Cognitive Artificial Intelligence Decision Support System based on Knowledge Growing System

Abstract

Accurate and faster decision making has been a challenge for systems based on
Artificial Intelligence (AI). Since its emergence in the middle of 20th century, there has
been a fast development in AI methods for decision making. The most often approaches
used for decision making are from machine learning families such as support vector
method (SVM), artificial neural network (ANN), k-nearest neighbor (kNN), Decision Tree,
and naive Bayes (NB), which are based on supervised learning mechanism. The main
problem in supervised learning is it needs many data or training set to be learnt during
training phase. If the number of training set is not sufficient, the accuracy will be low, and
this will be dangerous to be used as the basis for making decisions. In this paper, we
propose a new approach for accurate and faster decision making by using a technology
from Cognitive Artificial Intelligence (CAI) domain called as Knowledge Growing System
(KGS). It has advantage to process multi-feature multi-label data which can be able to
deliver more accurate and faster result. We also give an example of its usage in
healthcare application, especially for medical diagnosis.