• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.31 no.4D
• /
• pp.539-546
• /
• 2011

Traffic accident collision interpretation is composed of various shapes, and speed variations working to the vehicle during collision are utilized as a very important factor in evaluating collision degrees between vehicles and safety of passengers who got in the vehicle. So, methods of interpreting results on speed variations utilizing simulation programs on the collision interpretation become necessary. By the way, reliability evaluation on each program is being required because various collision interpretations simulations are spread widely. This study utilized collision interpretation programs such as EDSMAC and PC-CRASH adopting completely different physical approaches, and then carried out collision experiments of one-dimensional front and two-dimensional right angle while changing values of a lot of collision factors such as vehicle's weight, center of gravity, rolling resistance, stiffness coefficient, and braking forces among early input conditions. Also, the study recognized effects of collision factors to speed variations as output results during crashing. As a result of this research, two simulation programs showed same speed variations together on the vehicle's weight, center of gravity, and braking forces. Stiffness coefficient of the vehicle reacted to EDSMAC only, and rolling resistance coefficient did not affect any particular influences on speed variations. However, there appeared a bit comparative differences from the speed variation's values, and this is interpreted as responding outcomes by applying fixed properties values to each simulation program plainly. Therefore, reliability on analysis of traffic accident collisions shall be improved by doing speed analysis after taking the fixed value of simulation programs into consideration.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.10
• /
• pp.293-302
• /
• 2016

Since the electricity is produced and consumed simultaneously, predicting the electric load and securing affordable electric power are necessary for reliable electric power supply. In particular, a university campus is one of the highest power consuming institutions and tends to have a wide variation of electric load depending on time and environment. For these reasons, an accurate electric load forecasting method that can predict power consumption in real-time is required for efficient power supply and management. Even though various influencing factors of power consumption have been discovered for the educational institutions by analyzing power consumption patterns and usage cases, further studies are required for the quantitative prediction of electric load. In this paper, we build an electric load forecasting model by implementing and evaluating various machine learning algorithms. To do that, we consider three building clusters in a campus and collect their power consumption every 15 minutes for more than one year. In the preprocessing, features are represented by considering periodic characteristic of the data and principal component analysis is performed for the features. In order to train the electric load forecasting model, we employ both artificial neural network and support vector machine. We evaluate the prediction performance of each forecasting model by 5-fold cross-validation and compare the prediction result to real electric load.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2007.05a
• /
• pp.1194-1199
• /
• 2007

본 연구에서는 도시배수관망의 간략화 모의 시 지선을 단순 생략하는 것이 아니라 2차원 관망을 1차원으로 전환시키는 방법인 등가하천 개념을 도입하여 도시유역의 유출량 산정에 있어서 여러 지선들을 개별적으로 모의하지 않으면서도 실제 존재하는 지선들의 효과를 고려할 수 있는 방법을 개발하고자 하였다. 자연하천에 대해 개발된 등가하천 개념은 최근의 수문모형의 경향인 물리적 분포형 모형의 복잡성을 피하면서 전통적인 개념적 집중형 모형이 가지는 간편성을 살리고 그 것이 가지고 있는 선형가정의 한계를 극복하기 위한 방안으로서 제안된 방법이다. 등가하천 개념을 도입하여 개발된 모형은 종국적으로 강우-유출관계에 있어서 강우의 크기, 선형 및 비선형성, 유역면적 등이 미치는 영향을 분석하기위한 도구로 개발되었으며, 본 연구에서는 출구로부터 동일 거리 s에 위치한 지점에서의 배수관망의 공간적인 분포 및 집중패턴을 파악하는 폭함수(width function, n(s))와 면적함수(area function, M(s))를 이용하여 관망을 간략화 하였다. 등가관의 수리기하조건 결정은 유역이 정상상태에 도달했을 경우에 대해서 이루어지게 되며 정상상태 모의를 통해 개별 관망단면들에 대해 얻어진 유량(Q), 면적(A), 수심(y) 자료간의 상관관계를 유추하여 Q(A), A(y) 함수를 유도하게 되면 종국적으로 관로홍수추적에 이용되는 지배방정식의 매개변수인 파속계수(c) 및 확산계수(D)를 계산할 수 있게 된다. 본 연구에서는 대상 유역으로 군자 배수구역을 선정하여 유역의 특성과 관망 자료를 수집하고 간략화 기법을 적용한 결과를 분석 하였다.다. 21세기 문화산업에서 우리가 판단하게 될 디자인의 가치는 계몽의 원리에 대한 '역사성'과 '현재성'의 변증법에 달려있는 것이며, 새로운 철학, 새로운 문명, 새로운 세계를 열어가는 것이다.r$ (地理志)에는 추현리와 이미 외리를 언급하면서 상주의 자기제작의 위상을 짐작하는 기록이 언급되면서 전국의 상품의 절반을 담당하고 있었음을 알 수 있었다. $\ulcorner$경상도지리지$\lrcorner$(慶尙道地理志)에는 상주가 8곳으로 1/3의 자기 생산을 담당하고 있었다. $\ulcorner$경상도지리지$\lrcorner$(慶尙道地理志)에는 $\ulcorner$세종실록$\lrcorner$(世宗實錄) $\ulcorner$지리지$\lrcorner$(地理志)와 동년대에 동일한 목적으로 찬술되었음을 알 수 있다. $\ulcorner$경상도실록지리지$\lrcorner$(慶尙道實錄地理志)에는 $\ulcorner$세종실록$\lrcorner$(世宗實錄) $\ulcorner$지리지$\lrcorner$(地理志)와의 비교를 해보면 상 중 하품의 통합 9개소가 삭제되어 있고, $\ulcorner$동국여지승람$\lrcorner$(東國與地勝覽) 에서는 자기소와 도기소의 위치가 완전히 삭제되어 있다. 이러한 현상은 첫째, 15세기

