• 터널과지하공간
• /
• 제30권6호
• /
• pp.540-550
• /
• 2020

최근 AI 기술의 발전과 정립으로 자동화 분야에서 머신러닝 기법의 활용이 활발하게 이루어지고 있다. 머신러닝 기법의 활용에 있어 중요한 점은 데이터 특성에 따라 적합한 알고리즘이 존재한다는 점이며, 머신러닝 기법 적용을 위한 데이터세트의 분석이 필요하다. 본 연구에서는 다양한 머신러닝 기법을 기반으로 하천 하부의 토사지반을 통과하는 토압식 쉴드TBM 터널 구간의 지반정보와 굴진정보를 사용하여 토압식 쉴드TBM의 굴진율을 예측하였다. 선형회귀모델에서 모델의 통계적인 유의성과 다중공선성에서는 문제가 없었으나 결정계수가 0.76으로 나타났고 앙상블 모델과 서포트 벡터 머신에서는 0.88이상의 예측성능을 보여, 분석한 데이터세트에서 토압식 쉴드TBM 굴진성능예측에 적합한 모델은 서포트 벡터 머신임을 알 수 있었다. 현재 도출된 결과로 볼 때, 토압식 쉴드TBM의 기계데이터와 지반정보가 포함된 데이터를 활용한 굴진성능 예측 모델의 적합성은 높다고 판단된다. 추가적으로 지반조건의 다양성과 데이터양을 늘리는 연구가 필요한 것으로 판단된다.

• 예술인문사회 융합 멀티미디어 논문지
• /
• 제6권3호
• /
• pp.291-300
• /
• 2016

스마트 디바이스와 사물 인터넷의 등장은 온라인과 오프라인의 경계를 허무는 O2O 서비스의 등장으로 이어졌다. 이는 오프라인 시장에 온라인 서비스의 강점이 덧붙여지면서 오프라인 공간이 디지털화가 됨을 의미하며, 오프라인 산업의 판도를 바꾸고 있다. 이러한 오프라인 시장의 변화 양상과는 다르게 전시 산업은 오프라인 산업에서 꾸준한 성장세를 보이고 있으나, 전시 산업 또한 O2O 서비스와의 접목으로 새로운 부가가치를 창출이 가능한 것으로 보았다. 본 논문은 코엑스에서 열린 '2015 서울 디자인 페스티벌'에서 20명을 대상으로 설문을 진행하였다. 설문은 공간 구조에 대한 분석 용도 및 기계학습을 위한 데이터 세트를 생성하는데 사용되었다. 본 논문은 기존의 공간 구조에 대한 분석연구가 가진 문제점을 파악하여 공간 구조에 대한 새로운 분석 방법을 제안하였다. 또한 생성된 데이터 세트를 기반으로 기계학습을 진행하여 전시 공간 내 O2O 서비스 배치를 위한 평가 모델을 제안한다.

• 한국기계가공학회지
• /
• 제10권5호
• /
• pp.1-6
• /
• 2011

Machine tool errors have to be characterized and predicted to improve machine tool accuracy. Therefore, it is very important to assess errors in machine tools. Volumetric error analysis has been developed by many researchers. This paper presents a useful technique for analyzing the volumetric errors in machine tools using the ball bar. The volumetric error model is proposed in specific vertical machining center and the program is developed for generating NC code, acquiring the ball bar data, and analyzing the volumetric errors. The developed system assesses the volumetric errors such as positional, straightness, squareness, and back lash. Also this system analyzes the dynamic performance such as servo gain mismatch. The radial data acquired by ball bar on 3D space is used for analyzing these errors. It is convenient to test the volumetric errors on 3D space because all errors are calculated at once. The developed system has been tested using an actual vertical machining center.

