• 전기전자학회논문지
• /
• 제25권4호
• /
• pp.613-618
• /
• 2021

표정 인식은 다양한 분야에서 지속적인 연구의 주제로서 자리 잡아 왔다. 본 논문에서는 얼굴 이미지 랜드마크 간의 거리를 계산하여 추출된 특징을 사용해 각 랜드마크들의 관계를 분석하고 5가지의 표정을 분류한다. 다수의 관측자들에 의해 수행된 라벨링 작업을 기반으로 데이터와 라벨 신뢰도를 높였다. 또한 원본 데이터에서 얼굴을 인식하고 랜드마크 좌표를 추출해 특징으로 사용하였으며 유전 알고리즘을 이용해 상대적으로 분류에 더 도움이 되는 특징을 선택하였다. 본 논문에서 제안한 방법을 이용하여 표정 인식 분류를 수행하였으며 제안된 방법을 이용하였을 때가 CNN을 이용하여 분류를 수행하였을 때 보다 성능이 향상됨을 볼 수 있었다.

• 대한인간공학회지
• /
• 제19권2호
• /
• pp.33-45
• /
• 2000

Present study was performed to compare different types of teleoperation performance measures. A modified Cooper-Harper rating scale and a distance measure were newly introduced and compared to two traditional measures, the error rate and time-to-completion. Participants performed a simulated telerobotic task with varying visual display interfaces. The results of correlation analyses revealed that the modified Cooper-Harper ratings had a close association with the error rate measure. The distance measure also appeared to be a consistent performance measure, which accounted for both the error rate and time-to-completion. A further analysis, however, showed that the effectiveness of each performance measure varied with the level of task difficulty. The results imply that the choice of performance measure should be made based on the task difficulty as well as the particular task being studied. The results revealed here also have implication for performance measures of various display and control systems including aircraft navigation displays and tactical displays.

• 한국자동차공학회논문집
• /
• 제9권5호
• /
• pp.75-81
• /
• 2001

This paper presents the atomization characteristics of single hole injector in the direct injection type diesel engine. The spray characteristics of fuel injector such as the droplet size and velocity were measured by phase Doppler particle analyzer. In this paper, the atomization characteristics of fuel spray are investigated for the experimental analysis of the measuring data by the results of mean diameter and mean velocity of droplet. The effect of fuel injection pressure on the droplet size shows that the higher injection pressure results in the decrease of mean droplet diameter in the fuel spray. The minimum size of fuel spray droplet appears on the location of 40mm axial distance from nozzle exit of diesel injector. Based on the experimental results, the correlation between the droplet diameter and mean velocity of the diesel spray due to the change of axial and radial distance from the nozzle tip were investigated.

• 한국자동차공학회논문집
• /
• 제6권5호
• /
• pp.182-190
• /
• 1998

Behaviour of ultra-high pressure diesel spray in a constant-volume pressure chamber was studied with injection pressure ranging from 20 to 160㎫. Sprays were observed by the right angle scattering method. As a result, the spray tip penetration is first proportional to a time, and after that, it is proportional to 0.52 of the time during at the time of injection pressure and back pressure increase. An empirical correlation was made for the parameters of injection pressure, air-fuel density ratio, spray tip distance, spray angle, jet angle of spray and max. spray width.

• 전기학회논문지
• /
• 제59권1호
• /
• pp.108-112
• /
• 2010

Design of experiment (DOE) method is employed for a systematic and highly efficient optimization of Ga-doped ZnO thin films synthesized by pulsed laser deposition (PLD) process. We sequentially adopted fractional-factorial design (FD) and central composite design (CCD) of the DOE methods. In fractional-FD stage, significant factors to make conductive electrode are found to target-substrate (T-S) distance and oxygen partial pressure. Moreover, correlation among the process factors is elucidated using surface profile modeling. Electrical properties of the GZO films grown on a glass substrate had been optimized to find that the lowest electrical resistivity of about $1.8'10^{-4}Wcm$ which was acquired with the T-S distance and the oxygen pressure of 4 cm and 7 mTorr, respectively. During the DOE-fueled optimization process, the transparency of the GZO films is ensured higher than 85 %.

