• Smart Structures and Systems
• /
• v.33 no.5
• /
• pp.325-332
• /
• 2024

This study proposes a novel long short-term memory (LSTM)-based approach for predicting carbonation depth, with the aim of enhancing the durability evaluation of concrete structures. Conventional carbonation depth prediction relies on statistical methodologies using carbonation influencing factors and in-situ carbonation depth data. However, applying in-situ data for predictive modeling faces challenges due to the lack of time-series data. To address this limitation, an LSTM-based carbonation depth prediction technique is proposed. First, training data are generated through random sampling from the distribution of carbonation velocity coefficients, which are calculated from in-situ carbonation depth data. Subsequently, a Bayesian theorem is applied to tailor the training data for each target bridge, which are depending on surrounding environmental conditions. Ultimately, the LSTM model predicts the time-dependent carbonation depth data for the target bridge. To examine the feasibility of this technique, a carbonation depth dataset from 3,960 in-situ bridges was used for training, and untrained time-series data from the Miho River bridge in the Republic of Korea were used for experimental validation. The results of the experimental validation demonstrate a significant reduction in prediction error from 8.19% to 1.75% compared with the conventional statistical method. Furthermore, the LSTM prediction result can be enhanced by sequentially updating the LSTM model using actual time-series measurement data.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.19 no.6
• /
• pp.612-620
• /
• 2013

In this study, time series analysis was tried, which is widely applied to demand forecast of diverse fields such as finance, economy, trade, and so on, different from previous regression analysis. Future marine traffic volume was forecasted on the basis of data of the number of ships entering Incheon port from January 1996 to June 2013, through courses of stationarity verification, model identification, coefficient estimation, and diagnostic checking. As a result of prediction January 2014 to December 2015, February has less traffic volume than other months, but January has more traffic volume than other months. Also, it was found out that Incheon port was more proper to ARIMA model than exponential smoothing method and there was a difference of monthly traffic volume according to seasons. The study has a meaning in that future traffic volume was forecasted per month with time series model. Also, it is judged that forecast of future marine traffic volume through time series model will be the more suitable model than prediction of marine traffic volume with previous regression analysis.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2008.05a
• /
• pp.694-698
• /
• 2008

In hydrology, it is a difficult task to deal with multivariate time series such as modeling streamflows of an entire complex river system. Normal distribution based model such as MARMA (Multivariate Autorgressive Moving average) has been a major approach for modeling the multivariate time series. There are some limitations for the normal based models. One of them might be the unfavorable data-transformation forcing that the data follow the normal distribution. Furthermore, the high dimension multivariate model requires the very large parameter matrix. As an alternative, one might be decomposing the multivariate data into independent components and modeling it individually. In 1985, Lins used Principal Component Analysis (PCA). The five scores, the decomposed data from the original data, were taken and were formulated individually. The one of the five scores were modeled with AR-2 while the others are modeled with AR-1 model. From the time series analysis using the scores of the five components, he noted "principal component time series might provide a relatively simple and meaningful alternative to conventional large MARMA models". This study is inspired from the researcher's quote to develop a multivariate simulation model. The multivariate simulation model is suggested here using Principal Component Analysis (PCA) and Independent Component Analysis (ICA). Three modeling step is applied for simulation. (1) PCA is used to decompose the correlated multivariate data into the uncorrelated data while ICA decomposes the data into independent components. Here, the autocorrelation structure of the decomposed data is still dominant, which is inherited from the data of the original domain. (2) Each component is resampled by block bootstrapping or K-nearest neighbor. (3) The resampled components bring back to original domain. From using the suggested approach one might expect that a) the simulated data are different with the historical data, b) no data transformation is required (in case of ICA), c) a complex system can be decomposed into independent component and modeled individually. The model with PCA and ICA are compared with the various statistics such as the basic statistics (mean, standard deviation, skewness, autocorrelation), and reservoir-related statistics, kernel density estimate.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.29 no.5
• /
• pp.505-511
• /
• 2023

In the present study, a deep learning model was established to predict the motion response of small fishing vessels. Hydrodynamic performances were evaluated for two small fishing vessels for the dataset of deep learning model. The deep learning model of the Long Short-Term Memory (LSTM) which is one of the recurrent neural network was utilized. The input data of LSTM model consisted of time series of six(6) degrees of freedom motions and wave height and the output label was selected as the time series data of six(6) degrees of freedom motions. The hyperparameter and input window length studies were performed to optimize LSTM model. The time series motion response according to different wave direction was predicted by establised LSTM. The predicted time series motion response showed good overall agreement with the analysis results. As the length of the time series increased, differences between the predicted values and analysis results were increased, which is due to the reduced influence of long-term data in the training process. The overall error of the predicted data indicated that more than 85% of the data showed an error within 10%. The established LSTM model is expected to be utilized in monitoring and alarm systems for small fishing vessels.

