Fundamental Study On Proposed Cad Based Paediatric Hydronephrosis Classification Model Framework By Enhanced Seed Pixel Region Growing Segmentation And Logistic Regression Classifier Algorithm

2016 ◽  
Author(s):  
N.Venkatesa Mohan ◽  
◽  
Valliappan Raman ◽  
Keyword(s):  
Logistic Regression ◽  
Region Growing ◽  
Classification Model ◽  
Model Framework ◽  
Fundamental Study ◽  
Region Growing Segmentation ◽  
Logistic Regression Classifier ◽  
Seed Pixel

scholarly journals Automated Kidney Stone Segmentation by Seed Pixel Region Growing Approach: Initial Implementation and Results

2018 ◽  
Vol 7 (4.15) ◽  
pp. 43 ◽  
Author(s):  
Sujata Navaratnam ◽  
Siti Fazilah ◽  
Valliappan Raman ◽  
Sundresan Perumal
Keyword(s):  
Kidney Stone ◽  
Clinical Decision Making ◽  
Early Stage ◽  
Texture Feature ◽  
Region Growing ◽  
Clinical Decision ◽  
Seed Region ◽  
Region Growing Segmentation ◽  
Aided Diagnosis ◽  
Seed Pixel

This research develop a computer aided diagnosis prototype for early detection of kidney stone. Once a kidney stone is diagnosed accurately, this will be useful for the patients to change their diet condition. The proposed approach is based on five stages which includes kidney image acquisition, pre-processing, segmentation, feature extraction and classification. The enhanced seed region growing segmentation depends on the extracted feature granularities. Noise may be visible and more prevalent in certain dimensions of an image, where this particular specific portion will be extracted. The segmentation process is based on the thresholds of the identified renal stone regions. The segmented stone size portion is classified based on rules; if the size is greater than 2mm, then the stone is at benign stage; if the size is greater than 5mm, then it is in malignant stage; if the size is lesser than 2mm, then this leads to absence of stone. The proposed work is implemented in MATLAB with the development of an initial prototype with the detection of stone accuracy of 92%. Based on the experimental analysis, texture feature, threshold intensity values and stone sizes are evaluated. This study will help the urologist to take decision whether there is a presence or absence of stone in early stage diagnosis and clinical decision-making.  

scholarly journals A Research and Application of the Processing Methods of Railway Measurement Based on Self-Mobile Scanning Measurement System

2020 ◽  
Author(s):  
Jiancai Zhang ◽  
Hang Mu ◽  
Feng Han ◽  
Shumin Han
Keyword(s):  
Measurement System ◽  
High Speed ◽  
Automatic Segmentation ◽  
Laser Scanner ◽  
Region Growing ◽  
Image Sensor ◽  
Operating Conditions ◽  
Secondary Development ◽  
Railway Line ◽  
Region Growing Segmentation

With the gradual improvement of China’s railway net, the opening of international railways as well as the continuous growth of railway operating mileage, the workload of remeasuring railways is increasing. The traditional methods of remeasuring railways can not meet current high-speed and high-density operating conditions anymore in terms of safety, efficiency and quality, so a safer and more efficient measurement method is urgently needed.This thesis integrated various sensors on a self-mobile instrument, such as 3D laser scanner, digital image sensor and GNSS_IMU, designing a set of intelligent and integrated self-mobile scanning measurement system. This thesis proposed region growing segmentation based on the reflection intensity of point cloud. Through the secondary development of CAD, the menu for automatic processing of self-mobile scanning measurement system is designed to realize rail automatic segmentation, extraction of rail top points, fitting of plane parameters of railway line, calculation of curve elements and mileage management.The results show that self-mobile scanning measurement system overcomes the shortcomings of traditional railway measurement to some extent, and realizes intelligent measurement of railways.

scholarly journals REGION GROWING IMAGE SEGMENTATION ON LARGE DATASETS USING GPU

2016 ◽  
Vol 15 (14) ◽  
pp. 7486-7497
Author(s):  
Gurpreet Kaur ◽  
Sonika Jindal
Keyword(s):  
Image Segmentation ◽  
Traffic Control ◽  
Cluster Computing ◽  
Region Growing ◽  
Large Data ◽  
Maximum Speed ◽  
Processing Unit ◽  
Small Areas ◽  
Best Fitting ◽  
Seed Pixel

