IEEE - Aerospace and Electronic Systems - July 2021 - 62

Feature Article:
DOI. No. 10.1109/MAES.2020.3043072
Artificial Intelligence and Data Fusion at the Edge
, Air Force Office ofScientific Research, Arlington,VA22203USA
, Air Force Research Laboratory Information Directorate,
Arslan Munir , Kansas State University, Manhattan, KS 66506 USA
Erik Blasch
Jisu Kwon andJoonho Kong , Kyungpook National University, Daegu 41566,
South Korea
AlexanderAved
Rome, NY 13441 USA
INTRODUCTION
Advancements and miniaturization of electronic devices
that are not only able to sense and process data but can also
communicate with other devices have engendered an era of
Internet of Things (IoT). These IoT devices are often
equipped with a multitude of sensors and generate zillions
bytes of data at the network edge. Many of the applications
that need to utilize this data have embraced artificial intelligence
(AI) and machine learning (ML). However, transferring
this gigantic data to the cloud is often infeasible due to
limited network bandwidth and real-time constraints of
many applications including aerospace systems. Thus, there
is a desire to push AI frontiers to the network edge to utilize
the enormous amount of data generated by IoT devices
nearer to the data source. This desire has led to the merger of
edge computing (a novel trend in computing that pushes
computing power away from the centralized nodes to the
logical extreme edges ofa network [1]) and AI, resulting in a
new discipline-AI at the edge or edge intelligence.In
the edge AI model, AI computations take place either on the
user device or somewhere in the network stack beneath the
cloud, perhaps on an edge server. According to Steve Roddy,
Authors' current address: Arslan Munir, Department
of Computer Science, Kansas State University,
Manhattan, KS 66506 USA (e-mail: famunir@ksu.
edu). Erik Blasch, Air Force Office of Scientific
Research (AFOSR) Arlington, VA 22203-1768 USA (email:
erik.blasch.1@us.af.mil). Jisu Kwon, Joonho
Kong, School of Electronic and Electrical Engineering,
Kyungpook National University, Daegu 41566, South
Korea (e-mail: jisu92@knu.ac.kr, joonho.kong@knu.
ac.kr). Alex Aved, Air Force Research Laboratory
(AFRL), Information Directorate, Rome, NY 13441
USA (e-mail: Alexander.Aved@us.af.milg).
Manuscript received March 1, 2020, revised September
10, 2020; accepted November 14, 2020, and ready for
publication December 3, 2020.
Review handled by Chee-Yee Chong.
0885-8985/21/$26.00 ß 2021 IEEE
62
the Vice-President (VP) of Special Projects in Arm's
Machine Learning Group [2]: " The edge is the next stage of
the evolution ofAI technology because of the physical constraints,
the cost constraints, and the practical constraints of
running all AI applications in the cloud. It simply does not
make sense to send all the bits for things like video and audio
streaming to the cloud and back down for every situation,
every endpoint. "
In the age of AI, what is important is not the data alone
but what we can do with this data and how to make sense of
this data. As more and more data are being collected at the
network edge due to the proliferation of IoT and sensing
devices, the capability gap to make sense of this gigantic
data, whether at the edge or the cloud, in a timely manner, is
also increasing. For instance, in surveillance applications,
the number of traditional sensors (e.g., ground radar and
cameras), nontraditional sensors (e.g., IoT), and nonorganic
airborne platforms (e.g., unmanned aerial systems) has
increased the opportunity to detect, track, and identify targets,
as well as to counter threats; however, there is a lack of
processing capability to do so efficiently and effectively [3].
It is noted that for many applications, much of the collected
data is time sensitive and become useless if not utilized
timely. Hence, solutions such as data fusion are of paramount
significance to enhance the effectiveness and usage
of sensed data in a timely manner. Data fusion is defined as
the process ofcombining data from multiple sources to produce
more accurate, consistent, and concise information
than that provided by any individual data source.
The concept of both data fusion and AI has biological
origins. Data fusion is inspired from the capability of
advanced biological organisms to assimilate information
from multiple senses (e.g., sight, touch, smell, and taste)
to make better sense of environment and increase their
chances of survival. AI is also inspired from the cognition
displayed by advanced biological organisms (e.g.,
humans). Both data fusion and AI are complementary to
enable machines to accomplish various intelligent tasks
and missions. Whether the AI computations are performed
at the cloud or at the network edge, data fusion is needed
IEEE A&E SYSTEMS MAGAZINE
JULY 2021
IEEE - Aerospace and Electronic Systems - July 2021

Table of Contents for the Digital Edition of IEEE - Aerospace and Electronic Systems - July 2021
