• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.3
• /
• pp.175-184
• /
• 2023

Korean Wave is now internationalized through the internet by social media, which have no space-time restrictions. This research examine the continuance use of K-Pop promotion using social media in Indonesia. In this study we apply the Expectation-Confirmation Model to analyze the effects of individual self-efficacy and perceived enjoyment on perceived usefulness, confirmation, and satisfaction of Social Media. As a research method for that purpose, the conformity of the model and the research hypothesis were verified using the structural equation model. As a result, it was found that the perceived enjoyment positively influences perceived usefulness, self-efficacy has a positive influence on perceived usefulness. We also found that confirmation positively affects both perceived usefulness and satisfaction, and that perceived usefulness positively affects satisfaction. Finally, satisfaction was found to always have a positive effect on intention to use.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.349-349
• /
• 2020

기후변화로 인한 돌발홍수와 같은 집중적인 강우현상은 노후화된 제방의 안정성 저하 및 붕괴 등을 야기시킨다. 향후 홍수량이 증가함에 따라 하천의 통수면적이 부족하여 침수 및 범람의 위험성이 증가할 것으로 생각된다. 계획규모 이상의 홍수가 발생하여 홍수위가 제방고보다 높을 때 월류에 의한 제방붕괴로 이어지며, 이러한 월류에 의한 제방붕괴는 가장 전형적인 것이다. 지금까지 월류에 의한 제방붕괴에 관한 연구는 연구자의 다양한 관점 및 방법을 통해 진행되고 있다. 실제 제방붕괴를 관측하는 것은 불가능하므로 기존의 소규모 수리실험 및 모델링을 통한 제방붕괴 메커니즘 분석에는 사실상 한계가 있다. 이러한 점에서 실규모 수리실험을 통한 월류에 의한 제방붕괴 메커니즘을 3차원으로 분석할 필요가 있다. 본 연구에서는 드론 영상을 이용하여 제방붕괴 메커니즘 분석 연구를 수행하였다. 제방은 시간의 흐름에 따라 붕괴양상이 발전한다는 점 등에서 매우 복잡한 물리적 특성이 있다. 드론의 오토촬영 기법을 통한 제방이 붕괴되는 순간을 촬영하기는 쉽지 않기 때문에 셔터스피드촬영 기법을 적용하였다. 특히, 짧은 시간에 변화되는 제방의 붕괴양상을 구체적으로 표현하기 위해 두 대의 드론을 횡·종 방향으로 동시에 비행하여 분석 시 3차원 입체감을 최대화하였다. 이후 횡·종 방향에서 동 시간대 수집된 드론 이미지를 분류하여 PIX4D 매핑 기법을 활용한 최소 정합을 통하여 드론을 활용한 제방붕괴 메커니즘 분석의 활용 가능성을 제시하였다. 향후 스마트 시대의 물산업 경쟁력을 제고함에 있어, 폭이 좁은 하천에 효율적이며 고해상도 시공간 자료를 확보할 수 있는 드론을 활용한 스마트 하천재해 예측 및 관리기술 개발을 통한 하천 원격탐사의 경쟁력을 확보하는 것이 중요하다고 사료된다.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2023.05a
• /
• pp.104-105
• /
• 2023

해양 관측과 위성 원격탐사를 이용하여 시공간적으로 다양하게 변하는 생태 어장 환경 및 선박 관련 자료를 획득할 수 있다. 이번 연구의 주요 목적은 야간 불빛 위성 자료를 이용하여 광범위한 해역에 대한 어선의 위치 분포를 파악하는 딥러닝 기반 모델을 제안하는 것이다. 제안한 모델의 정확성을 평가하기 위해 야간 조업 어선의 위치를 포함하고 있는 AIS(Automatic Identification System) 정보와 상호 비교 평가 하였다. 이를 위해, 먼저 AIS 자료를 획득 및 분석하는 방법을 소개한다. 해양안전종합시스템(General Information Center on Maritime Safety & Security, GICOMS)으로부터 제공받은 AIS 자료는 동적정보와 정적정보로 나뉜다. 동적 정보는 일별 자료로 구분되어있으며, 이 정보에는 해상이동업무식별번호(Maritime Mobile Service Identity, MMSI), 선박의 시간, 위도, 경도, 속력(Speed over Ground, SOG), 실침로(Course over Ground, COG), 선수방향(Heading) 등이 포함되어 있다. 정적정보는 1개의 파일로 구성되어 있으며, 선박명, 선종 코드, IMO Number, 호출부호, 제원(DimA, DimB, DimC, Dim D), 홀수, 추정 톤수 등이 포함되어 있다. 이번 연구에서는 선박의 정보에서 어선의 정보를 추출하여 비교 자료로 사용하였으며, 위성 자료는 구름의 영향이 없는 깨끗한 날짜의 영상 자료를 선별하여 사용하였다. 야간 불빛 위성 자료, 구름 정보 등을 이용하여 야간 조업 어선의 불빛을 감지하는 심층신경망(Deep Neural Network; DNN) 기반 모델을 제안하였다. 본 연구의결과는 야간 어선의 분포를 감시하고 한반도 인근 어장을 보호하는데 기여할 것으로 기대된다.