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.371-371
• /
• 2019

우리나라는 홍수기(6~9월)에 집중되는 기상패턴과 하천 중하류부에 발달된 도시의 개발특성으로 인하여 가장 중요한 자연재해 중 하나로 홍수 및 도시침수가 거론되고 있다. 과거 집중호우로 침수 피해가 발생한 사례를 살펴보면, 피해가 발생하는 지역은 지방하천 및 소하천을 중심으로 형성된 도시지역이다. 중앙 지방 정부는 수차례 침수 피해를 겪으며 사후관리가 아닌 재난예방 및 사전관리 등의 방안 마련을 강조하고 있다. 하지만 기후변화에 의한 기상의 불확실성으로 치수 중심의 물관리 및 중 소하천의 하천 특성으로 여전히 홍수 발생에 대비할 수 있는 골든타임 확보 등에 어려움을 겪고 있다. 이러한 어려움을 극복하기 위해 사전 예방적 차원에서의 홍수대응 방안으로 중 소하천을 담당하는 지자체 중심의 홍수피해 저감 방안이 필요하다. 본 연구에서는 A 지자체를 대상으로 모니터링 대상 경계를 설정하여 우량 알람 기준을 예비알람, 주요 관측지점에 대해 강우에 따른 수위 상승 정도를 홍수대응 기준인 직접알람과 연계함으로써 예방적 재난대응 체계를 구축하였다. 모니터링 대상 지역은 해당 지자체를 포함하면서 유역 개념을 적용하여 만경강유역 전체로 설정하였다. 만경강 유역 내 유관기관(지자체, 환경부, K-water, 기상청 등)이 관할하는 우량국(41개소) 및 수위국(28개소), 저수용량이 30만톤 이상이 되는 농어촌공사 저수지(7개소)를 고려하여 홍수분석 모형(COSFIM)을 구축하였다. 해당 모형은 2018년 8월 호우사상에 대해 주요 수위관측 지점에서 $R^2$가 0.8 이상의 우수한 검증 결과를 보였다. 구축된 모형을 통해 예상강우량별 하천 내 수위지점별 최고수위, 최대유량, 도달시간 등 예상 조견표를 제시하여 호우 발생시 지자체 담당자가 참고할 수 있도록 제시하였다. 또한 수위지점별 홍수대응 기준은 평시, 관심, 주의, 경계, 심각 단계로 구분하여 담당자가 수위별 위험 정도를 인지할 수 있도록 지점별 도달되는 수위의 위험 정보를 알람기준으로 제시하였다. 홍수분석 모형은 상류에 위치한 주요시설물의 운영현황을 연계하고 있어 실제 강우 발생 시 기상예보를 고려하여 하천 내 수위관측 지점별 수위 상승 정도를 예상함으로써 사전에 홍수에 대비할 수 있는 단계별 시간 확보에 활용 가능하다. 향후 홍수대응기준은 하천 환경 변화를 반영하여 지속적인 보완이 필요하며 유관기관과의 수문자료 공유체계 확대로 예방적 차원의 홍수 대응 체계가 구축되어야 할 것이다.

• Journal of Convergence for Information Technology
• /
• v.11 no.11
• /
• pp.57-65
• /
• 2021

We propose a novel method to detect abnormal data of specific symptoms using deep learning in air pollution measurement system. Existing methods generally detect abnomal data by classifying data showing unusual patterns different from the existing time series data. However, these approaches have limitations in detecting specific symptoms. In this paper, we use DeepLab V3+ model mainly used for foreground segmentation of images, whose structure has been changed to handle one-dimensional data. Instead of images, the model receives time-series data from multiple sensors and can detect data showing specific symptoms. In addition, we improve model's performance by reducing the complexity of noisy form time series data by using 'piecewise aggregation approximation'. Through the experimental results, it can be confirmed that anomaly data detection can be performed successfully.

• Journal of Navigation and Port Research
• /
• v.46 no.4
• /
• pp.367-374
• /
• 2022

The purpose of this study was to propose a deep learning algorithm that applies to the fault diagnosis of fuel pumps and purifiers of autonomous ships. A deep learning algorithm reflecting the time dependence of the measured signal was configured, and the failure pattern was trained using the vibration signal, measured in the equipment's regular operation and failure state. Considering the sequential time-dependence of deterioration implied in the vibration signal, this study adopts Conv1D with sliding window computation for fault detection. The time dependence was also reflected, by transferring the measured signal from two-dimensional to three-dimensional. Additionally, the optimal values of the hyper-parameters of the Conv1D model were determined, using the grid search technique. Finally, the results show that the proposed data preprocessing method as well as the Conv1D model, can reflect the sequential dependency between the fault and its effect on the measured signal, and appropriately perform anomaly as well as failure detection, of the equipment chosen for application.

