• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.2
• /
• pp.256-264
• /
• 2024

In the last 10 years, AI has made rapid progress, and image classification, in particular, are showing excellent performance based on deep learning. Nevertheless, due to the nature of deep learning represented by a black box, it is difficult to actually use it in critical decision-making situations such as national defense, autonomous driving, medical care, and finance due to the lack of explainability of judgement results. In order to overcome these limitations, in this study, a model description algorithm capable of local interpretation was applied to the inception network-derived AI to analyze what grounds they made when classifying national defense data. Specifically, we conduct a comparative analysis of explainability based on confidence values by performing LIME analysis from the Inception v2_resnet model and verify the similarity between human interpretations and LIME explanations. Furthermore, by comparing the LIME explanation results through the Top1 output results for Inception v3, Inception v2_resnet, and Xception models, we confirm the feasibility of comparing the efficiency and availability of deep learning networks using XAI.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.20 no.3
• /
• pp.13-23
• /
• 2024

For the purpose of predicting credit card customer churn accurately through data analysis Detecting and tracking objects in continuous video is essential in self-driving cars, security and surveillance systems, sports analytics, medical image processing, and more. Correlation tracking methods such as Normalized Cross Correlation(NCC) and Sum of Absolute Differences(SAD) are used as an effective way to measure the similarity between two images. NCC, a representative correlation tracking method, has been useful in real-time environments because it is relatively simple to compute and effective. However, correlation tracking methods are sensitive to rotation and size changes of objects, making them difficult to apply to real-time changing videos. To overcome these limitations, this paper proposes an object tracking method using the Histogram of Oriented Gradients(HOG) feature to effectively obtain object data and the Convolution Neural Network(CNN) algorithm. By using the two algorithms, the shape and structure of the object can be effectively represented and learned, resulting in more reliable and accurate object tracking. In this paper, the performance of the proposed method is verified through experiments and its superiority is demonstrated.

• ETRI Journal
• /
• v.38 no.4
• /
• pp.735-745
• /
• 2016

The Paris agreement at the 21st Conference of the Parties (COP21) emphasizes the reduction of greenhouse gas emissions and increase in energy consumption in all areas. Thus, an important aspect is energy saving in buildings where the lighting is a major component of the electrical energy consumption. This paper proposes a building energy management system employing visible light communication (VLC) based on LED lighting. The proposed management system has key characteristics including personalization and localization by utilizing such VLC advantages as secure communication through light and location-information transmission. Considering the efficient implementation of an energy-consumption adjustment using LED luminaires, this paper adopts variable pulse position modulation (VPPM) as a VLC modulation scheme with simple controllability of the dimming level that is capable of providing a full dimming range. This paper analyzes the VPPM performances according to variable dimming for several schemes, and proposes a VPPM demodulation architecture based on dimming-factor acquisition, which can obtain an improved performance compared to a 2PPM-based scheme. In addition, the effect of a dimming-factor acquisition error is analyzed, and a frame format for minimizing this error effect is proposed.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.1063-1066
• /
• 2005

In this paper, we developed the UHF RFID system for EPC Class1 Generation 2 specification. The RFID is a technique of identifying an object using radio frequency transmission. UHF band RFID system communication between Reader and Tag for provide the power to tag when be active when reader’s command finished the transfer. RFID technology can be applied to the supply chain, security, logistics industry and etc. Especially, UHF RFID is worth noticing because of its relatively long identification rage and commercial UHF RFID systems are under development.

• Journal of Convergence Society for SMB
• /
• v.6 no.4
• /
• pp.31-36
• /
• 2016

User authentication is the first step to network security. There are lots of authentication types, and more than one authentication method works together for user's authentication in the network. Except for biometric authentication, most authentication methods can be copied, or someone else can adopt and abuse someone else's credential method. Thus, more than one authentication method must be used for user authentication. However, more credential makes system degrade and inefficient as they log on the system. Therefore, without tradeoff performance with efficiency, this research proposed user's behavior based authentication for secure communication, and it will improve to establish a secure and efficient communication.

