IEEE - Aerospace and Electronic Systems - July 2021 - 92

Machine Learning/Artificial Intelligence for Sensor Data Fusion-Opportunities and Challenges
Bayesian inference in Gaussian processes affords not only
the mean estimate but also the variance (using Bayesian
inference). AI/ML solutions to fuse data from physicsbased
(e.g., sensor) and human-derived (e.g., human text,
news, social media) sources support social sensing where
robust performance results from fusing unreliable data
and context [37], and explainable narratives.
Future issues for the coordination of AI/ML and data
fusion include:
Prepare for the big data and big sensor analysis
over the IoTs;
Consider doctrine changes that empower automated
response;
Utilize human knowledge with surveillance information;
and
Enhance generative methods for heterogeneous
data learning.
CONCLUSION
The coordination with AI/ML and SDF has many advantages
and results indicate promise by leveraging contextual
modeling, aligning big data AI/ML processing for
SDF object assessment, and providing methods for
human-machine teaming. SDF seeks to reduce uncertainty
with provable and consistent performance bounds while
AI/ML trains a model based on the available data. As with
the high-level information fusion challenges [38], the
opportunity is to further explore xAI/ML with SDF to generate
robustness guarantees of uncertainty estimates.
Some of the common themes of challenges and opportunities
from the panel are:
1) AI/ML big data analytics for SDF joint multimodal
object assessment;
2) AI/ML results feeding context-aware methods for
SDF situation assessment;
3) AI/ML model-based generative approaches for SDF
threat assessment;
4) AI/ML reinforcement learning for command and
control over complex, congested, and data-starved
AI/ML for SDF MDO process refinement;
5) AI/ML supports explainable results towards SDF
user refinement; and
6) AI/ML requires ROE for SDF mission refinement
policies.
ACKNOWLEDGMENTS
The views and conclusions contained herein are those of
the authors and should not be interpreted as necessarily
92
representing the official policies or endorsements, either
expressed or implied, of the U.S. Air Force, U.S. Army,
FKIE, or IBM.
REFERENCES
[1] J. Pearl, Probabilistic Reasoning in Intelligent Systems:
Networks of Plausible Inference.San Mateo,CA,USA:
Morgan Kauffman, 1988.
[2] E. Waltz and J. Llinas, Multisensor Data Fusion.Norwood,
MA, USA: Artech House, 1990.
[3] E. Blasch, E. Bosse, and D. A. Lambert, High-Level Information
Fusion Management and Systems Design.Norwood,
MA, USA: Artech House, 2012.
[4] L. Snidaro et al., Context-Enhanced Information Fusion:
Boosting Real-World Performance with Domain Knowledge.
Berlin, Germany: Springer, 2016.
[5] Y. LeCun, Y. Bengio, and G. Hinton, " Deep learning, "
Nature, vol. 521, no. 7553, pp. 436-444, 2015.
[6] S. Lo Piano, " Ethical principles in machine learning and
artificial intelligence: cases from the field and possible
ways forward, " Humanities Soc. Sci. Commun., vol. 7,
2020, Art. no. 9.
[7] H. P. Nii, E. A. Feigenbaum, J. J. Anton, and A. J. Rockmore,
" Signal-to-symbol transformation: HASP/SIAP case
study, " AI Magazine, 1982.
[8] J. E. Franklin, C. L. Carmody, K. Kellter, T. S. Levitt, and
B. L Buteau, " Expert system technology for the military:
Selected samples, " IEEE Proc., vol. 76, no. 10, pp. 1327-
1366, Oct. 1988.
[9] J. Launchbury, " A DARPA perspective on artificial
intelligence, " 2017.
[10] E. Blasch, S. Ravela, and A. Aved, Handbook ofDynamic
Data Driven Applications Systems.Berlin, Germany:
Springer, 2018.
[11] D. Gunning and D. W. Aha, " DARPA's Explainable Artificial
Intelligence Program, " AIMag., pp. 44-58, 2019.
[12] A. Milan, S. H. Rezatofighi, A. Dick, I. Reid, and K.
Schindler, " Online multi-target tracking using recurrent
neural networks, " in Proc. 31st AAAI Conf. Artif. Intell.,
2017, pp. 4225-4232.
[13] T. Nagel, " What is it like to be a bat? " Philos. Rev.,
vol. 83, no. 4, 435-450, Oct. 1974.
[14] E. Blasch, S. K. Rogers, H. Holloway, J. Tierno,
E. K. Jones, and R. I. Hammoud, " QuEST for information
fusion in multimedia reports, " Int. J. Monit. Surveill. Technol.
Res., vol. 2, no. 3, pp. 1-30, Sep. 2014.
[15] E. Blasch, I. Kadar, L. L. Grewe, G. Stevenson,
U. K. Majumder, and C. - Y. Chong, " Deep learning in AI
and information fusion panel discussion, " Proc. SPIE,
vol. 11018, 2019, Art. no. 110180Q.
[16] E. Blasch, J. Sung, T. Nguyen, C. P. Daniel, and
A. P. Mason, " Artificial intelligence strategies for security
and safety standards, " AAAI Fall meeting, 2019.
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