• Korean Journal of Remote Sensing
• /
• v.25 no.4
• /
• pp.339-357
• /
• 2009

The Saemangeum Reclamation Project was launched as a national project in 1991 to reclaim a large coastal area of 401 km$^2$ by constructing a 33-km long dyke. The final dyke enclosure in April 2006 has transformed the tidal flat into lake and land. The dyke construction has abruptly changed not only the estuarine tidal system inside the dyke, but also the coastal marine environment outside the dyke. In this study, we investigated the spatial change of SST distribution using the Landsat-5/7 and NOAA data before and after the dyke completion in the Saemangeum area. Satellite-induced SST was verified by compared with the various in situ measurements such as tower, buoy, and water sample. The correlation coefficient resulted in above 0.96 and RMSE was about 1$^{\circ}C$ in all data. 38 Landsat satellite images from 1985 to 2007 were analyzed to estimate the temporal and spatial change of SST distribution from the beginning to the completion of the Samangeum dyke's construction. The seasonal change in detailed spatial distribution of SST was measured, however, the estimation of change during the Saemangeum dyke's construction was hard to figure out owing to the various environmental conditions. Monthly averaged SST induced from NOAA data from 1998 to 2007 has been analyzed for a complement of Landsat's temporal resolution. At the inside of the dyke, the change of SST from summer to winter was large due to the relatively high temperature in summer. In this study, multi-sensor thermal remote sensing is an efficient tool for monitoring the temporal and spatial distribution of SST in coastal area.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.13 no.6
• /
• pp.77-87
• /
• 2014

It has reported that a median bus-stop island on an exclusive median bus lane (EMBL) has shortened a crossing distance unit, encouraged a pedestrian's illegal crossing, and increased the number of accidents in the area. This study presents (1) the analysis of inappropriate pedestrian crossing patterns collected on exclusive median bus corridors and (2) the estimated performance of safety barriers restraining the occurrence of those. Total 19,649 pedestrian crossing data collected at the 'Sookmyung-university' median bus-stop, and the inappropriate pedestrian crossing patterns among those were grouped in terms of time and space violations. Physical safety barriers restraining illegal pedestrian crossings were considered as an alternative, and its performance in safety was quantified through microscopic simulation with conflict analyses by using surrogate safety assessment model. The findings suggest the number of conflicts reduced be 24.9 percentages compared to the one of the present condition when the physical safety barriers are placed at each of the eight ends of the EMBL pedestrian crossing.

• Journal of Broadcast Engineering
• /
• v.23 no.3
• /
• pp.351-360
• /
• 2018

Human emotion recognition is a research topic that is receiving continuous attention in computer vision and artificial intelligence domains. This paper proposes a method for classifying human emotions through multiple neural networks based on multi-modal signals which consist of image, landmark, and audio in a wild environment. The proposed method has the following features. First, the learning performance of the image-based network is greatly improved by employing both multi-task learning and semi-supervised learning using the spatio-temporal characteristic of videos. Second, a model for converting 1-dimensional (1D) landmark information of face into two-dimensional (2D) images, is newly proposed, and a CNN-LSTM network based on the model is proposed for better emotion recognition. Third, based on an observation that audio signals are often very effective for specific emotions, we propose an audio deep learning mechanism robust to the specific emotions. Finally, so-called emotion adaptive fusion is applied to enable synergy of multiple networks. The proposed network improves emotion classification performance by appropriately integrating existing supervised learning and semi-supervised learning networks. In the fifth attempt on the given test set in the EmotiW2017 challenge, the proposed method achieved a classification accuracy of 57.12%.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.9 no.2
• /
• pp.144-159
• /
• 2006

