Weighted Signal-to-noise Ratio Research Articles

Non-redundant shift-invariant complex wavelet transform and fractional gorilla troops optimization-based deep convolutional neural network for video watermarking

With the development of multimedia processing approaches along with the Internet leads to various issues, like data tampering, data piracy, and illicit dissemination. The quick progression of fast communication networks for digital video transmission has formulated the prerequisite copyright protection for these media. On the other hand, the development of Internet technologies has directed the accessibility of images, audio, and videos in different structures. Moreover, unlicensed users manipulate the utilization of multimedia by broadcasting them on numerous internet sites to get money fraudulently without the involvement of the original copyright holder. Besides, watermarking is a process utilized to hide the watermark sign present in the multimedia statistics that are not perceptible to an intruder for manipulating any information. This paper devised a novel video watermarking technique which uses an optimized deep learning technique. Here, the binary pixel map generation is performed using DCNN for self-embedding in input video. In addition, weights as well as bias of DCNN are trained by designed Fractional Gorilla Troops Optimization-Deep Convolutional Neural Network algorithm, thus FGTO_DCNN algorithm is developed. Accordingly, the FGTO technique is newly introduced by integrating FC along with GTO algorithm. Moreover, non-redundant Shift Invariant Complex Wavelet Transform (SICWT) is employed for extracted key frame and thus watermark image is fed into embedding process. After that, inverse non-redundant SICWT is applied for embedding video, which is further passed to key frame extraction in extraction stage. Finally, non-redundant SICWT is utilized for obtaining extracted watermark image. The developed FGTO-driven DCNN model attained improved performance than other existing video watermarking techniques with Mean Square Error (MSE) of 0.0437, Normalized Correlation Coefficient (NCC) of 0.9998, high Peak Signal-to-Noise Ratio (PSNR) value of 51.93 dB, and high Weighted Signal-to-Noise Ratio (WSNR) of 49.86 dB.

Feature selection for high dimensional microarray gene expression data via weighted signal to noise ratio.

Feature selection in high dimensional gene expression datasets not only reduces the dimension of the data, but also the execution time and computational cost of the underlying classifier. The current study introduces a novel feature selection method called weighted signal to noise ratio (WSNR) by exploiting the weights of features based on support vectors and signal to noise ratio, with an objective to identify the most informative genes in high dimensional classification problems. The combination of two state-of-the-art procedures enables the extration of the most informative genes. The corresponding weights of these procedures are then multiplied and arranged in decreasing order. Larger weight of a feature indicates its discriminatory power in classifying the tissue samples to their true classes. The current method is validated on eight gene expression datasets. Moreover, results of the proposed method (WSNR) are also compared with four well known feature selection methods. We found that the (WSNR) outperform the other competing methods on 6 out of 8 datasets. Box-plots and Bar-plots of the results of the proposed method and all the other methods are also constructed. The proposed method is further assessed on simulated data. Simulation analysis reveal that (WSNR) outperforms all the other methods included in the study.

Multiscale Transform and Shrinkage Thresholding Techniques for Medical Image Denoising – Performance Evaluation

Abstract Due to sparsity and multiresolution properties, Mutiscale transforms are gaining popularity in the field of medical image denoising. This paper empirically evaluates different Mutiscale transform approaches such as Wavelet, Bandelet, Ridgelet, Contourlet, and Curvelet for image denoising. The image to be denoised first undergoes decomposition and then the thresholding is applied to its coefficients. This paper also deals with basic shrinkage thresholding techniques such Visushrink, Sureshrink, Neighshrink, Bayeshrink, Normalshrink and Neighsureshrink to determine the best one for image denoising. Experimental results on several test images were taken on Magnetic Resonance Imaging (MRI), X-RAY and Computed Tomography (CT). Qualitative performance metrics like Peak Signal to Noise Ratio (PSNR), Weighted Signal to Noise Ratio (WSNR), Structural Similarity Index (SSIM), and Correlation Coefficient (CC) were computed. The results shows that Contourlet based Medical image denoising methods are achieving significant improvement in association with Neighsureshrink thresholding technique.

Static Thresholded Pulse Coupled Neural Networks in Contourlet Domain — A New Framework for Medical Image Denoising

Image denoising, a significant research area in the field of medical image processing, makes an effort to recover the original image from its noise corrupted image. The Pulse Coupled Neural Networks (PCNN) works well against denoising a noisy image. Generally, image denoising techniques are directly applied on the pixels. From the literature review, it is reported that denoising after frequency domain transformation is performing better since noise removal is applied over the coefficients. Motivated by this, in this paper, a new technique called the Static Thresholded Pulse Coupled Neural Network (ST-PCNN) is proposed by combining PCNN with traditional filtering or threshold shrinkage technique in Contourlet Transform domain. Four different existing PCNN architectures, such as Neuromime Structure, Intersecting Cortical Model, Unit-Linking Model and Multichannel Model are considered for comparative analysis. The filters such as Wiener, Median, Average, Gaussian and threshold shrinkage techniques such as Sure Shrink, HeurShrink, Neigh Shrink, BayesShrink are used. For noise removal, a mixture of Speckle and Gaussian noise is considered for a CT skull image. A mixture of Rician and Gaussian noise is considered for MRI brain image. A mixture of Speckle and Salt and Pepper noise is considered for a Mammogram image. The Performance Metrics such as Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), Image Quality Index (IQI), Universal Image Quality Index (UQI), Image Enhancement Filter (IEF), Structural Content (SC), Correlation Coefficient (CC), and Weighted Signal-to-Noise Ratio (WSNR) and Visual Signal-to-Noise Ratio (VSNR) are used to evaluate the performance of denoising.

