scholarly journals Classification of Power Quality Disturbance Based on Multiscale Singular Spectral Analysis and Multi Resolution Wavelet Transforms

2019 ◽  
Vol 8 (4) ◽  
pp. 6654-6659
Keyword(s):  
Feature Extraction ◽  
Spectral Analysis ◽  
Power Quality ◽  
Classification Accuracy ◽  
Wavelet Transforms ◽  
Back Propagation ◽  
Renewable Energy Resources ◽  
Statistical Parameters ◽  
Singular Spectral Analysis

In real power system, Power quality disturbances (PQDs) have become major challenge due to the introduction of renewable energy resources and embedded power systems. In this research, two novel feature extraction methods multi resolution analysis wavelet transform (MRA-WT) and Multiscale singular spectral analysis (MSSA) have been analysed with convolution neural network classifier for the classification of PQDs. Statistical parameters are also applied for the optimal feature selection. MSSA is time-series tool and MRA-WT are applied for feature extraction and 1-dimensional CNN (1-DCNN) is used to classify the single and multiple PQDs. The architecture is built with forward propagation and back propagation is utilized to tune the data. Finally, the results of two selected feature extraction techniques are compared with classification accuracy. The simulation based results explained that MSSA with 1-DCNN has significantly higher classification accuracy under different noisy conditions.

scholarly journals Detection and Classification of Power Quality Disturbancewaveform Using MRA Based Modified Wavelet Transfrom and Neural Networks

2010 ◽  
Vol 61 (4) ◽  
pp. 235-240 ◽  
Author(s):  
Perumal Chandrasekar ◽  
Vijayarajan Kamaraj
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Network ◽  
Power Quality ◽  
Wavelet Transforms ◽  
Back Propagation ◽  
Voltage Sag ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Detection and Classification of Power Quality Disturbancewaveform Using MRA Based Modified Wavelet Transfrom and Neural Networks In this paper, the modified wavelet based artificial neural network (ANN) is implemented and tested for power signal disturbances. The power signal is decomposed by using modified wavelet transform and the classification is carried by using ANN. Discrete modified wavelet transforms based signal decomposition technique is integrated with the back propagation artificial neural network model is proposed. Varieties of power quality events including voltage sag, swell, momentary interruption, harmonics, transient oscillation and voltage fluctuation are used to test the performance of the proposed approach. The simulation is carried out by using MATLAB software. The simulation results show that the proposed scheme offers superior detection and classification compared to the conventional approaches.

scholarly journals Feature Extraction and Classification of Citrus Juice by Using an Enhanced L-KSVD on Data Obtained from Electronic Nose

Sensors ◽  
2019 ◽  
Vol 19 (4) ◽  
pp. 916 ◽  
Author(s):  
Wen Cao ◽  
Chunmei Liu ◽  
Pengfei Jia
Keyword(s):  
Feature Extraction ◽  
Kernel Function ◽  
Electronic Nose ◽  
Classification Accuracy ◽  
Extraction Methods ◽  
Object Function ◽  
Optimal Value ◽  
Processed Products

Aroma plays a significant role in the quality of citrus fruits and processed products. The detection and analysis of citrus volatiles can be measured by an electronic nose (E-nose); in this paper, an E-nose is employed to classify the juice which is stored for different days. Feature extraction and classification are two important requirements for an E-nose. During the training process, a classifier can optimize its own parameters to achieve a better classification accuracy but cannot decide its input data which is treated by feature extraction methods, so the classification result is not always ideal. Label consistent KSVD (L-KSVD) is a novel technique which can extract the feature and classify the data at the same time, and such an operation can improve the classification accuracy. We propose an enhanced L-KSVD called E-LCKSVD for E-nose in this paper. During E-LCKSVD, we introduce a kernel function to the traditional L-KSVD and present a new initialization technique of its dictionary; finally, the weighted coefficients of different parts of its object function is studied, and enhanced quantum-behaved particle swarm optimization (EQPSO) is employed to optimize these coefficients. During the experimental section, we firstly find the classification accuracy of KSVD, and L-KSVD is improved with the help of the kernel function; this can prove that their ability of dealing nonlinear data is improved. Then, we compare the results of different dictionary initialization techniques and prove our proposed method is better. Finally, we find the optimal value of the weighted coefficients of the object function of E-LCKSVD that can make E-nose reach a better performance.

