• Journal of the Korean Geotechnical Society
• /
• v.40 no.2
• /
• pp.65-79
• /
• 2024

This study employs traditional statistical auto-regressive integrated moving average (ARIMA) and deep learning-based long short-term memory (LSTM) models to predict the deformation of earth retaining walls using inclinometer data from excavation sites. It compares the predictive capabilities of both models. The ARIMA model excels in analyzing linear patterns as time progresses, while the LSTM model is adept at handling complex nonlinear patterns and long-term dependencies in the data. This research includes preprocessing of inclinometer measurement data, performance evaluation across various data lengths and input conditions, and demonstrates that the LSTM model provides statistically significant improvements in prediction accuracy over the ARIMA model. The findings suggest that LSTM models can effectively assess the stability of retaining walls at excavation sites. Additionally, this study is expected to contribute to the development of safety monitoring systems at excavation sites and the advancement of time series prediction models.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.11 no.2
• /
• pp.34-39
• /
• 2012

In this study, the friction welding experiment was performed by using the design of experiment. And the signal data acquired by acoustic emission sensor were analyzed to predict the tensile strength of friction welding part at friction welding process for AZ31 magnesium alloy. A dimensionless coefficient($\phi_{AE}$), which consisted in the square of AE rms and variance, was defined as the characteristic of friction welding and the prediction equation was obtained by using linear regression. As the result of analysis, it was seen that the correlation between predicted and measured values became very close and on-line prediction of the ensile strength was possible in friction welding part.

• Journal of Fashion Business
• /
• v.11 no.3
• /
• pp.46-58
• /
• 2007

The purpose of this study was to identify the physical surroundings and the salesperson's service in apparel stores, and to examine their effects on customer satisfaction and the intention to repurchase. The data was collected from a questionnaire conducted on 312 female adults who had just finished shopping, and was analyzed by frequency analysis, factor analysis, reliability analysis, regressive analysis and ANOVA analysis with SPSS 10.0. The results were as follows: (1) As a result of the factor analysis, five factors were identified with regard to physical surroundings: spatial layout and functionality, presentation and aesthetics, ambience, convenience, and information. The factors pertaining to the salesperson's service in apparel stores were divided into four dimensions: knowledge and assurance, convenience and responsiveness, etiquette, and empathy. (2) As far as physical surroundings are concerned, spatial layout and functionality, presentation and aesthetics, ambience, and convenience were all found to influence customer satisfaction. In terms of salesperson's service, convenience and responsiveness, etiquette, and empathy each had an influence on customer satisfaction. (3) Furthermore, physical surroundings and the salesperson's service influenced the intention to repurchase. The intention to repurchase is influenced by spatial layout and functionality, ambience, convenience, and information with regard to physical surroundings, by knowledge and assurance, convenience and responsiveness, and empathy with regard to the salesperson's service. (4) It was revealed that the significance of the physical surroundings and salesperson service factors varies depending on the consumer's age, level of education, and income.

• Journal of Korea Water Resources Association
• /
• v.50 no.9
• /
• pp.627-635
• /
• 2017

It is required to estimate reliable design floods for hydraulic structures in order to respond more effectively to recent climate change. In this study, differences of design floods that were estimated the flood frequency analysis (FFA) and the design rainfall-runoff analysis (DRRA) were analyzed. In Korea, due to lack of measured flood data, the DRRA method is used in practice to determine the design floods. However, assuming the design floods estimated by the FFA as true values, the DRRA method over estimated the design floods by 79%. Thus, this study proposed a practical method to estimated design flood in ungauaged watersheds through regressive adjustment of flood quantiles estimated from the DRRA method. To this end, after investigating the differences between design floods acquired from the FFA and the DRRA method, nonlinear regression analyses were performed to develop the adjustment formulas for 8 large-dam watersheds. Applying the adjustment formula, the accuracy was improved by 65.0% on average over the DRRA method. In addition, when considering the watershed size, the adjustment formula increases the accuracy by 2.1%p on average over when not considering the watershed size.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.38 no.2
• /
• pp.349-356
• /
• 2018

This paper attempts to develop a connection model based on FE analysis that can be applied to the evaluation of earthquake fragility of Steel Storage Racks lacking research in Korea. In order to accomplish this goal, shaking table tests, modal tests, and various member tests (8 case, push-over test) for structural members have been conducted to understand the behavior of steel storage racks. Based on the experimental results, detailed modeling of the joints was conducted using the NX-Nastran program in order to develop a connection model for Steel storage racks to be applied to the seismic vulnerability assessment. Especially, surface to surface contact element and spring element are applied to simulate the connection between the column member and the beam member connected by the simple latch method. Spring element model developed and applied ARX (Auto Regressive eXogenous) based mathematical model. The simulation results based on the FE model showed excellent reliability with a mutual error rate of less than 8% when compared with the member test results. As a result, it was confirmed that the FE model based connection model developed in the study can be applied to the analytical model for the seismic vulnerability assessment of Steel storage racks.