• 천문학회보
• /
• 제34권1호
• /
• pp.82.1-82.1
• /
• 2009

• 한국실내디자인학회논문집
• /
• 제16권5호
• /
• pp.81-88
• /
• 2007

Energy consumption has been increased world widely, and the energy retain is one of the most important economic alternatives. These tendencies expand the nuclear power plants not only quantitatively but also qualitatively. Despite of the increasing construction of nuclear power plants and related facilities, every system in main control room(MCR) has been designed and administered solely based on the safety-first principles because of the specificity of nuclear industry. However, recent main control rooms started with the concept that the operators' performance could be optimized though the organic interrelation between human, machine, and environments. Now, it has been recognised in the scope of Ergonomics and Space Design which acknowledge our living spaces as Man-Environment Interface and this change connotes the MCR spaces should be special spaces rather than ordinary spaces. This research investigated domestic and foreign nuclear power plants' MCRs to suggest basic alternatives which can be applied to future MCR. With the review of characteristics of MCR, an integration of interior design, lighting and Ergonomics was explored and classified as types. Futhermore, the classification of environmental characteristics within the relationships between human, machine, and environments was developed through the case analysis of nuclear power plants. The results of this study will provide a basis of space design for system environments that the high level of safety and function are extremely important.

• 천문학회보
• /
• 제44권2호
• /
• pp.74.2-74.2
• /
• 2019

We present a possible bias in the estimation of velocity dispersions for galaxy groups due to the contribution of subgroups which are infalling into the groups. We execute a systematic search for flux-limited galaxy groups and subgroups based on the spectroscopic galaxies with r < 17.77 mag of SDSS data release 12, by using DBSCAN (Density-Based Spatial Clustering of Application with Noise) and Hierarchical Clustering Method which are well known unsupervised machine learning algorithm. A total of 2042 groups with at least 10 members are found and ~20% of groups have subgroups. We found that the estimation of velocity dispersions of groups using total galaxies including those in subgroups are underestimated by ~10% compared to the case of using only galaxies in main groups. This result suggests that the subgroups should be properly considered for mass measurement of galaxy groups based on the velocity dispersion.

• ETRI Journal
• /
• 제40권4호
• /
• pp.499-510
• /
• 2018

A vector space based augmented structural kinematic (VSASK) feature descriptor is proposed for human activity recognition. An action descriptor is built by integrating the structural and kinematic properties of the actor using vector space based augmented matrix representation. Using the local or global information separately may not provide sufficient action characteristics. The proposed action descriptor combines both the local (pose) and global (position and velocity) features using augmented matrix schema and thereby increases the robustness of the descriptor. A multiclass support vector machine (SVM) is used to learn each action descriptor for the corresponding activity classification and understanding. The performance of the proposed descriptor is experimentally analyzed using the Weizmann and KTH datasets. The average recognition rate for the Weizmann and KTH datasets is 100% and 99.89%, respectively. The computational time for the proposed descriptor learning is 0.003 seconds, which is an improvement of approximately 1.4% over the existing methods.

• 센서학회지
• /
• 제21권1호
• /
• pp.28-33
• /
• 2012

The visual sensing of human hands plays an important part in many man-machine interaction/interface systems. Most existing visionbased hand detection techniques depend on the color cues of human skin. The RGB color image from a vision sensor is often transformed to another color space as a preprocessing of hand detection because the color space transformation is assumed to increase the detection accuracy. However, the actual effect of color space transformation has not been well investigated in literature. This paper discusses a comparative evaluation of the pixel classification performance of hand skin detection in four widely used color spaces; RGB, YIQ, HSV, and normalized rgb. The experimental results indicate that using the normalized red-green color values is the most reliable under different backgrounds, lighting conditions, individuals, and hand postures. The nonlinear classification of pixel colors by the use of a multilayer neural network is also proposed to improve the detection accuracy.

• ETRI Journal
• /
• 제10권3호
• /
• pp.140-156
• /
• 1988

This paper presents methodological and theoretical principles for constructing a machine thanslation system between Korean and Japanese. We focus our discussion on the real time computing problem of the machine translation system. This problem is characterized in the time and space complexity during the machine translation. The NARA system has the real time computing algorithm which is based on a mathematical model integrating the linguistic competence and the linguistic performance of both languages, with consequence that the system NARA has also the functional characteristic : the two-way translation mechanism.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1987년도 한국자동제어학술회의논문집; 한국과학기술대학, 충남; 16-17 Oct. 1987
• /
• pp.394-397
• /
• 1987

This paper presents an analysis of the man-machine control system. A man-machine system depends on the performance of a human operator for proper operation. The analysis method is based upon the assumption that human operator will act in a near optimal controller. Optimal control theory and its associated state space representation is used as the basis for the analytic procedure. The computer simulation for a given plant shows that plant parameters have limited range by the human operator.