Please use this identifier to cite or link to this item: http://hdl.handle.net/123456789/2006
Title: Machine Learning Implementation on Medical Domain to Identify Disease Insights using TMS
Authors: Sasubilli S.M
Kumar A
Dutt V.
Keywords: Health care
Machine Learning
Modeling
Prediction
Algorithm
Implementation
Issue Date: 2020
Publisher: Institute of Electrical and Electronics Engineers Inc.
Abstract: Machine learning has become as a part of our lives and we are living with the technology. We need to understand what is happening with the health of the person to be precise we need to analyze our own health. In this scenario we are implementing machine learning methodology in health care information for the problem statement of personalizing the medical information which is a private information we need to make it safe while using and implementing some sort of algorithms. In this paper we are discussing about understanding the human disease patterns and using which random forest and other machine learning models work and predict the actual procedure a person has to follow to get a good health and avoid the different health loss activities we are doing regularly. In this random forest is the most accurate algorithm worked with this concept and we need to analyze the other reasons for understanding which kind of information is most useful for performing machine learning. Machine learning cannot be implemented for all type of issues in the real time. But we can maintain a better break through of machine learning implementation on medical issues as mentioned in this article. We are performing a better algorithm to understand the human problems related to health care and we are proposing with sample implementations and explanation with relevant results. We tried to implement TMS algorithm which gives the trust on the algorithm based on the truth maintenance system.
URI: 10.1109/ICACCE49060.2020.9154960
http://hdl.handle.net/123456789/2006
Appears in Collections:Conferences

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.