检索结果-内蒙古大学图书馆

An Empirical Study of the Transmission Power Setting for Bluetooth-Based Indoor Localization Mechanisms

SENSORS 2017年第6期17卷 1318-1318页

作者： Castillo-Cara, Manuel Lovon-Melgarejo, Jesus Bravo-Rocca, Gusseppe Orozco-Barbosa, Luis Garcia-Varea, Ismael Univ Nacl Ingn Ctr Informat & Commun Technol Comp Sci Sch Sci Fac Lima 25 Peru Univ Castilla La Mancha Albacete Res Inst Informat Albacete 02071 Spain

Nowadays, there is a great interest in developing accurate wireless indoor localization mechanisms enabling the implementation of many consumer-oriented services. Among the many proposals, wireless indoor localization mechanisms based on the Received Signal Strength Indication (RSSI) are being widely explored. Most studies have focused on the evaluation of the capabilities of different mobile device brands and wireless network technologies. Furthermore, different parameters and algorithms have been proposed as a means of improving the accuracy of wireless-based localization mechanisms. In this paper, we focus on the tuning of the RSSI fingerprint to be used in the implementation of a Bluetooth Low Energy 4.0 (BLE4.0) Bluetooth localization mechanism. Following a holistic approach, we start by assessing the capabilities of two Bluetooth sensor/receiver devices. We then evaluate the relevance of the RSSI fingerprint reported by each BLE4.0 beacon operating at various transmission power levels using feature selection techniques. Based on our findings, we use two classification algorithms in order to improve the setting of the transmission power levels of each of the BLE4.0 beacons. Our main findings show that our proposal can greatly improve the localization accuracy by setting a custom transmission power level for each BLE4.0 beacon.

关键词： indoor positioning location fingerprinting bluetooth BLE4.0 supervised learning algorithm signal processing RSSI multipath fading transmission power

来源：评论

学校读者我要写书评

暂无评论

A Two-stage Pattern Recognition Method for Electric Customer Classification in Smart Grid 7

A Two-stage Pattern Recognition Method for Electric Customer...

引用

IEEE International Conference on Smart Grid Communications (SmartGridComm)

作者： Peng, Bo Wan, Can Dong, Shufeng Lin, Jin Song, Yonghua Zhang, Yi Xiong, Jun Zhejiang Univ Coll Elect Engn Hangzhou 310027 Zhejiang Peoples R China Tsinghua Univ Dept Elect Engn Beijing 10084 Peoples R China Hong Kong Polytech Univ Dept Elect Engn Hong Kong Hong Kong Peoples R China State Grid Fujian Elect Power Res Inst Fuzhou 350007 Peoples R China State Grid Xiamen Elect Power Supply Co Xiamen 361000 Peoples R China

ISBN: (纸本)9781509040759

Identifying the consumption patterns of electric customers and grouping them to classes according to their load characteristics can be very meaningful for power supply and demand side management in smart grid. Previously, tariff structures are mainly based on the type of activity. However, the type of activity and electrical behavior of the customer have poor relationship. Using clustering techniques to classify customer according to load curves is more meaningful. This paper proposes a two-stage clustering algorithm combining supervised learning methods to classify electric customer. Firstly, clustering results are obtained based unsupervised learning method. Clustering method and number to get the result of first-stage are selected via the clustering evaluation index. Secondly, customers are reclassified using supervised learning algorithm. Different supervised learning algorithms for second-step reclassification are compared in the case studies. Case studies show that second-step reclassification can make up for the weakness of first-step clustering in load shape similarity.

关键词： Load clustering data mining for power system load shape supervised learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Planetary gearbox fault diagnostic method using acoustic emission sensors

引用

IET SCIENCE MEASUREMENT & TECHNOLOGY 2015年第8期9卷 936-944页

作者： Yoon, Jae He, David Univ Illinois Dept Mech & Ind Engn Chicago IL 60607 USA

In this study, a new acoustic emission (AE) sensor-based planetary gearbox (PGB) fault diagnosis method is presented. The method includes a heterodyne-based AE data acquisition system, empirical mode decomposition (EMD)-based AE signal analysis method, and computation of condition indicators (CIs) for PGB fault diagnosis. The heterodyne technique is hardware-implemented to downshift the sampling frequency of AE signals at a rate compatible to vibration analysis. The sampled AE signals are processed using EMD to extract PGB fault features and compute the CIs. The CIs are input into supervised learning algorithms for PGB fault diagnosis. The method is validated on a set of seeded localised faults on all gears: sun gear, planetary gear, and ring gear. The validation results have shown a promising PGB fault diagnostic performance using the presented method.

关键词： gears fault diagnosis acoustic emission acoustic signal processing singular value decomposition heterodyne detection acoustic signal detection data acquisition condition monitoring signal sampling vibrations feature extraction learning (artificial intelligence) electric sensing devices acoustic devices acoustic emission sensor planetary gearbox fault diagnosis method heterodyne-based AE data acquisition system empirical mode decomposition EMD-based AE signal analysis method condition indicator computation PGB fault diagnosis sampling frequency vibration analysis AE signal processing PGB fault feature extraction supervised learning algorithm seeded localised fault sun gear planetary gear ring gear

来源：评论

学校读者我要写书评

暂无评论

Unmanned Hybrid Electric Vehicles FNN Control based on Self-organized learning algorithm and supervised learning algorithm

Unmanned Hybrid Electric Vehicles FNN Control based on Self-...

