• Proceedings of the Korean Society of Computer Information Conference
• /
• 2012.01a
• /
• pp.263-264
• /
• 2012

본 논문은 여러 개의 독립적인 시계열로 구성된 시계열 패널 자료를 이용하여 비선형 모형인 GRCA모형과 신경망을 이용하여 예측값을 구하여 서로 비교 분석하고자 한다. 먼저 GRCA모형에 대하여 연구하고 신경망의 구조와 예측값을 구하기 위한 여러 가지 변환함수를 유도한다. 단기 예측에서는 신경망 방법의 예측값이 더 좋았고, 장기예측에서는 비선형모형을 이용한 예측값이 더 좋은 것으로 나타났다.

• The Korean Journal of Applied Statistics
• /
• v.20 no.2
• /
• pp.219-227
• /
• 2007

The time series models have been used to analyze and predict the network traffic. In this paper, we compare the performance of the time series models for prediction of network traffic. The feasibility study showed that a class of nonlinear time series models can be outperformed than the linear time series models to predict the network traffic.

• The Korean Journal of Applied Statistics
• /
• v.16 no.2
• /
• pp.293-303
• /
• 2003

Under the case that we know the period and the reason of external events, we reviewed the method of model identification, parameter estimation and model diagnosis with the former papers that have been studied about the linear time series model with intervention, and compared with nonlinear time series model such as ARCH, GARCH model that it has been used widely in economic models, and also we compared with the combination prediction method that Tong(1990) introduced.

• The Journal of the Acoustical Society of Korea
• /
• v.3 no.2
• /
• pp.35-45
• /
• 1984

본 연구는 한국어의 발음상의 특징과 구조에 의해서 한국어를 음소별로 분리할 수 있음에 착안 하여, 자음과 모음으로 구성된 한국어 단음을 자음의 음소와 모음의 음소로 각각 분리하여 인식하는 새 로운 방법에 관한 연구이다. 특정 화자 2명에 대하여 한국어 단음 84자를 모음의 음소와 자음의 음소로 각각 분리하여 인삭한 실험결과 모음을 인식한 경우에는 선형 예측 계수를 이용하면 인식률이 95.2%이 고, 편자기 상관계수로 92.5%, 폴만트로 97.6%의 인식률을 얻었고, 자음을 인식한 경우에는 선형 예측 계수로 88.7%, 편자기 상관계수로 92.9%의 인식률을 얻었다. 또, 자음의 음소와 모음의 음소를 결합시킨 단음을 인식한 경우에는 선형 예측 계수로 83.9%, 편자기 상관계수로 86.3%의 인식률을 얻었다. 이 때, 각 음소들의 데이터의 수는 256개이고, 선형 예측 계수와 편자기 상관 계수와의 예측차는 15차이다. 이 와 같이 한국어를 자음의 음소와 모음의 음소로 분리하면 작은 데이터 양으로 처리 시간을 단축 시켜 한국어의 모든 단음, 단어, 연속음, 문장 등을 분석하고 인식할 수 있고, 또한 각 음소들을 원칙적으로 결합시켜 모든 한국어의 합성이 가능함을 알 수 있다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.7 no.2
• /
• pp.53-59
• /
• 2006

Dynamic neural networks have been applied to diverse fields requiring temporal signal processing such as system identification and signal prediction. This paper proposes the gamma neural network(GAM), which uses gamma memory kernel in the hidden layer of feedforward multilayered network, to improve dynamics of networks and then describes nonlinear adaptive prediction using the proposed network as an adaptive filter. The proposed network is evaluated in nonlinear signal prediction and compared with feedforword(FNN) and recurrent neural networks(RNN) for the relative comparison of prediction performance. Simulation results show that the GAM network performs better with respect to the convergence speed and prediction accuracy, indicating that it can be a more effective prediction model than conventional multilayered networks in nonlinear prediction for nonstationary signals.

