• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.5
• /
• pp.1963-1978
• /
• 2015

With the advancement of mobile web environments, identification and analysis of the user behavior play a significant role and remains a challenging task to implement with variations observed in the model. This paper presents an efficient method for mining optimized user behavior prediction model using genetic algorithm on mobile web structure. The framework of optimized user behavior prediction model integrates the temporary and permanent register information and is stored immediately in the form of integrated logs which have higher precision and minimize the time for determining user behavior. Then by applying the temporal characteristics, suitable time interval table is obtained by segmenting the logs. The suitable time interval table that split the huge data logs is obtained using genetic algorithm. Existing cluster based temporal mobile sequential arrangement provide efficiency without bringing down the accuracy but compromise precision during the prediction of user behavior. To efficiently discover the mobile users' behavior, prediction model is associated with region and requested services, a method called optimized user behavior Prediction Model using Genetic Algorithm (PM-GA) on mobile web structure is introduced. This paper also provides a technique called MAA during the increase in the number of models related to the region and requested services are observed. Based on our analysis, we content that PM-GA provides improved performance in terms of precision, number of mobile models generated, execution time and increasing the prediction accuracy. Experiments are conducted with different parameter on real dataset in mobile web environment. Analytical and empirical result offers an efficient and effective mining and prediction of user behavior prediction model on mobile web structure.

• Journal of Ocean Engineering and Technology
• /
• v.24 no.6
• /
• pp.97-102
• /
• 2010

This paper deals with the variability of short term creep rupture time based on previous creep rupture tests and the statistical methodology of the creep life prediction. The results of creep tests performed using constant uniaxial stresses at 600, 650, and $700^{\circ}C$ elevated temperatures were used for a statistical analysis of the inter-specimen variability of the short term creep rupture time. Even under carefully controlled identical testing conditions, the observed short-term creep rupture time showed obvious inter-specimen variability. The statistical aspect of the short term creep rupture time was analyzed using a Weibull statistical analysis. The effect of creep stress on the variability of the creep rupture time was decreased with an increase in the stress level. The effect of the temperature on the variability also decreased with increasing temperature. A long term creep life prediction method that considers this statistical variability is presented. The presented method is in good agreement with the Lason-Miller Parameter (LMP) life prediction method.

• The Korean Journal of Applied Statistics
• /
• v.24 no.6
• /
• pp.995-1006
• /
• 2011

A time series can be decomposed into simple components with a multiscale method. Empirical mode decomposition(EMD) is a recently invented multiscale method in Huang et al. (1998). It is natural to apply a classical prediction method such a vector autoregressive(AR) model to the obtained simple components instead of the original time series; in addition, a prediction procedure combining a classical prediction model to EMD and Hilbert spectrum is proposed in Kim et al. (2008). In this paper, we suggest to adopt principal component analysis(PCA) to the prediction procedure that enables the efficient selection of input variables among obtained components by EMD. We discuss the utility of adopting PCA in the prediction procedure based on EMD and Hilbert spectrum and analyze the daily worm account data by the proposed PCA adopted prediction method.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.59 no.6
• /
• pp.1159-1166
• /
• 2010

To improve prediction quality of a nonlinear prediction system, the system's capability for uncertainty of nonlinear data should be satisfactory. This paper presents a TSK fuzzy prediction system that can consider and deal with the uncertainty of nonlinear data sufficiently. In the design procedures of the proposed system, HCBKA(Hierarchical Correlationship-Based K-means clustering Algorithm) was used to generate the accurate fuzzy rule base that can control output according to input efficiently, and the first-order difference method was applied to reflect various characteristics of the nonlinear data. Also, multiple prediction systems were designed to analyze the prediction tendencies of each difference data generated by the difference method. In addition, to enhance the prediction quality of the proposed system, an error compensation method was proposed and it compensated the prediction error of the systems suitably. Finally, the prediction performance of the proposed system was verified by simulating two typical time series examples.

• 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.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.26 no.2
• /
• pp.39-46
• /
• 2018

Departure Manager (DMAN) is a tool to optimize the departure sequence and to suggest appropriate take-off time and off-block time of each departure aircraft to the air traffic controllers. To that end, Variable Taxi Time (VTT), which is time duration of the aircraft from the stand to the runway, should be estimated. In this paper, a study for development of VTT prediction algorithm based on machine learning techniques is presented. The factors affecting aircraft taxi speeds were identified through the analysis of historical traffic data on the airport surface. The prediction model suggested in this study consists of several sub-models that reflect different types of surface maneuvers based on the analysis result. The prediction performance of the proposed method was evaluated using the actual operational data.

• Industrial Engineering and Management Systems
• /
• v.14 no.3
• /
• pp.312-317
• /
• 2015

The dynamic system approach in time series has been used in many real problems. Based on Taken's embedding theorem, we can build the predictive function where input is the time delay coordinates vector which consists of the lagged values of the observed series and output is the future values of the observed series. Although the time delay coordinates vector from multivariate time series brings more information than the one from univariate time series, it can exhibit statistical redundancy which disturbs the performance of the prediction function. We apply dimension reduction techniques to solve this problem and analyze the effect of this approach for prediction. Our experiment uses delayed Lorenz series; least squares support vector regression approximates the predictive function. The result shows that linearly preserving projection improves the prediction performance.

• Communications for Statistical Applications and Methods
• /
• v.28 no.1
• /
• pp.39-57
• /
• 2021

Time series prediction is an area of great interest to many people. Algorithms for time series prediction are widely used in many fields such as stock price, temperature, energy and weather forecast; in addtion, classical models as well as recurrent neural networks (RNNs) have been actively developed. After introducing the attention mechanism to neural network models, many new models with improved performance have been developed; in addition, models using attention twice have also recently been proposed, resulting in further performance improvements. In this paper, we consider time series prediction by introducing attention twice to an RNN model. The proposed model is a method that introduces H-attention and T-attention for output value and time step information to select useful information. We conduct experiments on stock price, temperature and energy data and confirm that the proposed model outperforms existing models.

• The KIPS Transactions:PartA
• /
• v.11A no.4
• /
• pp.243-250
• /
• 2004

Monitoring is used to see if a real-time system provides a service on time. Generally, monitoring for real-time focuses on investigating the current status of a real-time system. To support a stable performance of a real-time system, it should have not only a function to see the current status of real-time process but also a function to predict executions of real-time processes, however. The legacy prediction model has some limitation to apply it to a real-time monitoring. First, it performs a static prediction after a real-time process finished. Second, it needs a statistical pre-analysis before a prediction. Third, transition probability and data about clustering is not based on the current data. We propose the execution prediction model based on learning algorithm to solve these problems and apply it to real-time monitoring. This model gets rid of unnecessary pre-processing and supports a precise prediction based on current data. In addition, this supports multi-level prediction by a trend analysis of past execution data. Most of all, We designed the model to support dynamic prediction which is performed within a real-time process' execution. The results from some experiments show that the judgment accuracy is greater than 80% if the size of a training set is set to over 10, and, in the case of the multi-level prediction, that the prediction difference of the multi-level prediction is minimized if the number of execution is bigger than the size of a training set. The execution prediction model proposed in this model has some limitation that the model used the most simplest learning algorithm and that it didn't consider the multi-regional space model managing CPU, memory and I/O data. The execution prediction model based on a learning algorithm proposed in this paper is used in some areas related to real-time monitoring and control.