Feature Extraction and Classification of Images Based on Corner Invariant Moments

2013 ◽  
Vol 475-476 ◽  
pp. 374-378
Author(s):  
Xue Ming Zhai ◽  
Dong Ya Zhang ◽  
Yu Jia Zhai ◽  
Ruo Chen Li ◽  
De Wen Wang
Keyword(s):  
Feature Extraction ◽  
Classification Accuracy ◽  
Image Feature ◽  
Support Vector ◽  
System Management ◽  
Image Feature Extraction ◽  
Invariant Moments ◽  
Harris Corner ◽  
Classification Of Images

Image feature extraction and classification is increasingly important in all sectors of the images system management. Aiming at the problems that applying Hu invariant moments to extract image feature computes large and too dimensions, this paper presented Harris corner invariant moments algorithm. This algorithm only calculates corner coordinates, so can reduce the corner matching dimensions. Combined with the SVM (Support Vector Machine) classification method, we conducted a classification for a large number of images, and the result shows that using this algorithm to extract invariant moments and classifying can achieve better classification accuracy.

Stationary wavelet singular entropy based electronic tongue for classification of milk

2020 ◽  
Vol 42 (4) ◽  
pp. 870-879 ◽  
Author(s):  
Pauroosh Kaushal ◽  
Rohini Mudhalwadkar
Keyword(s):  
Feature Extraction ◽  
Wavelet Transform ◽  
Classification Accuracy ◽  
Nearest Neighbor ◽  
Back Propagation ◽  
Electronic Tongue ◽  
Cow Milk ◽  
Model Parameters ◽  
K Nearest Neighbor ◽  
Feature Extraction Method

Electronic tongue mimics human gustatory sensation and is used to characterize and discriminate beverages and foods. Feature extraction plays a key role in improving the classification accuracy by preserving the distinct characteristics while reducing high dimensionality of data generated from electronic tongue. This paper presents a new feature extraction method based on stationary wavelet singular entropy for a developed electronic tongue system to classify pasteurized cow milk. The electronic tongue consists of an array of five working electrodes along with a reference and a counter electrode to characterize milk sample. The feature extraction of acquired data is done by computing stationary wavelet transform to obtain detail and approximate coefficients at different level of decomposition. These coefficients are processed using singular value decomposition followed by calculation of entropy to obtain stationary wavelet singular entropy values. These values form the feature set and feed to two classifiers, k-nearest neighbor and back propagation artificial neural network, and their classification accuracy is evaluated with variation in their model parameters. The proposed method is compared with other wavelet transform-entropy methods in terms of classification accuracy, which indicates that the proposed method is more effective in discriminating milk samples.

scholarly journals Power Quality Disturbance Monitoring and Classification Based on Improved PCA and Convolution Neural Network for Wind-Grid Distribution Systems

Energies ◽  
2019 ◽  
Vol 12 (7) ◽  
pp. 1280 ◽  
Author(s):  
Yue Shen ◽  
Muhammad Abubakar ◽  
Hui Liu ◽  
Fida Hussain
Keyword(s):  
Neural Network ◽  
Power Quality ◽  
Distribution System ◽  
Classification Accuracy ◽  
Distribution Systems ◽  
Principal Component ◽  
Original Data ◽  
Convolution Neural Network ◽  
Four Levels