• Journal of Korea Multimedia Society
• /
• v.13 no.5
• /
• pp.722-729
• /
• 2010

Prediction problems are widely used in medical domains. For example, computer aided diagnosis or prognosis is a key component in a CDSS (Clinical Decision Support System). SVMs with nonlinear kernels like RBF kernels, have shown superior accuracy in prediction problems. However, they are not preferred by physicians for medical prediction problems because nonlinear SVMs are difficult to visualize, thus it is hard to provide intuitive interpretation of prediction results to physicians. Nomogram was proposed to visualize SVM classification models. However, it cannot visualize nonlinear SVM models. Localized Radial Basis Function (LRBF) was proposed which shows comparable accuracy as the RBF kernel while the LRBF kernel is easier to interpret since it can be linearly decomposed. This paper presents a new tool named VRIFA, which integrates the nomogram and LRBF kernel to provide users with an interactive visualization of nonlinear SVM models, VRIFA visualizes the internal structure of nonlinear SVM models showing the effect of each feature, the magnitude of the effect, and the change at the prediction output. VRIFA also performs nomogram-based feature selection while training a model in order to remove noise or redundant features and improve the prediction accuracy. The area under the ROC curve (AUC) can be used to evaluate the prediction result when the data set is highly imbalanced. The tool can be used by biomedical researchers for computer-aided diagnosis and risk factor analysis for diseases.

• Communications for Statistical Applications and Methods
• /
• v.5 no.3
• /
• pp.599-605
• /
• 1998

본 연구에서는 단순구조 순환신경망을 이용한 신경망예측과 전통적인 시계열예측 방법을 이용하여, 순환변동이 있는 시계열자료의 단기예측 오차를 비교한다. 순환신경망모형의 입력자료를 변화시키는 개선된 학습방법을 적용하여 시계열자료를 학습하고, 신경망예측의 결과는 선형 AR(9)모형, 비선형 SETAR모형 그리고 이들의 결합모형을 이용한 예측결과와 비교한다. 실증분석에 적용된 시계열자료는 1700년부터 1987년 까지의 태양흑점 자료이며 예측에 이용된 검정자료는 1980년부터 8년 간의 자료이다.

• Proceedings of the Korean Statistical Society Conference
• /
• 2001.11a
• /
• pp.95-97
• /
• 2001

공간자료의 예측문제에 있어 전통적 예측방법인 크리깅방법과 최근 통계적문제 적용되기 시작한 신경망분석방법 간의 비교를 사례연구를 통해 행하였다. 일반적으로 크리깅에 의한 선형예측은 공간자료에 대한 일반적 통계모형으로서 간주되어 왔다. 한편 예측문제에 있어 뉴럴네트워크에 기초한 비모수적 방법이 관심의 대상이 되고 있으며 특히 대용량 자료의 경우 데이터마이닝 기법의 한 분야로 널리 사용되고 있는 실정이다. 본 연구에서는 공간 자료의 예측에 있어 유전자 알고리즘을 신경망분석 모형을 결합하여 기존의 크리깅방법과의 예측력을 비교한다.

• Journal of Korean Society of Transportation
• /
• v.21 no.1
• /
• pp.21-40
• /
• 2003

A traffic accident analysis method was developed and tested based on the highway alignment risk indices using geographic information systems(GIS). Impacts of the highway alignment on traffic accidents have been identified by examining accidents occurred on different alignment conditions and by investigating traffic accident risk indices(TARI). Evaluative criteria are suggested using geometric design elements as an independent variable. Traffic accident rates were forecasted more realistically and objectively by considering the interaction between highway alignment factors and the design consistency. And traffic accident risk indices and risk ratings were suggested based on model estimation results and accident data. Finally, forecasting traffic accident rates, evaluating the level of risk and then visualizing information graphically were combined into one system called risk assessment system by means of GIS. This risk assessment system is expected to play a major role in designing four-lane highways and developing remedies for highway sections susceptible to traffic accidents.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.5
• /
• pp.477-482
• /
• 2015

Linear regressions and evolutionary nonlinear regression based compensation techniques for the short-range prediction of wind speed are investigated. Development of an efficient MOS(Model Output Statistics) is necessary to correct systematic errors of the model, but a linear regression based MOS is hard to manage an irregular nature of weather prediction. In order to solve the problem, a nonlinear and symbolic regression method using GP(Genetic Programming) is suggested for a development of MOS for wind speed prediction. The proposed method is compared to various linear regression methods for prediction of wind speed. Also, statistical analysis of distribution for UM elements for each method is executed. experiments are performed for KLAPS(Korea Local Analysis and Prediction System) re-analysis data from 2007 to 2013 year for Jeju Island and Busan area in South Korea.