• Journal of the Korea Institute of Military Science and Technology
• /
• v.26 no.1
• /
• pp.10-21
• /
• 2023

For various target tracking applications, it is well known that the Kalman filter is the optimal estimator(in the minimum mean-square sense) to predict and estimate the state(position and/or velocity) of linear dynamical systems driven by Gaussian stochastic noise. In the case of nonlinear systems, Extended Kalman filter(EKF) and/or Unscented Kalman filter(UKF) are widely used, which can be viewed as approximations of the(linear) Kalman filter in the sense of the conditional expectation. However, to implement EKF and UKF, the exact dynamical model information and the statistical information of noise are still required. In this paper, we propose the recurrent neural-network based Kalman filter, where its Kalman gain is obtained via the proposed GRU-LSTM based neural-network framework that does not need the precise model information as well as the noise covariance information. By the proposed neural-network based Kalman filter, the state estimation performance is enhanced in terms of the tracking error, which is verified through various linear and nonlinear tracking problems with incomplete model and statistical covariance information.

• Convergence Security Journal
• /
• v.22 no.2
• /
• pp.27-42
• /
• 2022

In the era of the Fourth Industrial Revolution, digital transformation to increase the effectiveness of industry is becoming more important to achieving the goal of industrial innovation. The digital new deal and smart defense are required for digital transformation and utilize artificial intelligence, big data analysis technology, and the Internet of Things. These changes can innovate the industrial fields of national defense, society, and health with new intelligent services by continuously expanding cyberspace. As a result, work productivity, efficiency, convenience, and industrial safety will be strengthened. However, the threat of cyber-attack will also continue to increase due to expansion of the new domain of digital transformation. This paper presents the risk scenarios of cyber-attack threats in the Fourth Industrial Revolution. Further, we propose a preemptive intrusion response model to bolster the complex security environment of the future, which is one of the fundamental alternatives to solving problems relating to cyber-attack. The proposed model can be used as prior research on cyber security strategy and technology development for preemptive response to cyber threats in the future society.

• Journal of Advanced Navigation Technology
• /
• v.28 no.2
• /
• pp.193-200
• /
• 2024

This paper describes the design and development of a transmit receiver module(TRM) for mounting on X-band SAR of the NEXTSat-2. The TRM generates the chirp signal with required bandwidth through the DDS in X-band and performs frequency conversion, combination for the signal to transmit and be received and frequency synthesis. Tx path of the TRM produces signals of total 28 bandwidths up to 96.8 MHz and has output signal level of more than + 9.37 dBm. Rx path of the TRM has minimum noise figure of 15.7 dB. The measurement results show that required requirements are satisfied. The TRM is installed on the NEXTSat-2 flight model(FM), launched by KSLV-II(Nuri) on May 23, 2023 and currently operational.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.3
• /
• pp.33-42
• /
• 2020

There has been difficulties in identifying objects by relying on the naked eye in various surveillance systems. There is a growing need for automated surveillance systems to replace soldiers in the field of military surveillance operations. Even though the object detection technology is developing rapidly in the civilian domain, but the research applied to the military is insufficient due to a lack of data and interest. Thus, in this paper, we applied one of deep learning algorithms, Convolutional Neural Network-based binary classification to develop an autonomous identification model of both friend and foe helicopters (AH-64, Mi-17) among the military weapon systems, and evaluated the model performance by considering accuracy, precision, recall and F-measure. As the result, the identification model demonstrates 97.8%, 97.3%, 98.5%, and 97.8 for accuracy, precision, recall and F-measure, respectively. In addition, we analyzed the feature map on convolution layers of the identification model in order to check which area of imagery is highly weighted. In general, rotary shaft of rotating wing, wheels, and air-intake on both of ally and foe helicopters played a major role in the performance of the identification model. This is the first study to attempt to classify images of helicopters among military weapons systems using CNN, and the model proposed in this study shows higher accuracy than the existing classification model for other weapons systems.

• Journal of Information Management
• /
• v.41 no.3
• /
• pp.45-66
• /
• 2010

The purpose of this study is to develop service quality measurement model(DL-SQI model) which are able to measure objectively service quality of digital libraries in Korea and to measure user perceived service quality performance with DL-SQI model. This study also investigates the influence of service quality on customer satisfaction and customer loyalty. Before measurement, two principal rules and indicator formula were made to measure the service quality. Finally service quality of three digital libraries selected as samples was measured and analyzed in various points of view. It was developed a DL-SQI Consequences Model and testified it through path analysis using structural equation model.

