Online ISSN: 2515-8260

Keywords : Naive Bayes

Performance Study of ML Models and Neural Networks for Detection of Parkinson Disease using Dysarthria Symptoms

Harisudha Kuresan; Dhanalakshmi Samiappan; Arathy Jeevan; Sukirti Gupta

European Journal of Molecular & Clinical Medicine, 2021, Volume 8, Issue 3, Pages 767-779

Parkinson Disease (PD) is brain disorder that affects the central nervous system
that results in damage of nerve cells causing dopamine to drop. PD has a severe effect on
vocal features termed as Dysarthria symptoms including varied pitch, extended pauses,
monotonous and speaking slowly or with a slur. In this paper, a dataset containing various
vocal features are taken as input to analyze the performance of various Machine Learning
algorithms including Naive Bayes, Random Forest Classifier, Support Vector Machines
(SVM), Linear Regression, K Nearest Neighbor (KNN) and Neural Networks such as ANN
and LSTM. The best classification accuracy was obtained by ANN around 90.00%.

A Study Of Breast Cancer Analysis Using K-Nearest Neighbor With Different Distance Measures And Classification Rules Using Machine Learning.

M.D. Bakthavachalam; Dr.S .Albert Antony Raj

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 3, Pages 4842-4851

Breast Cancer is one of the life threatening disease among females all over the world. This killer disease however when it can be detected in its early stages can be a life saver for many. Radiologists uses the mammography images to detect the presence and absence of Breast Cancer. The field of Bio-informatics leverages the Machine learning techniques for diagnosis of Breast cancer in particular. This research work experiments with the two most popularly used Supervised Machine Learning Algorithms, K-Nearest Neighbour and Naive Bayes. This work predicts Breast Cancer on the The Breast Cancer Data Set (BCD) taken from the UCI Machine Learning Repository. A comparative analysis between the two approaches are made in terms of its performance metrics using CV techniques. The proposed work has achieved a best accuracy of 97.15% by employing the KNN algorithm and a lowest error rate of 96.19% using NB classifier.