• Proceedings of the Korea Information Processing Society Conference
• /
• 한국정보처리학회 2015년도 추계학술발표대회
• /
• pp.1205-1207
• /
• 2015

Fingerprinting 방식에서 KNN은 WLAN 기반 실내 측위에 가장 많이 적용되고 있지만 KNN의 성능은 k개의 이웃 수와 RP의 수에 따라 민감하다. 논문에서는 KNN 성능을 향상시키기 위해 ANN 군집화를 적용한 KNN과 ANN을 혼합한 알고리즘을 제안하였다. 제안한 알고리즘은 신호잡음비 데이터를 KNN 방법에 적용하여 k개의 RP을 선택한 후 선택된 RP의 신호잡음비를 ANN에 적용하여 k개의 RP를 군집하여 분류한다. 실험 결과에서는 위치 오차가 2m 이내에서 KNN/ANN 알고리즘이 KNN 알고리즘보다 성능이 우수하다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 한국수자원학회 2016년도 학술발표회
• /
• pp.159-159
• /
• 2016

북한 지역에서 시작되어 한반도의 금문댐까지 연결되는 임진강은 북한지역의 유출량 미계측으로 인해 유출량 산출에 많은 어려움이 있어왔다. 본 연구에서는 위성 데이터를 활용하여 미계측 유역의 유출량을 추정 할 수 있는 기법을 제시하였다. Satellite-derived Flow Signal (SDF)는 위성 기반 특정 지역의 유출 정보를 제공하며, JAXA의 GCOM-W1 위성에 탑재된 Advanced Microwave Scanning Radiometer 2(AMSR2) 센서에서 산출된다. 본 연구에서는 SDS 뿐 아니라 유출에 크게 관련이 있는 지표 토양수분 데이터와 식생인자를 임진강 유출 값을 예측하기 위한 입력 값으로 활용하였다. 토양수분 데이터는 Metop-A 위성에 탑재된 Advanced Scatterometer(ASCAT) 센서에서 산출되는 데이터를 활용하였으며, 식생데이터는 Aqua 위성에 탑재된 Moderate Resolution Imaging Spectroradiometer(MODIS) 센서에서 측정되는 Normalized Difference Vegetation Index(NDVI) 데이터를 활용하였다. 추가적으로 SDS, 토양수분, NDVI 데이터는 다양한 lag time으로 약 150여개의 입력데이터로 세분화되었다. 150개의 방대한 입력인자는 Partial Mutual Information(PMI) 방법을 통해 소수 중요 인자들로 간추려져 기계 학습 입력인자로 활용되었다. 기계학습에 있어서는 Support Vector Machine(SVM), Artificial Neural Network (ANN) 기법을 활용하였다. SVM, ANN을 통해 모델화된 유출데이터는 금문댐 유출데이터와 비교/분석되었다. SVM 기법 기반의 유출량은 실제 유출량과 0.73의 상관계수를 보여주었고, ANN 기법 기반의 유출량은 0.66의 상관계수를 결과를 나타내었다. 하지만 SVM 기반 유출데이터는 과소 산정 되는 경향을 보였으며, ANN 기법 기반의 유출량은 과대산정되는 결과가 산출되는 한계점이 있음을 파악할 수 있었다.

• Journal of Intelligence and Information Systems
• /
• 제10권1호
• /
• pp.109-123
• /
• 2004

Corporate financial distress and bankruptcy prediction is one of the major application areas of artificial neural networks (ANNs) in finance and management. ANNs have showed high prediction performance in this area, but sometimes are confronted with inconsistent and unpredictable performance for noisy data. In addition, it may not be possible to train ANN or the training task cannot be effectively carried out without data reduction when the amount of data is so large because training the large data set needs much processing time and additional costs of collecting data. Instance selection is one of popular methods for dimensionality reduction and is directly related to data reduction. Although some researchers have addressed the need for instance selection in instance-based learning algorithms, there is little research on instance selection for ANN. This study proposes a genetic algorithm (GA) approach to instance selection in ANN for bankruptcy prediction. In this study, we use ANN supported by the GA to optimize the connection weights between layers and select relevant instances. It is expected that the globally evolved weights mitigate the well-known limitations of gradient descent algorithm of backpropagation algorithm. In addition, genetically selected instances will shorten the learning time and enhance prediction performance. This study will compare the proposed model with other major data mining techniques. Experimental results show that the GA approach is a promising method for instance selection in ANN.

• Journal of The Korean Society of Agricultural Engineers
• /
• 제54권4호
• /
• pp.73-81
• /
• 2012

In this study, the settlement data of 32 center cored rockfill dams (total 39 monitored data) were collected and analyzed to develop the method to predict the crest settlement of a CCRD after impounding by using the internal settlement data occurred during construction. An artificial neural network (ANN) modeling was used in developing the method, which was considered to be a more reliable approach since in the ANN model dam height, core width, and core type were all considered as input variables in deriving the crest settlement, whereas in conventional methods, such as Clements's method, only dam height is used as a variable. The ANN analysis results showed a good agreement with the measured data, compared to those by the conventional methods using regression analysis. In addition, a simple procedure to use the ANN model for engineers in practice was provided by proposing the equations used for given input values.

