• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.320-320
• /
• 2019

유역의 수문 자료를 정확하게 분석하는 것은 수리 구조물을 효율적으로 운영하기 위한 중요한 요소이다. 인공신경망(Artificial Neural Networks, ANNs) 모형은 입 출력 자료의 비선형적인 관계를 해석할 수 있는 모형으로 강우-유출 해석 등 수문 분야에 다양하게 적용되어 왔다. 이후 기존의 인공신경망 모형을 연속적인(sequential) 자료의 분석에 더 적합하도록 개선한 회귀신경망(Recurrent Neural Networks, RNNs) 모형과 회귀신경망 모형의 '장기 의존성 문제'를 개선한 장단기메모리(Long Short-Term Memory Networks, 이하 LSTM)가 차례로 제안되었다. LSTM은 최근에 주목받는 딥 러닝(Deep learning) 기법의 하나로 수문 자료와 같은 시계열 자료의 분석에 뛰어난 성능을 보일 것으로 예상되며, 수문 분야에서 이에 대한 적용성 평가가 요구되고 있다. 본 연구에서는 인공신경망 모형과 LSTM 모형으로 유출량을 모의하여 두 모형의 성능을 비교하고 향후 LSTM 모형의 활용 가능성을 검토하고자 하였다. 나주 수위관측소의 수위 자료와 인접한 기상관측소의 강우량 자료로 모형의 입 출력 자료를 구성하여 강우 사상에 대한 시간별 유출량을 모의하였다. 연구 결과, 1시간 후의 유출량에 대해서는 두 모형 모두 뛰어난 모의 능력을 보였으나, 선행 시간이 길어질수록 LSTM의 정확성은 유지되는 반면 인공신경망 모형의 정확성은 점차 떨어지는 것으로 나타났다. 앞으로의 연구에서 유역 내 다양한 수리 구조물에 의한 유 출입량을 추가로 고려한다면 LSTM 모형의 활용성을 보다 더 확장할 수 있을 것이다.

• Journal of Korea Water Resources Association
• /
• v.54 no.spc1
• /
• pp.1083-1093
• /
• 2021

It is an essential to predict water usage for establishing an optimal supply operation plan and reducing power consumption. However, the water usage by consumer has a non-linear characteristics due to various factors such as user type, usage pattern, and weather condition. Therefore, in order to predict the water consumption, we proposed the methodology linking various techniques that can consider non-linear characteristics of water use and we called it as KWD framework. Say, K-means (K) cluster analysis was performed to classify similar patterns according to usage of each individual consumer; then Wavelet (W) transform was applied to derive main periodic pattern of the usage by removing noise components; also, Deep (D) learning algorithm was used for trying to do learning of non-linear characteristics of water usage. The performance of a proposed framework or model was analyzed by comparing with the ARMA model, which is a linear time series model. As a result, the proposed model showed the correlation of 92% and ARMA model showed about 39%. Therefore, we had known that the performance of the proposed model was better than a linear time series model and KWD framework could be used for other nonlinear time series which has similar pattern with water usage. Therefore, if the KWD framework is used, it will be possible to accurately predict water usage and establish an optimal supply plan every the various event.

• Journal of Korean Society of Transportation
• /
• v.22 no.7 s.78
• /
• pp.155-159
• /
• 2004

Recently, there are many trials about Artificial neural networks : ANNs structure and studying method of researches for forecasting traffic volume. ANNs have a powerful capabilities of recognizing pattern with a flexible non-linear model. However, ANNs have some overfitting problems in dealing with a lot of parameters because of its non-linear problems. This research deals with the application of a variety of model selection criterion for cancellation of the overfitting problems. Especially, this aims at analyzing which the selecting model cancels the overfitting problems and guarantees the transferability from time measure. Results in this study are as follow. First, the model which is selecting in sample does not guarantees the best capabilities of out-of-sample. So to speak, the best model in sample is no relationship with the capabilities of out-of-sample like many existing researches. Second, in stability of model selecting criterion, AIC3, AICC, BIC are available but AIC4 has a large variation comparing with the best model. In time-series analysis and forecasting, we need more quantitable data analysis and another time-series analysis because uncertainty of a model can have an effect on correlation between in-sample and out-of-sample.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2006.05a
• /
• pp.1037-1041
• /
• 2006

본 연구에서는 수질자료에 내재되어 있는 주기성 및 경향성 등을 파악하기 위해 웨이블렛 변환을 적용하였으며 비선형 시계열자료에 대한 예측력이 우수한 인공신경망을 적용하여 예측모형을 개발하였다. 대상자료는 섬진강 유역의 주암호 수질자동측정망 지점에서 측정되고 있는 수질자료 중 2002년 1월 1일 ${\sim}$ 2004년 12월 31일까지의 일 TOC 수질자료를 이용하였다. 웨이블렛 변환을 위해 사용한 기저함수로는 Daubechies의 10번 웨이블렛 함수('db10')를 사용하였으며, 각 스케일링 및 웨이블렛 함수를 이용하여 5단계까지 변환하였다. 최종 변환된 근사성분과 D5, D4, D3, D2의 상세성분 자료를 이용하여 1시간후 TOC 예측 모형을 구성하였으며 그 결과 은닉층의 노드의 수가 17개인 모형인 Model_5_17 모형이 가장 우수한 예측력을 보였다.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.12
• /
• pp.3866-3873
• /
• 2000

In this paper, we investigates the long-term memory and the Correct answer rate of the foreign exchange data (Yen/Dollar) that is one of economic time series, There are many cases where two kinds of fractal dimensions exist in time series generated from dynamical systems such as AR models that are typical models having a short terrr memory, The sample interval separating from these two dimensions are denoted by kcrossover. Let the fractal dimension be $D_1$ in K < $k^{crossover}$,and $D_2$ in K > $k^{crossover}$ from the statistics mode. In usual, Statistic models have dimensions D1 and D2 such that $D_1$ < $D_2$ and $D_2\cong2$ But it showed a result contrary to this in the real time series such as NIKKEL The exchange data that is one of real time series have relation of $D_1$ > $D_2$ When the interval between data increases, the correlation between data increases, which is quite a peculiar phenomenon, We predict exchange data by neural networks, We confirm that $\beta$ obrained from prediction errors and D calculated from time series data precisely satisfy the relationship $\beta$ = 2-2D which is provided from a non-linear model having fractal dimension, And We identified that the difference of fractal dimension appeaed in the Correct answer rate.