Image segmentation is an important image processing, and it seems everywhere if we want to analyze what inside the image. There are varieties of applications of image segmentation such as the field of filtering noise from image, medical imaging, and locating objects in satellite images and in automatic traffic control systems, machine vision in problem of feature extraction and in recognition. This paper focuses on accelerating the image segmentation mechanism using region growing algorithm inside GPU (Graphical Processing Unit). In region growing algorithm, an initial set of small areas are iteratively merged according to similarity constraints. We have started by choosing an arbitrary seed pixel and compare it with neighboring pixels. Region is grown from the seed pixel by adding in neighboring pixels that are similar, increasing the size of the region. When the growth of one region stops we simply choose another seed pixel which does not yet belong to any region and start again. This whole process is continued until all pixels belong to some region. If any of the segment makers has the fusion cost lower than the maximum fusion cost (a given threshold), it is selected to grow. Avoid information overlapping like two threads attempting to merge its segment with the same adjacent segment.  Experiments have demonstrated that the proposed shape features do not imply in a significant change of the segmentation results, as long as the algorithm’s parameters are properly adjusted. Moreover, experiments for performance evaluation indicated the potential of using GPUs to accelerate this kind of application. For a simple hardware (GeForce 630M GT), the parallel algorithm reached a maximum speed up of approximately 20-30% for different datasets. Considering that segmentation is responsible for a significant portion of the execution time in many image analysis applications, especially in object-oriented analysis of remote sensing images, the experimentally observed acceleration values are significant. Two variants of PBF (Parallel Best Fitting) and PLMBF (Parallel Local Mutual Best Fitting) have been used to analyze the best merging cost of the two segments. It has been found that the PLMBF has been performed better than PBF.  It should also be noted that these performance gains can be obtained with low investment in hardware, as GPUs with increasing processing power are currently available on the market at declining prices. The parallel computational scheme is well suited for cluster computing, leading to a good solution for segmenting very large data sets.

scholarly journals Ensembling Coalesce of Logistic Regression Classifier for Heart Disease Prediction using Machine Learning

2019 ◽  
Vol 8 (12) ◽  
pp. 127-133
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Heart Disease ◽  
Heart Diseases ◽  
Experimental Results ◽  
Disease Prediction ◽  
Feature Importance ◽  
The World ◽  
Feature Scaling ◽  
Logistic Regression Classifier

In today’s modern world, the world population is affected with some kind of heart diseases. With the vast knowledge and advancement in applications, the analysis and the identification of the heart disease still remain as a challenging issue. Due to the lack of awareness in the availability of patient symptoms, the prediction of heart disease is a questionable task. The World Health Organization has released that 33% of population were died due to the attack of heart diseases. With this background, we have used Heart Disease Prediction dataset extracted from UCI Machine Learning Repository for analyzing and the prediction of heart disease by integrating the ensembling methods. The prediction of heart disease classes are achieved in four ways. Firstly, The important features are extracted for the various ensembling methods like Extra Trees Regressor, Ada boost regressor, Gradient booster regress, Random forest regressor and Ada boost classifier. Secondly, the highly importance features of each of the ensembling methods is filtered from the dataset and it is fitted to logistic regression classifier to analyze the performance. Thirdly, the same extracted important features of each of the ensembling methods are subjected to feature scaling and then fitted with logistic regression to analyze the performance. Fourth, the Performance analysis is done with the performance metric such as Mean Squared error (MSE), Mean Absolute error (MAE), R2 Score, Explained Variance Score (EVS) and Mean Squared Log Error (MSLE). The implementation is done using python language under Spyder platform with Anaconda Navigator. Experimental results shows that before applying feature scaling, the feature importance extracted from the Ada boost classifier is found to be effective with the MSE of 0.04, MAE of 0.07, R2 Score of 92%, EVS of 0.86 and MSLE of 0.16 as compared to other ensembling methods. Experimental results shows that after applying feature scaling, the feature importance extracted from the Ada boost classifier is found to be effective with the MSE of 0.09, MAE of 0.13, R2 Score of 91%, EVS of 0.93 and MSLE of 0.18 as compared to other ensembling methods.

Sign in / Sign up

Export Citation Format

Share Document