• 한국지능시스템학회논문지
• /
• 제10권3호
• /
• pp.194-202
• /
• 2000

본 논문에서는 여러 분야에서 널리 응용되고 있는 적응 뉴로-퍼지 시스템(ANFIS)에서의 효과적인 퍼지 규칙 생성 방법을 제안한다. 기존의 입력공간 그리드 분할을 이용한 ANFIS의 규칙 생성에 있어서는 얻어진 규칙의 수가 지수적으로 증가하는 단점이 있다. 이에, 본 연구에서는 조건부적인 FCM을 이용하여 입.출력 데이터이 특성을 잘 반영할 수 있는 클러스터를 구하고, 퍼지 균등화 방법을 적용하여 출력변수의 소속함수를 자동 생성하도록 하엿다. 이렇게 함으로서 적은 규칙 수를 갖으며서도 효율적인 퍼지 규칙을 얻을 수 있도록 하였다. 이들 방법의 유용함을 보이고자 트럭 후진제어와 Box-Jenkins의 가스로 데이터의 모델리에 적용하여 제안된 방법이 이전의 연구보다 좋은 결과를 보임을 알 수 있다.

• 설비공학논문집
• /
• 제3권3호
• /
• pp.176-185
• /
• 1991

Pressure drop and flow characteristics through a filter medium have been investigated numerically. A basic model similar to the filter employed in a hard disk drive was established so that the inflow velocity was 0.1 m/s and the box size was $40mm{\times}50mm{\times}30mm$. The filter medium specifications were 0.38mm of thickness, $1{\mu}m$ of fiber diameter, 0.05 of packing density. And the filter medium was pleated by 10 within the filter box. Twenty-one sets of calculation were performed with different inlet velocities, pleated numbers, and packing densities from the basic model. As the result, it was found that the velocity after filter medium had maximum value at the rear of the upstream pleated line, but had minimum value at the rear of the downstream pleated line. This made the velocity distribution have sinusoidal form immediately after the filter medium. As the inlet velocity increased, the pressure drop increased linearly. But as the packing density increased the pressure drop increased quadratically.

• Korean Chemical Engineering Research
• /
• 제44권2호
• /
• pp.227-233
• /
• 2006

오염화석탄산(pentachlorophenol : PCP)으로 방부 처리된 탄약 목상자를 분해한 목재시료로부터 메탄올, 에탄올, 아세토니트릴을 추출용매로 사용하여 PCP를 추출하였다. 실험변수로는 용매종류, 건조목재 시료당 용매의 사용비율, 시료의 형태 및 크기, 추출온도 및 초음파 효과를 선정하였다. 목재의 PCP 농도는 평균 720 ppm 이었으며 추출효과는 메탄올이 가장 우수하였다. 농도가 가장 큰 시료(초기농도 1297 ppm)를 메탄올로 상온에서 추출한 결과 2시간 이내에 99％까지 제거되었다. 건조시료당 메탄올의 최소 사용비율(v/w)은 10이었으며 이 실험에서 시료의 형상(chip 및 톱밥)이나 추출온도 및 초음파 사용은 PCP 추출에 큰 영향을 미치지 않았다.

• 융합정보논문지
• /
• 제7권6호
• /
• pp.229-235
• /
• 2017

최근 물체를 인식하기 위해 많은 데이터를 기반으로 학습하여 인식하는 연구가 활성화 되고 있다. 본 논문에서는 도로주행 영상에서 장애물이라고 생각되는 객체를 추출하여 자동차, 사람, 오토바이로 구분하여 인식하는 시스템을 제안한다. 이동한 방향과 크기를 고려한 상태에서 광류 추정 알고리즘을 이용하여 객체를 추출하였으며, 추출한 객체를 CNN(Convolutional Neural Network) 인식 모델 중 하나인 AlexNet을 이용하여 인식하였다. 실험을 위해 도로 위의 다양한 영상을 블랙박스로 수집하여 실험하였고, 실험 결과 객체 추출 정확도는 92%, 객체 인식 정확도는 96%의 결과를 보였다.

• 한국지진공학회:학술대회논문집
• /
• 한국지진공학회 2003년도 춘계 학술발표회논문집
• /
• pp.329-336
• /
• 2003

The box system that is composed only of reinforced concrete walls and slabs are adopted on many high-rise apartment buildings recently constructed in Korea. And the framed structure with shear wall core that can effectively resist horizontal forces is frequently adopted for the structural system for high-rise building structures. In these structures, a shear wall may have one or more openings for functional reasons. It is necessary to use subdivided finite elements for accurate analysis of the shear wall with openings. But it would take significant amount of computational time and memory if the entire building structure is subdivided into a finer mesh. An efficient analysis method that can be used regardless of the number, size and location of openings is proposed in this study. The analysis method uses super element, substructure, matrix condensation technique and fictitious beam technique. Three-dimensional analyses of the box system and the framed structure with shear wall core having various types of openings were peformed to verify the efficiency of the proposed method. It was confirmed that the proposed method have outstanding accuracy with drastically reduced time and computer memory from the analyses of example structures.

