• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.4
• /
• pp.474-484
• /
• 2024

Reinforcement learning, which are also studied in the field of defense, face the problem of sample efficiency, which requires a large amount of data to train. Transfer learning has been introduced to address this problem, but its effectiveness is sometimes marginal because the model does not effectively leverage prior knowledge. In this study, we propose a stochastic initial state randomization(SISR) method to enable robust knowledge transfer that promote generalized and sufficient knowledge transfer. We developed a simulation environment involving a cooperative robot transportation task. Experimental results show that successful tasks are achieved when SISR is applied, while tasks fail when SISR is not applied. We also analyzed how the amount of state information collected by the agents changes with the application of SISR.

• Journal of Aerospace System Engineering
• /
• v.17 no.2
• /
• pp.56-61
• /
• 2023

Recently, advancement of AI-enabled autonomous MUM-T combat system and industrial revitalization are rapidly emerging as global issues. However, the Defense Business Act of the Ministry of National Defense in Korea is judged to be somewhat insufficient compared to NATO leading countries in advancement of operation part of a weapon system as MUM-T is centered on a weapon system's own device. We established the concept of AI-enabled autonomous MUM-T to strengthen international competitiveness of complex combat systems such as future global UGV, UAV, and UMS. In addition, NATO and US-centered autonomy, interoperability, and data standardization-based defense AI MUM-T top-level platform construction and operation plan, establishment of a national defense innovation committee such as the National Science and Technology Advisory Council, review and advisory function reinforcement, and additional governance measures are proposed.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.4
• /
• pp.372-380
• /
• 2022

This study proposes a distributed parallel processing system, called the Fast Analysis System for remote sensing daTa(FAST), for large-scale satellite image processing and analysis. FAST is a system that designs jobs in vertices and sequences, and distributes and processes them simultaneously. FAST manages data based on the Hadoop Distributed File System, controls entire jobs based on Apache Spark, and performs tasks in parallel in multiple slave nodes based on a docker container design. FAST enables the high-performance processing of progressively accumulated large-volume satellite images. Because the unit task is performed based on Docker, it is possible to reuse existing source codes for designing and implementing unit tasks. Additionally, the system is robust against software/hardware faults. To prove the capability of the proposed system, we performed an experiment to generate the original satellite images as ortho-images, which is a pre-processing step for all image analyses. In the experiment, when FAST was configured with eight slave nodes, it was found that the processing of a satellite image took less than 30 sec. Through these results, we proved the suitability and practical applicability of the FAST design.

• Journal of the Korean Society of Systems Engineering
• /
• v.18 no.1
• /
• pp.90-98
• /
• 2022

On February 12, 2019, the U.S. Department of Defense newly established and announced the "Defense AI Strategy" to accelerate the use of artificial intelligence (AI) technology for military purposes. As China and Russia invested heavily in AI for military purposes, the U.S. was concerned that it could eventually lose its advantage in AI technology to China and Russia. In response, China and Russia, which are hostile countries, and especially China, are speeding up the development of new military theories related to the overall construction and operation of the Chinese military based on AI. With the rapid development of AI technology, major advanced countries such as the U.S. and China are actively researching the application of AI technology, but most existing studies do not address the special topic of defense. Fortunately, the "Future Defense 2030 Technology Strategy" classified AI technology fields from a defense perspective and analyzed advanced overseas cases to present a roadmap in detail, but it has limitations in comparing private technology-oriented benchmarking and AI technology's maturity level. Therefore, this study tried to overcome the limitations of the "Future Defense 2030 Technology Strategy" by comparing and analyzing Chinese and U.S. military research cases and evaluating the maturity level of military use of AI technology, not AI technology itself.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.3
• /
• pp.300-310
• /
• 2022

A vast amount of labeled data is required for deep neural network training. A typical strategy to improve the performance of a neural network given a training data set is to use data augmentation technique. The goal of this work is to offer a novel image augmentation method for improving object detection accuracy. An object in an image is removed, and a similar object from the training data set is placed in its area. An in-painting algorithm fills the space that is eliminated but not filled by a similar object. Our technique shows at most 2.32 percent improvements on mAP in our testing on a military vehicle dataset using the YOLOv4 object detector.