• ETRI Journal
• /
• v.26 no.6
• /
• pp.622-634
• /
• 2004

In this paper, we discuss the design problem and the robustness of space-frequency trellis codes (SFTCs) for multiple input multiple output, orthogonal frequency division multiplexing (MIMO-OFDM) systems. We find that the channel constructed by the consecutive subcarriers of an OFDM block is a correlated fading channel with the regular correlation function of the number and time delay of the multipaths. By introducing the first-order auto-regressive model, we decompose the correlated fading channel into two independent components: a slow fading channel and a fast fading channel. Therefore, the design problem of SFTCs is converted into the joint design in both slow fading and fast fading channels. We present an improved design criterion for SFTCs. We also show that the SFTCs designed according to our criterion are robust against the multipath time delays. Simulation results are provided to confirm our theoretic analysis.

• Proceedings of the KSRS Conference
• /
• 1999.11a
• /
• pp.429-432
• /
• 1999

Vegetation cover classification is examined based on a time series NOAA/AVHRR data. Time series data analysis methods including Fourier transform, Auto-Regressive (AR) model and temporal signature similarity matching are developed to extract phenological features of vegetation from a time series NDVI data from NOAA/AVHRR and to classify vegetation types. In the Fourier transform method, typical three spectral components expressing the phenological features of vegetation are selected for classification, and also in the AR model method AR coefficients are selected. In the temporal signature similarity matching method a new index evaluating the similarity of temporal pattern of the NDVI is introduced for classification.

• THE INTERNATIONAL COMMERCE & LAW REVIEW
• /
• v.34
• /
• pp.135-156
• /
• 2007

Trade Portal Site(TPS) is one of the essential tools which can make it possible for small and medium enterprises(SMEs) to perform international trade activity more efficiently using newest information and communication technology including the Internet. Therefore, Korean SMEs need to utilize TPS more actively to enhance their export competitiveness. In this context, this article analyzes the determinants of export performances of Korean SMEs in utilizing the service of TPS based on the Service Quality Model. As a result of an empirical research by using regressive analysis, various measures of service reliability such as reliability, empathy, and tangibilities have positive effects on SMEs export performance in utilizing TPS. These results provides many useful implications to the TPS managers, e-trade related government agency, along with managers of SMEs using TPS.

• Industrial Engineering and Management Systems
• /
• v.13 no.4
• /
• pp.357-368
• /
• 2014

Since its birth in 1993, fuzzy time series have seen different classes of models designed and applied, such as fuzzy logic relation and rule-based models. These models have both advantages and disadvantages. The major drawbacks with these two classes of models are the difficulties encountered in identification and analysis of the model. Therefore, there is a strong need to explore new alternatives and this is the objective of this paper. By transforming a fuzzy number to a real number via integrating the inverse of the membership function, new autoregressive models can be developed to fit the observation values of a fuzzy time series. With the new models, the issues of model identification and parameter estimation can be addressed; and trends, seasonalities and multivariate fuzzy time series could also be modeled with ease. In addition, asymptotic behaviors of fuzzy time series can be inspected by means of characteristic equations.

• Journal of Korean Society for Atmospheric Environment
• /
• v.27 no.3
• /
• pp.358-366
• /
• 2011

The purpose of this study was to analyze the monthly and seasonal PM10 data using the Autoregressive Error (ARE) model at the southern part of the Gyeonggi-Do, Pyeongtaek monitoring site in Korea. In the ARE model, six meteorological variables and four pollution variables are used as the explanatory variables. The six meteorological variables are daily maximum temperature, wind speed, amount of cloud, relative humidity, rainfall, and global radiation. The four air pollution variables are sulfur dioxide ($SO_2$), nitrogen dioxide ($NO_2$), carbon monoxide (CO), and ozone ($O_3$). The result shows that monthly ARE models explained about 17~49% of the PM10 concentration. However, the ARE model could be improved if we add the more explanatory variables in the model.