• 방송공학회논문지
• /
• 제23권6호
• /
• pp.760-767
• /
• 2018

첨단 운전자 지원 시스템(ADAS)은 차량 기술 분야에서 활발한 연구가 이루어지고 있는 기술이다. ADAS 기술은 직접적으로 차량을 제어하는 기술과 간접적으로 운전자에게 편의를 제공하는 기술로 나뉜다. 본 논문에서는 야간 도로 영상을 보정하여 운전자에게 시각적 편의를 제공하는 시스템을 제안한다. 제안하는 시스템은 전방 블랙박스 카메라로부터 촬영된 도로 영상을 입력받는다. 입력된 영상은 가로 축을 따라 세 부분으로 분할된 뒤 일괄적으로 이미지 변환 모듈을 통해 각각 낮 영상으로 변환된다. 변환된 영상은 다시 결합된 뒤 운전자에게 제공되어 시각적 편의를 제공한다. 본 논문의 실험 결과를 통해 제안한 시스템이 기존의 밝기 변환 알고리즘과 비교하여 우수한 성능을 보임을 입증한다.

• 한국안전학회지
• /
• 제33권6호
• /
• pp.50-57
• /
• 2018

The purpose of this study is to evaluate the practical application of the self consolidating concrete for the steel concrete pannel (SCP) in module LNG storage tank proposed in the previous research. We evaluated the physical properties and filling performance of developed concrete for the SCP module. First, a slump flow test was conducted to evaluate the performance of the proposed guidelines for the filling test. As a result, all of the concrete used showed satisfactory performance. Based on the results of the previous study, it was found that the reliability of the required time measured by the $T_{500}$ test and the rheometer results measured before and after pumping was 0.94 which means the separation and blocking should not occur. The L-box test and the U-box test were conducted before and after pumping. All of the guidelines suggested showed satisfactory performance. SCP module for LNG storage tanks was fabricated on actual size scale to evaluate the practical application at the final site. As a result, it was confirmed that satisfactory filling performance was obtained in all the specimens.

• 대한안전경영과학회지
• /
• 제23권4호
• /
• pp.49-53
• /
• 2021

The objective of this study was to understand which type of fire hose should be placed in indoor fireplug box upon analyzing the preparation time between rack-type fire hose and reel-type one. With respect to the type of hose, rack-type stacking method was used and hose preparation time was measured with 5 times of repeat test, separating men and women. Study results reveal that preparation time of reel-type fire hose took longer than that of rack-type one in both men and women. For both rack-type hose and reel-type hose, preparation time by two persons took shorter than that by one man. Also, preparation time by three persons took shorted than that by two women. Preparation time for both rack-type hose and reel-type one by men took shorter than that by women. In summary, it was confirmed that rack-type hose could be prepared within shorter time than reel-type one. Since the size of drum set in the reel-type fire hose is relatively small, it had some difficulty in preparation of fire hose timely.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권7호
• /
• pp.2328-2344
• /
• 2022

2D human pose estimation still faces difficulty in low-resolution images. Most existing top-down approaches scale up the target human bonding box images to the large size and insert the scaled image into the network. Due to up-sampling, artifacts occur in the low-resolution target images, and the degraded images adversely affect the accurate estimation of the joint positions. To address this issue, we propose a multi-resolution input feature fusion network for human pose estimation. Specifically, the bounding box image of the target human is rescaled to multiple input images of various sizes, and the features extracted from the multiple images are fused in the network. Moreover, we introduce a guiding channel which induces the multi-resolution input features to alternatively affect the network according to the resolution of the target image. We conduct experiments on MS COCO dataset which is a representative dataset for 2D human pose estimation, where our method achieves superior performance compared to the strong baseline HRNet and the previous state-of-the-art methods.

• 한국인공지능학회지
• /
• 제11권1호
• /
• pp.9-15
• /
• 2023

As mobile devices such as smartphones, tablets, and kiosks become increasingly prevalent, there is growing interest in developing alternative input systems in addition to traditional tools such as keyboards and mouses. Many people use their own bodies as a pointer to enter simple information on a mobile device. However, methods using the body have limitations due to psychological factors that make the contact method unstable, especially during a pandemic, and the risk of shoulder surfing attacks. To overcome these limitations, we propose a simple information input system that utilizes gaze-tracking technology to input passwords and control web surfing using only non-contact gaze. Our proposed system is designed to recognize information input when the user stares at a specific location on the screen in real-time, using intelligent gaze-tracking technology. We present an analysis of the relationship between the gaze input box, gaze time, and average input time, and report experimental results on the effects of varying the size of the gaze input box and gaze time required to achieve 100% accuracy in inputting information. Through this paper, we demonstrate the effectiveness of our system in mitigating the challenges of contact-based input methods, and providing a non-contact alternative that is both secure and convenient.