No abstract

No abstract

Timely discovery of the presence of cardiovascular disease can be the difference between life and death. There has been great importance in the construction of processing tools for prognosis and diagnosis of cardiac disease and, especially, cardio vascular events. Classifying data is a customary duty of machine learning. Data mining in health care is a forthcoming arena that attains huge importance for delivering prognosis and a profound realization of medical data. The usage of SVM dependent methodologies in identification the cardio vascular diseases has some restrictions. The important drawbacks of SVM is the severe absence of transparency of outcomes. The ELM learning algorithm is a simple process and it provides accurate result when compared to other traditional algorithms. As the proposal of this research, to enhance the generalization capacity of ELM, KELM is utilized. To improve the classification accuracy of KELM, in this paper a nature inspired swarm intelligence Grey Wolf Algorithm is utilized. Grey Wolf Algorithm is utilized in optimizing the parameter of KELM. By performing classification, accuracy is improved along with high precision and low error rate. Experimental results clearly indicate that the proposed GWO – KELM classifier performs better on comparison with some classifiers that are currently used for the identification of the Cardio Vascular Disease.

No abstract

Design and Development of new Image Registration Techniques by using complex mathematical transformation functions are attempted in this research work as there is a requirement for the performance measurement of image registration complexity. The design and development of new image registration techniques are carried out with complex mathematical transformations of Radon and Slant functions due to their importance. And the rotation and translation geometric function are considered for better insight into the complex image registration process. The newly developed image registration techniques areevaluated and analyzed with openly available images of Lena, Cameraman and VegCrop. The accuracy as a performance measure of the newly developed image registration techniques are attempted to measure with popularly known metrics of RMSE, PSNR and Entropy. And the results obtained after successful image registration process are compared are presented. It is observed from the results that the developed new image registration techniques using Radon and Slant transformation functions with rotation and translation are superior and useful for the requirement and purpose in the digital image processing domain. Finally a research effort is made to development of new image registration techniques that are useful to extract intelligence embedded in the images with complex transformation function and an attempt is made to measure its performance also.