DYNAMIC ONTOLOGY MODELLING FOR HUMAN ACTIVITY RECOGNITION
Author(s):
Anum Afzal1, Syeda Hiba Ahmad2, Hameeza Ahmed3, Muhammad Ali Ismail4
1 Postgraduate student, Technical University of Munich, Germany, Ph. +49 89 289 25027, Fax: +49 89 289 22507, Email: anumafzaldogar@hotmail.com.
2 Analyst Programmer at ForwardU, Pakistan, Ph. +92-(0)302-2881994, Email: syeda.hiba.a@gmail.com.
3 PhD student, Department of Computer and Information Systems Engineering, NED University of Engineering and Technology, Karachi, Pakistan, Ph. +92(0)21-99261261×2237, Fax: +92(0)91-99261255, Email hameeza@neduet.edu.pk.
4 Associate Professor, Department of Computer and Information Systems Engineering, NED University of Engineering and Technology, Pakistan, Pakistan, Ph. +92(0)21-99261261×2237, Fax: +92(0)91-99261255, Email: maismail@neduet.edu.pk.
Volume:
Special Issue on First International Conference on Innovations in Computer Science & Software Engineering (ICONICS-2016)
Pages:
1 - 13
Date:
December 2018
Abstract:
In the human activity recognition (HAR) process, ontology can be described as the semantic of context information by exploiting the knowledge engineering. Besides, ontology can be useful to maintain the accuracy and integrity of the data while its representation. In this paper an approach to dynamically generate ontologies is presented which focuses on HAR. Initially, an ontology model is created for the HAR which is mapped to the activity dataset. The end user can automatically generate the complete ontology by just specifying the schema and dataset. Therefore, the proposed model is both efficient and time saving compared to the static ontology generation approaches.