• Journal of Korea Water Resources Association
• /
• v.37 no.3
• /
• pp.195-206
• /
• 2004

One of the main factors which reduces the efficiency of a sewage treatment plant is the Inflow/Infiltration(Ⅰ/Ⅰ) in the sewer First we must calculate the quantity of Ⅰ/Ⅰ via the investigation of each sewer to establish the reduction plan of Ⅰ/Ⅰ. However, in Korea, we apply the results of a surveyed sample to the entire study area to establish the reduction plan of Ⅰ/Ⅰ. This methodology just considers the total Ⅰ/Ⅰ for the entire study area but it does not consider the quantity of Ⅰ/Ⅰ for the individual sewer systems. Therefore, we may need the model to consider the Ⅰ/Ⅰ in the individual sewer systems and we develop the model to calculate the Ⅰ/Ⅰ that happen in urban sewer systems. We estimate the Ⅰ/Ⅰ of individual systems by the developed model and the estimated Ⅰ/Ⅰ are utilized as the basic data for the establishment of Ⅰ/Ⅰ reduction plan. The observed Ⅰ/Ⅰ for the entire study area is distributed into the individual sewer systems according to their defect states. Here, the weights of defect elements are calculated using AHP(Analytic Hierarchy Process) and we perform the uncertainty analysis for considering the errors using MCS(Monte Carlo Simulation).

• Journal of KIISE
• /
• v.43 no.9
• /
• pp.1015-1025
• /
• 2016

Currently, software testing is becoming increasingly important in the industrial field and a large body of research supports the improvement of efficient software testing. Model-based testing is generally used to formalize user requirement data for test design. Complex system that includes loop and concurrency has a high probability of path explosion problem. Specially, as threads are added to concurrency, test scenarios have also increased exponentially. However, it is difficult to solve this problem using existing techniques. In this paper, we propose novel path-search technique that focuses on behavioral features of concurrency path in order to avoid path explosion problem. A system that contains concurrent paths is represented by activity diagram in case study section. Efficiency of our study is shown through comparison with several generated test scenarios of other studies. The result indicate that our approach is efficient for finding faults in loop and concurrency with fewer test scenario.

• The KIPS Transactions:PartB
• /
• v.12B no.7 s.103
• /
• pp.811-822
• /
• 2005

Automated text categorization is to classify free text documents into predefined categories automatically and whose main goals is to reduce considerable manual process required to the task. The researches to improving the text categorization performance(efficiency) in recent years, focused on enhancing existing classification models and algorithms itself, but, whose range had been limited by feature based statistical methodology. In this paper, we propose RTPost system of different style from i.ny traditional method, which takes fault tolerant system approach and data mining strategy. The 2 important parts of RTPost system are reinforcement training and post-processing part. First, the main point of training method deals with the problem of defining category to be classified before selecting training sample documents. And post-processing method deals with the problem of assigning category, not performance of classification algorithms. In experiments, we applied our system to documents getting low classification accuracy which were laid on a decision boundary nearby. Through the experiments, we shows that our system has high accuracy and stability in actual conditions. It wholly did not depend on some variables which are important influence to classification power such as number of training documents, selection problem and performance of classification algorithms. In addition, we can expect self learning effect which decrease the training cost and increase the training power with employing active learning advantage.

• 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.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.1-8
• /
• 2023

If there is a defect in the wheel bearing, which is a major part of the car, it can cause problems such as traffic accidents. In order to solve this problem, big data is collected and monitoring is conducted to provide early information on the presence or absence of wheel bearing failure and type of failure through predictive diagnosis and management technology. System development is needed. In this paper, to implement such an intelligent wheel hub bearing maintenance system, we develop an embedded system equipped with sensors for monitoring reliability and soundness and algorithms for predictive diagnosis. The algorithm used acquires vibration signals from acceleration sensors installed in wheel bearings and can predict and diagnose failures through big data technology through signal processing techniques, fault frequency analysis, and health characteristic parameter definition. The implemented algorithm applies a stable signal extraction algorithm that can minimize vibration frequency components and maximize vibration components occurring in wheel bearings. In noise removal using a filter, an artificial intelligence-based soundness extraction algorithm is applied, and FFT is applied. The fault frequency was analyzed and the fault was diagnosed by extracting fault characteristic factors. The performance target of this system was over 12,800 ODR, and the target was met through test results.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.2
• /
• pp.7-13
• /
• 2019

This study aims to develop a FE Model to simulate dissimilar friction stir welding and to address its potential for fundamental analysis and practical applications. The FE model is based on Coupled Eulerian-Lagrangian approach. Multiphysics systems are calculated using explicit time integration algorithm, and heat generations by friction and inelastic heat conversion as well as heat transfer through the bottom surface are included. Using the developed model, friction stir welding between an Al6061T6 plate and an AZ61 plate were simulated. Three simulations are carried out varying the welding parameters. The model is capable of predicting the temperature and plastic strain fields and the distribution of void. The simulation results showed that temperature was generally greater in Mg plates and that, as a rotation speed increase, not the maximum temperature of Mg plate increased, but did the temperature of Al plate. In addition, the model could predict flash defects, however, the prediction of void near the welding tool was not satisfactory. Since the model includes the complex physics closely occurring during FSW, the model possibly analyze a lot of phenomena hard to discovered by experiments. However, practical applications may be limited due to huge simulation time.

