检索结果-内蒙古大学图书馆

18th ACM/IEEE-CS Joint Conference on Digital Libraries (JCDL)

作者： He, Guoxiu Fang, Junwei Cui, Haoran Wu, Chuan Lu, Wei Wuhan Univ Sch Informat Management Wuhan Hubei Peoples R China

ISBN: (纸本)9781450351782

Keyphrase is an important way to quickly get the topic of a document by providing highly-summative information. The previous approaches for keyphrase extraction simply rank keyphrases according to statistics-based model or graph-based model, which ignore the influence of external knowledge. In this paper, we take prior knowledge, which contains controlled vocabulary of keyphrases and their prior probability, into consideration to enhance previous methods. First, we build a controlled vocabulary of keyphrases introduced by keyphrases from existing collections and a keyphrase candidate set is filtered from a given document by it. Then, we use prior probability to represent the importance of keyphrases candidate with TF-IDF and TextRank. Finally, a supervised learning algorithm is used to learn optimal weights of these three features. Experiments on four benchmark datasets show the great advantages of prior knowledge on keyphrase extraction. Furthermore, we achieve competitive performance compared with the state-of-the art methods.

关键词： Keyphrase Extraction Prior Knowledge TF-IDF TextRank supervised learning algorithm

来源：评论

学校读者我要写书评

暂无评论

An Optimal Construction and Training of Second Order RBF Network for Approximation and Illumination invariant Image Segmentation

An Optimal Construction and Training of Second Order RBF Net...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Cai, Xun Tyagi, Kanishka Manry, Michael T. Shandong Univ Sch Comp Sci & Technol Jinan 250101 Shandong Peoples R China Univ Texas Arlington Dept Elect Engn Arlington 76010 TX USA

ISBN: (纸本)9781424496365

In this paper, we proposed an hybrid optimal radial-basis function (RBF) neural network for approximation and illumination invariant image segmentation. Unlike other RBF learning algorithms, the proposed paradigm introduces a new way to train RBF models by using optimal learning factors (OLFs) to train the network parameters, i.e. spread parameter, kernel vector and a weighted distance measure (DM) factor to calculate the activation function. An efficient second order Newton's algorithm is proposed for obtaining multiple OLF's (MOLF) for the network parameters. The weights connected to the output layer are trained by a supervised-learning algorithm based on orthogonal least square (OLS). The error obtained is then back-propagated to tune the RBF parameters. By applying RBF network for approximation on some real-life datasets and classification to reduce illumination effects of image segmentation, the results show that the proposed RBF neural network has fast convergence rates combining with low computational time cost, allowing it a good choice for real-life application such as image segmentation.

关键词： Classification algorithms Delta modulation Image color analysis Image segmentation Newton method RBF learning algorithm RBF network training Radial basis function networks Support vector machine classification Training activation function backpropagation backpropagation hybrid optimal radial-basis function neural network illumination effect reduction illumination invariant image segmentation image classification image classification image segmentation kernel vector least squares approximations network parameter training optimal RBF network construction optimal learning factors orthogonal least square radial basis function networks second order Newton algorithm second order RBF network spread parameter supervised learning algorithm weighted distance measure factor

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Neuro-Fuzzy Architecture for Intelligent Control of a Servo System and its Experimental Evaluation

An Adaptive Neuro-Fuzzy Architecture for Intelligent Control...

引用

IEEE International Symposium on Industrial Electronics (ISIE)

作者： Aras, Ayse Cisel Kayacan, Erdal Oniz, Yesim Kaynak, Okyay Abiyev, Rahib Bogazici Univ Dept Elect & Elect Engn TR-34342 Istanbul Turkey Near East Univ Dept Comp Engn Nicosia Cyprus

ISBN: (纸本)9781424463916

In this paper the development of an adaptive neuro-fuzzy architecture for the speed control of a servo system with nonlinear load is presented. The synthesis of the structure is described and a learning algorithm for the neuro-fuzzy control system is derived. The supervised learning algorithm is used to train the unknown coefficients of the system, and then the fuzzy rules of the neuro-fuzzy system are generated. A number of simulation studies are carried out, and the results are compared with those obtained with a PI controller tuned using desired time response characteristics. These and the experimental studies presented show that the neuro-fuzzy control system has a better control performance than the conventional PI controller.

