Narrow Results

Parkinson’s disease (PD) occurs while particular cells of the brain are not able to create dopamine that is required for regulating the count of non-motor as well as motor activities of the human body. One of the earlier symptoms of PD is voice disorder and current research shows that approximately about 90% of patients affected by PD suffer from vocal disorders. Hence, it is vital to extract pathology information in voice signals for detecting PD, which motivates to devise the approaches for feature selection and classification of PD. Here, an effectual technique is devised for the classification of PD, which is termed as Hybrid Leader Namib beetle optimization algorithm-based LeNet (HLNBO-based LeNet). The considered input voice signal is subjected to pre-processing of the signal phase. The pre-processing is carried out to remove the noises and calamities using a Gaussian filter whereas in the feature extraction phase, several features are extracted. The extracted features are given to the feature selection stage that is performed employing the Hybrid Leader Squirrel Search Water algorithm (HLSSWA), which is the combination of Hybrid Leader-Based Optimization (HLBO), Squirrel Search Algorithm (SSA), and Water Cycle Algorithm (WCA) by considering the Canberra distance as the fitness function. The PD classification is conducted using LeNet, which is tuned by the designed HLNBO. Additionally, HLNBO is newly presented by merging HLBO and the Namib beetle optimization algorithm (NBO). Thus, the new technique achieved maximal values of accuracy, TPR, and TNR of about 0.949, 0.957, and 0.936, respectively.

The medical images are considered an essential part of healthcare applications. The noise associated with the images can minimize the clearness of the image, which leads to the misidentification of the diseases. Hence, the denoising of images is an essential process in healthcare applications. In this work, a medical image denoising method based on chronological walrus behavior optimization (CWaOA) is proposed. The process begins by identifying the noisy pixels in the image, which is achieved using LeNet to detect the noisy pixel map. The CWaOA algorithm is used for removing the noise from the image. To enhance the image pixels, the vectorial total variation (VTV) norm is employed. Simultaneously, the input image undergoes transformation using the dual-tree complex wavelet transform (DTCWT) to process its low-frequency components. A Gaussian filter is applied for image filtering, and the denoised image is obtained by applying inverse DTCWT. Based on the image quality accessed metrics like natural image quality evaluator (NIQE), universal quality index (UQI), and structural similarity index (SSIM), the denoised image and pixel-enhanced image fusion is done at the final step. Additionally, the performance of the model is evaluated using the peak signal-to-noise ratio (PSNR), second derivative-like measure of enhancement (SDME), and SSIM metrics, yielding superior results with PSNR of 30.03 dB, SDME of 41.94 dB, and SSIM of 0.883. The source code of the article is available at “ https://github.com/Rashmita-S/CWaOA.git”.

One of the nice properties of the Gaussian scale space map is its well behavedness. This rather well-behaved nature is somewhat deceptive, however, as portions of the map may not have any direct relationship to the features in the unfiltered image.⁴ It has been shown that not all zero-crossing surface patches can be associated with intensity changes in the unfiltered image. Zero-crossings give rise to both authentic and phantom scale map contours. Recently, we proposed an edge enhancement operator, the LWF, which is a weighted combination of the Gaussian and its second derivative.⁶ In this paper, we prove analytically and demonstrate experimentally that the LWF produces the authentic scale map contours only. We also show that the LWF has excellent edge localization (i.e. the points marked by the operator is very close to center of the true edge). A performance comparison between the Laplacian of Gaussian and LWF operators with respect to the localization property is also presented.

Inspite of technological advancement, inherent processing capability of current age sensors limits the desired details in the acquired image for variety of remote sensing applications. Pan-sharpening is a prominent scheme to integrate the essential spatial details inferred from panchromatic (PAN) image and the desired spectral information of multispectral (MS) image. This paper presents an effective two-stage pan-sharpening method to produce high resolution multispectral (HRMS) image. The proposed method is based on the premise that the HRMS image can be formulated as an amalgam of spectral and spatial components. The spectral components are estimated by processing the interpolated MS image with a filter approximated with modulation transfer function (MTF) of the sensor. Sparse representation theory is adapted to construct the spatial components. The high-frequency details extracted from the PAN image and its low resolution variant are utilized to construct dual dictionaries. The dictionaries are jointly learned by an efficient training algorithm to enhance the adaptability. The hypothesis of sparse coefficients invariance over scales is also incorporated to reckon the appropriate spatial information. Further, an iterative filtering mechanism is developed to enhance the quality of fused image. Four distinct datasets generated from QuickBird, IKONOS, Pléiades and WorldView-2 sensors are used for experimentation. The comprehensive assessment at reduced-scale and full-scale persuade the effectiveness of proposed method in the retention of spectral information and intensification of the spatial details.