• Journal of the Korea Society of Computer and Information
• /
• v.28 no.1
• /
• pp.1-8
• /
• 2023

In this paper, we propose a training method of a recommendation learning model that analyzes the battlefield situation and recommends a suitable hypothesis for the current situation. The proposed learning model uses the preference determined by comparing the two hypotheses as a label data to learn which hypothesis best analyzes the current battlefield situation. Our model is based on Siamese neural network architecture which uses the same weights on two different input vectors. The model takes two hypotheses as an input, and learns the priority between two hypotheses while sharing the same weights in the twin network. In addition, a score is given to each hypothesis through the proposed post-processing ranking algorithm, and hypotheses with a high score can be recommended to the commander in charge.

• Aerospace Engineering and Technology
• /
• v.8 no.2
• /
• pp.83-91
• /
• 2009

This paper concerns the dynamic property of TVC system in the upper stage of KSLV-I. The minimum bandwidth of TVC system is predicted by gathering and comparing the dynamic test data through whole development phases of KSLV-I. The linear models which approximate the dynamic data are also suggested. It is shown that the minimum bandwidth of KSLV-I TVC system is guaranteed over 6.0 Hz at one degree command. It is also shown that the linear model of KSLV-I TVC dynamics takes the form of the transfer function with an 8-th order denominator and a 2-nd order numerator. These results will play an important role in analyzing the flight stability and performance of KSLV-I.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.1
• /
• pp.64-70
• /
• 2014

In this paper, we propose a method that gives motion command to a mobile robot to recognize human being's hand gesture. Former way of the robot-controlling system with the movement of hand used several kinds of pre-arranged gesture, therefore the ordering motion was unnatural. Also it forced people to study the pre-arranged gesture, making it more inconvenient. To solve this problem, there are many researches going on trying to figure out another way to make the machine to recognize the movement of the hand. In this paper, we used third-dimensional camera to obtain the color and depth data, which can be used to search the human hand and recognize its movement based on it. We used HMM method to make the proposed system to perceive the movement, then the observed data transfers to the robot making it to move at the direction where we want it to be.

• Journal of Astronomy and Space Sciences
• /
• v.20 no.4
• /
• pp.339-350
• /
• 2003

Engineering qualification model payload for a communications and broadcasting satellite(CBS) was developed by ETRI from May, 2000 to April, 2003. For. the purpose of functional test and verification of the payload, a real-time hardware-in-the-loop(HITL) CBS simulator(CBSSIM) was also developed. We assumed that the spacecraft platform for the CBSSIM is a geostationary communication satellite using momentum bias three-axis stabilization control technique based on Koreasat. The payload hardware is combined with CBSSIM via Power, Command and Telemetry System(PCTS) of Electrical Ground Support Equipment(EGSE). CBSSIM is connected with PCTS by TCP/IP and the payload is combined with PCTS by MIL-STD-1553B protocol and DC harness. This simulator runs under the PC-based simulation environment with Windows 2000 operating system. The satellite commands from the operators are transferred to the payload or bus subsystem models through the real-time process block in the simulator. Design requirements of the CBSSIM are to operate in real-time and generate telemetry. CBSSIM provides various graphic monitoring interfaces and control functions and supports both pre-launch and after-launch of a communication satellite system. In this paper, the HITL simulator system including CBSSIM, communications payload and PCTS as the medium of interface between CBSSIM and communications payload will be described in aspects of the system architecture, spacecraft models, and simulator operation environment.

• Journal of the Korean Society of Systems Engineering
• /
• v.19 no.2
• /
• pp.126-134
• /
• 2023

Drones are emerging as a new security threat, and the world is working to reduce them. Detection and identification are the most difficult and important parts of the anti-drone systems. Existing detection and identification methods each have their strengths and weaknesses, so complementary operations are required. Detection and identification performance in anti-drone systems can be improved through the use of artificial intelligence. This is because artificial intelligence can quickly analyze differences smaller than humans. There are three ways to utilize artificial intelligence. Through reinforcement learning-based physical control, noise and blur generated when the optical camera tracks the drone may be reduced, and tracking stability may be improved. The latest NeRF algorithm can be used to solve the problem of lack of enemy drone data. It is necessary to build a data network to utilize artificial intelligence. Through this, data can be efficiently collected and managed. In addition, model performance can be improved by regularly generating artificial intelligence learning data.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.51 no.3
• /
• pp.155-160
• /
• 2002

