• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.5
• /
• pp.512-519
• /
• 2003

In this paper, we propose a neuro-fuzzy modeling to improve the performance using the hierarchical clustering and Gaussian Mixture Model(GMM). The hierarchical clustering algorithm has a property of producing unique parameters for the given data because it does not use the object function to perform the clustering. After optimizing the obtained parameters using the GMM, we apply them as initial parameters for Adaptive Network-based Fuzzy Inference System. Here, the number of fuzzy rules becomes to the cluster numbers. From this, we can improve the performance index and reduce the number of rules simultaneously. The proposed method is verified by applying to a neuro-fuzzy modeling for Box-Jenkins s gas furnace data and Sugeno's nonlinear system, which yields better results than previous oiles.

• The Journal of the Korea Contents Association
• /
• v.18 no.8
• /
• pp.525-535
• /
• 2018

If the frequency of a particular class is excessively higher than the frequency of other classes in the classification problem, data imbalance problems occur, which make machine learning distorted. Corporate bankruptcy prediction often suffers from data imbalance problems since the ratio of insolvent companies is generally very low, whereas the ratio of solvent companies is very high. To mitigate these problems, it is required to apply a proper sampling technique. Until now, oversampling techniques which adjust the class distribution of a data set by sampling minor class with replacement have popularly been used. However, they are a risk of overfitting. Under this background, this study proposes ROSE(Random Over Sampling Examples) technique which is proposed by Menardi and Torelli in 2014 for the effective corporate bankruptcy prediction. The ROSE technique creates new learning samples by synthesizing the samples for learning, so it leads to better prediction accuracy of the classifiers while avoiding the risk of overfitting. Specifically, our study proposes to combine the ROSE method with SVM(support vector machine), which is known as the best binary classifier. We applied the proposed method to a real-world bankruptcy prediction case of a Korean major bank, and compared its performance with other sampling techniques. Experimental results showed that ROSE contributed to the improvement of the prediction accuracy of SVM in bankruptcy prediction compared to other techniques, with statistical significance. These results shed a light on the fact that ROSE can be a good alternative for resolving data imbalance problems of the prediction problems in social science area other than bankruptcy prediction.

• Convergence Security Journal
• /
• v.7 no.2
• /
• pp.17-25
• /
• 2007

In this paper, an algorithm that provisions proportional differentiation of packet delays is proposed with an objective for enhancing quality of service (QoS) in future packet networks. It features an adaptive scheme that adjusts the target delay every time slot to compensate the deviation from the target delay which is caused by the prediction error on the traffic to be arrived in the next time slot. It predicts the traffic to be arrived at the beginning of a time slot and measures the actual arrived traffic at the end of the time slot. The difference between them is utilized to the delay control operation for the next time slot to offset it. As it compensates the prediction error continuously, it shows superior adaptability to the bursty traffic as well as the exponential rate traffic. It is demonstrated through simulations that the algorithm meets the quantitative delay bounds and shows superiority to the traffic fluctuation in comparison with the conventional non-adaptive mechanism. The algorithm is implemented with VHDL on a Xilinx Spartan XC3S1500 FPGA and the performance is verified under the test board based on the XPC860P CPU.

• Journal of Advanced Navigation Technology
• /
• v.27 no.5
• /
• pp.510-518
• /
• 2023

This paper introduces a MATLAB graphical user interface (GUI) based software for performance analysis of navigation message and wide area differential correction of regional navigation satellite system (RNSS). This software was developed to analyze satellite orbit/clock-related performance of navigation message and wide area differential correction simulating RNSS for regions near Korea based on different distributions of monitor and reference stations. As a result of software operation, navigation message and wide area differential correction are given as output in MATLAB file format. From the analysis of output, it was confirmed that valid navigation message and wide area differential correction could be generated from the results about statistical feature of orbit and clock prediction errors, cm-level fitting errors for navigation message parameters, and 81.9% enhancement in range error for wide area differential correction.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.20 no.5
• /
• pp.526-534
• /
• 2014

In this study, single-input transfer function model is applied to forecast monthly mean sea surface temperature(SST) in 2010 at Yeosu in Korean coastal waters. As input series, monthly mean air temperature series for ten years(2000-2009) at Yeosu in Korea is used, and Monthly mean SST at Yeosu station in Korean coastal waters is used as output series(the same period of input). To build transfer function model, first, input time series is prewhitened, and then cross-correlation functions between prewhitened input and output series are determined. The cross-correlation functions have just two significant values at time lag at 0 and 1. The lag between input and output series, the order of denominator and the order of numerator of transfer function, (b, r, s) are identified as (0, 1, 0). The selected transfer function model shows that there does not exist the lag between monthly mean air temperature and monthly mean SST, and that transfer function has a first-order autoregressive component for monthly mean SST, and that noise model was identified as $ARIMA(1,0,1)(2,0,0)_{12}$. The forecasted values by the selected transfer function model are generally $0.3-1.3^{\circ}C$ higher than actual SST in 2010 and have 6.4 % mean absolute percentage error(MAPE). The error is 2 % lower than MAPE by ARIMA model. This implies that transfer function model could be more available than ARIMA model in terms of forecasting performance of SST.