Wavelet Based Waveform Distortion Measures for Assessment of Denoised EEG Quality With Reference to Noise-Free EEG Signal

An objective distortion measure is very crucial to accurately quantify the distortion introduced in the electroencephalogram (EEG) signal during the denoising process. Most of the existing algorithms report their denoising performance by comparing the original EEG signal and the reconstructed EEG signal using root mean square error (RMSE) and other similar measures. However, it is very important to quantify the distortion in each band of EEG signal since each band provides distinct information about the specific brain activity. Furthermore, quantification of band-wise distortion enables the selection of particular denoising algorithm for the application-specific EEG signal analysis. Therefore, in this paper, we propose two robust distortion measures such as weighted signal to noise ratio (WSNR) and weighted correlation coefficient (WCC) for accurately representing the objective reconstruction loss in each band. These performance measures are computed between the wavelet subbands of the original and the denoised/reconstructed signal with weights equal to the relative wavelet energy and wavelet entropy of the corresponding subband wavelet coefficients. To demonstrate the effectiveness of the proposed performance measures, we evaluate the performance of six existing denoising methods using these measures. Results depict that these measures can adequately provide high mutual agreement between objective scores and subjective analysis.

Weighted signal-to-noise ratio robust design for a new double sampling [formula omitted] chart

Recently, to monitor the mean shifts of a process by using attribute inspection, a new np chart, called npx chart, was proposed to synthesize the advantages of attribute and variable charts. Attracted by the easy-implementation property and good performance of this chart, in this paper, we propose a double-sampling (DS) npx chart to improve the efficiency of the single-sampling npx chart. We build up a process cost model to compare the performance of DS npx chart and the traditional npx chart. To minimize the process cost with uncertainty, we introduce a robust design method based on the “weighted signal-to-noise ratio (WSNR)”. Specifically, we take into account the weighted expectation on multiple scenarios and regard signal-to-noise ratio as a response to variance. Compared to the traditional designs, the WSNR robust design not only preserves the statistical strengths and economic efficiency, but also shows the advantages of flexibility and adaptability. Then, numerical experiments are conducted to measure the performance of our model. The results demonstrate that the DS npx chart is superior to the npx chart in controlling the ARL1 and the process cost. By analyzing the process cost, we find that the larger the scenario range is, the better the WSNR robust design performs. In addition, the performance of the proposed robust design presents clear advantages to the existing robust measures (e.g., absolute robustness, robust deviation, and relative robustness), for which the WSNR will be a promising approach for the practitioners.

An underdamped stochastic resonance method with stable-state matching for incipient fault diagnosis of rolling element bearings

Most traditional overdamped monostable, bistable and even tristable stochastic resonance (SR) methods have three shortcomings in weak characteristic extraction: (1) their potential structures characterized by single stable-state type are insufficient to match with the complicated and diverse mechanical vibration signals; (2) they vulnerably suffer the interference from multiscale noise and largely depend on the help of highpass filters whose parameters are selected subjectively, probably resulting in false detection; and (3) their rescaling factors are fixed as constants generally, thereby ignoring the synergistic effect among vibration signals, potential structures and rescaling factors. These three shortcomings have limited the enhancement ability of SR. To explore the SR potential, this paper initially investigates the SR in a multistable system by calculating its output spectral amplification, further analyzes its output frequency response numerically, then examines the effect of both damping and rescaling factors on output responses and finally presents a promising underdamped SR method with stable-state matching for incipient bearing fault diagnosis. This method has three advantages: (1) the diversity of stable-state types in a multistable potential makes it easy to match with various vibration signals; (2) the underdamped multistable SR, equivalent to a moving nonlinear bandpass filter that is dependent on the rescaling factors, is able to suppress the multiscale noise; and (3) the synergistic effect among vibration signals, potential structures and rescaling and damping factors is achieved using quantum genetic algorithms whose fitness functions are new weighted signal-to-noise ratio (WSNR) instead of SNR. Therefore, the proposed method is expected to possess good enhancement ability. Simulated and experimental data of rolling element bearings demonstrate its effectiveness. The comparison results show that the proposed method is able to obtain higher amplitude at target frequency and larger output WSNR, and performs better than traditional SR methods.

