• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2009년도 추계학술대회 논문집
• /
• pp.275-276
• /
• 2009

• 제어로봇시스템학회논문지
• /
• 제18권1호
• /
• pp.54-61
• /
• 2012

In this paper, the pose estimation method for the satellite GTB (Ground Test Bed) using vision/MEMS IMU (Inertial Measurement Unit) integrated system is presented. The GTB for verifying a satellite system on the ground is similar to the mobile robot having thrusters and a reaction wheel as actuators and floating on the floor by compressed air. The EKF (Extended Kalman Filter) is also used for fusion of MEMS IMU and vision system that consists of a single camera and infrared LEDs that is ceiling landmarks. The fusion filter generally utilizes the position of feature points from the image as measurement. However, this method can cause position error due to the bias of MEMS IMU when the camera image is not obtained if the bias is not properly estimated through the filter. Therefore, it is proposed that the fusion method which uses the position of feature points and the velocity of the camera determined from optical flow of feature points. It is verified by experiments that the performance of the proposed method is robust to the bias of IMU compared to the method that uses only the position of feature points.

• 한국컴퓨터정보학회논문지
• /
• 제28권9호
• /
• pp.17-25
• /
• 2023

본 논문에서는 매개변수가 더 적고, 빠르게 추정 가능한 MobileViT 기반 모델을 통해 사람 자세 추정 과업을 수행할 수 있는 모델을 제안한다. 기반 모델은 합성곱 신경망의 특징과 Vision Transformer의 특징이 결합한 구조를 통해 경량화된 성능을 입증한다. 본 연구에서 주요 매커니즘이 되는 Transformer는 그 기반의 모델들이 컴퓨터 비전 분야에서도 합성곱 신경망 기반의 모델들 대비 더 나은 성능을 보이며, 영향력이 커지게 되었다. 이는 사람 자세 추정 과업에서도 동일한 상황이며, Vision Transformer기반의 ViTPose가 COCO, OCHuman, MPII 등 사람 자세 추정 벤치마크에서 모두 최고 성능을 지키고 있는 것이 그 적절한 예시이다. 하지만 Vision Transformer는 매개변수의 수가 많고 상대적으로 많은 연산량을 요구하는 무거운 모델 구조를 가지고 있기 때문에, 학습에 있어 사용자에게 많은 비용을 야기시킨다. 이에 기반 모델은 Vision Transformer가 많은 계산량을 요구하는 부족한 Inductive Bias 계산 문제를 합성곱 신경망 구조를 통한 Local Representation으로 극복하였다. 최종적으로, 제안 모델은 MS COCO 사람 자세 추정 벤치마크에서 제공하는 Validation Set으로 ViTPose 대비 각각 5분의 1과 9분의 1만큼의 3.28GFLOPs, 972만 매개변수를 나타내었고, 69.4 Mean Average Precision을 달성하여 상대적으로 우수한 성능을 보였다.

• 한국조사연구학회지:조사연구
• /
• 제1권1호
• /
• pp.73-108
• /
• 2000

사이버공간이 독특한 사회적 공간으로 자리잡고 이에 대한 경험적 자료의 필요성이 중대됨에 따라 컴퓨터 통신망을 이용한 사회조사가 늘어나고 있다. 본 연구는 사이버공간이 보여주는 기술적 기능성을 방법론적으로 검토해 봄으로써 온라인 사회조사의 발전가능성을 탐색하고 있다. 온라인 사회조사는 표집틀, 응답자 접촉방식, 질문지 형태 등에 따라 회원 조사, 방문자조사, 전자우편조사, 전자설문조사로 구분될 수 있으며 기존의 조사방법에 비하여 조사비용의 저렴하고 조사의 실행이 용이하다는 특징을 가지고 있다. 그러나 체계적 오차와 관련하여 온라인 사회조사는 표본설계(모집단의 규정, 표집틀 오차, 추출오차), 측정(측정도구의 구성, 시스템의 안정성과 충실성, 비 응답 및 응답오차) 조사윤리의 측면에서 많은 과제를 안고 있다. 이러한 방법론적인 쟁점에 대한 충분한 고려가 이루어질 때 온라인 사회조사는 본격적인 조사연구의 한 방법으로 자리잡을 수 있을 것이다.

• 한국초전도학회:학술대회논문집
• /
• 한국초전도학회 2000년도 High Temperature Superconductivity Vol.X
• /
• pp.85-85
• /
• 2000

The normal state of high-Tc superconducting materials has been believed to contain important clues to finding the correct mechanism of the high-Tc superconductivity. One example is the existence of pseudogap in the normal state even above Tc, as observed in various measurements such as photoemission spectroscopy and tunneling conductance. In this pseudogap regime the existence of preformed pairs only with local phase coherence has been debated. Recently Choi, Bang, and Campbell[1] have proposed the occurrence of the zero-bias conductance enhancement due to Andreev quasiparticle reflection from the preformed pairs even with the local phase coherence. In this study we examine the zero-bias enhancement of the differential conductance near or slightly above Tc, using c-axis tunneling in mesa structure of Bi2Sr20a0u208+d single crystals. In slightly overdoped samples zero-bias conductance enhancement (ZBCE) has been observed over a range of 2 K above Tc. In contrast, in underdoped samples with Tc${\sim}$72K the ZBCE appears over a range of 5-6 K above Tc, a much wider temperature range than in overdoped samples. This result may pose as positive signs of the existence of prefurmed pairs in the normal state of high- Tc superconducting materials.

