Contribution of enhanced DWT and non-negative structured sparse representation for image super resolution: A performance analysis

2020 ◽  
Vol 18 (06) ◽  
pp. 2050049
Author(s):  
A. Valli Bhasha ◽  
B. D. Venkatramana Reddy
Keyword(s):  
Sparse Representation ◽  
Hyperspectral Image ◽  
Super Resolution ◽  
Image Resolution ◽  
Discrete Wavelet ◽  
Spotted Hyena ◽  
Resolution Model ◽  
Deep Cnn ◽  
Image Super Resolution ◽  
Two Phases

The image super-resolution methods with deep learning using Convolutional Neural Network (CNN) have been producing admirable advancements. The proposed image resolution model involves the following two main analyses: (i) analysis using Adaptive Discrete Wavelet Transform (ADWT) with Deep CNN and (ii) analysis using Non-negative Structured Sparse Representation (NSSR). The technique termed as NSSR is used to recover the high-resolution (HR) images from the low-resolution (LR) images. The experimental evaluation involves two phases: Training and Testing. In the training phase, the information regarding the residual images of the dataset are trained using the optimized Deep CNN. On the other hand, the testing phase helps to generate the super resolution image using the HR wavelet subbands (HRSB) and residual images. As the main novelty, the filter coefficients of DWT are optimized by the hybrid Fire Fly-based Spotted Hyena Optimization (FF-SHO) to develop ADWT. Finally, a valuable performance evaluation on the two benchmark hyperspectral image datasets confirms the effectiveness of the proposed model over the existing algorithms.

A multi-objective opposition-based barnacles mating optimization for image super resolution using hyper-Spectral images

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Valli Bhasha A. ◽  
Venkatramana Reddy B.D.
Keyword(s):  
Neural Network ◽  
Wavelet Transform ◽  
Convolutional Neural Network ◽  
Super Resolution ◽  
Discrete Wavelet ◽  
Content Type ◽  
Resolution Model ◽  
Deep Cnn ◽  
Image Super Resolution ◽  
Better Than

Purpose The problems of Super resolution are broadly discussed in diverse fields. Rather than the progression toward the super resolution models for real-time images, operating hyperspectral images still remains a challenging problem. Design/methodology/approach This paper aims to develop the enhanced image super-resolution model using “optimized Non-negative Structured Sparse Representation (NSSR), Adaptive Discrete Wavelet Transform (ADWT), and Optimized Deep Convolutional Neural Network”. Once after converting the HR images into LR images, the NSSR images are generated by the optimized NSSR. Then the ADWT is used for generating the subbands of both NSSR and HRSB images. The residual image with this information is obtained by the optimized Deep CNN. All the improvements on the algorithms are done by the Opposition-based Barnacles Mating Optimization (O-BMO), with the objective of attaining the multi-objective function concerning the “Peak Signal-to-Noise Ratio (PSNR), and Structural similarity (SSIM) index”. Extensive analysis on benchmark hyperspectral image datasets shows that the proposed model achieves superior performance over typical other existing super-resolution models. Findings From the analysis, the overall analysis of the suggested and the conventional super resolution models relies that the PSNR of the improved O-BMO-(NSSR+DWT+CNN) was 38.8% better than bicubic, 11% better than NSSR, 16.7% better than DWT+CNN, 1.3% better than NSSR+DWT+CNN, and 0.5% better than NSSR+FF-SHO-(DWT+CNN). Hence, it has been confirmed that the developed O-BMO-(NSSR+DWT+CNN) is performing well in converting LR images to HR images. Originality/value This paper adopts a latest optimization algorithm called O-BMO with optimized Non-negative Structured Sparse Representation (NSSR), Adaptive Discrete Wavelet Transform (ADWT) and Optimized Deep Convolutional Neural Network for developing the enhanced image super-resolution model. This is the first work that uses O-BMO-based Deep CNN for image super-resolution model enhancement.

scholarly journals Fault location identification of double circuit transmission line using discrete wavelet transform

2019 ◽  
Vol 15 (3) ◽  
pp. 1356
Author(s):  
Abdul Hadi Bin Mustapha ◽  
R Hamdan ◽  
F. H. Mohd Noh ◽  
N. A. Zambri ◽  
M. H. A. Jalil ◽  
...  
Keyword(s):  
Fourier Transform ◽  
Wavelet Transform ◽  
Transmission Line ◽  
Fast Fourier Transform ◽  
Discrete Wavelet Transform ◽  
Fault Location ◽  
Detection Algorithm ◽  
Percentage Error ◽  
Discrete Wavelet ◽  
Fast Fourier Transform Algorithm

