• The Journal of Korea Robotics Society
• /
• v.18 no.3
• /
• pp.293-298
• /
• 2023

The military is facing a continuous decrease in personnel, and in order to cope with potential accidents and challenges in operations, efforts are being made to reduce the direct involvement of personnel by utilizing the latest technologies. Recently, the use of various sensors related to Manned-Unmanned Teaming and artificial intelligence technologies has gained attention, emphasizing the need for flexible utilization methods. In this paper, we propose four dataset construction methods that can be used for effective training of robots that can be deployed in military operations, utilizing not only RGB image data but also data acquired from IR image sensors. Since there is no publicly available dataset that combines RGB and IR image data, we directly acquired the dataset within buildings. The input values were constructed by combining RGB and IR image sensor data, taking into account the field of view, resolution, and channel values of both sensors. We compared the proposed method with conventional RGB image data classification training using the same learning model. By employing the proposed image data fusion method, we observed improved stability in training loss and approximately 3% higher accuracy.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.155-155
• /
• 2022

Low head, ogee spillways is popularly used to defense against floods as well as to provide water for irrigation. Spillway is also used to assess compliance with water quality regulations by controlling amount of discharge to the downstream of a channel. For the purpose of water resource management and/or environmental aspects as explained above, the flow discharge through spillways need to be correctly rated as a function of geometry and hydraulic variables. Typically, four flow conditions are encountered during the operation of spillway: (a) uncontrolled free flow (UF); (b) uncontrolled submerged flow (US); controlled free flow (CF); and controlled submerged flow (CS), and each condition has a unique rating equation. However, one of the tricky part of the spillway operation is finding correct flow type over the spillway because structures can operate under both submerged and free flow conditions, and the types are continuously changing over time depending on the amount of discharge, head water and tail water elevation. Quite obviously, if the wrong rating curve relationship is applied because of misjudgment of the flow type due to a transition, a serious error can occur. Thus, an hydraulic model study of one of spillway structure located in South Florida was conducted for the purpose of developing transition relationships. In this presentation, US to UF transition is highlighted.

• Journal of Korean Society for Quality Management
• /
• v.51 no.1
• /
• pp.37-54
• /
• 2023

Purpose: A main aims are to check the level of satisfaction of service quality and derive service quality factors in the field of defense quality assurance activities that need improvement. Furthermore, the paper presents a basic data for identifying future development directions. Methods: Classify the level of service perceived by customers and calculate the customer satisfaction coefficient and PCSI index. In addition, the direction of future research is established by empirically comparing and analyzing the data of this study and the past data. Results: The paper derive the service quality factors to be provided to small businesses in the current state. Moreover, It shows the increasing trend of new companies using comparative analysis with past data Conclusion: Since the new company consists of small businesses with less than 50 employees, further research on small businesses is needed in the future.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.26 no.3
• /
• pp.252-261
• /
• 2023

Analysis of dynamic characteristics and flight vibration test for unmanned aerial vehicles was studied by using dummy test body. The FEM model for dummy test body was supplemented by results of modal and random vibration test. The free end boundary condition to simulate flight environments was made by test setup using bungee cable. Prior to the flight vibration test using a dual electric vibration exciters, the test procedure to calculate quantitative vibration level was studied by using military specification. The actual test was successfully done by using the analysis and pretest results. From the analysis results, it was possible to determine the feasibility of the test by predicting the excitation force of the flight vibration test and to get the response of any point which could not be measured by the test. The results of this study will much contribute to the Test and Evaluation of unmanned aerial vehicles.

• Annual Conference of KIPS
• /
• 2022.11a
• /
• pp.803-805
• /
• 2022

자율주행의 시대가 도래함에 따라, 딥러닝 모델에 대한 적대적 공격 위험이 함께 증가하고 있다. 카메라 기반 자율주행차량이 공격받을 경우 보행자나 표지판 등에 대한 오분류로 인해 심각한 사고로 이어질 수 있어, 자율주행 시스템에서의 적대적 공격에 대한 방어 및 보안 기술 연구가 필수적이다. 이에 본 논문에서는 GTSRB 표지판 데이터를 이용하여 각종 공격 및 방어 기법을 개발하고 제안한다. 시간 및 정확도 측면에서 성능을 비교함으로써, 자율주행에 최적인 모델을 탐구하고 더 나아가 해당 모델들의 완전자율주행을 위한 발전 방향을 제안한다.

