Fuzzy Logic

2198 Words9 Pages

An Empirical approach for fuzzy rules using Classification and Regression Tree

A.Poongodai
Research scholar, Pondicherry University, Karaikal campus
Pondicherry, India a_poongodai@yahoo.co.in R.G. Babukarthik
Research scholar (part time category ? B)
Bharatiyar University
r.g.babukarthik@gmail.com

S.Bhuvaneswari
Central University of Tamil Nadu
Thiruvarur, India booni_67@yahoo.co.in Abstract
Fuzzy logic has been extensively used in designing of medical diagnosis expert system. Fuzzy logic is adopted due to its capability of decisions making in an environment of imprecision, uncertainty and incompleteness of information. The Fuzzy based system is proposed to diagnose the Parkinson disease (PD) by measuring its level of severity using the …show more content…

Learning systems are data-driven approaches that are derived directly from routinely monitored system operating data. They rely on the assumption that the statistical characteristics of the data are stable, unless a malfunctioning event occurs in the system. Data-driven approaches can either use ?conventional? numerical algorithms, such as linear regression or Kalman filters, or they can use algorithms from the machine learning and data mining AI communities, such as neural networks, decision trees, and support vector machines. The limitation of this system is larger number of rules in the knowledge base which increase the memory space, reduce the rule access rate, increase the response time and hence the system performance is degraded. To overcome this limitation fuzzy logic is adopted to construct fuzzy rule and fuzzy expert system is built for diagnosis purpose. The objective of the research is to apply the concept of fuzzy logic technology to predict the severity level of …show more content…

The dataset was created by Athanasios Tsanas and Max Littlle of the University of Oxford, in collaboration with 10 medical centers in the US and Intel Corporation who developed the telemonitoring device to record the speech signals. The original study used a range of linear and nonlinear regression methods to predict the clinician?s Parkinson?s disease symptom score on the updrs scale.

This dataset is the collection of a range of biomedical voice measurements from 42 people. The voice recordings were automatically captured in the patient's homes on the weekly basis and processed appropriately in the clinic to predict the updrs score. The updrs score value was assessed at baseline (onset of trial) and after three months and 6

Open Document