<span lang="EN-GB">The importance of supplying undisturbed electricity keep increasing due to modernization and lifestyle. Any disturbance in the power system may lead to discontinuation and degradation in the power quality. Therefore, detecting fault, fault type and fault location is a major issue in power transmission system in order to ensure reliable power delivery system. This paper will compare two prominent methods to estimate the fault location of double circuit transmission line. Those methods are Discrete Wavelet Transform algorithm and Fast Fourier Transform algorithm. Simulations has been carried out in MATLAB/Simulink and a variety of fault has been imposed in order to analyse the capability and accuracy of the fault location detection algorithm. Results obtained portrayed that both algorithms provide good performance in estimating the fault location. However, the maximum percentage error produced by the Discrete Wavelet Transform is only 0.25%, 0.6% lower than maximum error produces by Fast Fourier Transform algorithm. As a conclusion, Discrete Wavelet Transform possesses better capability to estimate fault location as compared to Fast Fourier Transform algorithm.</span>

scholarly journals An Approach on MCSA-Based Fault Detection Using Discrete Wavelet Transform and Fault Classification Based on Deep Neural Networks

2021 ◽  
Vol 10 (3) ◽  
pp. 2256-2259
Keyword(s):  
Fourier Transform ◽  
Wavelet Transform ◽  
Fast Fourier Transform ◽  
Discrete Wavelet Transform ◽  
Three Dimensional ◽  
Fault Classification ◽  
Signal Frequency ◽  
Discrete Wavelet ◽  
Novel Approach ◽  
Motor Current Signature Analysis

This paper presents a novel approach on motor current signature analysis (MCSA) forbroken Rotor Bar fault and High Contact Resistance fault using stator current signals as an input from the three phases of Induction motors. Discrete Wavelet Transform is preferred over the Fast Fourier Transform (FFT). Fast Fourier Transform (FFT) converts signals from time domain to frequency domain on the other hand Discrete Wavelet Transform (DWT) gives complete three-dimensional information of the signal, frequency, amplitude, and the time where the frequency components exist. In wavelet analysis, thesignal is converted into scaled and translated version of mother wavelet, which is very irregular so cannot be predicted. Hence, mother wavelets are more appropriate for predicting the local behavior of the signal including irregularities and spikes. In this research features are extracted using DWT and then features are trained in Deep NN sequential model for the purpose of classification of the faults. In this research, MATLAB software has been used for building the motor model in Simulink environment and PyCharm software is used to implement Deep NN for getting accuracy and classification results. This research helps in early detection of the faults that assists in prevention from unscheduled downtimes in industry, economy loss and production loss as well.

scholarly journals Separation of the Structure Signal by the Maximal Overlap Discrete Wavelet Transform and Fast Fourier Transform

2021 ◽  
Vol 2021 ◽  
pp. 1-15
Author(s):  
Thanh Q. Nguyen
Keyword(s):  
Fourier Transform ◽  
Wavelet Transform ◽  
Fast Fourier Transform ◽  
Discrete Wavelet Transform ◽  
Power Spectra ◽  
Vibration Signal ◽  
Discrete Wavelet ◽  
Single Spectrum ◽  
Power Spectral ◽  
Vibration Process

Power spectral density (PSD) is used for evaluating a structure’s vibration process. Moreover, PSD not only shows a discrete form of vibration but also presents various components in a vibration structure. The superposition of multiple vibration patterns on the same spectrum poses difficulty in analyzing the spectral information in the way needed to find the structure’s discrete vibration. This paper proposes a method for separating the synthetic vibration signal into a structure’s discrete vibration and other extraneous vibrations using the maximal overlap discrete wavelet transform (MODWT) method combined with the method of fast Fourier transform (FFT). With the combination of these two algorithms, MODWT and FFT, the signals of the synthesized vibration have been separated into component signals with different frequency ranges. This means that PSD will be formed, which is based on the combination of the single power spectra of the component signals. Thus, the single spectrum of each of these constructed components can be used to evaluate the types of discrete vibrations coexisting in a structure’s vibration process. The survey results in this paper show the sensitivity and suitability of select types of discrete vibrations to be separated out during the assessment of the structural change, so as to achieve the best possible plan for eliminating the unwanted and unexpected noise and vibration components.

Sign in / Sign up

Export Citation Format

Share Document