• 한국정보통신학회논문지
• /
• 제25권12호
• /
• pp.1835-1845
• /
• 2021

본 논문에서는 블랙 아이스를 정확하게 인식하고 도로 노면 정보를 운전자에게 미리 알려줘서 속도를 제어하고 예방 조치를 취할 수 있도록 하기 위해 열화 도로 영상을 기반으로 블랙 아이스 검출하기 위해 lightweight 네트워크를 제안한다. 전이학습을 이용하여 블랙 아이스 인식 실험을 하였고, 블랙 아이스 인식의 정확도 향상을 위해 MobileNetV2 기반의 개선된 lightweight 네트워크를 개발하였다. 계산량을 줄이기 위해 Linear Bottleneck 및 Inverted Residuals를 활용하여 4개의 Bottleneck 그룹을 사용하고 모델의 인식률 향상을 위해 각 Bottleneck 그룹에 3×3 컨볼루션 레이어를 연결하여 지역적 특징 추출을 강화하고 특징 맵의 수를 늘렸다. 마지막으로 구축된 블랙 아이스 데이터 세트 대상으로 블랙 아이스 인식 실험을 진행하였으며, 제안된 모델은 블랙 아이스에 대해 99.07%의 정확한 인식률을 나타내었다.

• 한국지형학회지
• /
• 제26권3호
• /
• pp.53-67
• /
• 2019

The purpose of this study is to identify the quality of landslide susceptibility in a landslide-prone area (Jinbu-myeon, Gangwon-do, South Korea) by spatial prediction modeling approach and compare the results obtained. For this goal, a landslide inventory map was prepared mainly based on past historical information and aerial photographs analysis (Daum Map, 2008), as well as some field observation. Altogether, 550 landslides were counted at the whole study area. Among them, 182 landslides are debris flow and each group of landslides was constructed in the inventory map separately. Then, the landslide inventory was randomly selected through Excel; 50% landslide was used for model analysis and the remaining 50% was used for validation purpose. Total 12 contributing factors, such as slope, aspect, curvature, topographic wetness index (TWI), elevation, forest type, forest timber diameter, forest crown density, geology, landuse, soil depth, and soil drainage were used in the analysis. Moreover, to find out the co-relation between landslide causative factors and incidents landslide, pixels were divided into several classes and frequency ratio for individual class was extracted. Eventually, six landslide susceptibility maps were constructed using the Bayesian Predictive Discriminant (BPD), Empirical Likelihood Ratio (ELR), and Linear Regression Method (LRM) models based on different category dada. Finally, in the cross validation process, landslide susceptibility map was plotted with a receiver operating characteristic (ROC) curve and calculated the area under the curve (AUC) and tried to extract success rate curve. The result showed that Bayesian, likelihood and linear models were of 85.52%, 85.23%, and 83.49% accuracy respectively for total data. Subsequently, in the category of debris flow landslide, results are little better compare with total data and its contained 86.33%, 85.53% and 84.17% accuracy. It means all three models were reasonable methods for landslide susceptibility analysis. The models have proved to produce reliable predictions for regional spatial planning or land-use planning.

• 대한의용생체공학회:의공학회지
• /
• 제32권3호
• /
• pp.245-250
• /
• 2011

Parallel imaging technique can provide several advantages for a multitude of MRI applications. Especially, in SENSE technique, sensitivity maps were always required in order to determine the reconstruction matrix, therefore, a number of difference approaches using sensitivity information from coils have been demonstrated to improve of image quality. Moreover, many filtering methods were proposed such as adaptive matched filter and nonlinear diffusion technique to optimize the suppression of background noise and to improve of image quality. In this study, we performed SENSE reconstruction using computer simulations to confirm the most suitable method for the feasibility of filtering effect and according to changing order of polynomial fit that were applied on variation of spatial resolution of sensitivity map. The image was obtained at 0.32T(Magfinder II, Genpia, Korea) MRI system using spin-echo pulse sequence(TR/TE = 500/20 ms, FOV = 300 mm, matrix = $128{\times}128$, thickness = 8 mm). For the simulation, obtained image was multiplied with four linear-array coil sensitivities which were formed of 2D-gaussian distribution and the image was complex white gaussian noise was added. Image processing was separated to apply two methods which were polynomial fitting and filtering according to spatial resolution of sensitivity map and each coil image was subsampled corresponding to reduction factor(r-factor) of 2 and 4. The results were compared to mean value of geomety factor(g-factor) and artifact power(AP) according to r-factor 2 and 4. Our results were represented while changing of spatial resolution of sensitivity map and r-factor, polynomial fit methods were represented the better results compared with general filtering methods. Although our result had limitation of computer simulation study instead of applying to experiment and coil geometric array such as linear, our method may be useful for determination of optimal sensitivity map in a linear coil array.

