检索结果-内蒙古大学图书馆

The effects on classifier performance of 2d discrete wavelet transform analysis and whale optimization algorithm for recognition of power quality disturbances

引用

COGNITIVE SYSTEMS RESEARCH 2022年 75卷 1-15页

作者： Karasu, Seckin Sarac, Zehra Zonguldak Bulent Ecevit Univ Elect & Elect Engn Dept TR-67100 Zonguldak Turkey Istanbul Medeniyet Univ Elect & Elect Engn Dept TR-34700 Istanbul Turkey

Power Quality (PQ) is becoming more and more important day by day in the electric network. signal processing, pattern recognition and machine learning are increasingly being studied for the automatic recognition of any disturbances that may occur during the generation, transmission, and distribution of electricity. There are three main steps to identify the PQ disturbances. These include the use of signal processing methods to calculate the features representing the disturbances, the selection of those that are more useful than these feature sets to prevent the creation of a complex classification model, the creating a classification model that recognizes multiple classes using the selected feature subsets. In this study, one-dimensional (1d) PQ disturbances signals are transformed into two-dimensional (2d) signals, 2d discrete wavelet transforms (2d-dWT) are used to extract the features. The features are extracted by using the wavelet families such as daubechies, Biorthogonal, Symlets, Coiflets and Fejer-Korovkin in 2d-dWT to analyze PQ disturbances. Whale Optimization Algorithm (WOA) and k-nearest neighbor (KNN) classifier determine the feature subsets. Then, WOA and k nearest neighbor (KNN) classifier are used to determine the feature group. By using KNN and Support Vector Machines (SVM) classifi-cation methods, Classifier models that distinguish PQ disturbances are formed. The main aim of the study is to determine the features derived from 2d wavelet coefficients for different wavelet families and to determine which of them has a better classification performance to distinguish PQ disturbances signals. At the same time, different classification methods are simulated and a model which can classify PQ disturbances signals with high performance is created. Also, the generated models are analysed for their performance in terms of different noise levels (40 dB, 30 dB, 20 dB). The result of this simulation study shows that the model developed to classify PQ disturbanc

关键词： Power quality disturbances 2d discrete wavelet transform Wavelet families Whale optimization algorithm 2d signal processing Evolutionary feature selection

来源：评论

学校读者我要写书评

暂无评论

Investigation of power quality disturbances by using 2d discrete orthonormal S-transform, machine learning and multi-objective evolutionary algorithms

引用

SWARM ANd EVOLUTIONARY COMPUTATION 2019年 44卷 1060-1072页

作者： Karasu, Seckin Sarac, Zehra Zonguldak Bulent Ecevit Univ Elect & Elect Engn Dept TR-67100 Zonguldak Turkey

The aim of this paper is to investigate the power quality analysis by using 2d discrete orthonormal S-transform, machine learning and multi-objective evolutionary algorithms. The fact that PQ signals are one-dimensional (1d) signals due to their nature leads to the search for feature extraction approaches based on 1d signal processing methods. due to the electric network is getting more and more complicated day by day, it is necessary to determine effectively the disturbances events. In the proposed method, extraction of a new feature based on two-dimensional (2d) signal processing by 2d Fast discrete Orthonormal Stockwell Transform (2d-FdOST) method and determination of the most suitable feature group by Non-dominated Sorting Genetic Algorithm II (NSGA-II) method are performed. Eleven different PQ events are synthetically produced based on mathematical modelling. 1d signals are transformed into 2d signals with equal row and column numbers. Statistical and image-based features are created on the amplitude and phase matrices obtained by 2d-FdOST method from 2d signals. The NSGA-II method, which is one of the multi-objective evolutionary optimization methods, is used to convert a large number of feature vectors into a small number of useful feature groups. NSGA-II produces the optimal solution for two different fitness functions that calculate the number of features and classifier performance. By using different machine learning classifiers for selected features, a model classifying PQ disturbances with high performance and robust structure against noisy situations is created.