• Journal of the Society of Disaster Information
• /
• v.17 no.2
• /
• pp.245-253
• /
• 2021

Purpose: This study develops a risk prediction model that predicts the risk of a fire site by using initial information such as building information and reporter acquisition information, and supports effective mobilization of fire fighting resources and the establishment of damage minimization strategies for appropriate responses in the early stages of a disaster. Method: In order to identify the variables related to the fire damage scale on the fire statistics data, a correlation analysis between variables was performed using a machine learning algorithm to examine predictability, and a learning data set was constructed through preprocessing such as data standardization and discretization. Using this, we tested a plurality of machine learning algorithms, which are evaluated as having high prediction accuracy, and developed a risk prediction model applying the algorithm with the highest accuracy. Result: As a result of the machine learning algorithm performance test, the accuracy of the random forest algorithm was the highest, and it was confirmed that the accuracy of the intermediate value was relatively high for the risk class. Conclusion: The accuracy of the prediction model was limited due to the bias of the damage scale data in the fire statistics, and data refinement by matching data and supplementing the missing values was necessary to improve the predictive model performance.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2005.11a
• /
• pp.238-241
• /
• 2005

디지털 미디어 기술의 발전은 코딩 분야를 비롯하여 다양하게 발전하고 있다. 특히 오디오 신호 처리 분야에서는 디지털 오디오 신호의 생성, 압축, 복원의 단계가 다양한 형태로 개발되고 있다. 오디오 신호 처리에서 인간의 청각 기관을 모델링한 심리음향 기법은 이용하여 압축뿐만 아니라 잡음 신호의 개선에서도 효과적으로 이용되고 있다. 이러한 심리음향모델을 기반으로 하여 구성된 적응지각필터는 지각필터를 이용하여 적응적으로 잡음에 열화된 신호를 개선한다. 이때, 적응지각필터 반복 수행 계수의 효과적인 결절은 오디오 신호의 청각적 손실을 줄이는 동시에 정확한 잡음 제거를 수행한다. 성능을 확인하기 위해서 SNR 및 NMR 비교를 수행하였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.07a
• /
• pp.322-325
• /
• 2015

본 논문에서는 개선된 자세 인식을 위한 학습을 통한 자세 인식 기법을 제안한다. 제안 자세 인식 기법은 영상의 모든 픽셀 값을 사용하지 않으며 인체의 골격의 위치 정보와 자세의 학습을 기반으로 한다. 최근 자세 인식기법에 다양한 기계 학습 기법을 적용하여 제스처 인식률을 높이는 연구가 진행되고 있지만 실시간 프레임에 적용하는데 한계가 있다. 반면 고차원의 특징점을 추출하여 신경망 학습방식을 이용하면 적은 계산량과 손쉬운 실행이 가능하다. 고차원의 특징점은 깊이 정보로부터 사람의 골격 정보를 이용해 추출하여 차원을 감소시키며 신경망 학습 방식에서는 각 자세에 대한 고차원의 특징점을 이용하여 자세의 학습을 진행한다. 신경망학습은 학습 단계에서는 미리 알려진 자세와 예측된 자세의 비교를 통해 오류를 최소화 하는 방향으로 학습을 진행하며, 판별 단계에서는 새로운 자세를 입력하여 고차원 특징점을 이용한 신경망 학습 기반의 제안 기술의 성능을 평가한다. 실험에 의하면 제안 기법은 약 96%의 자세 인식률을 보이고 자세 인식기법을 동작 인식으로 확장 가능성 또한 보인다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.16 no.3
• /
• pp.259-269
• /
• 1991

In this paper, power line harmonic noise which is the most serious problem in the secondary power distribution line is eliminated and analyzed using adaptive noise cancellers with two adaptive algorithms, LMS and individual tap LMS(ITLMS) algorithm. To testify the improvement of data transmission characteristics made by the adaptive filter with two adaptive algorithms, BER was measured in DS spread spectrum communication system including the noise canceller.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2013.11a
• /
• pp.209-212
• /
• 2013

본 논문에서 적응적 탐색 영역(Adaptive Search Range)을 이용하여 개선한 제한된 1비트 변환 알고리즘을 제안하였다. 이 변환은 전역 검색 알고리즘 (Full Search Algorithm)을 사용한다. 그러나 이것은 매우 많은 연산량과 복잡도를 가진다. 제안된 알고리즘에서는 각 블록의 탐색범위를 결정하기 위한 움직임 벡터 (Motion Vector)와 함께 제한된 1비트 변환 알고리즘의 제한된 마스크 (Constrained Mask)를 사용한다. 실험결과를 통해 제안된 알고리즘은 움직임 예측의 정확도에 대한 성능을 비슷하게 유지하면서 평균적으로 Search Point의 수를 84% 줄일 수 있음을 보여준다.