The low concentration gas detection based on parameters tuning stochastic resonance

The stochastic resonance (SR) theory provides a new method for the detection of weak signal submerged in strong noise. Aiming at the shortcomings of the existing technologies in low concentrations gas detection and the difficulties in optimising the system parameters of stochastic resonance, this paper proposed an adaptive parameters tuning algorithm and applied it in low concentrations gas detection. First, the input signal is preprocessed to satisfy the requirements of SR system, then we developed the adaptive parameters tuning algorithm to seek the maximum weighted signal-to-noise ratio (WSNR), which was used to evaluate the performance of the system. In the end, the relationship between the maximum WSNR and concentration of gas was analysed. The experiment results indicate that the proposed method is effective in low concentrations gas detection and could be expanded to other practical engineering applications.

Attenuating noise from computed tomography medical images using a coefficients‐driven total variation denoising algorithm

ABSTRACTThe aim of image denoising is to recover a visually accepted image from its noisy observation with as much detail as possible. The noise exists in computed tomography images due to hardware errors, software faults and/or low radiation dose. Because of noise, the analysis and extraction of accurate medical information is a challenging task for specialists. Therefore, a novel modification on the total variational denoising algorithm is proposed in this article to attenuate the noise from CT images and provide a better visual quality. The newly developed algorithm can properly detect noise from the other image components using four new noise distinguishing coefficients and reduce it using a novel minimization function. Moreover, the proposed algorithm has a fast computation speed, a simple structure, a relatively low computational cost and preserves the small image details while reducing the noise efficiently. Evaluating the performance of the proposed algorithm is achieved through the use of synthetic and real noisy images. Likewise, the synthetic images are appraised by three advanced accuracy methods –Gradient Magnitude Similarity Deviation (GMSD), Structural Similarity (SSIM) and Weighted Signal‐to‐Noise Ratio (WSNR). The empirical results exhibited significant improvement not only in noise reduction but also in preserving the minor image details. Finally, the proposed algorithm provided satisfying results that outperformed all the comparative methods.

Fault feature enhancement of gearbox in combined machining center by using adaptive cascade stochastic resonance

The difficulty to select the best system parameters restricts the engineering application of stochastic resonance (SR). An adaptive cascade stochastic resonance (ACSR) is proposed in the present study. The proposed method introduces correlation theory into SR, and uses correlation coefficient of the input signals and noise as a weight to construct the weighted signal-to-noise ratio (WSNR) index. The influence of high frequency noise is alleviated and the signal-to-noise ratio index used in traditional SR is improved accordingly. The ACSR with WSNR can obtain optimal parameters adaptively. And it is not necessary to predict the exact frequency of the target signal. In addition, through the secondary utilization of noise, ACSR makes the signal output waveform smoother and the fluctuation period more obvious. Simulation example and engineering application of gearbox fault diagnosis demonstrate the effectiveness and feasibility of the proposed method.

Efficient two-stage vector quantization speech coder using wavelet coefficients of excitation signals

An improved backward prediction coder featuring two-stage vector quantization (VQ) of shape codevectors is presented. Efficient two-stage VQ is achieved using the wavelet coefficients of excitation signals; i.e., wavelet coefficients are calculated by applying a discrete wavelet transform to excitation signals, and the results are divided into an approximation group and a detail group. The data lengths of both approximation and detail coefficients are half that of conventional two-stage VQ systems. Simulation results show that the proposed coder achieves a better weighted signal-to-noise ratio (WSNR) than conventional coders and, in terms of reconstructed speech quality, ranks between the FS-1016 Code Excited Linear Prediction (CELP) coder and the Vector Sum Excited Linear Predictive Coding (VSELP) coder.

Perceptually weighted vector quantisation in the DCT domain

A new vector quantisation scheme based on a perceptually weighted signal-to-noise ratio (WSNR) is proposed. The Letter shows that the application of the LBG procedure in the DCT domain using the WSNR as the function to be optimised leads to substantial improvement in the perceptual quality of the decoded images, compared to the LBG procedure in the pixel domain.

静止画の画質を評価するための空間周波数領域上の重み付け関数の実験的導出

A “weighting function” is defined for evaluating monochrome still-picture quality in the spatial frequency domain. The weighting values of the function can be determined from the relationship between the MOS (Mean Opinion Score) and the spatial-frequency-selective noise level. A hundred and six weighting values are calculated in the spatial frequency dommain of 256 (TV lines) x 256 (TV lines). When the ratio of viewing distance to picture height is 7, the weighting value at 3 (cpd, cycle per degree) shows maximum value. The function is isotropic in the region from 3 (cpd) to 8 (cpd) and anisotropic at over 10 (cpd).Using the weighting function, a new objective measure named WSNR (Weighted Signal-to-Noise Ratio) is also defined and applied to pictures degraded artificially. The picture quality is degraded by adding random noise, by passing through a two-dimensional low-pass filter, or by distorting blocks. Experiments using different portrait pictures show good correlation coefficients between the MOS and the WSNR, 0.93-0.97.