关键词： Power quality disturbances 2d-fast discrete orthonormal Stockwell Transform Multi-objective evolutionary feature selection NSGA-II 2d signal processing

来源：评论

学校读者我要写书评

暂无评论

A deterministic Compressive Sensing Approach for Compressed domain Image Analysis

A Deterministic Compressive Sensing Approach for Compressed ...

引用

IEEE International Symposium on signal processing and Information Technology (ISSPIT)

作者： Mitra, dipayan Rajan, Sreeraman Balaji, Bhashyam Carleton Univ Dept Syst & Comp Engn Ottawa ON Canada Def R&D Canada 3701 Carling Ave Ottawa ON Canada

ISBN: (纸本)9781538675687

Compressive sensing (CS) is a signal processing technique for acquiring sparse signals at sampling rates much lower than the Nyquist rate. Traditionally to avoid generation of large sensing matrices for 2d signals or images, individual rows or columns of the images are compressed in the sensing phase. This increases the number of matrix multiplication operations and results in a compressed image with a different aspect ratio than the original uncompressed image. To overcome these issues, in this paper, we investigate a 2d deterministic sensing technique that maintains both the aspect ratio and the morphology of the image. We use a linear filtering-based measurement matrix. Through this paper, we demonstrate that deterministic CS will preserve the features and there by enable analysis of the images such as detection and identification of objects in the compressed domain without the need to perform a computationally expensive reconstruction. In order to demonstrate this, images obtained by infra-red electro-optic camera on an airborne platform (low resolution), LandSat (medium resolution) and multispectral images (high resolutions) are chosen. Features of chosen objects from an uncompressed image are compared with those corresponding objects in the compressed image using template matching to demonstrate that such image analysis can be done in the compressed domain. Frobenius norm-based structural similarity analysis for the images at different levels of compression is presented to demonstrate the similarity in structure. Robustness of the deterministic CS technique is shown by performing template matching based image analysis on noisy compressed images.

关键词： Compressive Sensing 2d signal processing Image processing Feature Extraction Frobenius Norm SURF Algorithm

来源：评论

学校读者我要写书评

暂无评论

A deterministic Compressive Sensing Approach for Compressed domain Image Analysis 14

A Deterministic Compressive Sensing Approach for Compressed ...

引用

14th IEEE Sensors Applications Symposium (SAS)

作者： Mitra, dipayan Rajan, Sreeraman Balaji, Bhashyam Carleton Univ Dept Syst & Comp Engn Ottawa ON Canada Def R&D Canada 3701 Carling Ave Ottawa ON Canada

ISBN: (纸本)9781538677131

Compressive sensing (CS) is a signal processing technique for acquiring sparse signals at sampling rates much lower than the Nyquist rate. Traditionally to avoid generation of large sensing matrices for images, the columns or rows are compressed in the sensing phase. This increases the number of matrix multiplication operations and results in a compressed image with a different aspect ratio than the original uncompressed image. To overcome these issues, in this paper, we investigate a 2d deterministic sensing technique that maintains both the aspect ratio and the morphology of the image. We use a linear filtering-based measurement matrix. Through this paper, we demonstrate that deterministic CS will preserve the features and there by enable analysis of the images such as detection and identification of objects in the compressed domain without the need to perform a computationally expensive reconstruction. In order to demonstrate this, images obtained by infra-red electro-optic camera on an airborne platform (low resolution), LandSat (medium resolution) and multispectral images (high resolution) are chosen. Features of chosen objects from an uncompressed image are compared with those of corresponding objects in the compressed image using template matching to demonstrate that image analysis can be done in the compressed domain. Frobenius norm-based structural similarity analysis for the images at different levels of compression is presented to demonstrate the similarity in structure. Robustness of the deterministic CS technique is demonstrated through template matching using SURF algorithm.

关键词： Compressive Sensing 2d signal processing Image processing Feature Extraction Frobenius Norm SURF 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：