The excessive use of power semiconductor devices in a grid utility increases the malfunction of the control system, produces power quality disturbances (PQDs) and reduces the electrical component life. The present work proposes a novel algorithm based on Improved Principal Component Analysis (IPCA) and 1-Dimensional Convolution Neural Network (1-D-CNN) for detection and classification of PQDs. Firstly, IPCA is used to extract the statistical features of PQDs such as Root Mean Square, Skewness, Range, Kurtosis, Crest Factor, Form Factor. IPCA is decomposed into four levels. The principal component (PC) is obtained by IPCA, and it contains a maximum amount of original data as compare to PCA. 1-D-CNN is also used to extract features such as mean, energy, standard deviation, Shannon entropy, and log-energy entropy. The statistical analysis is employed for optimal feature selection. Secondly, these improved features of the PQDs are fed to the 1-D-CNN-based classifier to gain maximum classification accuracy. The proposed IPCA-1-D-CNN is utilized for classification of 12 types of synthetic and simulated single and multiple PQDs. The simulated PQDs are generated from a modified IEEE bus system with wind energy penetration in the balanced distribution system. Finally, the proposed IPCA-1-D-CNN algorithm has been tested with noise (50 dB to 20 dB) and noiseless environment. The obtained results are compared with SVM and other existing techniques. The comparative results show that the proposed method gives significantly higher classification accuracy.

Disease Classification Using ECG Signals Based on R-Peak Analysis With ABC and ANN

2019 ◽  
Vol 8 (2) ◽  
pp. 67-86 ◽  
Author(s):  
Suman Lata ◽  
Rakesh Kumar
Keyword(s):  
Feature Extraction ◽  
Comparative Analysis ◽  
Classification Accuracy ◽  
Disease Classification ◽  
Cardiac Diseases ◽  
Ecg Signals ◽  
Processing Steps ◽  
Ann Classification ◽  
Selection Of

ECG feature extraction has an important role in identifying a number of cardiac diseases. Lots of work has been done in this field but the most important challenges faced in previous work are the selection of proper R-peaks and R-R intervals due to the lack of appropriate pre-processing steps like decomposition, smoothing, filtering, etc., and the optimization of the features for proper classification. In this article, DWT-based pre-processing and ABC is used for optimization of features which helps to achieve better classification accuracy. It is utilized for initial diagnosis of abnormalities. The signals are taken from MIT-BIH arrhythmia database for the analysis. The aim of the research is to classification of six diseases; Normal, Atrial, Paced, PVC, LBBB, RBBB with an ABC optimization algorithm and an ANN classification algorithm on the basis of the extracted features. Various parameters, like, FAR, FRR, and accuracy are measured for the execution. Comparative analysis is shown of the proposed and the existing work to depict the effectiveness of the work.

scholarly journals Identification and classification of bulk paddy, brown, and white rice cultivars with colour features extraction using image analysis and neural network 

2014 ◽  
Vol 32 (No. 3) ◽  
pp. 280-287 ◽  
Author(s):  
I. Golpour ◽  
ParianJA ◽  
R.A. Chayjan
Keyword(s):  
Neural Network ◽  
Feature Selection ◽  
Classification Accuracy ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Rice Cultivars ◽  
Image Processing Algorithm ◽  
White Rice ◽  
Colour Features

We identify five rice cultivars by mean of developing an image processing algorithm. After preprocessing operations, 36 colour features in RGB, HSI, HSV spaces were extracted from the images. These 36 colour features were used as inputs in back propagation neural network. The feature selection operations were performed using STEPDISC analysis method. The mean classification accuracy with 36 features for paddy, brown and white rice cultivars acquired 93.3, 98.8, and 100%, respectively. After the feature selection to classify paddy cultivars, 13 features were selected for this study. The highest mean classification accuracy (96.66%) was achieved with 13 features. With brown and white rice, 20 and 25 features acquired the highest mean classification accuracy (100%, for both of them). The optimised neural networks with two hidden layers and 36-6-5-5, 36-9-6-5, 36-6-6-5 topologies were obtained for the classification of paddy, brown, and white rice cultivars, respectively. These structures of neural network had the highest mean classification accuracy for bulk paddy, brown and white rice identification (98.8, 100, and 100%, respectively).

Sign in / Sign up

Export Citation Format

Share Document