• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.50 no.5
• /
• pp.233-240
• /
• 2001

This paper presents a time series prediction method using a fuzzy rule-based system. Extracting fuzzy rules by performing a simple one-pass operation on the training data is quite attractive because it is easy to understand, verify, and extend. The simplest method is probably to relate an estimate, x(n+k), with past data such as x(n), x(n-1), ..x(n-m), where k and m are prefixed positive integers. The relation is represented by fuzzy if-then rules, where the past data stand for premise part and the predicted value for consequence part. However, a serious problem of the method is that it cannot handle nonstationary data whose long-term mean is varying. To cope with this, a new training method is proposed, which utilizes the difference of consecutive data in a time series. In this paper, typical previous works relating time series prediction are briefly surveyed and a new method is proposed to overcome the difficulty of prediction nonstationary data. Finally, computer simulations are illustrated to show the improved results for various time series.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.638-639
• /
• 2013

Anymon Plus(ver 3.0)은 통합 로그 분석 시스템으로 대용량 로그 및 빅데이터의 실시간 수집 저장 분석할 수 있는 제품(초당 40,000 이벤트 처리)으로서, 방화벽 로그 분석을 통한 비정상 네트워크 행위 탐지, 웹 로그 분석을 통한 사용 패턴 분석, 인터넷 쇼핑몰 사기 주문 분석 및 탐지, 내부 정부 유출 분석 및 탐지 등과 같은 다양한 분야로 응용이 확대되고 있다. 본 논문에서는 보안관련 인프라 로그를 분석하고 예측하여 예상 보안사고 시기에 집중적 경계를 통한 선제적 대응을 모색하기 위해 통계적 이론에 기반한 통합 로그 분석 시스템을 개발하기 위해, 회귀분석 및 시계열 분석이 가능한 예측 엔진 시스템을 설계하고 구현한다.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.32 no.6
• /
• pp.411-419
• /
• 2020

The experiment of unsteady rip current generated at the successive ends of breaking wave crests of honeycomb pattern waves was conducted in a laboratory wave basin, and its time-varying evolution was observed by using ortho-rectified images. The present experiment utilized the generation of a quasi nodal line of the honeycomb-pattern waves formed by out-of-phase motion of two piston-type wavemakers arranged in the transverse direction, instead of the original honeycomb pattern waves which are generated when two wave trains propagate with slightly different wave directions. The velocities of rip current were measured by using the LSPIV (Large-Scale Particle Image Velocimetry) technique. As a result, the unsteady rip current was generated between successive ends of wave crests, and evolved with its shear fluctuations in this experiment. Also, the time series of LSPIV velocity of the unsteady rip current showd its short component due to waves and its long component due to wave-induced currents.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.27 no.4
• /
• pp.763-773
• /
• 2017

In recent years, personal information leakage and technology leakage accidents are frequently occurring. According to the survey, the most important part of this spill is the 'insider' within the organization, and the leakage of technology by insiders is considered to be an increasingly important issue because it causes huge damage to the organization. In this paper, we try to learn the normal behavior of employees using machine learning to prevent insider threats, and to investigate how to detect abnormal behavior. Experiments on the detection of abnormal behavior by implementing an Autoencoder composed of Recurrent Neural Network suitable for learning time series data among the neural network models were conducted and the validity of this method was verified.

• The Korean Journal of Applied Statistics
• /
• v.35 no.1
• /
• pp.49-62
• /
• 2022

Realized volatility is well known to have long memory, strong association with other global financial markets and interdependences among macroeconomic indices such as exchange rate, oil price and interest rates. This paper proposes autoencoder factor-augmented heterogeneous autoregressive (AE-FAHAR) model for realized volatility forecasting. AE-FAHAR incorporates long memory using HAR structure, and exogenous variables into few factors summarized by autoencoder. Autoencoder requires intensive calculation due to its nonlinear structure, however, it is more suitable to summarize complex, possibly nonstationary high-dimensional time series. Our AE-FAHAR model is shown to have smaller out-of-sample forecasting error in empirical analysis. We also discuss pre-training, ensemble in autoencoder to reduce computational cost and estimation errors.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2006.05a
• /
• pp.1465-1469
• /
• 2006