• Industry Promotion Research
• /
• v.8 no.1
• /
• pp.35-45
• /
• 2023

This paper addressed the analysis of the trend and direction of the US defense strategy based on their third offset strategy and presented the practical policy implication of ensuring the security of South Korea appropriately in the future national defense environment. The countermeasures for the development ability of advanced weapon systems and secure core technologies for Korea were presented in consideration of the US third offset strategy for the future national defense environment. First, to carry out the innovation of national defense in Korea based on artificial intelligence(AI), the long-term basis strategy for the operation of the unmanned robot and autonomous weapon system should be suggested. Second, the platform for AI has to be developed to obtain the development of algorithms and computing abilities for securing the collection/storage/management of national defense data. Lastly, advanced components and core technologies are identified, which the Korean government can join to develop with the US on a basis of the Korea-US alliance, and the technical cooperation with the US should be stronger.

• Journal of Internet Computing and Services
• /
• v.25 no.1
• /
• pp.189-198
• /
• 2024

AI is accepted not only in the private sector but also in the defense sector as a cutting-edge technology that must be introduced for the development of national defense. In particular, artificial intelligence has been selected as a key task in defense science and technology innovation, and the importance of data is increasing. As the national defense department shifts from a closed data policy to data sharing and activation, efforts are being made to secure high-quality data necessary for the development of national defense. In particular, we are promoting a review of the business budget system to secure data so that related procedures can be improved to reflect the unique characteristics of AI and big data, and research and development can begin with sufficient large quantities and high-quality data. However, there is a need to establish standardization and quality standards for structured data and unstructured data at the national defense level, but the defense department is still proposing standardization and quality standards for structured data, so this needs to be supplemented. In this paper, we propose an unstructured data set standard format for defense unstructured data sets, which are most needed in defense artificial intelligence, and based on this, we propose a standardization method for defense unstructured data sets.

• Convergence Security Journal
• /
• v.23 no.1
• /
• pp.109-115
• /
• 2023

The future outlook for defense faces various and challenging environments such as the acceleration of uncertainty in the global security landscape and limitations in domestic social and economic conditions. In response, the Ministry of National Defense seeks to address the problems and threats through defense innovation based on scientific and technological advancements such as artificial intelligence, drones, and robots. To introduce advanced AI-based technology, it is essential to integrate and utilize data on IT environments such as cloud and 5G. However, existing traditional security policies face difficulties in data sharing and utilization due to mainly system-oriented security policies and uniform security measures. This study proposes a paradigm shift to a data value-based security policy based on theoretical background on data valuation and life-cycle management. Through this, it is expected to facilitate the implementation of scientific and technological innovations for national defense based on data-based task activation and new technology introduction.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.2
• /
• pp.256-264
• /
• 2024

In the last 10 years, AI has made rapid progress, and image classification, in particular, are showing excellent performance based on deep learning. Nevertheless, due to the nature of deep learning represented by a black box, it is difficult to actually use it in critical decision-making situations such as national defense, autonomous driving, medical care, and finance due to the lack of explainability of judgement results. In order to overcome these limitations, in this study, a model description algorithm capable of local interpretation was applied to the inception network-derived AI to analyze what grounds they made when classifying national defense data. Specifically, we conduct a comparative analysis of explainability based on confidence values by performing LIME analysis from the Inception v2_resnet model and verify the similarity between human interpretations and LIME explanations. Furthermore, by comparing the LIME explanation results through the Top1 output results for Inception v3, Inception v2_resnet, and Xception models, we confirm the feasibility of comparing the efficiency and availability of deep learning networks using XAI.

• Journal of the Korean Society of Systems Engineering
• /
• v.19 no.1
• /
• pp.91-106
• /
• 2023

Multidimensional efforts such as budgeting, organizing, and institutionalizing are being carried out for the adoption of defense AI. However, there is little interest in eliminating duplication of defense resources that may occur during the AI adoption. In this study, we propose a theoretical conceptual model to optimize duplication of AI technology that may occur during the AI adoption in the vast defense field. For a systematic approach, the JCA of the US DoD and system abstraction method are applied, and the IMO logical structure is used to decompose AI requirements and identify duplication. As a result of analyzing the effectiveness of our conceptual model through six example defense AI requirements, it was found that the amount of requirements of data and AI technologies could be reduced by up to 41.7% and 70%, respectively, and estimated costs could be reduced by up to 35.5%.