• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.4
• /
• pp.42-48
• /
• 2021

Recently, the defense industry has been improving high technology by developing convergence technology through the 4th industrial revolution. On the other hand, it is very difficult to guarantee the performance of high-tech weapon systems because the test for weapon systems has many risks and cannot perform in an actual operating environment. Therefore, M&S resources are needed to make sound weapon systems, but many people demand reliable M&S resources. Owing to the continuous demand and execution of the VV&A work, related rules have developed significantly, but tools and techniques for performing the work have not been developed. Hence, there are inefficient parts in the performance of work due to the absence of a systematic system. Accordingly, many risks may cause various safety accidents, such as security. This paper suggests a direction for the development of VV&A work procedures by improving efficiency and reducing risk.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.5
• /
• pp.668-674
• /
• 2022

Machine learning techniques using visual data have high usability in fields of industry and service such as scene recognition, fault detection, security and user analysis. Among these, user analysis through the videos from CCTV is one of the practical way of using vision data. Also, many studies about lightweight artificial neural network have been published to increase high usability for mobile and embedded environment so far. In this study, we propose the network combining the object detection and classification for mobile graphic processing unit. This network detects pedestrian and face, classifies age and gender from detected face. Proposed network is constructed based on MobileNet, YOLOv2 and skip connection. Both detection and classification models are trained individually and combined as 2-stage structure. Also, attention mechanism is used to improve detection and classification ability. Nvidia Jetson Nano is used to run and evaluate the proposed system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.2
• /
• pp.626-643
• /
• 2023

As mobile forensics has emerged as an essential technique, the demand for technology development, education and training is increasing, wherein images are used. Academic societies in South Korea and national institutions in the US and the UK are leading the Mobile Forensic Image development. However, compared with disks, images developed in a mobile environment are few cases and have less active research, causing a waste of time, money, and manpower. Mobile Forensic Images are also difficult to trust owing to insufficient verification processes. Additionally, in South Korea, there are legal issues involving the Telecommunications Business Act and the Act on the Protection and Use of Location Information. Therefore, in this study, we requested a review of a standard model for the development of Mobile Forensic Image from experts and designed an 11-step development model. The steps of the model are as follows: a. setting of design directions, b. scenario design, c. selection of analysis techniques, d. review of legal issues, e. creation of virtual information, f. configuring system settings, g. performing imaging as per scenarios, h. Developing a checklist, i. internal verification, j. external verification, and k. confirmation of validity. Finally, we identified the differences between the mobile and disk environments and discussed the institutional efforts of South Korea. This study will also provide a guideline for the development of professional quality verification and proficiency tests as well as technology and talent-nurturing tools. We propose a method that can be used as a guide to secure pan-national trust in forensic examiners and tools. We expect this study to strengthen the mobile forensics capabilities of forensic examiners and researchers. This research will be used for the verification and evaluation of individuals and institutions, contributing to national security, eventually.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.3
• /
• pp.89-100
• /
• 2023

Recently, on-device artificial intelligence (AI) solutions using mobile devices and embedded edge devices have emerged in various fields, such as computer vision, to address network traffic burdens, low-energy operations, and security problems. Although vision transformer deep learning models have outperformed conventional convolutional neural network (CNN) models in computer vision, they require more computations and parameters than CNN models. Thus, they are not directly applicable to embedded edge devices with limited hardware resources. Many researchers have proposed various model compression methods or lightweight architectures for vision transformers; however, there are only a few studies evaluating the effects of model compression techniques of vision transformers on performance. Regarding this problem, this paper presents a performance evaluation of vision transformers on embedded platforms. We investigated the behaviors of three vision transformers: DeiT, LeViT, and MobileViT. Each model performance was evaluated by accuracy and inference time on edge devices using the ImageNet dataset. We assessed the effects of the quantization method applied to the models on latency enhancement and accuracy degradation by profiling the proportion of response time occupied by major operations. In addition, we evaluated the performance of each model on GPU and EdgeTPU-based edge devices. In our experimental results, LeViT showed the best performance in CPU-based edge devices, and DeiT-small showed the highest performance improvement in GPU-based edge devices. In addition, only MobileViT models showed performance improvement on EdgeTPU. Summarizing the analysis results through profiling, the degree of performance improvement of each vision transformer model was highly dependent on the proportion of parts that could be optimized in the target edge device. In summary, to apply vision transformers to on-device AI solutions, either proper operation composition and optimizations specific to target edge devices must be considered.

• International conference on construction engineering and project management
• /
• 2005.10a
• /
• pp.550-557
• /
• 2005

Because each building is built in different time, there exists different equipment to meet the need for each age. Before the announcement of "Community Management Regulation", the old communities usually suffer the problem of lower requirement and living quality. This may bring some security problem that we should face. In this research, we construct "Building Administration System" to provide users a tool to perform a standard operation procedure in community management. This powerful tool will also help manager to effectively handle important tasks in property administrating by reducing unnecessary documentation. In the current regulation, all community committee members shall be voted each year. This will seriously affect the cumulative of management knowledge and cause a worse efficiency. In this research, we use Object Oriented concept and Visual Modeling techniques to combine with Interbase, ER/Studio, and Delphi to develop this management system for Building Property. Through the help of current computing technology, we can solve the problem that can not be inherited and the storing of the huge amount of data. In this system, we develop the modules such as Basic Data Module, Administrative Expense Calculation, Receipt Print, and Inquiring for Inheritance. In this system, we have integrated all houses, parking lots, and public equipments in it. Manager will only need to handle some basic accounting data; the system will automatically handle the rest. Through the help of this system, the community management staff can be easily accomplished and put more manpower on some needed aspect to improve the living quality.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.115-117
• /
• 2022