引用

2010 International Conference on Computer,Mechatronics,Control and Electronic Engineering(2010计算机、机电、控制与电子工程国际会议 CMCE 2010)

作者： Yun Zhang Xuemei Chen Xiumin Yu Mingshuang Bi College of Automobile Engineering Jilin University Changchun China Water Resources Department of the JiLin Province Changchun China

ISBN: (纸本)9781424479573

To resolve unmanned hybrid electric vehicles control problems, the fuzzy neural network control method based on self-organized learning algorithm and supervised learning algorithm is proposed in this paper. This algorithm can learn proper fuzzy logic rules and optimal memberships functions from training examples. Using this control method,,we can control an unmanned hybrid electric vehicle by learning the driving technique of a skilled drive. By combining both unsu per vised self-organized and supervised learning algorithm,the learning speed converges much faster than the original backpropagation learning algorithm. Simulation results are presented to illustrate the performance and applicability of the proposed learning algorithm.

关键词： unmanned hybrid electric vehicle fuzzy neural network(FNN) self-organized learning algorithm supervised learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Unmanned Hybrid Electric Vehicles FNN Control based on Self-organized learning algorithm and supervised learning algorithm

Unmanned Hybrid Electric Vehicles FNN Control based on Self-...

引用

2010 International Conference on Computer,Mechatronics, Control and Electronic Engineering (CMCE 2010)

作者： Yun Zhang Xiumin Yu Xuemei Chen College of Automobile Engineering Jilin University Changchun, China Mingshuang Bi Water Resources Department of the JiLin Province Changchun, China

To resolve unmanned hybrid electric vehicles control problems, the fuzzy neural network control method based on self-organized learning algorithm and supervised learning algorithm is proposed in this paper. This algorithm can learn proper fuzzy logic rules and optimal memberships functions from training examples. Using this control method,,we can control an unmanned hybrid electric vehicle by learning the driving technique of a skilled drive. By combining both unsupervised self-organized and supervised learning algorithm,the learning speed converges much faster than the original backpropagation learning algorithm. Simulation results are presented to illustrate the performance and applicability of the proposed learning algorithm.

关键词： unmanned hybrid electric vehicle fuzzy neural network(FNN) self-organized learning algorithm supervised learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Combination of Nonlinear Feature Extraction Techniques for ECG Arryhtmia Detection System

引用

Research Journal of Applied Sciences, Engineering and Technology 2015年第9期11卷 1024-1029页

作者： Fatin Ahmed Elhaj Arief R. Harris Tan Tian Swee Naomie Salim Faculty of Biosciences and Medical Engineering Universiti Teknologi Malaysia Johor Malaysia

Electrocardiogram (ECG) is a noninvasive method used to detect arrhythmias or heart abnormalities. It describes the electrical activity of the heart. Physicians are faced with difficulties in detecting irregular heartbeats due to the presence of noise and subtle changes in the signal amplitude and duration. Depending on human visual detection alone may lead to misdiagnosis or insignificant detection of cardiovascular diseases. A computer-aided diagnosis of the ECG will assist physicians to significantly detect the cardiovascular diseases. Non-linear method is useful to extract and capture hidden information in the ECG signal. In this study we present a combination of two nonlinear methods; Higher Order Statistics (HOS) cumulants and Independent Component Analysis (ICA), performed on the dynamics ECG signals for arrhythmia detection. The abnormal heartbeats focused in this study are Right Bundle Branch Block (RBBB), Left Bundle Branch Block (LBBB), Atrial Premature Contraction (APC), Ventricular Premature Contraction (VPC) and Paced beat (P). The HOS and ICA features were fed to the Support Vector Machine (SVM) with kernel functions for automatic classification and neural network. In our study, we obtained the highest accuracy of 96.34% with Radial Basis Function (RBF) kernel and neural network.

关键词： ECG feature extraction HOS ICA supervised learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Image receptive fields for artificial neural networks

引用

NEUROCOMPUTING 2014年 144卷 258-270页

作者： Buessler, Jean-Luc Smagghe, Philippe Urban, Jean-Philippe Univ Haute Alsace Fac Sci & Tech F-68093 Mulhouse France

This paper describes the structure of the Image Receptive Fields Neural Network (IRF-NN) introduced recently by our team. This structure extends simplified learning introduced by Extreme learning Machine and Reservoir Computing techniques to the field of images. Neurons are organized in a single hidden layer feedforward network architecture with an original organization of the network's input weights. To represent color images efficiently, without prior feature extraction, the weight values linked to a neuron are determined by a 2-D Gaussian function. The activation of a neuron by an image presents the properties of a nonlinear localized receptive field, parameterized with a small number of degrees of freedom. A network composed of a large number of neurons, each associated with a randomly initialized and constant receptive field, induces a remarkable representation of the images. supervised training determines only the output weights of the network. It is therefore extremely fast, without retro-propagation or iterations, adapted to large sets of images. The network is easy to implement, presents excellent generalization performances for classification applications, and allows the detection of unknown inputs. The efficiency of this technique is illustrated with several benchmarks, photo and video datasets. (C) 2014 Elsevier B.V. All rights reserved.

