• Korean Journal of Cognitive Science
• /
• v.16 no.4
• /
• pp.323-331
• /
• 2005

This paper proposes an improved system for recognizing facial expressions in various internal states that is illumination-invariant and without detectable rue such as a neutral expression. As a preprocessing to extract the facial expression information, a whitening step was applied. The whitening step indicates that the mean of the images is set to zero and the variances are equalized as unit variances, which reduces murk of the variability due to lightening. After the whitening step, we used the facial expression information based on principal component analysis(PCA) representation excluded the first 1 principle component. Therefore, it is possible to extract the features in the lariat expression images without detectable cue of neutral expression from the experimental results, we ran also implement the various and natural facial expression recognition because we perform the facial expression recognition based on dimension model of internal states on the images selected randomly in the various facial expression images corresponding to 83 internal emotional states.

• Journal of Korean Society for Atmospheric Environment
• /
• v.20 no.5
• /
• pp.583-591
• /
• 2004

In this study, methodologies for the rational organization of air pollution monitoring network were examined by understanding the characteristics of temporal and spatial distribution of secondary air pollution, whose significance would increase hereafter. The data on $O_3$ and $NO_2$ concentrations during high ozone period in 1998~1999 recorded at the nine air pollution monitoring station in Busan were analysed using principal component analysis (PCA) and cumulative semivariogram. It was found that the ozone concentration was deeply associated with the daily emission characteristics or the $O_3$ precusors, and nitrogen dioxide concentration largely depends on the emission strength of regional sources. According to the spatial distribution analysis of ozone and nitrogen dioxide in Busan using cumulative semivariograms, the number of monitoring stations for the secondary air pollution can be reduced in east-west direction, but reinforced in north-south direction to explain the spacial variability. More scientific and rational relocation of air pollution monitoring network in Busan would be needed to investigate pollution status accurately and to plan and implement the pollution reduction policies effectively.

• Journal of Sensor Science and Technology
• /
• v.27 no.2
• /
• pp.118-125
• /
• 2018

An evaluation system for an electronic-nose concept using three types of metal oxide gas sensors that react similarly to the human olfactory cells was constructed for the quantitative and qualitative evaluation of aroma fragrances. Four types of aroma fragrances (lavender, orange, jasmine, and Roman chamomile), which are commonly used in aromatherapy, were evaluated. All the gas sensors reacted remarkably to the aroma fragrances and the good correlation of r=0.58-0.88 with the aromatic odor intensities by olfaction was confirmed. From the results of the analysis of an electronic-nose concept for classifying the characteristics of aroma oil fragrances, aroma oils could be classified using the fragrance characteristics and oil extraction methods with the cumulative variability contribution rate of 95.65% (F1: 69.65%, F2: 26.03%) by principal component analysis. In the pattern recognition based on the artificial neural network, the four aroma fragrances were 100% recognized through the training data of 56 cases (70%) out of 80 cases, and the pattern recognition rate was 57.1%-71.4% through the validation and testing data of 24 cases (30%). The pattern recognition success rate through all confusion matrices was 82.1%, indicating that the classification of aroma oil fragrances using the three types of gas sensors was successful.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.10 no.4
• /
• pp.53-66
• /
• 1990

Rainfall is a phenomenon that shows a high variability both in space and time, Hy drologists are usually interested in the description of spatial distribution of rainfall over watershed. The theory of Kriging, generalized covariance technique using nonstationary mean in the regions under orographic effect, was chosen to construct random surface of total storm depth. For the constructed random surface, the double Fourier analysis of the total storm depths was performed, and the principal harmonics of storm were determined. The local component, or storm residuals was obtained by subtracting the periodic component of the storm from total storm depths. It is assumed that the residuals are a sample function of a homogeneous random field. This random field can be characterized by an isotropic one dimensional autocorrelation function or its corresponding spectral density function. Under this assumption, this study proposed a theorectical model for spectral density function adapted to two watersheds.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.54 no.3
• /
• pp.198-205
• /
• 2005

In this paper, we proposed a new algorithm for the separation of fetal ECG from single channel abdominal ECG. The algorithm consists of a stage of demixing vector calculation for initial signal and a stage of fetal beat detection for the rest of signal. The demixing vector was obtained by applying independent component analysis technique to projected signals into time-frequency domain. For the test of this algorithm, simulation signals, De Lathauwer's data and some measured data, which was acquired from 8 healthy volunteers whose pregnant periods ranged from 22 weeks to 35 weeks and whose ages from 27 to 37, were used. For each data, the accuracy of fetal beat detection was $100\%$ and with the location of fetal beats, fetal heart rate variability and morphology could be offered. In conclusion, this proposed algorithm showed the possibility of fetal beat separation with a single channel abdominal ECG and it might be adopted to a fetal health monitoring system, by which a single channel abdominal ECG is acquired.