• The Journal of the Korea Contents Association
• /
• v.18 no.8
• /
• pp.459-468
• /
• 2018

Cyberattacks on information systems used by applications related to weapon system and organizations associated with national defense put national security at risk. To reduce these threats, continuous efforts such as applying secure coding from the development stage or managing detected vulnerabilities systematically are being made. It also analyzes and detects vulnerabilities by using various analysis tools, eliminates at the development stage, and removes from developed applications. However, vulnerability analysis tools cause problems such as undetected, false positives, and overdetected, making accurate vulnerability detection difficult. In this paper, we propose a new vulnerability detection method to solve these problems, which can assess the risk of certain applications and create and manage secured application with this data.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.6
• /
• pp.2713-2717
• /
• 2011

To transmit data from straggling sensors in water-processing basic industries etc., used Binary-CDMA system has safety voluntarily. But Binary-CDMA is necessity that react very sensitively in environment change as defense about hacking and cracking of various way that change suddenly. Therefore, this paper is that see added cryptographic algorithm for safety and easy update on correlator that a bottle-neck phenomenon is happened in Binary-CDMA to solve problem that is such. Added cryptographic algorithm does to communicate safe information in channel that is not safe as that achieve 1:1 confrontation for sensors by symmetric cryptographic algorithm.

• Journal of Information Technology Services
• /
• v.10 no.2
• /
• pp.223-234
• /
• 2011

Loosely coupled properties of SOA(Service Oriented Architecture) services do not guarantee that service applications always work properly. Service errors may also influence other services of SOA. These characteristics adversely affect software reliability. Therefore, it is a challenge to effectively manage system change and errors for operating services normally. In this study, we propose a SOA based framework using AOP(Aspect Oriented Programming) for reliable service applications. AOP provides a way to manipulate cross-cutting concerns such as logging, security and reliability and these concerns can be added to applications through weaving process. We define a service specification and an aspect specification for this framework. This framework also includes service provider, requester, repository, platform, manager, and aspect weaver to handle changes and exceptions of applications. Independent Exception Handler is stored to exhibited external Aspect Service Repository. When exception happened, Exception Handler is linked dynamically according to aspect rule that is defined in aspect specification and offer function that handle exception alternate suitable service in systematic error situation. By separating cross-cutting concerns independently, we expect that developer can concentrate on core service implementation and reusability, understanding, maintainability increase. Finally, we have implemented a prototype system to demonstrate the feasibility of our framework in case study.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2012.05a
• /
• pp.28-29
• /
• 2012

IT 및 자동차 관련 기술의 융합 기술의 발전에 따라 자동차의 안전 및 운전편의 정보 제공에 대한 관심이 높아지면서 인간의 시각 및 지각의 한계를 보완해 줄 수 있는 보조 도구들에 대한 연구 및 개발이 활발히 이루어지고 있다. 그러나 기존의 컴퓨터 비전 기반 도로 교통 표지판 자동 검출 및 인식 기술들은 센싱 장비들의 가격 또는 조도와 원근감에 따른 교통 표지판의 색상과 모양 왜곡으로 인해 해당 표지판들의 검출을 어렵게 한다. 따라서 본 논문에서는 차량 내 탑재가 가능한 저가의 비전 카메라를 이용하여 교통표지판 칼라 분석 및 원근 보정을 통해 운전자에게 효과적으로 도로표지판 정보를 제공할 수 있는 검출기법을 제안한다. 실험을 통해 도로주행영상 내 도로표지판들을 효과적으로 검출할 수 있음을 확인하였다.

• The KIPS Transactions:PartC
• /
• v.12C no.1 s.97
• /
• pp.29-36
• /
• 2005

A key agreement protocol is the most important part to establish a secure cryptographic system and the effort to standardize the key agreement protocols is in rapid progress. Several efficient and secure key agreement protocols have been proposed so far since Diffie-Hellman proposed a public key agreement system in 1976. But, since Diffie-Hellman based key agreement protocols need a lot of computation to establish the session key, they are not suitable for wireless Internet environment. In this paper, we propose the efficient key agreement protocol using Proxy server. The Proposed Protocol gives the security equivalent to that the Diffie-Hellman based Protocol and the computation work of mobile user can be decreased using proxy server.