Hydrological models are tools intended to realistically represent the basin's complex system in which hydrological characteristics result from a number of physical, vegetative, climatic, and anthropomorphic factors. Spatially distributed hydrological models were first developed in the 1960s, Remote sensing(RS) data and Geographical Information System(GIS) play a rapidly increasing role in the field of hydrology and water resources development. Although very few remotely sensed data can applied in hydrology, such information is of great. One of the greatest advantage of using RS data for hydrological modeling and monitoring is its ability to generate information in spatial and temporal domain, which is very crucial for successful model analysis, prediction and validation. In this paper, SLURP model is selected as semi-distributed hydrological model and MODIS Leaf Area Index(LAI), Normalized Difference Vegetation Index(NDVI) as Remote sensing input data to hydrological modeling of Kyung An-chen basin. The outlet of the Kyung An stage site was simulated, We evaluated two RS data, based on ability of SLURP model to simulate daily streamflows, and How the two RS data influence the sensitivity of simulated Evapotranspiration.

• Journal of Broadcast Engineering
• /
• v.15 no.4
• /
• pp.474-486
• /
• 2010

In this paper, we propose a new method for detection moving object contour using spatial and temporal edge. In general, contour pixels of the moving object are likely present around pixels with high gradient value along the time axis and the spatial axis. Therefore, we can detect the contour of the moving objects by finding pixels which have high gradient value in the time axis and spatial axis. In this paper, we introduce a new computation method, termed as temporal edge, to compute an gradient value along the time axis for any pixel on an image. The temporal edge can be computed using two input gray images at time t and t-2 using the Sobel operator. Temporal edge is utilized to detect a candidate region of the moving object contour and then the detected candidate region is used to extract spatial edge information. The final contour of the moving object is detected using the combination of these two edge information, which are temporal edge and spatial edge, and then the post processing such as a morphological operation and a background edge removing procedure are applied to remove noise regions. The complexity of the proposed method is very low because it dose not use any background scene and high complex operation, therefore it can be applied to real-time applications. Experimental results show that the proposed method outperforms the conventional contour extraction methods in term of processing effort and a ghost effect which is occurred in the case of entropy method.

• Journal of Digital Convergence
• /
• v.15 no.9
• /
• pp.301-309
• /
• 2017

The purpose of this study was to explore family caregiver's need for online education for dementia caregiving. Participants in this study were 220 family caregivers from district dementia centers in Seoul. Family caregiver's usability and needs of online education program were assessed using self-administered questionnaires. Descriptive statistics and t-test comparisons were conducted. About 50% of family caregivers answered they could use and have intention to use online education. The results showed that there were the highest demand for the video lectures which give information about dementia and case video about caregiving skills. There were differences in needs of online program according to the gender and age. The use of online program offers users the opportunity to participate support program at their own time and pace. In order to maximize the effects of online support programs, it is important to establish the strategies of the customized programs considering the characteristics of the caregivers.

• Journal of the Korea Computer Graphics Society
• /
• v.9 no.3
• /
• pp.23-29
• /
• 2003

There is the temporal correlation of the video sequence between the motion vector of current block and the motion vector of the previous block. If we can obtain useful and enough information from the motion vector of the same coordinate block of the previous frame, the total number of search points used to find the motion vector of the current block may be reduced significantly. In this paper, we propose the block-matching motion estimation using an adaptive initial search point by the predicted motion information from the same block of the previous frame. And the first search point of the proposed algorithm is moved an initial point on the location of being possibility and the searching process after moving the first search point is processed according to the fast search pattern. Simulation results show that PSNR(Peak-to-Signal Noise Ratio) values are improved UP to the 1.05dB as depend on the image sequences and improved about 0.33~0.37dB on an average. Search times are reduced about 29~97% than the other fast search algorithms. Simulation results also show that the performance of the proposed scheme gives better subjective picture quality than the other fast search algorithms and is closer to that of the FS(Full Search) algorithm.