• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.158-160
• /
• 2022

Many office workers spend a lot of time performing repetitive office tasks in inefficient ways. We developed a user-friendly chatbot system based on Kakaotalk to automate repetitive tasks and used the chatbot in the real workplace. In the process of operating the chatbot, if several people use the chatbot at the same time, the server was down or could not respond. To address these issues, we performed code migration of programs used by chatbot back-end servers and tried several ways to improve server performance such as database redesign and load balancing. To determine how much each method affects performance improvement, we measured total request per second and average latency. After that, we proposed ways to improve the problems of using the chatbot in the work environment.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.42 no.10
• /
• pp.884-892
• /
• 2014

In this paper, a meta model using neural network substituting for the simulator aerodynamic database is proposed to improve simulation fidelity near the critical flight area and real-time performance. It is shown that the accuracy of the meta model is relatively higher than the existing table lookup methods for arbitrary nonlinear database and the calculation speed is also improved for a specific F-16 maneuver simulation. The increase in the number of hidden nodes in the meta model for better accuracy of database representations causes a delay in function generation due to increased time required for computing exponential functions. In order to make up this drawback, we additionally study the fast exponential function method.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.107-119
• /
• 2023

The technology that recognizes a soldier's motion and movement status has recently attracted large attention as a combination of wearable technology and artificial intelligence, which is expected to upend the paradigm of troop management. The accuracy of state determination should be maintained at a high-end level to make sure of the expected vital functions both in a training situation; an evaluation and solution provision for each individual's motion, and in a combat situation; overall enhancement in managing troops. However, when input data is given as a timer series or sequence, existing feedforward networks would show overt limitations in maximizing classification performance. Since human behavior data (3-axis accelerations and 3-axis angular velocities) handled for military motion recognition requires the process of analyzing its time-dependent characteristics, this study proposes a high-performance data-driven classifier which utilizes the long-short term memory to identify the order dependence of acquired data, learning to classify eight representative military operations (Sitting, Standing, Walking, Running, Ascending, Descending, Low Crawl, and High Crawl). Since the accuracy is highly dependent on a network's learning conditions and variables, manual adjustment may neither be cost-effective nor guarantee optimal results during learning. Therefore, in this study, we optimized hyperparameters using Bayesian optimization for maximized generalization performance. As a result, the final architecture could reduce the error rate by 62.56% compared to the existing network with a similar number of learnable parameters, with the final accuracy of 98.39% for various military operations.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.1
• /
• pp.10-19
• /
• 2022

Recently, the Defense Advanced Research Projects Agency(DARPA) in the United States is studying a new concept of war called Mosaic Warfare, and MUM-T(Manned-Unmanned Teaming) through the division of missions between expensive manned and inexpensive unmanned aircraft is at the center. This study began with the aim of deriving the priority of autonomous functions according to the role of unmanned aerial vehicles in the present and present collaboration that is emerging along with the concept of mosaic warfare. The autonomous function of unmanned aerial vehicles between the presence and absence collaboration may vary in priority depending on the tactical operation of unmanned aerial vehicles, such as air-to-air, air-to-ground, and surveillance and reconnaissance. In this paper, ACE (Air Combat Evaluation), Skyborg, and Longshot, which are recently studied by DARPA, derive the priority of autonomous functions according to air-to-air collaboration, and use AHP analysis. The results of this study are meaningful in that it is possible to recognize the priorities of autonomous functions necessary for unmanned aircraft in order to develop unmanned aerial vehicles according to the priority of autonomous functions and to construct a roadmap for technology implementation. Furthermore, it is believed that the mass production and utilization of unmanned air vehicles will increase if one unmanned air vehicle platform with only essential functions necessary for air-to-air, air-to-air, and surveillance is developed and autonomous functions are expanded in the form of modules according to the tactical operation concept.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.20 no.4
• /
• pp.566-578
• /
• 2017

For optimizing the operation plan when strike packages attack multiple targets, this article suggests a new mathematical model and a parallel hybrid genetic algorithm (PHGA) as a solution methodology. In the model, a package can assault multiple targets on a sortie and permitted the use of mixed munitions for a target. Furthermore, because the survival probability of a package depends on a flight route, it is formulated as a mixed integer programming which is synthesized the models for vehicle routing and weapon-target assignment. The hybrid strategy of the solution method (PHGA) is also implemented by the separation of functions of a GA and an exact solution method using ILOG CPLEX. The GA searches the flight routes of packages, and CPLEX assigns the munitions of a package to the targets on its way. The parallelism enhances the likelihood seeking the optimal solution via the collaboration among the HGAs.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.45 no.10
• /
• pp.49-58
• /
• 2008

