Online ISSN: 2515-8260

Keywords : Principal component analysis


MULTIWAVELET TRANSFORM BASED GLAUCOMA CLASSIFICATION USING RANDOM FOREST

R. Manimegala; K. Priya; S. Ranjana

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 9, Pages 1470-1475
DOI: 10.31838/ejmcm.07.09.158

Glaucoma is a group of eye disorders that damage the optic nerve, essential for good vision. Often this damage comes from an abnormally high pressure in the eye. The early diagnosis of glaucoma detection is required because it leads to loss of vision. The fundus images are decomposed by Multi Wavelet Transform (MWT). Then the sub-band coefficients of MWT are extracted by using energy features. Then the redundant features are reduced by Principal Component Analysis (PCA). Finally, Random Forest (RF) classifier is used for prediction. The classification results are obtained in the experimental results and discussion section. The system produces classification accuracy of 93% by using MWT based PCA reduction and RF classifier.

MACHINE LEARNING TECHNIQUE BASED PARKINSON’S DISEASE DETECTION FROM SPIRAL AND VOICE INPUTS

Jaichandran R; Leelavathy S; Usha Kiruthika S; Goutham Krishna; Mevin John Mathew; Jomon Baiju

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 4, Pages 2815-2820

Parkinson’s disease is a dynamic neurodegenerative disorder influencing over 6 million people
worldwide. However there is no recognized test for PD for patients, particularly in the early stages. This
results in increased mortality rate. Thus detection system of Parkinson’s disease with easy steps and
feasible one to detect parkinson’s disease at the early stage is essential. The proposed system invokes
parkinson’s disease detection using voice and spiral drawing dataset. The patients voice dataset is
analyzed using RStudio with kmeans clustering and decision tree based machine learning techniques.
The patients spiral drawing is analyzed using python. From these drawings principal component analysis
(PCA) algorithm for feature extraction from the spiral drawings. From the spiral drawings : X ; Y; Z;
Pressure; Grip Angle; Timestamp; Test ID values are been extracted. The extracted values are been
matched with the trained database using machine learning technique (Support vector machine) and
results are produced. Thus our experimental results will show early detection of disease which facilitates
clinical monitoring of elderly people and increase their life span by improving their lifestyle which leads
to a peaceful life.