• 한국군사과학기술학회지
• /
• 제27권4호
• /
• 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.

• 한국군사과학기술학회지
• /
• 제25권3호
• /
• pp.219-230
• /
• 2022

In implementing a robust automatic target recognition(ATR) system with synthetic aperture radar(SAR) imagery, one of the most important issues is accurate classification of target variants, which are the same targets with different serial numbers, configurations and versions, etc. In this paper, a deep learning network with channel attention modules is proposed to cope with the recognition problem for target variants based on the previous research findings that the channel attention mechanism selectively emphasizes the useful features for target recognition. Different from other existing attention methods, this paper employs the channel attention modules without dimensionality reduction along the channel direction from which direct correspondence between feature map channels can be preserved and the features valuable for recognizing SAR target variants can be effectively derived. Experiments with the public benchmark dataset demonstrate that the proposed scheme is superior to the network with other existing channel attention modules.

• 한국군사과학기술학회지
• /
• 제26권2호
• /
• pp.188-196
• /
• 2023

In the future battlefield centered on the concept of mosaic warfare, the need for an unmanned combat system will increase to value human life. It is necessary for Multiple/Heterogeneous Unmanned Combat Systems to have suitable mission planning method in order to perform various mission. In this paper, we propose the MTSR model for mission planning of the unmanned combat system, and introduce a method of identifying a task by a combination of services using a request operator and a method of allocating resources to perform a task using the requested service. In order to verify the performance of the proposed task-resource matchmaking algorithm, simulation using occupation scenarios is performed and the results are analyzed.

• 한국군사과학기술학회지
• /
• 제25권1호
• /
• pp.30-44
• /
• 2022

The advent of deep learning-based algorithms has facilitated researches on target detection from synthetic aperture radar(SAR) imagery. While most of them concentrate on detection tasks for ships with open SAR ship datasets and for aircraft from SAR scenes of airports, there is relatively scarce researches on the detection of SAR ground vehicle targets where several adverse factors such as high false alarm rates, low signal-to-clutter ratios, and multiple targets in close proximity are predicted to degrade the performances. In this paper, a dataset of ground vehicle targets acquired from TerraSAR-X(TSX) satellite SAR images is presented. Then, both detection and instance segmentation are simultaneously carried out on this dataset based on the deep learning-based Mask R-CNN. Finally, this paper shows the future research directions to further improve the performances of detecting the SAR ground vehicle targets.

• 전자통신동향분석
• /
• 제36권1호
• /
• pp.89-98
• /
• 2021

The Ministry of National Defense aims to create an environment in which transparent and reasonable defense policies can be implemented in real time by establishing the vision of smart defense innovation based on the Fourth Industrial Revolution and promoting innovation in technology-based defense operation systems. Artificial intelligence (AI) based defense technology is at the level of basic research worldwide, includes no domestic tasks, and involves classified military operation data and command control/decision information. Further, it is needed to secure independent technologies specialized for our military. In the army, military power continues to decline due to aging and declining population. In addition, it is expected that there will be more than 500,000 units should be managed simultaneously, to recognize the battle situation in real time on the future battlefields. Such a complex battlefield, command decisions will be limited by the experience and expertise of individual commanders. Accordingly, the study of AI core technologies supporting real-time combat command is actively pursued at home and abroad. It is necessary to strengthen future defense capabilities by identifying potential threats that commanders are likely to miss, improving the viability of the combat system, ensuring smart commanders always win conflicts and providing reasonable AI digital staff based on data science. This paper describes the recent research trends in AI military staff technology supporting commander decision-making, broken down into five key areas.

• International Journal of Computer Science & Network Security
• /
• 제23권2호
• /
• pp.173-182
• /
• 2023

The UAE government has set its sights on creating a smart, electronic-based government system that utilizes AI. The country's collaboration with India aims to bring substantial returns through AI innovation, with a target of over $20 billion in the coming years. To achieve this goal, the UAE launched its AI strategy in 2017, focused on improving performance in key sectors and becoming a leader in AI investment. To ensure public safety as the role of AI in government grows, the country is working on developing integrated cyber security solutions for SCADA systems. A questionnaire-based study was conducted, using the AI IQ Threat Scale to measure the variables in the research model. The sample consisted of 200 individuals from the UAE government, private sector, and academia, and data was collected through online surveys and analyzed using descriptive statistics and structural equation modeling. The results indicate that the AI IQ Threat Scale was effective in measuring the four main attacks and defense applications of AI. Additionally, the study reveals that AI governance and cyber defense have a positive impact on the resilience of AI systems. This study makes a valuable contribution to the UAE government's efforts to remain at the forefront of AI and technology exploitation. The results emphasize the need for appropriate evaluation models to ensure a resilient economy and improved public safety in the face of automation. The findings can inform future AI governance and cyber defense strategies for the UAE and other countries.

• 문화기술의 융합
• /
• 제10권3호
• /
• pp.19-24
• /
• 2024

미래의 군사 전투 환경은 현재의 군(軍) 인구 감소 및 변화하는 양상에 맞춰 국방 분야에서 인공지능(AI)의 역할과 중요성이 급격히 확대되고 있다. 특히, 민간에서의 AI(Artificial Intelligence) 개발은 OpenAI의 Chat-GPT 등장 이후 초거대 AI(Super-Giant AI, also known as Hyperscale AI), 즉 파운데이션 모델을 기반으로 새로운 영역에서 부상하고 있다. 미국 국방부는 CDAO(Chief Digital and AI Office) 산하의 Task Force Lima를 조직하여 LLM(Large Language Model)과 생성형 AI의 활용 방안에 대한 연구를 진행 중이며, 중국, 이스라엘 등 군사 선진국에서도 초거대 AI를 군에 적용하기 위한 연구를 수행 중이다. 따라서, 우리 군도 무기체계에 초거대 AI 모델의 활용 가능성과 적용분야에 대한 연구의 필요성이 대두되고 있다. 본 논문에서는 기존의 특화 AI와 초거대 AI(파운데이션 모델, Foundation Model)의 특징 및 장·단점을 비교하고, 무기체계에 적용될 수 있는 초거대 AI의 새로운 적용분야를 발굴하였다. 본 연구는 미래의 적용 분야와 잠재적인 도전과제에 대한 예측과 함께 초거대 인공지능을 국방작전에 효과적으로 통합하기 위한 통찰력을 제공하고, 선진화된 인공지능 시대에서의 국방 정책 개발, 국제 안보 전략을 형성하는 데 기여할 것으로 기대한다.

• 한국군사과학기술학회지
• /
• 제27권2호
• /
• 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.

• 전자통신동향분석
• /
• 제39권4호
• /
• pp.21-31
• /
• 2024

Major global powers are investing heavily in artificial intelligence (AI) and hyper-connected networks, demonstrating their crucial role in future warfare. To advance and utilize AI in national defense, it is essential to have policy support at the governmental or national level. This includes establishing a research and development infrastructure, creating a common development environment, and fostering AI expertise through education and training programs. To achieve advancements in hyper-connected networks, it is essential to establish a foundation for a robust and resilient infrastructure by comprehensively building integrated satellite, aerial, and ground networks, along with developing 5G & edge computing and low-orbit satellite communication technologies. This multi-faceted approach will ensure the successful integration of AI and hyper-connected networks, strengthening national defense and positioning nations at the forefront of technological advancements in warfare.

• 한국군사과학기술학회지
• /
• 제25권4호
• /
• 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.