Remote diagnosis of diabetics patient through speech engine and fuzzy based machine learning algorithm
- PDF / 1,584,356 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 40 Downloads / 170 Views
Remote diagnosis of diabetics patient through speech engine and fuzzy based machine learning algorithm G. Siva Shankar1 · K. Manikandan1 Received: 17 April 2020 / Accepted: 14 July 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract As recent development of technology, it enables patients to get treatment remotely from doctors through audio conversation. The fourth highest number of death every year is caused by diabetics. Almost 50% to 80% of patients can avoid diabetics if the cause is found at the early stage. In this paper, we propose a new methodology to detect Diabetes at an early stage and recommend few attributes in which the patient needs to be careful in order to avoid diabetics. The proposed methodology makes use of fuzzy logic and kNN classifier to find out the caution attributes and recommends them as soon as possible. The proposed algorithm detects the audio signals from patients or clinical labs to process the data. We implemented our proposed methodology on Pima Indian dataset and compared with existing algorithms and the result shows that our algorithm outperforms existing algorithms. Keywords Diabetes detection · Individual attribute · Fuzzy rules · kNN · Machine learning
1 Introduction Most of the people ignore to go to hospitals to get treatments for diabetics due to lots of reasons which include time, travel and so on. In this paper, we aim to diagnose a patient remotely by the doctors through speech technology. A lot of machine learning algorithms have been researched for the field of automatic decision-making system in recent years. However not all the research outcomes are adopted in various medical and biological fields due to lack of availability of data, lack of technical knowledge, hence good availability of data and strong data knowledge is mandatory for developing real-time algorithms that help to serve patients better. There are two categories of disease namely contagious and non-contagious. A contagious disease is the one that is transmissible either by physical contact or by casual contact by affected persons body secretions. Non contagious disease is the one which is not been transmissible from person to person. Any form of non- contagious disease can be avoided * K. Manikandan [email protected] G. Siva Shankar [email protected] 1
School of Computer Science and Engineering, VIT University, Vellore, TN 632014, India
based upon the symptoms diabetes mellitus (DM) is the most common and threatening disease among us nowadays. According to the Hindustan times survey the number of diabetes communities will get double in the coming decades.1 The rate of DM disease among a set of the population in Southeast Asia people is growing rapidly day by day (Pradhan et al. 2012) and it is an important cause for the increase in the human mortality rate. Detection of any disease at an early stage with the help of advancement in technologies like data mining and health care analytics can be achieved. Based upon the symptom for diabetic disease i.e.,
Data Loading...