• 대한원격탐사학회지
• /
• 제22권6호
• /
• pp.553-563
• /
• 2006

본 연구의 목적은 MODIS 다중시기영상과 선형분광혼합화소분석(Linear Spectral Mixture Analysis : LSMA)을 이용하여 한반도의 토지피복도를 작성하는 것이다. 다양한 공간해상도와 광역적인 촬영스케일의 MODIS 영상에 LSMA를 이용하여 토지피복분류기 정확도의 향상과 한반도 생물계절적인 특성을 분석하고자 하였다. LSMA는 하나의 화소를 단일의 지표물로 가정하여 영상을 처리하는 기존의 기법과 달리 대상지의 토지피복 특성을 가장 잘 반영하는 순수한 물체의 화소값(Endmember)을 선택하여 자연환경요소들의 하나하나를 분리하는 기법이다. 본 연구에서 MODIS 다중시기 영상에 LSMA를 적용한 결과 남, 북한의 농경지 및 산림지역에 대한 서로 다른 생물계절적인 특성을 파악 할 수 있었으며, 이러한 결과 영상을 ISODATA 무감독분류기법을 통해서 대분류와 중분류하였다. 대분류에서는 79.94%의 전체 정확도를 보였으며, 농업지역은 85.45%, 산림지역은 88.12%로 다른 분류군들에 비해서 가장 높은 정확도를 보였다. 중분류에서는 산림지역과, 농업지역을 더욱 세분화하여 분류하였다. 전체정확도는 82.09%였으며, 활엽수림 86.96%, 논 85.38%로 분류군중 가장 높은 정확도를 나타냈다.

• 제어로봇시스템학회논문지
• /
• 제16권6호
• /
• pp.566-571
• /
• 2010

EPS (Electric Power Steering) is important device for improving vehicle's dynamics and static performances. This paper deals with simulator design for C-EPS (Colum type-EPS), development assist and returnability control algorithm. First, C-EPS system model was simply designed because EPS system is complex control system that has many unknown variables. These parameters were simplified through assumptions. Second, C-EPS simulator was designed for development of control algorithm. This simulator has SAS (Steering Angle Sensor), dual torque sensor, dual load cell for measuring rack force, dual linear actuator for generating tire force and Data Acquisition System. Using this simulator, control methods ware tested. Third, control algorithm was designed for torque assist and returnability. Assist torque map and returnability torque map were found by lots of simulation test. These torque maps were tuned for EPS actuator control. The simulation result was compared with non-EPS system result. In this research, the C-EPS simulator was designed for development of control algorithm about torque assistant and returnability. Using this simulator, control algorithm was improved.

• 대한토목학회논문집
• /
• 제4권2호
• /
• pp.125-132
• /
• 1984

황해(黃海) 및 동지나해(東支那海)의 육붕(陸棚)의 성층(成層) 혼합(混合)모델이 제시(提示)되었다. 결과(結果)는 이 해역(海域)의 비선형(非線形) 조석(潮汐)모델로부터 산정(算定)된 조석(潮汐)에너지의 소산량(消散量)을 근거(根據)로 한 성층계수(成層係數)의 분포도(分布圖)로서 제시(提示)되었다. 해양자료(海洋資料)와 산정(算定)된 성층계수(成層係數)를 이용(利用)하여 우리 나라 서해안(西海岸) 태안반도(泰安半島) 근해(近海)의 조경(潮境)에 이러한 조석혼합조건(潮汐混合條件)의 적용여부(適用如否)를 검토(檢討)하는 것이 궁극적(窮極的)인 연구목표(硏究目標)이다.