Characteristics of JEM(Jet Engine Modulation) are measured and principal meanings are grasped in this paper. This study's object is to measure RCS and JEM for actual aircraft, especially low speed craft. In experiment, various error are generated from unknown cause and for removal these, calibration technique known as IACT(Isolated Antenna Calibration Technique) is used. Experiment is executed at outdoor and target is T-103 which play in beginner course for ROKAF pilot. JEM spectrum of T-103 and frequency characteristics, doppler effects are extracted. X-band used in military aircraft for air-to-air fighting are selected. The data obtained through this study are analyzed to discriminate target especially low speed aircraft for current using radar(X-band)'s performance.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.44 no.7
• /
• pp.620-628
• /
• 2016

The homotopy algorithm provides a robust method for determining optimal control, in some cases the global minimum solution, as a continuation parameter is varied gradually to regulate the contributions of the nonlinear terms. In this paper, the Successive Backward Sweep (SBS) method, which is insensitive to initial guess, augmented with a homotopy algorithm is suggested. This approach is effective for highly nonlinear problems such as low-thrust trajectory optimization. Often, these highly nonlinear problems have multiple local minima. In this case, the SBS-homotopy method enables one to steadily seek a global minimum.

• Journal of the Korean Applied Science and Technology
• /
• v.36 no.4
• /
• pp.1060-1068
• /
• 2019

The physical fitness of the cadets of the Air Force Academy, which will protect the airspace of the Republic of Korea, is of paramount importance to fulfill the given mission. Therefore, the purpose of this study was to confirm the characteristics of body composition and physical fitness of female cadets of Air Force Academy and to verify their relationship with physical fitness according to body fat % level of total female cadets. To achieve the purpose of the study, 50 female cadets of the Korea Air Force Academy (1grade 13, 2grade 18, 3grade 9, 4grade 10) were measured in body composition (skeletal strength, body fat mass, body mass index, body fat %, abdominal obesity rate, basal metabolic rate) and physical fitness (muscle strength, muscular endurance, power, agility, flexibility and balance). One way ANOVA was performed for data processing to identify body composition and physical fitness characteristics by grade and to identify differences in physical fitness according to body fat rate levels. According to the study, the 1 grade was lower in body fat mass and body fat % among female cadets, the 2 grade was lower than the 3 and 4 grades, and the body mass index was lower than the third and fourth grades. Also, there was no difference in the physical fitness of the rest of the year. The intergroup physical fitness according to the body fat rate was higher than that of those with less than 20 percent of net worth and 25 percent to less than 25.1 percent to 30 percent, while those with less than 20 percent balance were higher than those with less than 25.1 to 30 percent. The results of this study showed differences in body composition by grade in female cadets, especially in power and balance according to body fat %. Therefore, female cadets of the Air Force Academy need to manage body fat to have the power and balance capability related to the airborne mission environment.

• Journal of the Korea Society for Simulation
• /
• v.28 no.1
• /
• pp.57-65
• /
• 2019

Air refueling is expected to increase the efficiency of the air force operations. This follows from the introduction of air refueling aircraft, which should to increase operational time by increasing the range and duration of fighter jets. Despite the effectiveness of the air refueling air crafts, the astronomical costs of adapting the air tankers call for careful discussions on whether to acquire any air craft and if so, how many. However there is no academic study on the subject to our knowledge. Thus, we use the ABM(Agent Based Modeling) technique to calculate the optimal number of air tankers during patrol operation. We have enhanced the reliability of the simulation by entering the specifications of the current aircraft operated by the Korean Air Force. As an optimization tool for determining the optimal number of counts, we use OptQuest built into the simulation tools and show that the optimal number of air tanker is 4.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.17 no.6
• /
• pp.764-772
• /
• 2014

The stealth performance of supersonic aircraft in recent air battlefield is one of the most significant feature for latest fighters. Especially, as the technology is advancing, the IR stealth capability becomes more important because of its passive characteristic. To design an aircraft with stealth capability, we must know how much the IR signature is generated from the aircraft. Also, predicting the IR signature of enemy's aircraft is tactically crucial. In this study, we calculated MWIR and LWIR infrared signature of $5^{th}$ generation supersonic aircraft against air-to-air and surface-to-air threat using IR simulation code and CFD coupled procedure.