Page 17 - Artificial Intelligence for the Internet of Everything

4 Artificial Intelligence for the Internet of Everything

commercial applications, but also their present and future use in military
applications that are now evolving into IoBT. From their perspective, the
authors believe that IoBT must be capable of not only working with mixed
commercial and military technologies, but also leveraging them for maxi-
mum effect and advantage against opponents in the field. These applications
in the field present several operational challenges in tactical environments,
which the authors review along with the proposed solutions that they offer.
Unlike commercial applications, the IoBT challenges for the army include
limitations on bandwidth and interruptions in network connectivity, inter-
mittent or specialized functionality, and network geographies that vary con-
siderably over space and time. In contrast to IoT devices’ common use in
commercial and industrial systems, army operational constraints make the
use of the cloud impractical for IoBT systems today. However, while cloud
use in the field is impractical now, the army’s significant success with an inte-
grated mission command network (e.g., NOC, 2018) is an encouraging sign
and motivation for the research proposed by Jalaian and his coauthor. The
authors also discuss how machine learning and AI are intrinsic and essential
to IoBT for the decision-making problems that arise in underlying control,
communication, and networking functions within the IoBT infrastructure,
as well as higher-order IoBT applications such as surveillance and tracking.
In this chapter they highlight the research challenges on the path towards
providing quantitative intelligence services in IoBT networked infrastruc-
tures. Specifically, they focus on uncertainty quantification for machine
learning and AI within IoBT, which is critically essential to provide accurate
predictive output errors and precise solutions. They conclude that uncer-
tainty quantification in IoBT workflows enables risk-aware decision making
and control for subsequent intelligent systems and/or humans within the
information-analytical pipeline. The authors propose potential solutions
to address these challenges (e.g., machine learning, statistical learning, sto-
chastic optimization, generalized linear models, inference, etc.); what they
hope is fertile ground to encourage more research for themselves and by
others in the mathematical underpinnings of quantitative intelligence for
IoBT in resource-constrained tactical networks. The authors provide an
excellent technical introduction to the IoT and its evolution into the IoBT
for field use by the US army. The authors are working at the cutting edge of
technological applications for use in the field under circumstances that com-
bine uncertainty with widely varying conditions, and in a highly dynamic
application space.