AIRCC's International Journal of Computer Science and Information Technology

Kunjam Nageswara Rao ¹, P. Srinivasa Rao ¹, Allam Appa Rao ², G. R. Sridhar ³

Affiliations
1 Dept. of CS&SE, Andhra University, Visakhapatnam, IN
2 Dr. CR Rao AIMSCS, University of Hydeabad, Hyderabad, IN
3 Endocrine and Diabetes Centre, Visakhapatnam, IN

Abstract

The purpose of this study is to identify and quantify the neurovascular risk factors for foot problems in patients with diabetes mellitus, which is a major public health concern these days. The most feared factor among the diabetic patients is lower extremity amputation. The sequence of events leading to amputation is initiated by ulceration combined with sensation loss. To prevent complications and amputations it is necessary to detect the foot at risk of plantar ulceration at an early stage of sensation loss. Doctors use imaging test to determine whether the plantar ulceration has spread to upper areas in the leg, and to evaluate the size and location of the ulcer. To locate the ulceration area and assess the severity, doctor's uses an imaging technology, such as ultrasound, fluoroscopy, a computed tomography (CT or CAT) scan, x-ray, or a magnetic resonance imaging (MRI) test, this procedure is called as an image-guided biopsy. To access the severity of foot ulcer, a new method is introduced, which is a popular edge detection method. This method is known as Sobel method, which uses edge detection function for derivative approximation to find edges. The Sobel edge method returns edges at those points where the gradient of the considered image is maximum, so the recognition of risk factors will be analyzed in efficient manner. Based on the severity of foot ulcer, preventive foot maintenance and regular foot examinations will take place in diabetes patients.

Keywords

Diabetes, Foot Ulcer, Amputation, Plantar, Imaging.

Full Text

   

K. Karteeka Pavan ¹, Allam Appa Rao ², A. V. Dattatreya Rao ³, G. R. Sridhar ⁴

Affiliations
1 Department of Computer Applications, Rayapati Venkata Ranga Rao and Jagarlamudi Chadramouli College of Engineering, Guntur, IN
2 Jawaharlal Nehru Technological University, Kakinada, IN
3 Department of Statistics, Acharya Nagarjuna University, Guntur, IN
4 Endocrine and Diabetes Centre, Andhra Pradesh, IN

Abstract

Selection of initial seeds greatly affects the quality of the clusters and in k-means type algorithms. Most of the seed selection methods result different results in different independent runs. We propose a single, optimal, outlier insensitive seed selection algorithm for k-means type algorithms as extension to k-means++. The experimental results on synthetic, real and on microarray data sets demonstrated that effectiveness of the new algorithm in producing the clustering results.

Full Text