Whitebox encryption technique is a method of preventing exposure of encryption keys by mixing encryption key information with a software-based encryption algorithm. Whitebox encryption technique is attracting attention as a technology that replaces conventional hardware-based security encryption techniques by making it difficult to infer confidential data and keys by accessing memory with unauthorized reverse engineering analysis. However, in the encryption and decryption process, a large lookup table is used to hide computational results and encryption keys, resulting in a problem of slow encryption and increased memory size. In particular, it is difficult to apply whitebox cryptography to low-cost, low-power, and light-weight Internet of Things products due to limited memory space and battery capacity. In addition, in a network environment that requires real-time service support, the response delay time increases due to the encryption/decryption speed of the whitebox encryption, resulting in deterioration of communication efficiency. Therefore, in this paper, we analyze whether the AES-based whitebox(WBC-AES) proposed by S.Chow can satisfy the speed and memory requirements based on the experimental results.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.5
• /
• pp.1310-1338
• /
• 2023

As Internet of Things (IoT) applications and devices rapidly grow, cyber-attacks on IoT networks/systems also have an increasing trend, thus increasing the threat to security and privacy. Botnet is one of the threats that dominate the attacks as it can easily compromise devices attached to an IoT networks/systems. The compromised devices will behave like the normal ones, thus it is difficult to recognize them. Several intelligent approaches have been introduced to improve the detection accuracy of this type of cyber-attack, including deep learning and machine learning techniques. Moreover, dimensionality reduction methods are implemented during the preprocessing stage. This research work proposes deep Autoencoder dimensionality reduction method combined with Artificial Neural Network (ANN) classifier as botnet detection system for IoT networks/systems. Experiments were carried out using 3- layer, 4-layer and 5-layer pre-processing data from the MedBIoT dataset. Experimental results show that using a 5-layer Autoencoder has better results, with details of accuracy value of 99.72%, Precision of 99.82%, Sensitivity of 99.82%, Specificity of 99.31%, and F1-score value of 99.82%. On the other hand, the 5-layer Autoencoder model succeeded in reducing the dataset size from 152 MB to 12.6 MB (equivalent to a reduction of 91.2%). Besides that, experiments on the N_BaIoT dataset also have a very high level of accuracy, up to 99.99%.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.169-171
• /
• 2021

Image processing through cameras such as self-driving, CCTV, mobile phone security, and parking facilities is being used to solve many real-life problems. Simple classification is solved through image processing, but it is difficult to find images or in-image features of complexly mixed objects. To solve this feature point, we utilize deep learning techniques in classification, detection, and segmentation of image data so that we can think and judge closely. Of course, the results are better than just image processing, but we confirm that the results judged by the method of image segmentation using deep learning have deviations from the real object. In this paper, we study how to perform accuracy improvement through simple image processing just before outputting the output of deep learning image segmentation to increase the precision of image segmentation.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.246-248
• /
• 2021

Recently data has been transformed into a data economy and society that acts as a catalyst for the development of all industries and the creation of new value, and COVID-19 is accelerating digital transformation. In the upcoming intelligent Internet of Things era, the availability of decentralized systems such as blockchain and mixnet is emerging to solve the security problems of centralized systems that makes it difficult to utilize data safely and efficiently. Blockchain manages data in a transparent and decentralized manner and guarantees the reliability and integrity of the data through agreements between participants, but the transparency of the data threatens the privacy of users. On the other hand, mixed net technology for protecting privacy protects privacy in distributed networks, but due to inefficient power consumption efficiency and processing speed issues, low cost, light weight, low power consumption Internet Hard to use. In this paper, we analyze the limitations of conventional mixed-net technology and propose a mixed-net technology method for low power consumption, high speed, and the Internet of things.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.4
• /
• pp.246-262
• /
• 2023

The purpose of this study is to identify the major peacekeeping activities that the Korean armed forces has performed from the past to the present. To do this, we collected 692 press releases from the National Defense Daily over the past 20 years and performed topic modeling and social network analysis. As a result of topic modeling analysis, 112 major keywords and 8 topics were derived, and as a result of examining the Korean armed forces's peacekeeping activities based on the topics, 6 major activities and 2 related matters were identified. The six major activities were 'Northeast Asian defense cooperation', 'multinational force activities', 'civil operations', 'defense diplomacy', 'ceasefire monitoring group', and 'pro-Korean activities', and 'general troop deployment' related to troop deployment in general. Next, social network analysis was performed to examine the relationship between keywords and major keywords related to topic decision, and the keywords 'overseas', 'dispatch', and 'high level' were derived as key words in the network. This study is meaningful in that it first examined the topic of the Korean armed forces's peacekeeping activities over the past 20 years by applying big data techniques based on the National Defense Daily, an unstructured document. In addition, it is expected that the derived topics can be used as a basis for exploring the direction of development of Korea's peacekeeping activities in the future.