关键词： DC motor PI control PI control adaptive control adaptive neuro-fuzzy architecture control system synthesis fuzzy neural nets fuzzy rules intelligent control intelligent control learning (artificial intelligence) neurocontrollers servo system servomechanisms speed control supervised learning algorithm velocity control

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

An Experimental Research of Traffic Identification algorithms in Broadband Network

An Experimental Research of Traffic Identification Algorithm...

引用

1st International Symposium on Computer Network and Multimedia Technology

作者： Chen, Na Shou, Guochu Hu, YiHong Guo, ZhiGang Beijing Univ Posts & Telecommun Sch Informat & Commun Engn Beijing 100088 Peoples R China

ISBN: (纸本)9781424452729

Adopting the machine learning method to identify the traffic in the broadband network has become a new research direction in this field. In this paper, we evaluate 11 kinds of supervised learning algorithm of the machine learning through the index of testing time, modeling time, accuracy rate and CPU utilization ratio, then select suitable algorithms for the broadband network. Through the analysis we draw the conclusion that the algorithms of C4.5, RandomTree. OneR and BayesNet fit the traffic identification in the broadband network.

关键词： traffic identification machine learning supervised learning algorithm broadband network

来源：评论

学校读者我要写书评

暂无评论

A Comparison of Sound Localisation Techniques using Cross-Correlation and Spiking Neural Networks for Mobile Robotics

A Comparison of Sound Localisation Techniques using Cross-Co...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Wall, Julie A. McGinnity, Thomas M. Maguire, Liam P. Univ Ulster Intelligent Syst Res Ctr Sch Comp & Intelligent Syst Coleraine BT52 1SA Londonderry North Ireland

ISBN: (纸本)9781424496365

This paper outlines the development of a cross-correlation algorithm and a spiking neural network (SNN) for sound localisation based on real sound recorded in a noisy and dynamic environment by a mobile robot. The SNN architecture aims to simulate the sound localisation ability of the mammalian auditory pathways by exploiting the binaural cue of interaural time difference (ITD). The medial superior olive was the inspiration for the SNN architecture which required the integration of an encoding layer which produced biologically realistic spike trains, a model of the bushy cells found in the cochlear nucleus and a supervised learning algorithm. The experimental results demonstrate that biologically inspired sound localisation achieved using a SNN can compare favourably to the more classical technique of cross-correlation.

关键词： Correlation Delay Delay lines Ear Microphones Neurons Robots bushy cells cochlear nucleus control engineering computing correlation methods cross-correlation algorithm encoding encoding layer interaural time difference learning (artificial intelligence) mammalian auditory pathway medial superior olive mobile robotics mobile robots neural nets sound localisation ability simulation sound localisation technique spike trains spiking neural network supervised learning algorithm

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

A Training algorithm for SpikeProp Improving Stability of learning Process

A Training Algorithm for SpikeProp Improving Stability of Le...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Wakamatsu, Toshiki Takase, Haruhiko Kawanaka, Hiroharu Tsuruoka, Shinji Mie Univ Grad Sch Engn Tsu Mie 514 Japan

ISBN: (纸本)9781424496365

In this paper, we aims to improve stability of learning processes by the SpikeProp algorithm. We proposed the method that reduce the increase of the error in learning processes. It repeats two steps: (1) original SpikeProp algorithm, and (2) use a linear search in the steepest descent direction only if the first step is failed. Some experimental results shows the improvement of learning processes.

关键词： Biological neural networks Iris Iris recognition Mathematical model Neurons SpikeProp algorithm SpikeProp network Surges Training feed-forward networks feedforward neural nets learning (artificial intelligence) learning process spiking neural networks stability stability improvement supervised learning algorithm training algorithm

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

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：