• The KIPS Transactions:PartB
• /
• v.9B no.1
• /
• pp.35-46
• /
• 2002

The EEG is a time series of electrical potentials representing the sum of a very large number of neuronal dendrite potentials in the brain. The collective dynamic behavior of neural mass of different brain structures can be assessed from EEG with depth electrodes measurements at regular time intervals. In recent years, the theory of nonlinear dynamics has developed methods for quantitative analysis of brain function. In this paper, we considered it is reasonable or not for ICA apply to EEG analysis. Then we applied ICA to EEG for big toe movement and separated the independent components for 15 samples. The strength of each independent component can be represented on the topological map. We represented ICA can be applied for time and spatial analysis of EEG.

• Journal of Industrial Technology
• /
• v.29 no.B
• /
• pp.17-23
• /
• 2009

In many cases, clustering algorithms have been used for extracting and discovering useful information from non-linear data. They have made a great effect on performances of the systems dealing with non-linear data. Thus, this paper presents a new approach called hierarchically structured clustering algorithm, and it is applied to the prediction system for non-linear time series data. The proposed hierarchically structured clustering algorithm (called HCKA: Hierarchical Cross-correlation and K-means clustering Algorithms) in which the cross-correlation and k-means clustering algorithm are combined can accept the correlationship of non-linear time series as well as statistical characteristics. First, the optimal differences of data are generated, which can suitably reveal the characteristics of non-linear time series. Second, the generated differences are classified into the upper clusters for their predictors by the cross-correlation clustering algorithm, and then each classified differences are classified again into the lower fuzzy sets by the k-means clustering algorithm. As a result, the proposed method can give an efficient classification and improve the performance. Finally, we demonstrates the effectiveness of the proposed HCKA via typical time series examples.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.12
• /
• pp.346-351
• /
• 2017

This research examines 240 patients who visited a center a specific city, between July-September 2017. Subjects underwent body composition analysis and brainwave measurements, and were subsequently divided into groups according to BMI and body fat percentage. These patients were measured by timeseries linear analysis for their brain function and observed via brainwave activities. Results of the research are as follows: there is a difference in stress-resistance between obese and those in the healthy weight range. This implies there is a causal relationship between stress and obesity. In addition, the methodology used in this study, which is a scientific and objective physiological indicator of a scientific and objective physiological index, suggests that the results of the study are reliable. Results support that managing stress moderates obesity-related problems.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.31 no.5
• /
• pp.278-293
• /
• 2019

The joint distribution of wave height and period has been maltreated despite of its great engineering value due to the absence of any analytical model for wave period, and as a result, no consensus has been reached about the effect of nonlinearity on these joint distribution. On the other hand, there was a great deal of efforts to study the effects of non-linearity on the wave height distribution over the last decades, and big strides has been made. However, these achievements has not been extended to the joint distribution of wave height and period. In this rationale, we first express the joint distribution of wave height and period as the product of the marginal distribution of wave heights with the conditional distribution of associated periods, and proceed to derive the joint distribution of wave heights and periods utilizing the models of Longuet-Higgins (1975, 1983), and Cavanie et al. (1976) for conditional distribution of wave periods, and height distribution derived in this study. The verification was carried out using numerically simulated data based on the Wallops spectrum, and the nonlinear wave data obtained via the numerical simulation of random waves approaching toward the uniform beach of 1:15 slope. It turns out that the joint distribution based on the height distribution for finite banded nonlinear waves, and Cavanie et al.'s model (1976) is most promising.

• Korean Journal of Remote Sensing
• /
• v.34 no.6_2
• /
• pp.1229-1238
• /
• 2018

We examined if a state of sea-ice in Bering Sea acts as a prelude of variation in that of Chukchi Sea by using satellites-based Arctic sea-ice concentration time series. Datasets consist of monthly values of sea-ice concentration during 36 years (1982-2017). Time series analysis armed with Transfer entropy is performed to describe how sea-ice data in Chukchi Sea is affected by that in Bering Sea, and to explain the relationship. The transfer entropy is a measure which identifies a nonlinear coupling between two random variables or signals and estimates causality using modification of time delay. We verified this measure checked a nonlinear coupling for simulated signals. With sea-ice concentration datasets, we found that sea-ice in Bering Sea is influenced by that in Chukchi Sea 3, 5, 6 months ago through the transfer entropy measure suitable for nonlinear system. Particularly, when a sea-ice concentration of Bering Sea has a local minimum, sea ice concentration around Chukchi Sea tends to decline 5 months later with about 70% chance. This finding is considered to be a process that inflow of Pacific water through Bering strait reduces sea-ice in Chukchi Sea after lowering the concentration of sea-ice in Bering Sea. This approach based on information theory will continue to investigate a timing and time scale of interesting patterns, and thus, a coupling inherent in sea-ice concentration of two remote areas will be verified by studying ocean-atmosphere patterns or events in the period.