수문순환 과정은 기상현상과 밀접한 관련을 가지고 서로 연관되어 있다. 이러한 연관성을 규명하여 수자원관리에 위험도를 감소시키려는 노력은 많은 분야에서 이루어지고 있으며, 주요 연구 주제가 되고 있다. 이러한 기상현상 중에서 가뭄은 여러 가지 요소가 복합되어 발생되는 것으로 알려지고 있으나 이를 설명하기에는 여전히 부족한 면이 존재한다. 가뭄을 발생시키는 몇 가지 가능한 원인으로는 E1 Nino-Southern Oscillation(ENSO)현상으로 잘 알려져 있는 비정상적인 해수면 온도의 변화나 기후 시스템의 비선형적 거동을 들 수 있다. 특히, 기후 시스템은 대개 경년 변화(inter-annual variability) 및 10년 이상의 주기(decadal variability) 특성을 가지고 있으며 가뭄 또한 경년변화의 주기 특성을 나타내고 있는 것으로 알려지고 있다. 이러한 관점에서 수문시계열을 특정 주파수(frequency)에서 고립시킨 후, 분석이 가능한 분해방법(decomposition method)을 통해 보다 해석적으로 접근하는 것이 가능하다. 이를 위해 본 연구에서는 Wavelet Transform분석을 도입하였으며 통계적으로 유의한 성분을 시계열로부터 추출하여 가뭄과 기상인자와의 변동성 분석을 실시하였다.

• The Korean Journal of Financial Management
• /
• v.21 no.1
• /
• pp.87-124
• /
• 2004

Some studies indicate that investors systematically underreact to new information in the stock market and Other studies indicate that investors systematically overreact. If investors irrationally react to the R&D intensity information, The portfolio strategy based on the R&D intensity information will be provided substantial excess returns. This study investigate that investors systematically underreact or overreact to the R&D intensity and whether portfolio strategy based on the R&D intensity is useful or not. Major results we as follows. First, This study indicate that investor systematically underreact to high R&D intensity and overreact low R&D intensity information. Second, after controlling the firm's specific factor such as firm size, BV/MV and past price performance, it is found that the performance of portfolio strategy based on the R&D intensity is not significant.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1994.06c
• /
• pp.368-372
• /
• 1994

확률적 모델을 이용한 HMM 으로 한국어 연속 음성 인식시스템을 구성하였다. 학습 모델로서는 양자화 DCK가 없는 연속출력 확률밀도를 사용한 연속출력 확률분포 HMM과 과도 구간 및 정상 구간의 시간구조를 충분히 BYGUS할 수 없는 것을 계속시간 확률 파라메터를 추가하여 보완한 이산 지속시간 제어 연속출력 확률분포 HMM을 이용하였다. 인식 알고리즘은 시계열 패턴의 시간축상에서의 비선형 신축을 고려한 에 매칭으로서, 음절의 경계를 자동으로 검출하는 O에을 이용하였다. 실험에서 사용된 연속음성데이타는 4연 숫자음과 연속음성 10문장으로 하였다. 인식 실험 결과 4연 숫자음에서 CHMM은 80.7%, DDCHMM은 92.9%의 인식률을 얻었고, 신문 사설에서 발췌한 연속 음성문장의 경우 CHMM 54.2%, DDCHMM에서는 68.9%을 얻어, 시간장 제어를 고려한 DDCHMM이 CHMM보다 SHB은 인식률을 얻었다.

• KDI Journal of Economic Policy
• /
• v.35 no.2
• /
• pp.107-131
• /
• 2013

In this paper, we test and estimate the stochastic non-fundamental trend in Korean stock market. For this, following Kim (2011), we exploit that the long-run equilibrium stock price may be decomposed into fundamental and stochastic non-fundamental trends (i.e., the sum of dividend innovations and a part that are orthogonal with the dividend innovations) by using the Beveridge-Nelson decomposition and projections. In this VAR construction, there is an error correction mechanism through which stock prices converge to their long-run equilibrium, which also contain the stated stochastic non-fundamental trend as well as fundamental trend. The estimation and test results using yearly data from the Korea (1976-2012) indicated that fluctuations in stock prices during that period can be explained mainly not by the stochastic non-fundamental trend but by the dividend trend. However, during some periods like after Seoul Olympic Games, we may observe the non-fundamental trend affected to the stock price variation.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.25 no.12
• /
• pp.888-894
• /
• 2015

A new method for the simulation of the vehicle's interior road noise is proposed in the present study. The road noise model can synthesize road noise of a vehicle for varying driving speed within a range. In the proposed method, interior road noise is considered as a stochastic time-series, and is modeled by a nonstationary parametric model via two steps. First, each interior road noise signal, obtained from constant speed driving tests performed within a range of speed, is modeled as an autoregressive model whose parameters are estimated by using a standard method. Finally, the parameters obtained for different driving speeds are interpolated based on the varying driving speed to yield a time-varying autoregressive model. To model a full band road noise, audible frequency range is divided into an octave band using a wavelet filter bank, and the road noise in each octave band is modeled.