• Journal of computational fluids engineering
• /
• v.17 no.3
• /
• pp.25-32
• /
• 2012

This work was devoted to compare two different cavitation models to study the dependency of model constants. The cavitation model of Merkle et al.(2006) and Kunz et al.(2000) were used for the present computational study. The cavitation models were coupled with the incompressible unsteady Reynolds-Averaged Navier-Stokes solver to indicate the vaporization and condensation processes. For this purpose, a preconditioning method was added as the pseudo-time term to solve the unsteady stiffness problems. For the validation of the numerical simulation, the computation was performed for the cavitating flow in a converging-diverging channel. The present results show that Merkle's cavitation model is independent to the model constants, and the higher numerical accuracy over Kunz's cavitation model.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.48 no.8
• /
• pp.573-580
• /
• 2020

One of challengeable problems of multi-agent systems is a positioning control. Augmented Cucker-Smale model is using for controlling position and velocity of the multi-agent system. The original model applies same coefficients to all agents in same group, so that does not consider characteristic of each agent. To enhance performance of the original model, this paper transforms original coefficients to Mahalanobis distance coefficients that reflects an initial distribution of multi-agent systems and applies statistical degrees of freedom. This paper not only confirms tendency of enhanced performance of the suggested model by using monte-carlo simulation, but also additionally compares trajectory of the original model with the suggested model to confirm coefficients of Mahalanobis distance performing correctly.

• Journal of the Society of Naval Architects of Korea
• /
• v.46 no.1
• /
• pp.43-56
• /
• 2009

The Korean navy has made many efforts to apply the concepts of PLM (Product Lifecycle Management) and M&S to its naval design and production. However, most of the efforts that have being applied to some acquisition processes, focused only on the element technologies without information models and data frameworks. This study discusses an information model of naval ships for advanced naval acquisitions. We introduce a naval ship product model, and it refers to the DPD (Distributed Product Description) concept of SBA (Simulation-Based Acquisition). To realize the product model concept, we design a data architecture and develop a Product Model Management System (PMMS) based on a PDM System. It is validated through the case study of building the product model of the battle ship that the PMMS has the applicability to effectively manage the naval ship acquisition data on the basis of a 3D product model.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.6 no.1
• /
• pp.64-69
• /
• 2006

Due to the inherent nonlinear nature of Electro-rheological (ER) fluid dampers, one of the challenging aspects for utilizing these devices to achieve high system performance is the development of accurate models and control algorithms that can take advantage of their unique characteristics. In this paper, the nonlinear damping force model is made to identify the properties of the ER damper using higher order spectrum. The higher order spectral analysis is used to investigate the nonlinear frequency coupling phenomena with the damping force signal according to the sinusoidal excitation of the damper. Also, this paper presents an inverse model of the ER damper, i.e., the model can predict the required voltage so that the ER damper can produce the desired force for the requirement of vibration control of vehicle suspension systems. The inverse model is constructed by using a multi-layer perceptron neural network. A quarter-car suspension model is considered in this paper for analysis and simulation. Simulation results show that the proposed inverse model of ER damper can obtain control voltage of ER damper for required damping force.

• Journal of the Korean Society of Industry Convergence
• /
• v.23 no.6_2
• /
• pp.1103-1110
• /
• 2020

In this study, a segmented model with Upside-Down bathtub shaped failure intensity for a repairable system are proposed under the assumption that the occurrences of the failures of a repairable system follow the Non-Homogeneous Poisson Process. The proposed segmented model is the compound model of S-PLP and LIP (Segmented Power Law Process and Logistic Intensity Process), that fits the separate failure intensity functions on each segment of time interval. The maximum likelihood estimation is used for estimating the parameters of the S-PLP and LIP model. The case study of system A shows that the S-PLP and LIP model fits better than the other models when compared by AICc (Akaike Information Criterion corrected) and MSE (Mean Squared Error). And it also implies that the S-PLP and LIP model can be useful for explaining the failure intensities of similar systems.