• Korean Journal of Remote Sensing
• /
• v.27 no.2
• /
• pp.121-130
• /
• 2011

This paper highlights the reconstruction of the rectilinear type of 3D rooftop model from satellite image data using centroid neural network. The main idea of the proposed 3D reconstruction method is based on the grouping of 3D line segments. 3D lines are extracted by 2D lines and DEM (Digital Elevation Map) data evaluated from a pair of stereo images. Our grouping process consists of two steps. We carry out the first grouping process to group fragmented or duplicated 3D lines into the principal 3D lines, which can be used to construct the rooftop model, and construct the groups of lines that are parallel each other in the second step. From the grouping result, 3D rooftop models are reconstructed by the final clustering process. High-resolution IKONOS images are utilized for the experiments. The experimental result's indicate that the reconstructed building models almost reflect the actual position and shape of buildings in a precise manner, and that the proposed approach can be efficiently applied to building reconstruction problem from high-resolution satellite images of an urban area.

• Journal of Korea Multimedia Society
• /
• v.3 no.3
• /
• pp.253-262
• /
• 2000

This paper proposes a new RBF neural network that determines the number and the center of hidden neurons based on the adaptive feature extraction for the input data. The principal component analysis is applied for extracting adaptively the features by reducing the dimension of the given input data. It can simultaneously achieve a superior property of both the principal component analysis by mapping input data into set of statistically independent features and the RBF neural networks. The proposed neural networks has been applied to classify the 200 breast cancer databases by 2-class. The simulation results shows that the proposed neural networks has better performances of the learning time and the classification for test data, in comparison with those using the k-means clustering algorithm. And it is affected less than the k-means clustering algorithm by the initial weight setting and the scope of the smoothing factor.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.11b
• /
• pp.569-572
• /
• 2003

본 연구에서는 뉴우턴법에 기초한 고정점 알고리즘의 신경망 기반 독립성분분석에 kurtosis를 추가한 독립성분의 군집화를 제안하였다. 여기서 뉴우턴법의 고정점 알고리즘은 엔트로피에 기초한 목적 함수의 근을 구하는 근사화 방법으로 빠른 성분분석을 위함이고, kurtosis는 독립성분의 추출순서를 고려하지 않는 속성을 개선하기 위함이다. 제안된 기법을 256$\times$256 픽셀의 8개 혼합영상의 분리에 적용한 결과, 제안된 방법은 기존의 독립성분분석에서 분석순서를 고려치 않는 제약을 효과적으로 해결 할 수 있음을 확인하였다.

• Journal of Korean Society of Transportation
• /
• v.20 no.6
• /
• pp.59-68
• /
• 2002

AADT(Annual Average Daily Traffic) can be obtained by using short-term counted traffic data rather than using traffic data collected for 365 days. The process is a very important in estimating AADT using short-term traffic count data. Therefore, There have been many studies about estimating AADT. In this Paper, we tried to improve the process of the AADT estimation based on the former AADT estimation researches. Firstly, we found the factor showing differences among groups. To do so, we examined hourly variables(divided to total hours, weekday hours. Saturday hours, Sunday hours, weekday and Sunday hours, and weekday and Saturday hours) every time changing the number of groups. After all, we selected the hourly variables of Sunday and weekday as the factor showing differences among groups. Secondly, we classified 200 locations into 10 groups through cluster analysis using only monthly variables. The nile of deciding the number of groups is maximizing deviation among hourly variables of each group. Thirdly, we classified 200 locations which had been used in the second step into the 10 groups by applying statistical techniques such as Discriminant analysis and Neural network. This step is for testing the rate of distinguish between the right group including each location and a wrong one. In conclusion, the result of this study's method was closer to real AADT value than that of the former method. and this study significantly contributes to improve the method of AADT estimation.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.8
• /
• pp.64-71
• /
• 2017

A damage estimation method is presented for jacket-type support structure of offshore wind turbine using a change of modal properties due to damage and committee of neural networks for effective structural health monitoring. For more practical monitoring, it is necessary to monitor the critical and prospective damaged members with a limited number of measurement locations. That is, many data channels and sensors are needed to identify all the members appropriately because the jacket-type support structure has many members. This is inappropriate considering economical and practical health monitoring. Therefore, intensive damage estimation for the critical members using a limited number of the measurement locations is carried out in this study. An analytical model for a jacket-type support structure which can be applied for a 5 MW offshore wind turbine is established, and a training pattern is generated using the numerical simulations. Twenty damage cases are estimated using the proposed method. The identified damage locations and severities agree reasonably well with the exact values and the accuracy of the estimation can be improved by applying the committee of neural networks. A verification experiment is carried out, and the damage arising in 3 damage cases is reasonably identified.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.23 no.4
• /
• pp.347-355
• /
• 2013

