• 융합신호처리학회논문지
• /
• 제12권1호
• /
• pp.26-32
• /
• 2011

This paper proposes a new method to process panoramic image stitching using SURF(Speeded Up Robust Features). Panoramic image stitching is considered a problem of the correspondence matching. In computer vision, it is difficult to find corresponding points in variable environment where a scale, rotation, view point and illumination are changed. However, SURF algorithm have been widely used to solve the problem of the correspondence matching because it is faster than SIFT(Scale Invariant Feature Transform). In this work, we also describe an efficient approach to decreasing computation time through the homography estimation using RANSAC(random sample consensus). RANSAC is a robust estimation procedure that uses a minimal set of randomly sampled correspondences to estimate image transformation parameters. Experimental results show that our method is robust to rotation, zoom, Gaussian noise and illumination change of the input images and computation time is greatly reduced.

• ETRI Journal
• /
• 제41권3호
• /
• pp.348-357
• /
• 2019

Fog radio access network (F-RAN) architectures provide markedly improved performance compared to conventional approaches. In this paper, an efficient genetic algorithm-based content distribution scheme is proposed that improves the throughput and reduces the transmission delay of a F-RAN. First, an F-RAN system model is presented that includes a certain number of randomly distributed fog access points (F-APs) that cache popular content from cloud and other sources. Second, the problem of efficient content distribution in F-RANs is described. Third, the details of the proposed optimal genetic algorithm-based content distribution scheme are presented. Finally, simulation results are presented that show the performance of the proposed algorithm rapidly approaches the optimal throughput. When compared with the performance of existing random and exhaustive algorithms, that of the proposed method is demonstrably superior.

• 대한수학회논문집
• /
• 제34권3호
• /
• pp.967-979
• /
• 2019

Chaotic dynamical systems, preferably on a Cantor-like space with some arithmetic operations are considered as good pseudo-random number generators. There are many definitions of chaos, of which Devaney-chaos and pos itive topological entropy seem to be the strongest. Let $A=\{0,1,{\dots},p-1\}$. We define a continuous map on $A^{\mathbb{Z}}$ using addition with a carry, in combination with the shift map. We show that this map gives rise to a dynamical system with positive entropy, which is also Devaney-chaotic: i.e., it is transitive, sensitive and has a dense set of periodic points.

• Nuclear Engineering and Technology
• /
• 제51권1호
• /
• pp.146-154
• /
• 2019

An improved principal component analysis (PCA) method is applied for sensor fault detection and isolation (FDI) in a nuclear power plant (NPP) in this paper. Data pre-processing and false alarm reducing methods are combined with general PCA method to improve the model performance in practice. In data pre-processing, singular points and random fluctuations in the original data are eliminated with various techniques respectively. In fault detecting, a statistics-based method is proposed to reduce the false alarms of $T^2$ and Q statistics. Finally, the effects of the proposed data pre-processing and false alarm reducing techniques are evaluated with sensor measurements from a real NPP. They are proved to be greatly beneficial to the improvement on the reliability and stability of PCA model. Meanwhile various sensor faults are imposed to normal measurements to test the FDI ability of the PCA model. Simulation results show that the proposed PCA model presents favorable performance on the FDI of sensors no matter with major or small failures.

• Journal of information and communication convergence engineering
• /
• 제20권2호
• /
• pp.131-136
• /
• 2022

The recommendation system applied in museums has been widely adopted owing to its advanced technology. However, it is unclear which recommendation is suitable for indoor museum guidance. This study evaluated a recommender system based on social-filtering and statistical methods applied to actual museum databases. We evaluated both methods using two different datasets. Statistical methods use collective data, whereas social methods use individual data. The results showed that both methods could provide significantly better results than random methods. However, we found that the trip time length and the dataset's sizes affect the performance of both methods. The social-filtering method provides better performance for long trip periods and includes more complex calculations, whereas the statistical method provides better performance for short trip periods. The critical points are defined to indicate the trip time for which the performances of both methods are equal.

• Journal of information and communication convergence engineering
• /
• 제21권3호
• /
• pp.225-232
• /
• 2023

Owing to advancements in intelligent transportation systems (ITS) and artificial-intelligence technologies, various machine-learning models can be employed to simulate and predict the number of traffic accidents under different weather conditions. Furthermore, we can analyze the relationship between weather and traffic accidents, allowing us to assess whether the current weather conditions are suitable for travel, which can significantly reduce the risk of traffic accidents. In this study, we analyzed 30000 traffic flow data points collected by traffic cameras at nearby intersections in Washington, D.C., USA from October 2012 to May 2017, using Pearson's heat map. We then predicted, analyzed, and compared the performance of the correlation between continuous features by applying several machine-learning algorithms commonly used in ITS, including random forest, decision tree, gradient-boosting regression, and support vector regression. The experimental results indicated that the gradient-boosting regression machine-learning model had the best performance.