• Journal of Korean Society for Geospatial Information Science
• /
• 제13권3호
• /
• pp.33-40
• /
• 2005

The aim of remotely sensed data classification is to produce the best accuracy map of the earth surface assigning each pixel to its appropriate category of the real-world. The classification of satellite multi-spectral image data has become tool for generating ground cover map. Many classification methods exist. In this study, MLC(Maximum Likelihood Classification), ANN(Artificial neural network), SVM(Support Vector Machine), Naive Bayes classifier algorithms are compared using IKONOS image of the part of Dalsung Gun, Daegu area. Two preprocessing methods are performed-PCA(Principal component analysis), ICA(Independent Component Analysis). Boosting algorithms also performed. By the combination of appropriate feature selection pre-processing and classifier, the best results were obtained.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• 제20권10호
• /
• pp.27-34
• /
• 2006

This paper proposes a new method of on-line estimation for rotor resistance of the induction motor in the indirect vector controlled drive, using artificial neural network (ANN). The back propagation algorithm is used for training of the neural networks. The error between the desired state variable of an induction motor and actual state variable of a neural network model is back propagated to adjust the weight of a neural network model, so that the actual state variable tracks the desired value. The performance of rotor resistance estimator and torque and flux responses of drive, together with these estimators, are investigated variations rotor resistance from their nominal values. The rotor resistance are estimated analytically, using the proposed ANN in a vector controlled induction motor drive.

• Journal of Korea Water Resources Association
• /
• 제50권10호
• /
• pp.681-690
• /
• 2017

This study estimated the daily maximum snow depth using the Artificial Neural Network (ANN) model in Korean Peninsula. First, the optimal ANN model structure was determined through the trial-and-error approach. As a result, daily precipitation, daily mean temperature, and daily minimum temperature were chosen as the input data of the ANN. The number of hidden layer was set to 1 and the number of nodes in the hidden layer was set to 10. In case of using the observed value as the input data of the ANN model, the cross validation correlation coefficient was 0.87, which is higher than that of the case in which the daily maximum snow depth was spatially interpolated using the Ordinary Kriging method (0.40). In order to investigate the performance of the ANN model for estimating the daily maximum snow depth of the ungauged area, the input data of the ANN model was spatially interpolated using Ordinary Kriging. In this case, the correlation coefficient of 0.49 was obtained. The performance of the ANN model in mountainous areas above 200m above sea level was found to be somewhat lower than that in the rest of the study area. This result of this study implies that the ANN model can be used effectively for the accurate and immediate estimation of the maximum snow depth over the whole country.

• Proceedings of the Korea Water Resources Association Conference
• /
• 한국수자원학회 2018년도 학술발표회
• /
• pp.167-167
• /
• 2018

토양수분은 토양에 포함된 평균 수분량을 나타내며 수문 순환 관점에서 매우 중요한 수문변량 중 하나이다. 본 연구에서는 대표적인 기계학습 방법인 Support Vector Machine (SVM)을 이용한 토양 함수 예측 기법을 개발하고자 하며, 예측인자로서 원격 탐측 기반의 토양함수자료, 강수량, 온도 등을 활용하고자 한다. SVM은 Kernel 함수를 이용하여 복잡한 비선형 관계를 선형 가정을 통해서 해석하는 기계학습 방법으로서 전역모델(global model)로서 다양한 수문기상분야에 적용이 이루어지고 있다. SVM의 장점은 일정 부분의 오차를 허용함으로서 모형의 일반화 측면에서 기존 인공신경망(artificial neural network, ANN)에 비해 우수한 성능을 나타내며, 특히 예측모형으로서 적용성이 매우 크다. 본 연구에서는 과거 토양 함수 자료와 강수, 온도, 위성 관측 기반 정보 등을 이용하여 모형을 적합시키고 이를 미계측 유역으로 확장하는데 연구의 목적이 있으며, 본 연구를 통해 제안된 모형은 용담댐 시험유역을 대상으로 적용되며 기존 ANN 모형 및 다중회귀분석 결과와 비교를 통해 모형의 적합성을 평가하고자한다.

• Journal of Navigation and Port Research
• /
• 제32권1호
• /
• pp.81-88
• /
• 2008

The forecast of a container traffic has been very important for port plan and development. Generally, statistic methods, such as regression analysis, ARIMA, have been much used for traffic forecasting. Recent research activities in forecasting with artificial neural networks(ANNs) suggest that ANNs can be a promising alternative to the traditional linear methods. In this paper, a hybrid methodology that combines both ARIMA and ANN models is proposed to take advantage of the unique strength of ARIMA and ANN models in linear and nonlinear modeling. The results with port traffic data indicate that effectiveness can differ according to the characteristics of ports.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 한국항해항만학회 2007년도 추계학술대회 및 제23회 정기총회
• /
• pp.259-260
• /
• 2007

The forecast of a container traffic has been very important for port plan and development Generally, statistic methods, such as regression analysis, ARIMA, have been much used for traffic forecasting. Recent research activities in forecasting with artificial neural networks(ANNs) suggest tint ANNs am be a promising alternative to the traditional linear methods. In this paper, a hybrid methodology that combines both ARIMA and ANN models is proposed to take advantage of the unique strength of ARIMA and ANN models in linear and nonlinear modeling. The results with port traffic data indicate tint effectiveness can differ according to the ch1racteristics of ports.