A damage estimation method for monopile support structure of offshore wind turbine using modal properties and committee of neural networks is presented for effective structural health monitoring. An analytical model for a monopile support structure is established, and the natural frequencies, mode shapes, and mode shape slopes for the support structure are calculated considering soil condition and added mass. The input to the neural networks consists of the modal properties and the output is composed of the stiffness indices of the support structure. Multiple neural networks are constructed and each individual network is trained independently with different initial synaptic weights. Then, the estimated stiffness indices from different neural networks are averaged. Ten damage cases are estimated using the proposed method, and the identified damage locations and severities agree reasonably well with the exact values. The accuracy of the estimation can be improved by applying the committee of neural networks which is a statistical approach averaging the damage indices in the functional space.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2010.05a
• /
• pp.1164-1168
• /
• 2010

수자원이 우리 생활의 전반적으로 중요한 역할을 차지하면서 댐의 효율적인 운영과 안정적인 용수공급에 대한 연구는 지속적으로 수행되어지고 있다. 1990년대 이후 비선형적인 특성을 잘 모의하는 장점을 가진 인공신경망(ANN)을 이용하여 유입량 예측에 대한 많은 연구가 수행되었다. 하지만 ANN 모형을 포함한 회귀모형은 월 강우 및 유입량의 예측에 대해 간편하게 사용을 할 수 있지만, 예측의 정확성에 한계를 가지고 있다. 본 연구에서는 ANN 모형과 회귀모형의 예측오차를 후처리 과정을 통하여 오차를 줄임으로써 예측모형의 성과를 향상시키는 방법을 제안하였다. 연구지역은 금강수계의 대청댐 유역으로, 1982년 9월부터 2005년 12월에 해당하는 유역 내 11개 지점의 강우관측소에서 관측한 월 강우와 댐 유입량을 수집하여 모형을 구축하였다. 강우량과 유입량 자료에 대해 자기상관함수와 교차상관함수를 이용하여 입력변수를 결정하였고, 정규화를 통한 전처리 과정을 거쳐 ANN 모형과 회귀모형을 이용한 예측모형을 구축하였으며, 예측성과의 향상을 위하여 군집 분석을 이용하여 오차를 재조정하였다. 이러한 오차 후처리 과정을 포함한 모형은 RMSE와 상관계수를 이용하여 비교 평가한 결과, 예측성과를 약 40% 정도 향상시켰다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.9C
• /
• pp.861-866
• /
• 2007

A clustering algorithm for Gaussian Probability Distribution Function (GPDF) data called Centroid Neural Network with a Bhattacharyya Kernel (BK-CNN) is proposed in this paper. The proposed BK-CNN is based on the unsupervised competitive Centroid Neural Network (CNN) and employs a kernel method for data projection. The kernel method adopted in the proposed BK-CNN is used to project data from the low dimensional input feature space into higher dimensional feature space so as the nonlinear problems associated with input space can be solved linearly in the feature space. In order to cluster the GPDF data, the Bhattacharyya kernel is used to measure the distance between two probability distributions for data projection. With the incorporation of the kernel method, the proposed BK-CNN is capable of dealing with nonlinear separation boundaries and can successfully allocate more code vector in the region that GPDF data are densely distributed. When applied to GPDF data in an image classification probleml, the experiment results show that the proposed BK-CNN algorithm gives 1.7%-4.3% improvements in average classification accuracy over other conventional algorithm such as k-means, Self-Organizing Map (SOM) and CNN algorithms with a Bhattacharyya distance, classed as Bk-Means, B-SOM, B-CNN algorithms.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.297-299
• /
• 2021

Predicting future productivity of tight oil is an important task for analyzing residual oil recovery and reservoir behavior. In general, productivity prediction is made using the decline curve analysis(DCA). In this study, we intend to propose an effective model for predicting future production using deep learning-based recurrent neural networks(RNN), LSTM, and GRU algorithms. As input variables, the main parameters are oil, gas, water, which are calculated during the production of tight oil, and the type curve calculated through various cluster analyzes. the output variable is the monthly oil production. Existing empirical models, the DCA and RNN models, were compared, and an optimal model was derived through hyperparameter tuning to improve the predictive performance of the model.

• Journal of Korea Game Society
• /
• v.18 no.2
• /
• pp.89-98
• /
• 2018

The recent Neural Network technique has shown good performance in content generation such as image generation in addition to the conventional classification problem and clustering problem solving. In this study, we propose an image generation method using artificial neural network as a next generation content creation technique. The proposed artificial neural network model receives two images and combines them into a new image by taking color from one image and shape from the other image. This model is made up of Convolutional Neural Network, which has two encoders for extracting color and shape from images, and a decoder for taking all the values of each encoder and generating a combination image. The result of this work can be applied to various 2D image generation and modification works in game development process at low cost.