• Proceedings of the KOSOMBE Conference
• /
• v.1996 no.11
• /
• pp.217-220
• /
• 1996

In this paper, we compare three mehods to obtain PSD of HRV - FFT, AR modeling, and residual integration. Using these methods we speculate the balances of the LP and HF powers of HRV at $0^{\circ}$, $45^{\circ}$, $90^{\circ}$ tilt levels of head-up tilt table for young and healthy 24 men. R peaks are located at the highest point of QRS complex detected from modified spacial velocity algorithm. In general FFT is the most fast way to obtain PSD but PSD from FFT has too many peaks and valleies. AR PSD can show frequency of ANS activity effectively but LF component of PSD is often invisible due to interference of VLF power. The residual integration method that decomposes the AR PSD is very efficient way to extract LF component. Applying the above three methods to HRV we can visualize the trend of PSD variations along tilt levels.

• Journal of KIISE:Software and Applications
• /
• v.30 no.5_6
• /
• pp.398-413
• /
• 2003

Component-based Software Development(CBSD) supported by both component and reusability can reduce development time and cost, and also can achieve high productivity. To support component reusability systematically domain analysis and design in parallel with CBSD-process is needed. And also it is needed to suggest objective analysis process to fine out commonality and variability in domain, which is lacked in current domain analysis and design method. And to abstract domain component from the information which is well reflected in domain model, and to express it in domain architecture is needed. In this paper, we suggest the method to define, analyze and design domain systematically for enhancing reusability effectively in Component-base Software Development. We abstract components which can be reusable in domain, in other word, which have commonality from requirement analysis level. We sustain and refine them. And we reflect them to the products of each level. From these process, we can produce the domain component which have commonality. On this basis, we can design domain architecture. In this paper, to produce reusable software we investigate new systematic approach to domain analysis and design from the view point of software reusability.

• Journal of Biomedical Engineering Research
• /
• v.29 no.1
• /
• pp.73-81
• /
• 2008

The purpose of this study is to observe the brain activity patterns during visual oddball tasks with two difficulty levels by the analysis of high-density event-related potential (ERP). Along with conventional statistical analysis of averaged ERP waveforms, we applied independent component analysis (ICA) for the individual, single-trial analysis and verified its effectiveness. We could identify multiple ERP components such as early visual components (P1, N1), and two components which seem to be important task-related components and showed difficulty-dependent variability (P2, P300). The P2 was found around central region at $180{\sim}220ms$, and the P300 was found globally at $300{\sim}500ms$ poststimulus. As the task became difficult, the P2 amplitude increased, and the P300 amplitude decreased. After single-trial ERPs were decomposed into multiple independent components (ICs), several ICs resulting from P2 and P300 sources were identified. These ICs were projected onto scalp electrodes and the projected ICs were statistically compared according to two task difficulties. For most subjects, the results obtained from single-trial/individual analysis using ICA gave the tendencies of amplitude change that are similar to the averaged ERP analysis for most subjects. The temporal pattern and number of ICs corresponding to ${\mu}$ rhythm was not dependent on the task difficulty. It seems that the motor response was not affected by the task difficulty.

• Journal of KIISE:Software and Applications
• /
• v.27 no.9
• /
• pp.920-930
• /
• 2000

컴포넌트 기반의 소프트웨어 개발이 소프트웨어 복잡성, 비용, 그리고 품질을 해결하기 위한 새로운 대안으로 소개되고 있다. COM, Enterprise JavaBeans, CORBA 컴포넌트 모델등과 같은 다양한 컴포넌트 아키텍쳐들이 소개되고 있으며 컴포넌트 기반의 소프트웨어 개발 방법론과 여러 CASE 도구들이 이를 지원하고 있다.[1,2,3,4]. 그러나 현재 컴포넌트를 구현할 수 있는 기술은 제시되어 있지만 컴포넌트를 모델링하는 기법들에 대한 연구는 미약한 상태이다. 본 논문에서는 도메인 분석에서 공통성과 가변성 추출 및 클러스터링 기법을 이용한 컴포넌트를 분석하는 기법을 제시한다. 즉 컴포넌트 추출 기법, 컴포넌트의 핫스팟(또는 가변성)표현 기법, 컴포넌트 요구사항 정의 기법 등을 제시한다. 컴포넌트 개발에 있어서 이러한 모델링 기법을 적용함으로써 컴포넌트를 효율적으로 개발할 수 있을 뿐만 아니라 재사용성이 높은 고품질의 컴포넌트 개발을 지원할 수 있다.

• Ocean Systems Engineering
• /
• v.6 no.2
• /
• pp.191-201
• /
• 2016

Stern bearing is a key component of marine propulsion plant. Its environment is diverse, working condition changeable, and condition severe, so that stern bearing load is of strong time variability, which directly affects the safety and reliability of the system and the normal navigation of ships. In this paper, three affecting factors of the stern bearing load such as hull deformation, propeller hydrodynamic vertical force and bearing wear are calculated and characterized by random theory. The uncertainty mathematical model of stern bearing load is established to research the relationships between factors and uncertainty load of stern bearing. The validity of calculation mathematical model and results is verified by examples and experiment yet. Therefore, the research on the uncertainty load of stern bearing has important theoretical significance and engineering practical value.