This paper focuses on the problem of local obstacle avoidance of mobile robots. To solve this problem, the safety direction section search algorithm is suggested. This concept is mainly composed with non-collision section and collision section from the detecting area of laser scanning sensor. Then, we will search for the most suitable direction in these sections. The proposed local motion planning method is simple and requires less computation than others. An environment model is developed using the vector space concept to determine robot motion direction taking the target direction, obstacle configuration, and robot trajectory into account. Since the motion command is obtained considering motion dynamics, it results in smooth and fast as well as safe movement. Using the mobile base, the proposed obstacle avoidance method is tested, especially in the environment with pillar, wall and some doors. Also, the proposed autonomous motion planning and control algorithm are tested extensively. The experimental results show the proposed method yields safe and stable robot motion through the motion speed is not so fast.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2002.10a
• /
• pp.219-224
• /
• 2002

This paper aims to derive a mathematical model of the dynamics of handling tasks in robot finger which stable grasping and manipulates a rigid object with some dexterity. Firstly, a set of differential equation describing dynamics of the manipulators and object together with geometric constraint of tight area-contacts is formulated by Lagrange's equation. Secondly, problems of controlling both the internal force and the rotation angle of the grasped object under the constraints of area-contacts of tight area-contacts are discussed. The effect of geometric constraints of area-contacts on motion of the overall system is analyzed and a method of computer simulation for overall system of differential-algebraic equations is presented. Thirdly, simulation results are shown and the effects of geometric constraints of area-contact is discussed. Finally, it is shown that even in the simplest case of dual single D.O.F manipulators there exists a sensory feedback from sensing data of the rotational angle of the object to command inputs to joint actuators and this feedback connection from sensing to action eventually realizes secure grasping of the object, provided that the object is of rectangular shape and motion is confined to a horizontal plane.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.25 no.5
• /
• pp.22-33
• /
• 2011

An induction motor operated with a conventional direct self controller(DSC) shows a sluggish response during startup and under changes of torque command. Fuzzy logic controller(FLC) is used in conjection with DSC to minimize these problems. A FLC chooses the switching states based on a set of fuzzy variables. Flux position, error in flux magnitude and error in torque are used as fuzzy state variables. Fuzzy rules are determinated by observing the vector diagram of flux and currents. This paper proposes hybrid fuzzy controller for direct torque control(DTC) of induction motor drives. The speed controller is based on adaptive fuzzy learning controller(AFLC), which provide high dynamics performances both in transient and steady state response. Flux position, error in flux magnitude and error in torque are used as FLC state variables. The speed is estimated with model reference adaptive system(MRAS) based on artificial neural network(ANN) trained on-line by a back-propagation algorithm. This paper is controlled speed using hybrid fuzzy controller(HFC) and estimation of speed using ANN. The performance of the proposed induction motor drive with HFC controller and ANN is verified by analysis results at various operation conditions.

• Journal of Industrial Convergence
• /
• v.21 no.9
• /
• pp.41-48
• /
• 2023

Recently, there has been a sharp increase in the damages caused by ransomware across various sectors of society, including individuals, businesses, and nations. Ransomware is a malicious software that infiltrates user computer systems, encrypts important files, and demands a ransom in exchange for restoring access to the files. Due to its diverse and sophisticated attack techniques, ransomware is more challenging to detect than other types of malware, and its impact is significant. Therefore, there is a critical need for accurate detection and mitigation methods. To achieve precise ransomware detection, an inference engine of a detection system must possess knowledge of ransomware features. In this paper, we propose a model to extract and classify the characteristics of ransomware for accurate detection of ransomware, calculate the similarity of the extracted characteristics, reduce the dimension of the characteristics, group the reduced characteristics, and classify the characteristics of ransomware into attack tools, inflow paths, installation files, command and control, executable files, acquisition rights, circumvention techniques, collected information, leakage techniques, and state changes of the target system. The classified characteristics were applied to the existing ransomware to prove the validity of the classification, and later, if the inference engine learned using this classification technique is installed in the detection system, most of the newly emerging and variant ransomware can be detected.

• Journal of the Korea Society for Simulation
• /
• v.23 no.2
• /
• pp.25-33
• /
• 2014

In this study, the border security problem of the ROK Army is examined by applying the agent-based modeling and simulation (ABMS) concept as well as its platform, MANA. Based on the approximately optimized behavior of the infiltrator obtained using genetic algorithm (GA), we evaluate the GOP border security system which consists of human resources, surveillance, as well as command and control (C2) systems. We use four measures of effectiveness (MOEs) to evaluate its performance, and we apply a near optimal latin hypercube (NOLH) design to deal with the large number of factors of interest in our model. By using a NOLH design, our simulation runs are implemented efficiently. We hope the results of this study provide valuable data for deciding the configuration of the border security system structure and the number of soldiers assigned in the platoon.