Novel Kernel to Diagnose Dermatological Disorders

Journal Title: Journal of Applied Computer Science & Mathematics - Year 2018, Vol 12, Issue 25

Abstract

Development of computer aided system to diagnose dermatological disorders works as a second opinion when skin diseases have very little differences in clinical features. Support Vector Machine (SVM) is a good classifier for non linear data with appropriate choice of kernels. Generally, Positive (semi) Definite (PSD) kernels called Mercer’s kernels are used in SVM. Mercer’s condition is the traditional requirement for classical kernel methods like SVM. But, for many empirical data indefinite kernels can give better result. In this study we use SVM with a novel kernel (Modified Gaussian Kernel) which is Indefinite (ID) kernel to diagnose skin disorders. We also investigate various distance substitution kernels to diagnose skin disorders and determine Eigen values of the Gram matrices obtained from two dermatological data sets under study to discuss their definiteness property. Results show that our proposed modified Gaussian kernel gives good classification accuracy to diagnose dermatological disorders.

Authors and Affiliations

Krupal PARIKH, Trupti P. SHAH

Keywords

Related Articles

Oscillation Theorems for Fractional Order Neutral Differential Equations

The purpose of this paper is to study the oscillation of the fractional order neutral differential equation 𝑫𝒕 𝜢[𝒓(𝒕)[𝑫𝒕 𝜢(𝒙(𝒕) + 𝒑(𝒕)𝒙(𝝉(𝒕)))]𝜸] + 𝒒(𝒕)π’™πœΈ(𝝈(𝒕)) = 𝟎, where 𝑫𝒕 𝜢(β‹…) is a modified Riemann-Liouville derivati...

Enhanced White Cane for Visually Impaired People

ccording to WHO (World Health Organization) statistics, around 285 billion people in the world have visual impairment. They find difficulty in doing their everyday tasks and detecting objects in front of them that can be...

The Evolution of the Processing Power Needed by the Primary Cryptocurrencies and its profit.

This paper intends to follow the evolution of the processing power needed to mine cryptocurrencies. Because by this year, 2018, they evolved to being over 1500 cryptos, we shell consider reviewing the first 5: Bitcoin, E...

Enumerating Hamiltonian Cycles in a Planar Graph Using Combinatorial Cycle Bases

sed both for listing and enumerating Hamiltonian cycles contained in a planar graph. Planar cycle bases have a weighted induced graph whose weight values limited to 1. Hence making it was possible used in the Hamiltonian...

Removal of Baseline Wander Noise from Electrocardiogram (ECG) using Fifth-order Spline Interpolation

Abstract–Baseline wandering can mask some important features of the Electrocardiogram (ECG) signal hence it is desirable to remove this noise for proper analysis and display of the ECG signal. This paper presents the imp...

Download PDF file
  • EP ID EP532919
  • DOI 10.4316/JACSM.201801004
  • Views 173
  • Downloads 0

How To Cite

Krupal PARIKH, Trupti P. SHAH (2018). Novel Kernel to Diagnose Dermatological Disorders. Journal of Applied Computer Science & Mathematics, 12(25), 27-33. https://europub.co.uk/articles/-A-532919