fostering Resilient Growth in Asia, ACRS 2015

作者： More, Ravina Kale, Neha Kataria, Garima Yadav, Piyush Deshpande, Shailesh Dep. Computer Engineering Maharashtra Institute of Technology Savitribai Phule Pune University India TATA Research Development and Design Centre 54-B Hadapsar Industrial Estate Pune411013 India

Soaring temperatures of cities due to urbanisation leading to possible formation of an Urban Heat Island (UHI) is becoming a growing concern for India, a developing country, with the 2nd highest population in the world. Pune is no exception to that. Over the last few decades, the increasing urban landscape of the Pune city has led to fluctuations in the daily temperatures and disturbance in the thermal fluxes. To understand the nature and the consequences of this phenomenon, it is imperative to study the temperature changes and come up with a model that can quantify these changes. Whereas numerous studies have made use of satellite images for UHI analysis, only a few of these have paid significant attention to the analysis of long term changes. Our research aims to study the temperature profile of Pune city with the help of the Landsat-7 satellite imagery. The Land Surface Temperature (LST) and Land Use Land Cover (LULC) data extracted from these images is compared to find the correlation between the two. We used Hilbert Huang Transform (HHT) for analysing trends across the North-South and East-West extent of the city. The results are then compared with the Vegetation, Impervious and Soil (VIS) classification of the cross section to identify the relation of the trend with the classification. The results obtained show that the areas with residential, industrial have an average surface temperature of around 46 °C. That is higher by 2-3 degree on an average (5-6 degree worst case) than immediate surrounding vegetated region - indicating mild urban heat island effect. But because of physical geography of the region the outermost surrounding is covered with barren land, dry grass open area etc. and have similar temperatures to that of core of the city. Thus the observations indicate very specific temperature variation along the North-South and East-West cross sections of the city.

关键词： Surface temperature

来源：评论

学校读者我要写书评

暂无评论

Distributed Fault Detection Using Relative Information in Linear Multi-Agent Networks

引用

IFAC-PapersOnLine 2015年第21期48卷 446-451页

作者： Silvestre, Daniel Rosa, Paulo Hespanha, Joäo P. Silvestre, Carlos Dep. of Electrical and Computer Engineering Instituto Superior Técnico ISR 1046-001 Lisboa Portugal Deimos Engenharia Lisbon Portugal Dept. of Electrical and Computer Eng. University of California Santa Barbara CA 93106-9560 United States Department of Electrical and Computer Engineering of the Faculty of Science and Technology of the University of Macau Macao China on leave from Instituto Superior Técnico/Technical University of Lisbon Lisbon 1049-001 Portugal

This paper addresses the problem of fault detection in the context of a collection of agents performing a shared task and exchanging relative information over a communication network. A techniques in the literature is used to construct a meaningful observable system equivalent to the original unobservable system of systems. A solution involving Set-Valued Observers (SVOs) and a left-coprime factorization of the system is proposed to estimate the state in a distributed fashion and a proof of convergence of the estimates is given under mild assumptions. The performance of the detection algorithm against deterministic and stochastic faults;and when the system is subject to unmodeled disturbances is assessed through simulations. © 2015

关键词： Linear systems

来源：评论

学校读者我要写书评

暂无评论

Conducted EMI reduction of a soft-single-switched boost converter using heat-sink capacitance cancellation

Conducted EMI reduction of a soft-single-switched boost conv...

引用

Power Electronic and Drive Systems and Technologies Conference (PEDSTC)

作者： Mohammad Rouhollah Yazdani Maryam Alirezaei Hosein Farzanehfard Dep. of Electrical Engineering Islamic Azad University Isfahan Iran Dep. of Electrical and Computer Engineering Isfahan University of Technology Isfahan Iran

ISBN: (纸本)9781479976546

Conventional power supplies are considered as sources of electromagnetic interference. Increasing use of power converters leads to the need of electromagnetic emissions. Although soft switching methods are addressed to reduce electromagnetic emissions, the amount of EMI reduction may not be enough which leads to employ another EMI reduction methods. In this paper, a pulse width modulation soft-single-switched boost converter is modeled from conducted EMI viewpoint and its conducted EMI is predicted. To reduce EMI, a EMI reduction technique based on cancellation of the switch parasitic capacitor is investigated. This technique is applied to the converter and conducted EMI is simulated. The comparison between simulation results shows a considerable reduction in conducted EMI levels after applying this technique.

关键词： Switches Electromagnetic interference Electromagnetic compatibility Logic gates Pulse width modulation

来源：评论

学校读者我要写书评

暂无评论

Derivation of AC small signal model and analysis of trans Z-source inverter

Derivation of AC small signal model and analysis of trans Z-...

引用

Iranian Conference on Electrical Engineering (ICEE)

作者： Mehran Moslehi Bajestan Mohammad Ali Shamsinejad Davood Arab Khaburi Dep. of Electrical and Computer Engineering University of Birjand Birjand Iran Dep. of Electrical Engineering Iran University of Science and Technology Tehran Iran

This paper presents the ac small signal modeling and analysis of trans Z-Source inverter (trans ZSI). Trans ZSI has been derived from quasi Z-source converter recently. While maintaining all prominent features of pervious Z-source inverters, trans ZSI has several unique advantages such as increased voltage gain, reduced voltage stress and reduced components of impedance network. In the process of designing control schemes for the trans ZSI, knowledge of the transfer function representing its unique dc impedance network is essential. In particular, the state space averaging method is employed to deduce the transfer functions. These transfer functions reveal the presence of right half plane (RHP) zero, which imposes some limitations on controller design. The RHP zero trajectories with variations in network parameters can be studied using classical root-locus analyses. Considering system dynamic characteristics, the trans ZSI design guidelines for passive component sizing is investigated by parameter sweeping of the small signal model based transfer functions. Simulation results are presented to verify the dynamic modeling identified in this paper.

关键词： Inverters Electrical engineering Poles and zeros Capacitors Damping Analytical models

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：