• Journal of Korea Game Society
• /
• v.2 no.1
• /
• pp.55-61
• /
• 2002

유 무선환경에서 침입 패턴이 다양화되고, 모바일의 편리성이 강조되면서 네트워크 대역폭이 다양한 전송 기반을 요구하고 있다. 그리고 무선기반의 자료가 급증하고 있어, 무선환경에서의 침입탐지시스템 성능에 문제가 될 수 있다. 그러므로 게이트웨이를 근간으로 한 무선전송 기반을 보호하고, 컴퓨터 운영체제 상에 내재된 보안상의 결함을 보호하기 위하여 기존의 운영체제 내에 보안 기능을 추가한 운영체제이며, 커널의 핵심 부분을 인지하여 무선기반의 시스템 사용자에 대한 식별 및 인증, 강제적 접근 통제, 임의적 접근 통제, 해킹 대응 등의 보안 기능 요소들을 갖추게 하여 보안성에 강한 시스템 유지를 요구한다. 그러므로 감시대상의 정보를 미리 알고, WAP환경하에서 감시대상에 유효한 침입패턴만을 검사하도록 침입패턴 데이터베이스를 분리하는 모델을 제시하여, 이러한 문제점에 대한 해결책을 제시하고자 하였다. 따라서 기존 침입탐지시스템의 패턴 데이터베이스를 분석하였고, 이를 적절히 분리하여 이를 다시 운영체제에 반영하는 기법이다. 그리고 이를 제시한 모델을 검증하고자 실제 구현과 실험을 통해 이를 검증하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06b
• /
• pp.181-184
• /
• 2011

소프트웨어와 인터넷 연결이 일반화되고 소프트웨어 규모가 복잡해짐에 따라, 소프트웨어 보안 취약점 발생 수 및 관련 보안 사고가 나날이 증가하고 있다. 소프트웨어 보안 사고를 예방하기 위한 하나의 방법은 소프트웨어 개발 단계에서 취약점을 발견하여 제거하는 것이다. 이에 본 논문에서는 취약점 발견에 사용되는 대표적 테스팅 기법인 퍼징에 대해 연구하였다. 먼저, 웹 애플리케이션 서버와 관련된 기존의 공개된 취약점 정보를 분석하여 퍼징에 필요한 오용 케이스(misuse case) 생성 방법을 보인다. 생성된 오용 케이스는 URL과 HTTP 요청 메시지의 각 필드에 대한 테스팅 정보를 포함하고 있으며, 이 오용 케이스를 웹 애플리케이션 서버에 퍼징하여 실제 보안 관련 결함이 나타남을 확인하였다.

• Proceedings of the KIEE Conference
• /
• 2009.07a
• /
• pp.304_306
• /
• 2009

본 논문은 IEEE std 400에서 규정하고 있는 케이블 시험방법 중 Type 1, 파괴시험법(DC, 상용주파 내전압, 그리고 VLF내전압 시험)은 절연물 손상을 발생시키므로 예방진단에 사용될 수 없고 그렇지 않은 Type 2. 비파괴시험법에 대해 주로 소개하였다. 이와 추가하여 한전에서 사용 중인 IRC(Isothermal Relaxation Current) 측정법에 대해 간략하게 소개하고 더불어 IEEE Std 400에서 제시하고 있는 $Tan{\delta}$측정법의 문제점 및 개정 방향을 소개하고, 마지막으로 IEEE Std 400.3의 PD신호의 분석을 통해 결함위치와 열화정도를 평가 진단하는 기법에 대해 서술하고저 한다.

• Proceedings of the KIEE Conference
• /
• 2015.07a
• /
• pp.1569-1570
• /
• 2015

몰드변압기는 유입변압기와 달리 구조적으로 복잡하고 밀폐된 구조로 되어 있어서 사용기간 동안 고신뢰성을 확보하기 위해서 예방진단기술이 필요하다. 그러나 공장이나 빌딩 현장에서 몰드변압기의 열화상태 관리하는 방법은 온도관리, 소음진동관리 등의 수준으로 활선상태에서 사고를 예측하기에는 많은 한계가 있다. 이러한 문제점을 해결하고자 본 논문에서는 몰드변압기의 부분방전 측정을 중심으로 활선상태에서 열화 진단기술이 중요하다. 특히, 몰드변압기의 절연열화 진단을 위해서 상호보완적인 측정방법이 필요하고, 몰드변압기의 절연상태의 유무를 판정할 수 있는 분석방법을 개발하고자 하였다.