• Journal of information and communication convergence engineering
• /
• 제15권3호
• /
• pp.137-142
• /
• 2017

A general linearly constrained narrowband adaptive array is examined in the eigenvector space. The optimum weight vector in the eigenvector space is shown to have the same performance as in the standard coordinate system, except that the input signal correlation matrix and look direction steering vector are replaced with the eigenvalue matrix and transformed steering vector. It is observed that the variation in gain factor results in the variation in the distance between the constraint plane and the origin in the translated weight vector space such that the increase in gain factor decreased the distance from the constraint plane to the origin, thus affecting the nulling performance. Simulation results showed that the general linearly constrained adaptive array performed better at an optimal gain factor compared with the conventional linearly constrained adaptive array in a coherent signal environment and the former showed similar performance as the latter in a noncoherent signal environment.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2007년도 춘계학술대회논문집
• /
• pp.1157-1161
• /
• 2007

A construction noise is the main reason for people's petition among the pollution. The purpose of this study is to develop the noise prediction program to see the level of the noise on the construction site more accurately. For this purpose, the database of the power level on the various equipments was made. The noise reduction by distance and the noise reduction by diffraction of barrier were mainly considered and calculated. The simple noise prediction program will provide the information about proper height and length of the potable barrier which satisfies noise criteria of the construction sites from a construction planning stage. To investigate the reliability of this program, the predicted data was compared with the measured data. An average of difference between measured data and predicted data is 1.3 dB(A) and a coefficient of correlation is about 0.95.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제51권4호
• /
• pp.152-159
• /
• 2002

Fitness sharing that shares fitness if calculated distance between individuals is smaller than sharing radius is one of the representative speciation methods and can complement evolutionary algorithm which converges one solution. Recently, there are many researches on designing neural network architecture using evolutionary algorithm but most of them use only the fittest solution in the last generation. In this paper, we elaborate generating diverse neural networks using fitness sharing and combing them to compute outputs then, propose calculating distance between individuals using modified Kullback-Leibler entropy for improvement of fitness sharing performance. In the experiment of Australian credit card assessment, breast cancer, and diabetes in UCI database, proposed method performs better than not only simple average output or Pearson Correlation but also previous published methods.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1993년도 한국자동제어학술회의논문집(국내학술편); Seoul National University, Seoul; 20-22 Oct. 1993
• /
• pp.125-132
• /
• 1993

When a mobile robot moves around autonomously without man-made landmarks, it is essential to recognize the placement of surrounding objects especially for current position estimation, obstacle avoidance, or homing into the work station. In this paper, we propose a novel approach to recognize the floor paln for indoor mobile robot navigation using ultrasonic time-of-flight method. We model the floor plan as a collection of polygonal plane objects and recognize the floor plan by locating edges and vertices of the objects. The direction is estimated by the patterns of transmission beam and reception sensitivity of the ultrasonic transducer, and the distance is estimated by the correlation detection method. We show the validity of the proposed approach through experimental results and discuss the resolution and the accuracy of the estimation of direction and distance.

• Bulletin of the Korean Chemical Society
• /
• 제26권9호
• /
• pp.1421-1426
• /
• 2005

The stationary point structures and relative energies between them as well as binding energies of $(CO)_2$ have been investigated at the CCSD(T) level using the correlation-consistent basis sets aug-cc-pVXZ(X=T,Q,5). It is found that while the equilibrium structure corresponds to the C-bonded T-shaped configuration with intermolecular distance of 4.4 $\AA$, there exists another minimum, slightly higher in energy ($\sim$10 $cm^{-1}$) than the global minimum, corresponding to the O-bonded T-shaped configuration with the intermolecular distance of 3.9 $\AA$. The CCSD(T) basis set limit binding energy of $(CO)_2$ is estimated to be 132 $cm^{-1}$.