• 수완나부미
• /
• 제15권2호
• /
• pp.215-244
• /
• 2023

This study analyzes the effect of macroeconomic indicators such as foreign direct investment (FDI), domestic investment, trade, inflation, unemployment, population, and governance indicators on economic growth and points out the GDP growth rate in 2002- 2019 among ASEAN countries. Data were compiled from the Worldwide Governance Indicators (WGI) and the World Bank, and the effect of variables on GDP was predicted using the pooled ordinary least squares (POLS), fixed effects model (FEM), and random effects model (REM) methods. As a measure of growth, the GDP growth rate has been taken; FDI and domestic investment, trade, inflation, and governance indicators are positively connected and have an influence on economic growth in these ASEAN countries; domestic investment, population, and unemployment have a negative relationship to economic growth. The macroeconomic indicators and institutional stability of the nation have an effect on its economic growth. Comprehensive institutional stability and well-laid macroeconomic policies are required for growth to materialize.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2021년도 하계학술대회
• /
• pp.105-108
• /
• 2021

Generative adversarial networks (GANs) have reached a great result at creating the synthesis image, especially in the face generation task. Unlike other deep learning tasks, the input of GANs is usually the random vector sampled by a probability distribution, which leads to unstable training and unpredictable output. One way to solve those problems is to employ the label condition in both the generator and discriminator. CelebA and FFHQ are the two most famous datasets for face image generation. While CelebA contains attribute annotations for more than 200,000 images, FFHQ does not have attribute annotations. Thus, in this work, we introduce a method to learn the attributes from CelebA then predict both soft and hard labels for FFHQ. The evaluated result from our model achieves 0.7611 points of the metric is the area under the receiver operating characteristic curve.

• 한국습지학회지
• /
• 제23권1호
• /
• pp.27-34
• /
• 2021

본 연구에서는 랜덤포레스트를 이용하여 8개 보 지점별 남조류 발생 주요 영향인자를 도출하고, 조류경보제 기반의 범주형 예측모델을 개발하였다. 8개 보 지점의 랜덤포레스트의 변수 중요도를 살펴본 결과, 상류의 보 지점들은 남조류 발생에 있어 보 운영에 따른 영향을 직접적으로 받는 것으로 나타났다. 이는 효율적인 보 운영을 통한 남조류 관리가 가능할 수 있다는 것을 의미한다. 중류 구간은 DO와 E.C가 주요 영향인자로 도출되었다. 공간적으로 구미와 김천에 대규모 산업공단들이 밀집되어 있으며, 환경기초시설의 배출량이 큰 영향을 끼치는 구간이다. 따라서 폭염 및 가뭄 시기에 중류 유역에서 배출되는 환경기초시설의 방류는 본류의 E.C를 증가하게 하고 남조류 발생을 촉진 시키는 것으로 나타났다. 중·하류에 위치한 보 지점들은 폭염 및 가뭄의 영향을 가장 많이 받는 지역으로 여름철 가뭄에 따른 남조류 대발생에 대비하여 선제적인 관리가 필요한 지점으로 나타났다. 본 연구를 통해 지점별 남조류 발생 영향인자를 도출하였으며, 맞춤형 조류관리를 위한 정책적 의사결정의 기초자료로 제공될 수 있을 것으로 판단된다.

• 한국환경생태학회지
• /
• 제29권3호
• /
• pp.333-343
• /
• 2015

본 연구는 국내에서 아직 미흡한 조류 번식지 예측 모형을 이용해 참매의 서식지 예측 및 대체번식지로서 이용 가능한 지역을 선정하고, 향후 참매 번식 가능지역을 대상으로 보호관리 지역을 확대할 수 있는 근거를 제시하기 위한 방안이다. 참매의 번식지는 현장조사에서 확인된 둥지(N=10)를 이용하였으며, 출현지점은 제3차자연환경조사를 통해 확인된 참매출현지점(N=23)을 활용해 분석하였다. 모형변수로는 지형인자 4가지, 자연환경인자(식생) 3가지, 거리인자 7가지, 기후변수 9가지를 활용하였다. 활용변수 중 Random sampling을 통해 확보된 비출현 좌표와 출현좌표간 비모수 검증을 통해 최종 환경변수를 선정하였다. 유의성 검증을 통해 선택된 변수는 번식지 대상 10가지, 출현지점 대상 7가지였으며, 이 변수를 활용해 최종 서식지 예측 모형(MaxEnt)을 구축하였다. 모델 구축결과 번식에 활용된 각 변수별 모형 기여도는 온도의 계절적 변동, 혼효림 과의 거리, 입목밀도, 경급의 순이었으며, 출현지점에 활용된 각 변수별 모형 기여도는 온도의 계절적 변동, 수계와의 거리, 경작지와의 거리, 경사도의 순이었다. 번식지점을 대상으로 한 모델링은 기후환경과 숲 내부에서 번식하는 참매의 특성이 반영된 것으로 판단된다. 예상서식지는 충청북도 중부 이북지역으로 예상되었으며, 그 면적은 $189.5km^2$(2.55%)였다. 충북 이남지역은 청주와 충주 등의 비교적 큰 도시가 발달되어 있는 반면 충청북도 북부지역의 경우 산림과 경작지가 고루 발달되어 있어 번식에 있어 일정한 세력권과 먹이원이 필요한 참매로서는 번식에 유리한 지역일 것으로 판단된다. 출현지점 대상으로 한 모델링은 면적이 $3,071km^2$(41.38%)으로 확인되었으며, 이는 출현지점을 대상으로 하여 단순이동 관찰 및 계절적인 변동 미고려 등의 한계가 있기 때문에 번식지점을 대상으로 한 모델링보다 광범위한 서식예상지역을 예측하였다. 결과에서 확인된 예측지점은 번식지를 대상으로 하였을 경우 정밀한 서식예측이 가능하나, 둥지의 특성상 확인되는 지점이 적고, 참매의 행동영역을 반영하지 못하는 단점이 있다. 반면 출현지점을 대상으로 하였을 경우 더 광범위한 지점에 대한 결과 도출이 가능하였으나, 단순 이동이나 지속적인 이용실태를 반영하지 못하기 때문에 정밀도에서는 다소 떨어진다고 할 수 있다. 다만 이러한 결과들을 통해 참매의 서식지를 예측할 수 있으며, 특히 정밀한 번식지역의 예측자료는 환경영향평가나 개발계획 수립시 서식지 모형 결과를 도입하여 반영할 필요성이 있다.