• Journal of Information Processing Systems
• /
• v.18 no.5
• /
• pp.677-687
• /
• 2022

We propose a detection algorithm based on tree-structured convolutional neural networks (TsCNNs) that finds pornography, propaganda, or other inappropriate content on a social media network. The algorithm sequentially applies the typical convolutional neural network (CNN) algorithm in a tree-like structure to minimize classification errors in similar classes, and thus improves accuracy. We implemented the detection system and conducted experiments on a data set comprised of 6 ordinary classes and 11 inappropriate classes collected from the Korean military social network. Each model of the proposed algorithm was trained, and the performance was then evaluated according to the images and videos identified. Experimental results with 20,005 new images showed that the overall accuracy in image identification achieved a high-performance level of 99.51%, and the effectiveness of the algorithm reduced identification errors by the typical CNN algorithm by 64.87 %. By reducing false alarms in video identification from the domain, the TsCNNs achieved optimal performance of 98.11% when using 10 minutes frame-sampling intervals. This indicates that classification through proper sampling contributes to the reduction of computational burden and false alarms.

• Convergence Security Journal
• /
• v.23 no.2
• /
• pp.75-84
• /
• 2023

Recently, as the use of drones for military purposes is increasing, such as the Russia-Ukraine War, North Korea's reconnaissance against South Korea, and Army Tiger 4.0's dronebot system, anti-drone technology is developing a lot in each country. However, traditional anti-drone technologies in the form of using conventional weapons or electronic warfare weapons have the disadvantage of being expensive, so anti-drone technologies that can be performed at low cost are currently being newly researched. Therfore, in response to these anti-drone technologies, many efforts are being made to increase the survivability of our allies. In line with this trend, this study assumes a virtual anti-drone system applied with cyber domain and electronic warfare domain technologies that can be performed at low cost, rather than a technique using expensive conventional weapons or electronic warfare weapons among various anti-drone technologies. In response to this, we would like to present a plan to increase the survivability of friendly drones.

• Convergence Security Journal
• /
• v.20 no.4
• /
• pp.27-34
• /
• 2020

Recently, the fourth industrial revolution technology has not only changed everyday life greatly through technological development, but has also become a major keyword in the establishment of defense policy. In particular, Internet of Things, cloud, big data, mobile and cybersecurity technologies, called ICBMS, were selected as core leading technologies in defense information policy along with artificial intelligence. Amid the growing importance of the fourth industrial revolution technology, research is being carried out to develop the C4I system, which is currently operated separately by the Joint Chiefs of Staff and each military, including the KJCCS, ATCIS, KNCCS and AFCCS, into an integrated system in preparation for future warfare. This is to solve the problem of reduced interoperability for joint operations, such as information exchange, by operating the C4I system for each domain. In addition, systems such as the establishment of an integrated C4I system and the U.S. military's Risk Management Framework (RMF) are essential for efficient control and safe operation of weapons systems as they are being developed into super-connected and super-intelligent systems. Therefore, in this paper, the intelligent cyber threat detection, management of users' access to information, and intelligent management and visualization of cyber threat are presented in the future C4I system based on big data/cloud.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.26 no.1
• /
• pp.1-9
• /
• 2023

The skin structure of sensor pod mounted on the exterior of aircraft can be exposed to the acoustic dynamic load and static load such as aerodynamic pressure and inertial load during flight. Fatigue life prediction of structural model under acoustic load should be performed and also differential stiffness of model modified by static load should be considered. The acoustic noise test spectrum of MIL-STD-810G was applied to the structural model and the stress response power spectral density (PSD) was calculated. The frequency response analysis was performed with or without prestress induced by inplane static load, and the response spectrum was compared. Time series data was generated using the calculated PSD, and the time and frequency domain fatigue life were predicted and compared. The variation of stress response spectrum due to static load and predicted fatigue life according to the different structural model considering mean stress were examined and decreasing fatigue life was observed in the model with prestress of compressive static load.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.30 no.2
• /
• pp.155-161
• /
• 2010

Recently, the electromagnetic techniques of the eddy current testing(ECT), alternating current field testing, magnetic flux leakage testing and remote field testing have been used as a nondestructive evaluation method based on the electromagnetic induction. The eddy current testing is now widely accepted as a NDE method for the heat exchanger tube in the electric power industry, chemical, shipbuilding, and military. The ECT system mainly consists of the synthesizer module, analog module, analog-to-digital converter, power supplier, and data acquisition and analysis program. In this study, the synthesizer module and the analog module which are essential to the ECT system were primarily developed. The developed ECT system is basically a multifrequency type which is able to inject the maximum four frequencies based on the frequency and time domain multiplexing method. Conclusively, we confirmed that the EC signal was processed appropriately in each circuit modules, and the Lissajous EC signal was displayed in the impedance plane.

