Comparative study between Fuzzy Inference System, Adaptive Neuro-Fuzzy Inference System and Neural Network for Healthcare Monitoring
Maria Krizea
Industrial Systems Institute/ATHENA RC, Platani, Patras, Greece. University of Patras, Rio, Patras, Greece.
Email: mkrizea@ece.upatras.gr
John Gialelis
Industrial Systems Institute/ATHENA RC, Platani, Patras, Greece.
University of Patras, Rio, Patras, Greece.
Email: gialelis@isi.gr
Stavros Koubias
University of Patras, Rio, Patras, Greece.
Email: koubias@ece.upatras.gr
Abstract
— this paper compares three supervised machine learning
algorithms for healthcare monitoring. The first step of the
presented work is the collection of vital signs information data
that are utilized for training a Fuzzy Inference System (FIS), an
Adaptive Neuro-Fuzzy Inference System (ANFIS) and a Neural
Network (NN). Then, the trained algorithms are used to predict
the Health Status (HS) of patients. Extended comparison results
are demonstrated which indicate that the classifiers could be
utilized as a basis for HS assessment.
Keywords
—healthcare monitoring, health status, vital signs, FIS, ANFIS, NN