• 제어로봇시스템학회논문지
• /
• 제11권12호
• /
• pp.1045-1050
• /
• 2005

This paper describes a design experience of a low-cost 6 DOF spatial tracker system where relative low accuracy and relatively long ranges, wireless communication will be achieved by means of low cost accelerometers and gyros with contemporary microprocessor. However, there are two key problems; one is the bias drift problem and the other is that single or double integration of acceleration signal suffers not only from noise but also from nonlinear effects caused by gravity. To be specific, beginning and stopping of hand motions needs to be accurately detected to initiate and terminate integration process to get position and pose of the hand from accelerometer and gyro signals, since errors due to noise and/or hand-shaking motions accumulated by integration processes. Several experimental results are shown to validate our proposed algorithms.

• 한국컴퓨터정보학회논문지
• /
• 제27권4호
• /
• pp.9-17
• /
• 2022

최첨단 AI 시스템은 방대한 데이터 수집에서 알고리즘 편향에 이르기까지 많은 윤리적 문제를 드러내고 있다. 이에 본 논문에서는 연합학습과 블록체인을 결합하여, 더 윤리적인 AI 아키텍처를 제안하였다. AI의 윤리성에 관한 중요한 문제들을 논의하고, 문헌조사를 통하여 윤리적 AI 시스템에 대한 요구사항을 연구하고 도출한다. 제안한 아키텍처의 요구사항 만족을 분석하였다. 제안한 AI 구조를 디자인에 채택함으로써 AI 서비스를 보다 윤리적으로 수행할 수 있다.

• 한국멀티미디어학회논문지
• /
• 제10권12호
• /
• pp.1566-1576
• /
• 2007

Camera pose information from 2D face image is very important for making virtual 3D face model synchronize with the real face. It is also very important for any other uses such as: human computer interface, 3D object estimation, automatic camera control etc. In this paper, we have presented a camera position determination algorithm from a single 2D face image using the relationship between mouth position information and face region boundary information. Our algorithm first corrects the color bias by a lighting compensation algorithm, then we nonlinearly transformed the image into $YC_bC_r$ color space and use the visible chrominance feature of face in this color space to detect human face region. And then for face candidate, use the nearly reversed relationship information between $C_b\;and\;C_r$ cluster of face feature to detect mouth position. And then we use the geometrical relationship between mouth position information and face region boundary information to determine rotation angles in both x-axis and y-axis of camera position and use the relationship between face region size information and Camera-Face distance information to determine the camera-face distance. Experimental results demonstrate the validity of our algorithm and the correct determination rate is accredited for applying it into practice.

• Asian Pacific Journal of Cancer Prevention
• /
• 제13권6호
• /
• pp.2687-2693
• /
• 2012

Objective: Passive smoking has been considered as a risk factor of many cancers. To examine whether it might also pose a risk for cervical cancer, we performed a meta-analysis based on published case-control studies. Methods: We searched the PubMed database and references of included studies up to February 10th, 2012 for relevant studies. After two authors independently assessed the methodological quality and extracted data, a meta-analysis was conducted using CMA v2 software. Publication bias was evaluated by funnel plot, using Egger's and Begg's tests. Results: Finally 11 eligible studies yielded, involving 3,230 cases and 2,982 controls. The results showed that women who never smoke but exposed to smoking experience a 73% increase in risk of cervical cancer compared with non-exposed women (OR = 1.73, 95% CI = 1.35 - 2.21, p<0.001). Subgroup and sensitivity analyses indicated this result to be robust. Moderate publication bias was detected by visualing funnel plot, Egger's and Begg's tests. Conclusion: Based on currently available evidence, the findings of this meta-analysis suggests that passive smoking significantly and independently increases the risk of cervical cancer.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.63-75
• /
• 2022

The raw data collected by structural health monitoring (SHM) systems may suffer multiple patterns of anomalies, which pose a significant barrier for an automatic and accurate structural condition assessment. Therefore, the detection and classification of these anomalies is an essential pre-processing step for SHM systems. However, the heterogeneous data patterns, scarce anomalous samples and severe class imbalance make data anomaly detection difficult. In this regard, this study proposes a convolutional neural network-based data anomaly detection method. The time and frequency domains data are transferred as images and used as the input of the neural network for training. ResNet18 is adopted as the feature extractor to avoid training with massive labelled data. In addition, the focal loss function is adopted to soften the class imbalance-induced classification bias. The effectiveness of the proposed method is validated using acceleration data collected in a long-span cable-stayed bridge. The proposed approach detects and classifies data anomalies with high accuracy.