scholarly journals Detection and Classification of Recessive Weakness in Superbuck Converter Based on WPD-PCA and Probabilistic Neural Network

Electronics ◽  
2019 ◽  
Vol 8 (3) ◽  
pp. 290 ◽  
Author(s):  
Chenhao Wu ◽  
Jiguang Yue ◽  
Li Wang ◽  
Feng Lyu
Keyword(s):  
Neural Network ◽  
Classification Accuracy ◽  
Wavelet Decomposition ◽  
Probabilistic Neural Network ◽  
Wavelet Packet ◽  
Principal Component ◽  
Excellent Performance ◽  
Feature Vectors ◽  
Parseval’S Theorem

This paper proposes a detection and classification method of recessive weakness in Superbuck converter through wavelet packet decomposition (WPD) and principal component analysis (PCA) combined with probabilistic neural network (PNN). The Superbuck converter presents excellent performance in many applications and is also faced with today’s demands, such as higher reliability and steadier operation. In this paper, the detection and classification issue to recessive weakness is settled. Firstly, the performance of recessive weakness both in the time and frequency domain are demonstrated to clearly show the actual deterioration of the circuit system. The WPD and Parseval’s theorem are utilized in this paper to feature the extraction of recessive weakness. The energy discrepancy of the fault signals at different wavelet decomposition levels are then chosen as the feature vectors. PCA is also employed to the dimensionality reduction of feature vectors. Then, a probabilistic neural network is applied to automatically detect and classify the recessive weakness from different components on the basis of the extracted features. Finally, the classification accuracy of the proposed classification algorithm is verified and tested with experiments, which present satisfying classification accuracy.

scholarly journals Classification of Emotional Speech of Children Using Probabilistic Neural Network

2015 ◽  
Vol 5 (2) ◽  
pp. 311 ◽  
Author(s):  
Hemanta Kumar Palo ◽  
Mihir Narayan Mohanty
Keyword(s):  
Neural Network ◽  
Probability Density ◽  
Classification Accuracy ◽  
Probabilistic Neural Network ◽  
Probability Density Functions ◽  
Density Functions ◽  
Emotional Speech ◽  
Reasonable Accuracy ◽  
Class Probability

<p>Child emotions are highly flexible and overlapping. The recognition is a difficult task when single emotion conveys multiple informations. We analyze the relevance and importance of these features and use that information to design classifier architecture. Designing of a system for recognition of children emotions with reasonable accuracy is still a challenge specifically with reduced feature set. In this paper, Probabilistic neural network (PNN) has been designed for such task of classification. PNN has faster training ability with continuous class probability density functions. It provides better classification even with reduced feature set. LP_VQC and pH vectors are used as the features for the classifier. It has been attempted to design the PNN classifier with these features. Various emotions like angry, bore, sad and happy have been considered for this piece of work. All these emotions have been collected from children in three different languages as English, Hindi, and Odia. Result shows remarkable classification accuracy for these classes of emotions. It has been verified in standard databse EMO-DB to validate the result.</p>

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.

scholarly journals A Five-Level Wavelet Decomposition and Dimensional Reduction Approach for Feature Extraction and Classification of MR and CT Scan Images

2017 ◽  
Vol 2017 ◽  
pp. 1-9 ◽  
Author(s):  
Varun Srivastava ◽  
Ravindra Kumar Purwar
Keyword(s):  
Neural Network ◽  
Ct Scan ◽  
Wavelet Decomposition ◽  
Nearest Neighbor ◽  
Principal Component ◽  
Two Dimensional ◽  
Mr Images ◽  
Probabilistic Principal Component Analysis ◽  
Different Sources

This paper presents a two-dimensional wavelet based decomposition algorithm for classification of biomedical images. The two-dimensional wavelet decomposition is done up to five levels for the input images. Histograms of decomposed images are then used to form the feature set. This feature set is further reduced using probabilistic principal component analysis. The reduced set of features is then fed into either K nearest neighbor algorithm or feed-forward artificial neural network, to classify images. The algorithm is compared with three other techniques in terms of accuracy. The proposed algorithm has been found better up to 3.3%, 12.75%, and 13.75% on average over the first, second, and third algorithm, respectively, using KNN and up to 6.22%, 13.9%, and 14.1% on average using ANN. The dataset used for comparison consisted of CT Scan images of lungs and MR images of heart as obtained from different sources.

scholarly journals Classification of malignant and Benign Lung Using Probabilistic Neural Network

2019 ◽  
pp. 307-311
Author(s):  
Asmitha Shree R ◽  
Sajitha M ◽  
Subha S
Keyword(s):  
Neural Network ◽  
Computed Tomography ◽  
Lung Cancer ◽  
Feature Extraction ◽  
Probabilistic Neural Network ◽  
Principal Component ◽  
Classification Performance ◽  
Cancer Types ◽  
Extraction Stage

