检索结果-内蒙古大学图书馆

2014 International Conference on Interdisciplinary Advances in Applied Computing, ICONIAAC 2014

作者： Midhun, E.M. Nair, Sarath R. Nidhin Prabhakar, T.V. Sachin Kumar, S. Centre for Excellence in Computational Engineering Networking Amrita Vishwa Vidyapeetham Coimbatore641112 India

ISBN: (纸本)9781450329088

This paper presents an improved classification of hyperspectral images using deep learning, by extracting meaningful representations at higher levels. Deep learning is a set of algorithm in machine learning that attempt to model high level abstraction of data by using architectures composed of multiple non-linear transformation. It allows artificial systems to discover re-usable features that capture structure in an environment. The ability of undirected graphical models like Restricted Boltzmann Machine, to capture distribution among pixels at the hidden level is utilized here to extract features for each band in the hyperspectral image. To enhance the quality of image a band-by-band non-linear diffusion is introduced as a preprocessing step which ensures increased class separability and noise reduction. After preprocessing, a powerful regenerative model Restricted Boltzmann Machine (RBM) is used for the feature extraction. The generated feature vectors is feed as input to different classifiers for the classification. A statistical comparison of accuracies, obtained with RBM under different conditions illustrates the effectiveness of proposed method. Hyperspectral dataset acquired by Airborne Visible/Infrared imaging Spectrometer is used for experimentation. Copyright 2014 ACM.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Spatial preprocessing based multinomial logistic regression for hyperspectral image classification

Spatial preprocessing based multinomial logistic regression ...

引用

IUTAM Symposium on the Dynamics of Extreme Events Influenced by Climate Change (2013)

作者： Nidhin Prabhakar, T.V. Xavier, Gintu Geetha, P. Soman, K.P. Centre for Excellence in Computational Engineering and Networking Amrita Vishwa Vidyapeetham Coimbatore India

The paper presents a fast, reliable and efficient method for improving hyperspectral image classification aided by segmentation. The Multinomial Logistic Regression(MLR) algorithm can be extended to a semi-supervised learning of the posterior class distribution using unlabeled samples actively selected from the dataset. Classification results obtained from regression model is improved by performing a maximum a posteriori segmentation as it considers the spatial information of the hyperspectral image. The addition of the spatial processing step prior to the above mentioned classification scheme improves the overall accuracy of the process. The accuracies obtained before and after applying the preprocessing are compared. © 2015 The Authors. Published by Elsevier B.V.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Fault diagnosis of helical gear box using variational mode decomposition and random forest algorithm

引用

SDHM Structural Durability and Health Monitoring 2015年第1期10卷 55-80页

作者： Muralidharan, Akhil Sugumaran, V. Soman, K.P. Amarnath, M. SMBS VIT University Chennai Campus Vandalur-Kelambakkam Road Chennai India Centre for Excellence in Computational Engineering and Networking Amrita Vishwa Vidyapeetham Coimbatore Tamil Nadu India Department of Mechanical Engineering Indian Institute of Information Technology Design and Manufacturing Jabalpur Madhya Pradesh India

Gears are machine elements that transmit motion by means of successively engaging teeth. In purely scientific terms, gears are used to transmit motion. A faulty gear is a matter of serious concern as it affects the functionality of a machine to a great extent. Thus it is essential to diagnose the faults at an initial stage so as to reduce the losses that might be incurred. This necessitates the need for continuous monitoring of the gears. The vibrations produced by gears from good and simulated faulty conditions can be effectively used to detect the faults in these gears. The introduction of Variational Mode Decomposition (VMD) as a new signal pre-processing technique along with the different decision trees have provided good classification performance. VMD allows decomposition of the signal into various modes by identifying a compact frequency support around its central frequency, such that adding all the modes reconstructs the original signal. Alternating direction multiplier method (ADMM) is used by VMD to find the intrinsic mode functions on central frequencies. Meaningful statistical features can be extracted from VMD processed signals. J48 decision tree algorithm was used to identify the useful features and the selected features were used for classification using the decision trees namely, Random Forest, REP Tree and Logistic Model Tree algorithms. The performance analyses of various algorithms are discussed in detail. Copyright © 2014 Tech Science Press.

关键词： Variational mode decomposition

来源：评论

学校读者我要写书评

暂无评论

AMRITA-CEN@FIRE-2014: Morpheme extraction and lemmatization for Tamil using machine learning 6

AMRITA-CEN@FIRE-2014: Morpheme extraction and lemmatization ...

