@article{ART003040791},
author={Bae, Gimin and LEE, Janghyong},
title={Explainable artificial intelligence models for enhancing classification reliability of ground weapon systems},
journal={Journal of Advances in Military Studies},
issn={2635-5531},
year={2023},
volume={6},
number={3},
pages={83-104},
doi={10.37944/jams.v6i3.216}
TY - JOUR
AU - Bae, Gimin
AU - LEE, Janghyong
TI - Explainable artificial intelligence models for enhancing classification reliability of ground weapon systems
JO - Journal of Advances in Military Studies
PY - 2023
VL - 6
IS - 3
PB - Institute of Defense Acquisition Program
SP - 83
EP - 104
SN - 2635-5531
AB - This study focused on the development of a reliable artificial intelligence (AI) model to enhance the classification reliability of ground weapon systems for surveillance and reconnaissance applications. The proposed AI model overcomes the limited data availability of military objects such as tanks, canons, and multiple-launch rockets by leveraging transfer learning and fine-tuning techniques. A comprehensive evaluation of 35 deep learning models using the publicly available Military-Vehicles dataset on Kaggle identified MobileNet as the most suitable model for ground weapon system classification. The selected MobileNet model achieved an average F1 score of 92% when tested on a dataset comprising five types of ground-weapon systems. In addition, the application of the explainable AI technique Grad-CAM provided insights into the decision-making process of the proposed model and verified its reliability. Real-world evaluations using frames extracted from training videos demonstrated promising accuracy for tanks, canons, and multiple-launch rockets. However, challenges related to object occlusion and the absence of target objects in the images were observed, which resulted in misclassifications. Overall, this study contributes to the development of explainable and reliable AI models for enhancing the performance of ground surveillance and reconnaissance systems.
KW - classification of ground weapon systems;explainable artificial intelligence;transfer learning;MobileNet;Grad-CAM
DO - 10.37944/jams.v6i3.216
ER -
Bae, Gimin and LEE, Janghyong. (2023). Explainable artificial intelligence models for enhancing classification reliability of ground weapon systems. Journal of Advances in Military Studies, 6(3), 83-104.
Bae, Gimin and LEE, Janghyong. 2023, "Explainable artificial intelligence models for enhancing classification reliability of ground weapon systems", Journal of Advances in Military Studies, vol.6, no.3 pp.83-104. Available from: doi:10.37944/jams.v6i3.216
Bae, Gimin, LEE, Janghyong "Explainable artificial intelligence models for enhancing classification reliability of ground weapon systems" Journal of Advances in Military Studies 6.3 pp.83-104 (2023) : 83.
Bae, Gimin, LEE, Janghyong. Explainable artificial intelligence models for enhancing classification reliability of ground weapon systems. 2023; 6(3), 83-104. Available from: doi:10.37944/jams.v6i3.216
Bae, Gimin and LEE, Janghyong. "Explainable artificial intelligence models for enhancing classification reliability of ground weapon systems" Journal of Advances in Military Studies 6, no.3 (2023) : 83-104.doi: 10.37944/jams.v6i3.216
Bae, Gimin; LEE, Janghyong. Explainable artificial intelligence models for enhancing classification reliability of ground weapon systems. Journal of Advances in Military Studies, 6(3), 83-104. doi: 10.37944/jams.v6i3.216
Bae, Gimin; LEE, Janghyong. Explainable artificial intelligence models for enhancing classification reliability of ground weapon systems. Journal of Advances in Military Studies. 2023; 6(3) 83-104. doi: 10.37944/jams.v6i3.216
Bae, Gimin, LEE, Janghyong. Explainable artificial intelligence models for enhancing classification reliability of ground weapon systems. 2023; 6(3), 83-104. Available from: doi:10.37944/jams.v6i3.216
Bae, Gimin and LEE, Janghyong. "Explainable artificial intelligence models for enhancing classification reliability of ground weapon systems" Journal of Advances in Military Studies 6, no.3 (2023) : 83-104.doi: 10.37944/jams.v6i3.216