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권8호
• /
• pp.3359-3362
• /
• 2014

Increasing attention is being devoted to the mechanisms by which cells receive signals and then translate these into decisions for growth, death, or migration. Recent findings have presented significant breakthroughs in developing a deeper understanding of the activation or repression of target genes and proteins in response to various stimuli and of how they are assembled during signal transduction in cancer cells. Detailed mechanistic insights have unveiled new maps of linear and integrated signal transduction cascades, but the multifaceted nature of the pathways remains unclear. Although new layers of information are being added regarding mechanisms underlying ovarian cancer and how polymorphisms in VDR gene influence its development, the findings of this research must be sequentially collected and re-interpreted. We divide this multi-component review into different segments: how vitamin D modulates molecular network in ovarian cancer cells, how ovarian cancer is controlled by tumor suppressors and oncogenic miRNAs and finally how vitamin D signaling regulates miRNA expression. Intra/inter-population variability is insufficiently studied and a better understanding of genetics of population will be helpful in getting a step closer to personalized medicine.

• 한국측량학회지
• /
• 제34권6호
• /
• pp.547-557
• /
• 2016

Due to threats caused by social disasters, operating surveillance devices are essential for social safety. CCTV, infrared cameras and other surveillance equipment are used to observe threats. This research proposes a method for searching for the optimum location of surveillance sensors. A GA (Genetic Algorithm) was used, since this algorithm is one of the most reasonable and efficient methods for solving complex non-linear problems. The sensor specifications, a DEM (Digital Elevation Model) and VITD (Vector Product Interim Terrain Data) maps were used for input data. We designed a chromosome using the sensor pixel location, and used elitism selection and uniform crossover for searching final solution. A fitness function was derived by the number of detected pixels on the borderline and the sum of the detection probability in the surveillance zone. The results of a 5-sensor and a 10-sensor were compared and analyzed.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 2005년도 추계학술대회 논문집
• /
• pp.231-234
• /
• 2005

The high temperature deformation behavior of AZ 31 Mg alloy was investigated by designing a back propagation neural network that uses a gradient descent-learning algorithm. A neural network modeling is an intelligent technique that can solve non-linear and complex problems by learning from the samples. Therefore, some experimental data have been firstly obtained from continuous compression tests performed on a thermo-mechanical simulator over a range of temperatures $(250-500^{\circ}C)$ with strain rates of $0.0001-100s^{-1}$ and true strains of 0.1 to 0.6. The inputs for neural network model are strain, strain rate, and temperature and the output is flow stress. It was found that the trained model could well predict the flow stress for some experimental data that have not been used in the training. Workability of a material can be evaluated by means of power dissipation map with respect to strain, strain rate and temperature. Power dissipation map was constructed using the flow stress predicted from the neural network model at finer Intervals of strain, strain rates and subsequently processing maps were developed for hot working processes for AZ 31 Mg alloy. The safe domains of hot working of AZ 31 Mg alloy were identified and validated through microstructural investigations.

• 환경영향평가
• /
• 제22권3호
• /
• pp.231-240
• /
• 2013

The Purpose of this research was to propose positioning strategies of urban park (UP) based on the assessment of location characteristics at cheongju city. To do that, this research found out urban park service area (UPSA) using GIS network analysis and built socio-economic attribute database, UP map, and other public service thematic maps such as public transportation, education, child-care, and convenience services. And this research analyzed spatial and attribute data using Pearson's correlation analysis, multiple linear regression, and binary logistic regression methods. As a result of this analysis, 1) the nearer neighborhood park and children's park, the higher land price and assumption income level (AIL). 2) children's parks were closed to living convenience facilities such as bank, hospital, and convenience store. 3) land price, AIL, population, and other public services level (PSL) in UPSA were higher than that of non-UPSA. 4) The higher land price, AIL, population, and other PSL, the higher urban park service level. The results of this research may contribute to resolve the regional UP unbalance and to improve UP service level as public service.