From Different Sources with Artificial Intelligence
Relate Your Incoming Data

Most practitioners start by doing “exploratory data analysis” to learn about interesting patterns and features in the data when faced with a new dataset. Operations such as association rule mining and principal component analysis are often applied to reveal relationships between attributes of data. However, association rules are primarily designed for use on binary or categorical data, due to their use of rule-based machine learning. In real-world, data is continuous and the discreteness of such data leads to inaccurate and less informative attribution rules.

Ontology is widely used in information engineering, artificial intelligence, information retrieval, heterogeneous information process and semantic web mining. The goal of ontology is to capture the knowledge and expression contained in the relevant fields, to provide a common understanding of the field knowledge, to determine the vocabulary for common understanding in the field and to give a clear definition for this vocabulary and their relationships based on formal models consisting of different hierarchies.


Building an ontology has become a crucial task to increase efficiency and understand data. However, manual ontology creation is a complex and tricky task resulting in long ontology creation time and high cost.


LinkUS has been designed with the vision of eliminating these deficiencies and is used to automatically create ontology from existing database resources in order to increase the efficiency of Ontology construction and to find the most suitable data groups for the relations defined in the ontology by extracting the summary.