引用

6th International Workshop of the Forum for Information Retrieval Evaluation, FIRE 2014

作者： Anand Kumar, M. Soman, K.P. Centre for Excellence in Computational Engineering and Networking Amrita School of Engineering Amrita Vishwa Vidyapeetham Coimbatore641 112 India

ISBN: (纸本)9781450337557

This paper presents the method of Morpheme Extraction and lemmatization for Tamil language in Morpheme Extraction Task (MET) of FIRE-2014. Tamil is a morphologically rich and agglutinative language. Such a language needs deeper analysis at the word level to capture the meaning of the word from its morphemes and its categories. In this attempt, the methodology employed to extract Tamil morphemes and lemmas are based on a supervised machine learning algorithm for nouns and verbs and simple suffix stripping for pronouns and proper nouns. Morphemes are extracted for other Part-of-Speech categories using Tamil Part of Speech tagger. In supervised learning, Morphological analyzer problem is redefined as a classification problem. We decompose the problem of noun and verb morpheme extraction into two sub-problems: learning to perform morpheme identification of words in a text, and learning to perform morpheme tagging. In addition to the Morpheme extraction task results of FIRE-2014, we have carried out different experiments to show the effectiveness of the proposed method. © 2015 ACM.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Compressive sensing based image acquisition and reconstruction analysis

Compressive sensing based image acquisition and reconstructi...

引用

2014 IEEE International Conference on Green Computing, Communication and Electrical engineering, ICGCCEE 2014

作者： Ravindranath, Sabbisetti Ram, S.R Nishanth Subhashini, S. Reddy, A.V. Sesha Janarth, M. Aswathvignesh, R. Gandhiraj, R. Soman, K.P. Department of Electronics and Communication Engineering Amrita VishwaVidyapeetham Coimbatore India Centre for Excellence in Computational Engineering and Networking Amrita VishwaVidyapeetham Coimbatore India

ISBN: (纸本)9781479949823

Compressive sensing is a technique by which images are acquired and reconstructed from a relatively fewer measurements than what the Nyquist rate suggests. Compressive sensing is applicable when the signals under consideration are sparse, and most of the images are sparse in wavelet or frequency domain. In this paper, the mathematical formulation of compressive sensing is explained where in various notations and parameters like measurement matrices and sparsity-inducing matrices are dealt in detail. A deterministic measurement matrix, known as chess measurement matrix is implemented in an aperture assembly. Several reconstruction algorithms are analysed and the images reconstructed with PSNR plotted for every case. Based upon the results, it is proved that OMP is the efficient reconstruction algorithm among all. © 2014 IEEE.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Performance comparison of Variational Mode Decomposition over Empirical Wavelet Transform for the classification of power quality disturbances using Support Vector Machine

Performance comparison of Variational Mode Decomposition ove...

引用

IUTAM Symposium on the Dynamics of Extreme Events Influenced by Climate Change (2013)

作者： Aneesh, C. Kumar, Sachin Hisham, P.M. Soman, K.P. Centre for Excellence in Computational Engineering and Networking Amrita Vishwa Vidyapeetham Coimbatore Campus Tamilnadu641112 India

This work considers the classification of power quality disturbances based on VMD (Variational Mode Decomposition) and EWT (Empirical Wavelet Transform) using SVM (Support Vector Machine). Performance comparison of VMD over EWT is done for producing feature vectors that can extract salient and unique nature of these disturbances. In this paper, these two adaptive signal processing methods are used to produce three Intrinsic Mode Function (IMF) components of power quality signals. Feature vectors produced by finding sines and cosines of statistical parameter vector of three different IMF candidates are used for training SVM. Validation for six different classes of power qualities including normal sinusoidal signal, sag, swell, harmonics, sag with harmonics, swell with harmonics is performed using synthetic data in MATLAB. Classification results using SVM shows that VMD outperforms over EWT for feature extraction process and the classification accuracy is tabled. © 2015 The Authors. Published by Elsevier B.V.

关键词： Variational mode decomposition

来源：评论

学校读者我要写书评

暂无评论

A low cost implementation of multi-label classification algorithm using mathematica on raspberry Pi

A low cost implementation of multi-label classification algo...

