Journal of Advances in Military Studies

The actual condition and improvement of continuing education program for military personnel

Minhyuk Kim — 2023-12-31

The continuing education program for military personnel aims to provide mission execution abilities that correspond to their rank and position, as well as equip them with specialized knowledge and job performance abilities at an advanced level. This is a critical educational process for cultivating professional personnel. However, there are areas that require improvement. Therefore, this study conducted surveys, on-site inspections, expert interviews, and literature reviews to identify problems in the continuing education program for military personnel and propose solutions to address them. The issues identified and the corresponding solutions are as follows: First, education programs that have not been developed should be established in consideration of the capabilities of military schools, or external education agencies should be commissioned to provide proper education. Second, the educational period problem can be addressed by shortening the current period or strengthening remote education to reduce in-person education sessions. Third, the curriculum should be developed by periodically calculating the educational effects, importance, and understanding of each subject, and the decision to include one subject in the next education program should be made based on this analysis. Finally, remote education should be converted into a participatory, two-way learning approach that emphasizes learner-centered education and expanded through Internet-based remote education. In addition to these proposed solutions, further research is needed to compare the continuing education systems for military personnel in the army, navy, air force, and Ministry of National Defense, as well as to compare military personnel education systems in the United States. Further research is also needed to conduct detailed analytical studies on continuing education programs for each military personnel rank, considering the military education environment, and develop an education evaluation model.

Necessity and securing plan of airfield exclusive for test and evaluation infrastructure in military aviation fields

Sungkak Cho — 2023-12-31

This study addresses the problem of the absence of an airfield dedicated to flight tests, particularly since the need for flight tests has increased significantly with the development of the domestic aviation industry. In particular, the development of unmanned aerial vehicles, including small drones, along with the development of manned aircraft such as KF-21 “Boramae,” marine attack helicopters, and mine-sweeping helicopters, continues to increase flight test requirements. However, developers are not able to secure sufficient flight test time owing to program schedules. Accordingly, industry/academic/research/military and programrelated institutions involved in aircraft development strongly hope to establish an airfield infrastructure dedicated to flight tests. However, to secure a new airfield, several problems must be addressed, such as civil complaints in the region and securing a large budget. Accordingly, this study analyzed various measures to secure a flight test airfield in the defense sector and proposed that a flight test airfield connected to a military airport relocation project could be the most reasonable alternative for resolving regional conflicts and securing budgets.

Spatiotemporal analysis of drone operations using armed conflict location and event data (ACLED): Focusing on the Russia-Ukraine war

Hyungsuk Kim — 2023-12-31

This study was designed to determine the characteristics and tendencies of drones, which have emerged as a key weapon system in the Russian-Ukrainian War since 2022, and their use in modern warfare. A spatiotemporal analysis was conducted on 5,491 coordinates of drone-based battles within the city with a multidimensional model. The analysis revealed extensive drone operations by both Russia and Ukraine, with Ukraine shifting to offensive actions in 2023, and distinct temporal patterns by day of the week at battle sites, as indicated by the frequency of drone-based battles. Moreover, Russia maintained the momentum of offensive drone operations, intercepting 85.1% of Ukrainian drones and achieving a 54.0% success rate in drone-based attacks, whereas Ukraine intercepted 43.3% of Russian drones, with a success rate of only 14.3%. Based on this study, the spatiotemporal analysis of drone-based combat across Ukraine enabled an examination of the operating areas, roles, and efficiency of this weapon system as well as an understanding of the impact and multifaceted characteristics associated with its deployment on the battlefield.

Explainable artificial intelligence models for enhancing classification reliability of ground weapon systems

Gimin Bae — 2023-12-28

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.