• The Korean Journal of Applied Statistics
• /
• v.35 no.4
• /
• pp.553-568
• /
• 2022

The Household Income and Expenditure Survey is a representative survey of Statistics Korea, which aims to measure and analyze national income and consumption levels and their changes by understanding the current state of household balances. Recently, the disconnection problem in these time series caused by the large-scale reorganization of the survey methods in 2017 and 2019 has become an issue. In this study, we model the characteristics of the time series in the Household Income and Expenditure Survey up to 2016, and use the modeling to compute forecasts for linking the expenditures in 2017 and 2018. In order to evenly reflect the characteristics across all expenditure item series and to reduce the impact of a specific forecast model, we synthesize a total of 8 models such as regression models, time series models, and machine learning techniques. In particular, the noteworthy aspect of this study is that it improves the forecast by using the optimal combination technique that can exactly reflect the hierarchical structure of the Household Income and Expenditure Survey without loss of information as in the top-down or bottom-up methods. As a result of applying the proposed method to forecast expenditure series from 2017 to 2019, it contributed to the recovery of time series linkage and improved the forecast. In addition, it was confirmed that the hierarchical time series forecasts by the optimal combination method make linkage results closer to the actual survey series.

• Communications for Statistical Applications and Methods
• /
• v.21 no.6
• /
• pp.471-486
• /
• 2014

This study introduces a new type of symbolic data, a candle chart-valued time series. We aggregate four stock indices (i.e., open, close, highest and lowest) as a one data point to summarize a huge amount of data. In other words, we consider a candle chart, which is constructed by open, close, highest and lowest stock indices, as a type of symbolic data for a long period. The proposed candle chart-valued time series effectively summarize and visualize a huge data set of stock indices to easily understand a change in stock indices. We also propose novel approaches for the candle chart-valued time series modeling based on a combination of two midpoints and two half ranges between the highest and the lowest indices, and between the open and the close indices. Furthermore, we propose three types of sum of square for estimation of the candle chart valued-time series model. The proposed methods take into account of information from not only ordinary data, but also from interval of object, and thus can effectively perform for time series modeling (e.g., forecasting future stock index). To evaluate the proposed methods, we describe real data analysis consisting of the stock market indices of five major Asian countries'. We can see thorough the results that the proposed approaches outperform for forecasting future stock indices compared with classical data analysis.

• Korean Journal of Occupational Health Nursing
• /
• v.25 no.1
• /
• pp.65-74
• /
• 2016

Purpose: The purpose of this study is to predict industrial accident rate using time series analysis. Methods: The rates of industrial accident and occupational injury death were analyzed using industrial accident statistics analysis system of the Korea Occupational Safety and Health Agency from 2001 to 2014. Time series analysis was done using the most recent data, such as raw materials of Economically Active Population Survey, Economic Statistics System of the Bank of Korea, and e-National indicators. The best-fit model with time series analysis to predict occupational injury was developed by identifying predictors when the value of Akaike Information Criteria was the lowest point. Variables into the model were selected through a series of expertises' consultations and literature review, which consisted of socioeconomic structure, labor force structure, working conditions, and occupational accidents. Results: Indexes at the meso- and macro-levels predicting well occurrence of occupational accidents and occupational injury death were labor force participation rate for ages 45-49 and budget for small scaled workplace support. The rates of industrial accident and occupational injury death are expected to decline. Conclusion: For reducing industrial accident continuously, we call for safe employment policy of economically active middle aged adults and support for improving safety work environment of small sized workplace.

• The Korean Journal of Applied Statistics
• /
• v.32 no.1
• /
• pp.69-81
• /
• 2019

We consider bivariate long range dependent (LRD) time series forecasting using a deep learning method. A long short-term memory (LSTM) network well-suited to time series data is applied to forecast bivariate time series; in addition, we compare the forecasting performance with bivariate fractional autoregressive integrated moving average (FARIMA) models. Out-of-sample forecasting errors are compared with various performance measures for functional MRI (fMRI) data and daily realized volatility data. The results show a subtle difference in the predicted values of the FIVARMA model and VARFIMA model. LSTM is computationally demanding due to hyper-parameter selection, but is more stable and the forecasting performance is competitively good to that of parametric long range dependent time series models.

• The KIPS Transactions:PartB
• /
• v.11B no.4
• /
• pp.449-456
• /
• 2004

This paper proposes a novel recognition model, a recurrent fuzzy associative memory(RFAM), for recognizing time-series patterns contained an ambiguity. RFAM is basically extended from FAM(Fuzzy Associative memory) by adding a recurrent layer which can be used to deal with sequential input patterns and to characterize their temporal relations. RFAM provides a Hebbian-style learning method which establishes the degree of association between input and output. The error back-propagation algorithm is also adopted to train the weights of the recurrent layer of RFAM. To evaluate the performance of the proposed model, we applied it to a word boundary detection problem of speech signal.

• Proceedings of the KIEE Conference
• /
• 2000.07a
• /
• pp.239-241
• /
• 2000

This paper describes a modeling of a FACTS(Flexible AC Transmission System) device, namely, SSSC(Static Synchronous Series Compensator) model. The SSSC, a solid-state voltage source inverter coupled with a transformer, is connected in series with a transmission line. SSSC provides controllable compensating voltage, which is in quadrature with the line current, over an capacitive and an inductive range, independently of the magnitude of the line current. This SSSC model is obtained from the injection model for series connected VSC(Voltage Source Converter) by adding a constraint that the injected voltage should be in quadrature with the line current. The paper discusses the basic operating and performance characteristics of the SSSC, and power flow control in power system.