Lung Cancer is considered as one of the deadliest diseases among other lung disorders and cancer types and is the leading cause of cancer deaths worldwide. Lung cancer is a curable disease if detected in its early stages that makes up 13% of all cancer diagnoses and 27% of all cancer deaths. The objective of this paper is mainly focused on categorizing the patients Computed Tomography (CT) lung images as normal or abnormal. The images are subjected to segmentation to focus on detecting the cancerous region to classify. Effective feature selection and feature extraction is made by applying Watershed Transform and Principal Component Analysis. The emphasis is on the feature extraction stage to yield a better classification performance. The classification of CT images as benign or malignant is done using Machine Learning based Neural Network.

scholarly journals ISAR Image Classification with Wavelet and Watershed Transforms

2016 ◽  
Vol 6 (6) ◽  
pp. 3087
Author(s):  
B. Mamatha ◽  
V. Valli Kumar
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Image Classification ◽  
Classification Accuracy ◽  
Feature Vector ◽  
Synthetic Aperture ◽  
Watershed Transform ◽  
Feature Vectors ◽  
Radar Images

<p>Inverse Synthetic Aperture Radar images are playing a significant role in classification of sea and air targets. First we acquire the ISAR images of targets using a sensor like radar and extract the characteristics of targets from the ISAR images in the form of feature vectors. The computed feature vectors are used for classification of targets. In this work, widely used and efficient segmentation tool Watershed transform and the multi resolution technique wavelet transform are explored to derive the target features. An artificial neural network based classifier is used for classification. The Wavelet analysis divides the information of an image into approximation and detail sub signals. The approximate and three detail sub signal values are taken as feature vectors and given as input to the classifier for ship ISAR image classification. The widely used segmentation technique, Watershed transform is applied to the ISAR images. The wavelet coefficients are computed for the segmented ISAR images and used as feature vectors for classification of the ISAR images. Also, the statistical moments mean and standard deviation are computed for the color ISAR images itself, taken in RGB format. These statistical color moments are used as feature vector.  The classification accuracy is compared for the feature vectors.</p>

ISAR Image Classification with Wavelet and Watershed Transforms

2016 ◽  
Vol 6 (6) ◽  
pp. 3087 ◽  
Author(s):  
B. Mamatha ◽  
V. Valli Kumar
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Image Classification ◽  
Classification Accuracy ◽  
Feature Vector ◽  
Synthetic Aperture ◽  
Watershed Transform ◽  
Feature Vectors ◽  
Radar Images

<p>Inverse Synthetic Aperture Radar images are playing a significant role in classification of sea and air targets. First we acquire the ISAR images of targets using a sensor like radar and extract the characteristics of targets from the ISAR images in the form of feature vectors. The computed feature vectors are used for classification of targets. In this work, widely used and efficient segmentation tool Watershed transform and the multi resolution technique wavelet transform are explored to derive the target features. An artificial neural network based classifier is used for classification. The Wavelet analysis divides the information of an image into approximation and detail sub signals. The approximate and three detail sub signal values are taken as feature vectors and given as input to the classifier for ship ISAR image classification. The widely used segmentation technique, Watershed transform is applied to the ISAR images. The wavelet coefficients are computed for the segmented ISAR images and used as feature vectors for classification of the ISAR images. Also, the statistical moments mean and standard deviation are computed for the color ISAR images itself, taken in RGB format. These statistical color moments are used as feature vector.  The classification accuracy is compared for the feature vectors.</p>

scholarly journals Hyperspectral Image Classification Based on Multi-Scale Residual Network with Attention Mechanism

2021 ◽  
Vol 13 (3) ◽  
pp. 335
Author(s):  
Yuhao Qing ◽  
Wenyi Liu
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Image Classification ◽  
Classification Accuracy ◽  
Hyperspectral Image ◽  
Principal Component ◽  
Hyperspectral Image Classification ◽  
Deep Network ◽  
Multi Scale

In recent years, image classification on hyperspectral imagery utilizing deep learning algorithms has attained good results. Thus, spurred by that finding and to further improve the deep learning classification accuracy, we propose a multi-scale residual convolutional neural network model fused with an efficient channel attention network (MRA-NET) that is appropriate for hyperspectral image classification. The suggested technique comprises a multi-staged architecture, where initially the spectral information of the hyperspectral image is reduced into a two-dimensional tensor, utilizing a principal component analysis (PCA) scheme. Then, the constructed low-dimensional image is input to our proposed ECA-NET deep network, which exploits the advantages of its core components, i.e., multi-scale residual structure and attention mechanisms. We evaluate the performance of the proposed MRA-NET on three public available hyperspectral datasets and demonstrate that, overall, the classification accuracy of our method is 99.82 %, 99.81%, and 99.37, respectively, which is higher compared to the corresponding accuracy of current networks such as 3D convolutional neural network (CNN), three-dimensional residual convolution structure (RES-3D-CNN), and space–spectrum joint deep network (SSRN).

Sign in / Sign up

Export Citation Format

Share Document