Publication

The key concern that occurs in non invasive Kidney stone diagnosis using Ultrasound (US) imaging is speckle noise, as it reduces the diagnostic quality of images, required for further medication. In this work, different preprocessing filters like Median, Adaptive median, Weiner and Wavelet domain filtering are applied to both normal and kidney stone US images, with results showcase, Neigh Sure Shrink is preeminent for kidney stone US images. Objective feature assessment of the different preprocessing filters are evaluated for noise variance from 0.01 and 0.08 along with level of decomposition in Neigh Sure Shrink against the parameters like Signal to Noise Ratio (SNR), Peak Signal to Noise Ratio (PSNR), Root Mean Square error (RMSE), Mean Squared Error (MAE) with the investigational outcome shows the preeminence of projected filters over the existing methods. Further, the segmentation method allows bifurcation of the US image to detect the kidney stone on basis of Region of Interest, followed by determining the presence of Centroid and area for kidney stone US images. The Graphical User Interface allows easiness in locating the area of kidney stone for kidney US images. � 2020, Engg Journals Publications. All rights reserved.

Early prediction of Chronic Kidney Disease in human subjects is considered to be a critical factor for diagnosis and treatment. The use of data mining algorithms to reveal the hidden information from clinical and laboratory samples helps physician in early diagnosis, thus contributing towards increase in accuracy, prediction and detection of Chronic Kidney Disease. The experimental results obtained from this work, with subjected to optimal data mining algorithms for better classification and prediction, of Chronic Kidney Disease. The result of applying relevant algorithms, like K-Nearest Neighbors, Support Vector Machine, Multi Layer Perceptron, Random Forest, are studied for both clinical and laboratory samples. Our findings show that K - Nearest Neighbour algorithm provides the best classification for clinical data and, similarly, Random Forest for laboratory samples, when compared with the performance parameters like, precision, accuracy, recall and F1 Score of other data mining analysis techniques. � 2021. All Rights Reserved.

Blindness is a state of lacking the visual perception due to physiological or neurological factors. In this proposed work, a simple, cheap, friendly user, smart stick will be designed and implemented to improve the mobility of both blind and visually impaired people in a specific area. This multipurpose model is designed to help the blind person to navigate alone safely and to avoid any obstacles that may be encountered, whether fixed or mobile, to prevent any possible accident. The device provides voice output giving direction to the blind Using RFID technology, the destination of the bus is detected and voice announcement is given regarding the destination of the bus. The location of stick is added advantage to the current multipurpose device. Using RFID technology the location of the stick is achieved. The blind is provided with a push button to locate the stick. � 2016 IEEE.

The Ultrasound imaging is a non-invasive procedural technique which is used for detection of kidney diseases in the medical/clinical practice. This work emphasizes on different preprocessing methods to remove the speckle noise, embedded in kidney Ultrasound images. Preprocessing filters like, adaptive median and wiener are applied to both normal and renal calculi US images, evaluated for noise variance ranging from 0.01 and 0.08 against the parameters like Signal to Noise Ratio (SNR), Peak Signal to Noise Ratio (PSNR), Root Mean Square error (RMSE), Mean Squared Error (MAE), to determine the optimum noise variance value to be considered in preprocessing the Ultrasound images. The work also recommends adaptive median filter applied for kidney Ultrasound images with experimental results indicates increase in Peak Signal to Noise Ratio up to 33.51 dB, compared to Weiner filter. The next step is to select the best classifiers like Support Vector Machine with kernels, Multi-Layer Perceptron to preprocessed Ultrasound kidney images to estimate the accuracy, Recall, F1 score and precision. The experimental results obtained by Support Vector machine with poly kernel reaches an accuracy of 81.1% and are compared with results obtained from similar works. � 2021, Springer Nature Switzerland AG.