• Journal of Ethics
• /
• no.77
• /
• pp.73-112
• /
• 2010

This study aims to explore the character and problem of multicultural society in Korea in terms of the concept of moral panics. Its major issues are dealt with as follows: Firstly, this essay will apply two concepts of culture in multiculturalism - the pattern of meaning and a study of perfection- to three degrees of multicultural members: by individual, by groups and by a society as a whole. In this approach, moral panics of multicultural society in Korea have been manipulated by the secondary definitions like Korean government and media. In this study, however, the resource of the panics would be seen as nationalism in Korean history. To remove it in this essay, the conception of the pattern of meaning, which makes members understand others outer their norms, should be harmonized with that of a study of perfection by which they have identities. Secondly, the main subject of multiculturalism in Korea should at least be majority (groups)-Korean, not minority (groups)-foreigners. A stereotype of foreigners by majority is an image distorted by nationalities and races. People, for example, with the white skin from advanced countries are recognized as superior, while those born in the countries of Southeast Asia are, consciously or unconsciously, discriminated and have low positions due to socio-economic stratification in Korea. In this sense, a study of multicultural society in Korea should go forward to the inner direction to majority, because it is one of the real moral panics in Korea. In conclusion, it is important that there must be a study of identity which we can have of others in multicultural studies of Korea. It enables us to meet the conception of diversity. In that Korean government and media have neglected the danger of nationalism, it is also necessary that this study have any foundation of morality in ethics, which can give useful alternatives to the given polices of the secondary definitions.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.2
• /
• pp.173-178
• /
• 2014

In this study, we introduce ASM-based face recognition classifier and its design methodology with the aid of 2-dimensional 2-directional hybird preprocessing algorithm. Since the image of face recognition is easily affected by external environments, ASM(active shape model) as image preprocessing algorithm is used to resolve such problem. In particular, ASM is used widely for the purpose of feature extraction for human face. After extracting face image area by using ASM, the dimensionality of the extracted face image data is reduced by using $(2D)^2$hybrid preprocessing algorithm based on LDA and PCA. Face image data through preprocessing algorithm is used as input data for the design of the proposed polynomials based radial basis function neural network. Unlike as the case in existing neural networks, the proposed pattern classifier has the characteristics of a robust neural network and it is also superior from the view point of predictive ability as well as ability to resolve the problem of multi-dimensionality. The essential design parameters (the number of row eigenvectors, column eigenvectors, and clusters, and fuzzification coefficient) of the classifier are optimized by means of ABC(artificial bee colony) algorithm. The performance of the proposed classifier is quantified through yale and AT&T dataset widely used in the face recognition.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.1
• /
• pp.1-6
• /
• 2014

In this study, we propose optimized RBFNNs based on night vision face recognition simulator with the aid of $(2D)^2$ PCA algorithm. It is difficult to obtain the night image for performing face recognition due to low brightness in case of image acquired through CCD camera at night. For this reason, a night vision camera is used to get images at night. Ada-Boost algorithm is also used for the detection of face images on both face and non-face image area. And the minimization of distortion phenomenon of the images is carried out by using the histogram equalization. These high-dimensional images are reduced to low-dimensional images by using $(2D)^2$ PCA algorithm. Face recognition is performed through polynomial-based RBFNNs classifier, and the essential design parameters of the classifiers are optimized by means of Differential Evolution(DE). The performance evaluation of the optimized RBFNNs based on $(2D)^2$ PCA is carried out with the aid of night vision face recognition system and IC&CI Lab data.

• Korean Journal of Environmental Biology
• /
• v.29 no.1
• /
• pp.17-22
• /
• 2011

The distributional pattern of benthic diatoms in tidal flats of Hampyeong Bay, Korea, was studied from January to October in 2009. As benthic diatoms of Hampyeong Bay tidal flats, 45 species were identified, and the most dominant species was Paralia sulcata. The most diverse flora was observed at Gaip and Songseok sites in April with 22 species, and the least at Hyeonhwa site in January. The ranges of chlorophyll-a concentration in tidal flats were 21.2~31.8 mg$m^{-2}$ at Hyeonhwa site, 23.6~35.4 mg $m^{-2}$ at Gaip site, and 24.2~34.3 mg $m^{-2}$ at Songseok site. The concentrations of pheopigment ranged between 25.3 and 45.2 mg$m^{-2}$. The standing crops of benthic diatoms showed highest density in April and lowest in January, February, and October. The cell volumes of benthic diatoms were highest in April. The taxa and biomass of benthic diatoms showed correlations with temperature. On temperature variables, the benthic diatoms showed optimal occurrences at the range of $14{\sim}17^{\circ}C$.