International Journal of Artificial Intelligence Research ISSN: 2579-7298
Vol 6, No 2, December 2022
DOI: W : http://ijair.id | E : info@ijair.id
A Novel Approach for Recognition and Identification of Low-
Level Flight Military Aircraft using Naive Bayes Classifier and
Information Fusion
Arwin Datumaya Wahyudi Sumari
a,b,1,*,
, Afifah Millatina Nugraheni
c,2
, Yoppy Yunhasnawa
c,3
a
Cognitive Artificial Intelligence Research Group (CAIRG), Department of Electrical Engineering, State Polytechnic of
Malang, Indonesia
b
Abdulrachman Saleh Air Force Base, 2
nd
Operation Command, Indonesian Air Force, Indonesia
c
Department of Information Technology, State Polytechnic of Malang, Indonesia
1
arwin.sumari@polinema.ac.id*;
2
afifahmilla5@gmail.com;
3
yoppy.yunhasnawa@polinema.ac.id
* corresponding author
I. Introduction
Guarding the national airspace is the primary task of the National Air Defense Command (NADC).
For this carrying out this task, the Armed Forces deploys the Radar systems at some strategic locations
in order to detect, recognize, and identify the incoming aircrafts from any direction to the national
airspace. Even though, the Radar systems are designed to able to detect high-speed aircrafts at a long
distance, but they can be tricked if the aircrafts fly at low level altitude or it is said as flying nap-to-
the-earth [1], which is out-of-the Radar coverage. This kind of flight can occur anywhere and anytime
that can endanger the air sovereignty if such aircrafts are not detected, recognized, and identified at
the right time. Therefore, a ground-to-air surveillance to assist the Radar systems. This surveillance
can be carried out by the competent Armed Forces personnel who are already given a Visual Aircraft
Recognition (VACR) [2] training. This task is called as ground-to-air surveillance and it is performed
by using binoculars to assist a faraway observation to the incoming or passing aircrafts as depicted in
Fig. 1.
Ground-to-air surveillance is a time-consuming and tiring task while on the other hand, keeping in
mind so many types of military aircrafts will give another load that can bring the personnel into fatigue
situation and cause a mistake recognition and identification. Aircraft is any machine that can fly
because of having a lift caused by the air. It is divided into two categories namely, airplane which is
ARTICLE INFO ABSTRACT
Article history:
Received : 12 August 2021
Revised : 30 December 2021
Accepted : 19 Januari 2022
A problem that has been faced by the Radar is if the aircraft flies at
low level or near to the surface so its coming in the aerial-surveillance
airspace cannot be detected and endangers the air sovereignty. The
aircraft can be recognized and identified by carrying out a technique
called Visual Aircraft Recognition (VACR) using a binocular. This
technique requires military personnel that has capability carrying out
the air surveillance from the ground. Surveillance is a time-
consuming and tiring task so it can cause fatigue and impact to the
results of the recognition and identification. To cope with this
problem, we have designed and implemented a novel recognition and
identification method using the combination of Naive Bayes Classifier
(NBC) and information fusion. By using a dataset that consists of 45
military aircrafts, 35 civilian aircrafts, 40 military helicopters, and 35
civilian helicopters with 80:20 dataset distribution for the training
scheme and the validation one, we obtained the recognition accuracy
of 87.1%. We also found that the recognition and identification
process can be speeded up 1.2 seconds when using information fusion.
Copyright © 2021 International Journal of Artificial Intelligence Research.
All rights reserved.
Keywords:
Artificial Intelligence
Information Fusion
Low Level Flight
Military Aircraft
Naive Bayes Classifier
Recognition and Identification