• Journal of Information Technology and Architecture
• /
• v.9 no.3
• /
• pp.233-241
• /
• 2012

Architecture framework (AF) is a guideline to define components needed to develop and operate enterprise architecture (EA), and to define relationships among the components. There are many architecture frameworks to operate EA of governments and businesses such as Zachman framework, DoDAF, TOGAF, FEAF, and TEAF. DoDAF is the most representative AF to support the development of the EA in the military domain. DoDAF is composed of eight viewpoints and 40 views that are affiliated with the viewpoints. To develop an AF for a specific goal, system architects decide a set of views. Furthermore, they determine data that are needed for a view modeling. However, views and data in DoDAF are structurally inter-related explicitly and/or implicitly. So, developing an AF for a specific goal is going to be a project to be carried out over a long haul. To reduce the burden of its development, in this paper, we develop ONT-SAF (Ontology for DoDAF) that can infer inter-relationships like referential and transitive relationships and the sequences among the views. Furthermore, to promote reusability and consistency of the views and the data within an AF, we adopt the view-data separation strategy. ONT-DAT contains classes like 'viewpoint', 'view', 'data', 'expression method', and 'reference model', and 11 properties including 'hasView.' To prove the effectiveness of ONT-SAF, we perform a case study.

• Journal of Positioning, Navigation, and Timing
• /
• v.4 no.1
• /
• pp.9-16
• /
• 2015

The applications of Global Navigation Satellite System (GNSS) receivers are becoming wider in various commercial and military systems including even small weapon systems such as artillery shells. The precision-guided munitions such as Small Diameter Bomb (SDB) of United States can be used for pinpoint strike by acquiring and tracking GNSS signals in high mobility situation. In this paper, a small GNSS receiver with embedded interference suppression capability working under high dynamic stress is developed which is applicable to the various weapon systems and can be used in other several harsh environments. It applies a kind of matched filter and multiple correlator schemes for fast signal acquisition and tracking of even weak signals and frequency domain signal processing method to eliminate the narrowband interference. To evaluate the performance of the developed GNSS receiver, the test scenario of high mobility and interference environment with the GNSS simulator and signal generator is devised. Then, the signal acquisition time, navigation accuracy, sensitivity, and interference suppression performances under high dynamic operation are evaluated. And the comparison test with the commercial GNSS receiver which has high sensitivity is made under the same test condition.

• Convergence Security Journal
• /
• v.23 no.1
• /
• pp.139-145
• /
• 2023

The ROK Army is promoting cutting-edge, future-oriented military development such as a mobile, intelligent, and hyper-connected Army TIGER system. The future infantry brigade plans to increase mobility with squad-level tactical vehicles to enable combat in multi-domain operations and to deploy various weapon systems such as surveillance and reconnaissance drones. In addition, it will be developed into an intelligent unit that transmits and receives data collected through the weapon system through a hyper-connected network. Accordingly, the future infantry brigade will transmit and receive more data. However, the Army's tactical information communication system has limitations in operating as a tactical communication system for future units, such as low transmission speed and bandwidth and restrictions on communication support. Therefore, in this paper, the information distribution capability of the future infantry brigade is presented through the offensive operation scenario and M&S.

• Journal of computational fluids engineering
• /
• v.21 no.1
• /
• pp.50-57
• /
• 2016

In various industries related with construction and military machinery, a large amount of power is normally required because such machinery operations, such as digging or breaking, take place under difficult working conditions in a rough environment. Thus, a hydraulic system needs to be applied as the major power transfer system. To produce and supply hydraulic power depending on the various load conditions, a hydraulic piston pump is utilized as a typical power source for a hydraulic system. In the present study, numerical simulations were conducted using the commercial program, Ansys CFX 14.5. To lubricate the moving parts as the pump starts to operate, a small amount of oil leaks out through the clearance between the orifice in the piston-shoe and the recess at the swash-plate. Taking this into consideration, a cylindrically shaped computational domain was modeled to maintain the same equivalent leakage area. To validate the numerical method applied herein, the numerical results of the flow rate at the discharge port were compared with the experimental data, and a good agreement between them was shown. Using the verified method, the effects of the discharge pressure and the angle of the swash-plate were also evaluated under several load conditions. The results of the present study can be useful information for a hydraulic piston pump used in many different manufacturing industries.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.29 no.10
• /
• pp.783-790
• /
• 2018

The frequency-hopping technique is one of the spread-spectrum techniques. Frequency hopping is a communication system in which the carrier frequency channel is hopped within the wideband. Therefore, a frequency-hopping system has such advantages as antijamming and low probability of intercept. This system is often used in military communications. Because frequency-hopping signal detection is difficult, it is an important research issue. A novel detection technique is proposed that can improve detection probability. When the received signal is transformed to a frequency domain sample by fast Fourier transform, spectral leakage lowers the detection probability. This problem can be solved by using the Hamming window, and the detection probability can be increased. However, in a frequency-hopping environment, the windowing technique lowers the detection probability. The proposed method solves this weakness. The simulation results show that the proposed detection technique improves the detection probability by as much as 13 %.