引用

IUTAM Symposium on the Dynamics of Extreme Events Influenced by Climate Change (2013)

作者： John, Neethu Surya, R. Ashwini, R. Sachin Kumar, S. Soman, K.P. Centre for Excellence in Computational Engineering and Networking Amrita Vishwa Vidyapeetham Coimbatore Campus Tamilnadu641112 India

Implementation of data mining algorithms with low cost is one of the challenging tasks in the present world of massively increasing data. The key idea of this paper is to utilize the functionalities of Mathematica which is freely accessible on Raspberry Pi for the purpose of implementing Multi-label classification algorithm with low cost. With the facilities available in Mathematica software for Raspberry Pi, the line of code required for implementing data mining algorithms can be reduced sufficiently. Use of Random Kitchen Sink algorithm improves the accuracy of Multi-label classification and brings improvement in terms of memory usage for large dataset. © 2015 The Authors. Published by Elsevier B.V.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Spike detection of disturbed power signal using VMD

Spike detection of disturbed power signal using VMD

引用

IUTAM Symposium on the Dynamics of Extreme Events Influenced by Climate Change (2013)

作者： Viswanath, Amitha Jyotsna Jose, K. Krishnan, Nithya Sachin Kumar, S. Soman, K.P. Centre for Excellence in Computational Engineering and Networking Amrita Vishwa Vidyapeetham Coimbatore Campus Tamil Nadu641112 India

Most of the electronic equipments are susceptible to power disturbances. Transients are one of the most damaging power disturbances among them. In this paper, a modern adaptive signal decomposition technique called Variational Mode Decomposition (VMD) is used for the detection of impulsive transients or spikes from power *** decomposes the signal effectively in to several Intrinsic Mode Functions (IMF). Each IMF assumes to have a central frequency. The VMD algorithm focuses on finding these central frequencies and intrinsic mode functions using an optimization methodology called Alternating Direction Method of Multipliers (ADMM). In case of spike on a single tone signal like power signal, it is observed that the information about the original signal is dissolved in any of the modes and also observed that the energy of this mode will be higher when compared to other modes. Using the spectral information of this mode the signature of original signal is preserved. The proposed methodology is found to give good result in case of single tone signals. © 2015 The Authors. Published by Elsevier B.V.

关键词： Variational mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Novel svd based character recognition approach for malayalam language script

Advances in Intelligent Systems and Computing

引用

Advances in Intelligent Systems and Computing 2014年 235卷 435-442页

作者： Sachin Kumar, S. Manjusha, K. Soman, K.P. Centre for Excellence in Computational Engineering and Networking Amrita School of Engineering Coimbatore India

ISBN: (纸本)9783319017778

The research on character recognition for Malayalam script dates back to 1990’s. Compared to other Indian languages the research and developments on OCR reported for Malayalam script is very less. The character level and word level accuracy of the existing OCR tools for Indian languages can be improved by implementing robust character recognition and post-processing algorithms. In this paper, we are proposing a character recognition procedure based on Singular Value Decomposition (SVD) and k-Nearest Neighbor classifier (k-NN). The proposed character recognition scheme tested with the dataset created from Malayalam literature books and it could classify 94% of character images accurately. © Springer International Publishing Switzerland 2014.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Implementation of CDMA in GNU radio

Implementation of CDMA in GNU radio

引用

IUTAM Symposium on the Dynamics of Extreme Events Influenced by Climate Change (2013)

作者： Kavitha, P. Meera Mohan, K. Surya, R. Gandhiraj, R. Soman, K.P. Centre for Excellence in Computational Engineering and Networking Amrita Vishwa Vidyapeetham Coimbatore India Department of Electronics and Communication Engineering Amrita Vishwa Vidyapeetham Coimbatore India

This paper proposes the real time implementation of CDMA, a multiple access technique, which brings forth the complete bandwidth usage by spreading the data of same transmitted power, over the whole bandwidth thereby ensuring safe communication and preventing the occurrence of jamming. GNU Radio is a software defined radio which puts experiments into practice using software rather than the normal hardware implementation. Blocks for data spreading, code despreading with and without code tracking are created using Zero Correlation Zone code (ZCZ, a combination of ternary codes that is 1, 0 and -1 which is specified in the program). Thus the real time implementation of CDMA checks the feasibility of an asynchronous multiuser communication among users with good results. © 2015 Published by Elsevier B.V.

关键词： Bandwidth

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：