• International conference on construction engineering and project management
• /
• 2015.10a
• /
• pp.597-598
• /
• 2015

In order to improve the reliability of cost estimation results using CBR, there has been a continuous issue on similarity measurement to accurately compute the distance among attributes and cases to retrieve the most similar singular or plural cases. However, these existing similarity measures have limitations in taking the covariance among attributes into consideration and reflecting the effects of covariance in computation of distances among attributes. To deal with this challenging issue, this research examines the weighted Mahalanobis distance based similarity measure applied to CBR cost estimation and carries out the comparative study on the existing distance measurement methods of CBR. To validate the suggest CBR cost model, leave-one-out cross validation (LOOCV) using two different sets of simulation data are carried out. Consequently, this research is expected to provide an analysis of covariance effects in similarity measurement and a basis for further research on the fundamentals of case retrieval.

• International Journal of Computer Science & Network Security
• /
• v.24 no.4
• /
• pp.179-191
• /
• 2024

With the advancement of modern technology, cyber-attacks are always rising. Specialized defense systems are needed to protect organizations against these threats. Malicious behavior in the network is discovered using security tools like intrusion detection systems (IDS), firewall, antimalware systems, security information and event management (SIEM). It aids in defending businesses from attacks. Delivering advance threat feeds for precise attack detection in intrusion detection systems is the role of cyber-threat intelligence (CTI) in the study is being presented. In this proposed work CTI feeds are utilized in the detection of assaults accurately in intrusion detection system. The ultimate objective is to identify the attacker behind the attack. Several data sets had been analyzed for attack detection. With the proposed study the ability to identify network attacks has improved by using machine learning algorithms. The proposed model provides 98% accuracy, 97% precision, and 96% recall respectively.

• Transactions of Materials Processing
• /
• v.33 no.1
• /
• pp.18-35
• /
• 2024

In the present work, the evolution rules for the internal variables including continuum damage factors are obtained using the thermodynamic framework, which are in turn facilitated to derive the elastic-plastic constitutive relation for the particulate composites. Using the Mori-Tanaka scheme, the homogenization on state and internal variables such as back-stress and damage factors is carried out to procure the rate independent plasticity relations. Moreover, the degradation of mechanical properties of constituents is depicted by the distinctive damages such that the phase and interfacial damages are treated individually accordingly, whereas the kinematic hardening is depicted by combining the Armstrong-Frederick and Phillips' back-stress evolutions. On the other hand, the present constitutive relation for each phase is expressed in terms of the respective damage-free effective quantities, then, followed by transformation into the damage affected overall nominal relations using the aforementioned homogenization concentration factors. An emphasis is placed on the qualitative analyses for strain localization by observing the perturbation growth instead of the conventional bifurcation analyses. It turns out that the proposed constitutive model offers a wide range of strain localization behavior depending on the evolution of various internal variable descriptions.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.1
• /
• pp.24-30
• /
• 2024

The gas-gun test is a experimental approach employed to validate the operational or structural stability when subjected to the impact energy encountered during launch or target collision. Predicting the outcomes of the gas-gun test has traditionally relied on empirical knowledge, due to numerous factors such as the bird assembly's shape, weight, material, and flight velocity. However, due to the nonlinearity and complex interactions between these variables, numerous tests are necessary to identify the necessary requirements, resulting in significant expense and time consumption during the process. The objective of this study is to forecast the variations in impact energy in future tests by developing a numerical model and analysis that aligns with the test outcomes, utilizing the ABAQUS Explicit. The outcome of the numerical analysis produced a framework that anticipates the peak g and the duration of the actual gas-sun test results, throughout post-processing techniques using FFT and LPF filters.

• Korean Journal of Materials Research
• /
• v.34 no.3
• /
• pp.125-137
• /
• 2024

Composite laminates are used in a wide range of applications including defense, automotive, aviation and aerospace, marine, wind energy, and recreational sporting goods. These composite beams still exhibit problems such as buckling, local deformations, and interlaminar delamination. To overcome these drawbacks, a novel viscoelastic autoclave bonding with tapered epoxy reinforcement polyurethane films is proposed. In existing laminates, compression face wrinkling and interlaminar delamination is caused in the sandwich beam. The unique viscoelastic autoclave spunbond interlayer bonding is designed to prevent face wrinkling and absorb and distribute stresses induced by external loads, thereby eliminating interlaminar delamination in the sandwich beam. Also, the existing special reinforcement causes stress concentrations, and the core is not effectively connected, which directly affects the stiffness of the beam. To address this, a novel tapered epoxy polyurethane reinforcement adhesive film is proposed, whose reinforcement thickness gradually tapers as it enters the core material. This minimizes stress concentrations at the interface, preventing excessive adhesive squeeze-out during the bonding process, and improves the stiffness of the beam. Results indicate the proposed model avoids the formation of micro cracks, interlaminar delamination, buckling, and local deformations, and effectively improves the stiffness of the beam.