关键词： Computer vision Visual object recognition Artificial neural networks model supervised learning algorithm Visual receptive fields Extreme learning Machine

来源：评论

学校读者我要写书评

暂无评论

VOICE ACTIVITY DETECTION IN PRESENCE OF TRANSIENT NOISE USING SPECTRAL CLUSTERING AND DIFFUSION KERNELS 28

VOICE ACTIVITY DETECTION IN PRESENCE OF TRANSIENT NOISE USIN...

引用

IEEE 28th Convention of Electrical and Electronics Engineers in Israel (IEEEI)

作者： Rosen, Oren Mousazadeh, Saman Cohen, Israel Technion Israel Inst Technol IL-32000 Haifa Israel

ISBN: (纸本)9781479959877

In this paper, we introduce a voice activity detection (VAD) algorithm based on spectral clustering and diffusion kernels. The proposed algorithm is a supervised learning algorithm comprising of learning and testing stages: A sample cloud is produced for every signal frame by utilizing a moving window. Mel-frequency cepstrum coefficients (MFCCs) are then calculated for every sample in the cloud in order to produce an MFCC matrix and subsequently a covariance matrix for every frame. Utilizing the covariance matrix, we calculate a similarity matrix using spectral clustering and diffusion kernels methods. Using the similarity matrix, we cluster the data and transform it to a new space where each point is labeled as speech or non-speech. We then use a Gaussian Mixture Model (GMM) in order to build a statistical model for labeling data as speech or non-speech. Simulation results demonstrate its advantages compared to a recent VAD algorithm.

关键词： Gaussian processes covariance matrices learning (artificial intelligence) mixture models signal detection speech recognition voice communication GMM Gaussian mixture model MFCC matrix Mel-frequency cepstrum coefficients covariance matrix diffusion kernels labeling data moving window sample cloud signal frame similarity matrix spectral clustering statistical model supervised learning algorithm transient noise voice activity detection Clustering algorithms Covariance matrices Signal to noise ratio Speech Training Transient analysis

来源：评论

学校读者我要写书评

暂无评论

Cellular Automata learning algorithm for Classification

Cellular Automata Learning Algorithm for Classification

引用

International Electrical Engineering Congress (iEECON)

作者： Wongthanavasu, Sartra Ponkaew, Jesada Khon Kaen Univ Facultly Sci Dept Comp Sci Cellular Automata & Knowledge Engn CAKE Lab Khon Kaen 40002 Thailand

ISBN: (纸本)9781479931743

Cellular Automata (CA) were proved as universal computation model. This means that CA are capable of modeling any problems to arrive at the solutions. Since then, researchers have paid efforts to seek the possible classifiers being constructed on this model. However, there is a number of papers to date haing reported classification with limited applications using cellular automata. This paper presents a novel state of the art classification model on the basis of cellular automata. The proposed classifier was developed on the proposed Decision Support Elementary Cellular Automata (DS-ECA). It comprises double rule vectors and a decision function. Its structure comprises two layers;the first layer is employed to evolve an input pattern into feature space and the other then interprets the feature space to binary answer through the decision function. For performance evaluation, six datasets consisting of binary and non-binary features are implemented in comparison with Support Vector Machines (SVM) with the optimal kernel using k-fold cross validation. In this respect, the proposed method outperforms SVM for binary featured datasets, and reports equivalent and better results on average for non-binary features.

关键词： Cellular automata classification supervised learning algorithm support vector machines

来源：评论

学校读者我要写书评

暂无评论

Identifying high-risk online gamblers: a comparison of data mining procedures

引用

INTERNATIONAL GAMBLING STUDIES 2014年第1期14卷 53-63页

作者： Philander, Kahlil S. Univ Nevada William F Harrah Coll Hotel Adm Las Vegas NV 89154 USA

Using play data from a sample of virtual live action sports betting gamblers, this study evaluates a set of classification and regression algorithms to determine which techniques are more effective in identifying probable disordered gamblers. This study identifies a clear need for validating results using players not appearing in the original sample, as even methods that use in-sample cross-validation can show substantial differences in performance from one data set to another. Many methods are found to be quite accurate in correctly identifying player types in training data, but perform poorly when used on new samples. Artificial neural networks appear to be the most reliable classification method overall, but still fail to identify a large group of likely problem gamblers. Bet intensity, variability, frequency and trajectory, as well as age and gender are noted to be insufficient variables to classify probable disordered gamblers with arbitrarily reasonable accuracy.

关键词： supervised learning algorithm responsible gambling classification internet gambling

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：