• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1035-1046
• /
• 2022

This study evaluated the applicability of multi-resolution data fusion for land-cover classification. In the applicability evaluation, a spatial time-series geostatistical deconvolution/fusion model (STGDFM) was applied as a multi-resolution data fusion model. The study area was selected as some agricultural lands in Iowa State, United States. As input data for multi-resolution data fusion, Moderate Resolution Imaging Spectroradiometer (MODIS) and Landsat satellite images were used considering the landscape of study area. Based on this, synthetic Landsat images were generated at the missing date of Landsat images by applying STGDFM. Then, land-cover classification was performed using both the acquired Landsat images and the STGDFM fusion results as input data. In particular, to evaluate the applicability of multi-resolution data fusion, two classification results using only Landsat images and using both Landsat images and fusion results were compared and evaluated. As a result, in the classification result using only Landsat images, the mixed patterns were prominent in the corn and soybean cultivation areas, which are the main land-cover type in study area. In addition, the mixed patterns between land-cover types of vegetation such as hay and grain areas and grass areas were presented to be large. On the other hand, in the classification result using both Landsat images and fusion results, these mixed patterns between land-cover types of vegetation as well as corn and soybean were greatly alleviated. Due to this, the classification accuracy was improved by about 20%p in the classification result using both Landsat images and fusion results. It was considered that the missing of the Landsat images could be compensated for by reflecting the time-series spectral information of the MODIS images in the fusion results through STGDFM. This study confirmed that multi-resolution data fusion can be effectively applied to land-cover classification.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.26 no.5
• /
• pp.127-134
• /
• 2022

In this study, RCPTs (Rapid Chloride Penetration Test) were performed for fly ash concrete with curing age of 4 ~ 6 years. The concrete mixtures were prepared with 3 levels of water to binder ratio (0.37, 0.42, and 0.47) and 2 levels of substitution ratio of fly ash (0 and 30%), and the improved passed charges of chloride ion behavior were quantitatively analyzed. Additionally, the results were trained through the univariate time series models consisted of GRU (Gated Recurrent Unit) algorithm and those from the models were evaluated. As the result of the RCPT, fly ash concrete showed the reduced passed charges with period and an more improved resistance to chloride penetration than OPC concrete. At the final evaluation period (6 years), fly ash concrete showed 'Very low' grade in all W/B (water to binder) ratio, however OPC concrete showed 'Moderate' grade in the condition with the highest W/B ratio (0.47). The adopted algorithm of GRU for this study can analyze time series data and has the advantage like operation efficiency. The deep learning model with 4 hidden layers was designed, and it provided a reasonable prediction results of passed charge. The deep learning model from this study has a limitation of single consideration of a univariate time series characteristic, but it is in the developing process of providing various characteristics of concrete like strength and diffusion coefficient through additional studies.

• Journal of IKEEE
• /
• v.27 no.4
• /
• pp.486-493
• /
• 2023

In this paper, we propose an automatic hand gesture area extraction and recognition technique using FMCW radar-based point cloud and LSTM. The proposed technique has the following originality compared to existing methods. First, unlike methods that use 2D images as input vectors such as existing range-dopplers, point cloud input vectors in the form of time series are intuitive input data that can recognize movement over time that occurs in front of the radar in the form of a coordinate system. Second, because the size of the input vector is small, the deep learning model used for recognition can also be designed lightly. The implementation process of the proposed technique is as follows. Using the distance, speed, and angle information measured by the FMCW radar, a point cloud containing x, y, z coordinate format and Doppler velocity information is utilized. For the gesture area, the hand gesture area is automatically extracted by identifying the start and end points of the gesture using the Doppler point obtained through speed information. The point cloud in the form of a time series corresponding to the viewpoint of the extracted gesture area is ultimately used for learning and recognition of the LSTM deep learning model used in this paper. To evaluate the objective reliability of the proposed technique, an experiment calculating MAE with other deep learning models and an experiment calculating recognition rate with existing techniques were performed and compared. As a result of the experiment, the MAE value of the time series point cloud input vector + LSTM deep learning model was calculated to be 0.262 and the recognition rate was 97.5%. The lower the MAE and the higher the recognition rate, the better the results, proving the efficiency of the technique proposed in this paper.

• The Journal of Bigdata
• /
• v.8 no.2
• /
• pp.165-175
• /
• 2023

LNG is a representative imported cargo at Incheon Port and has a relatively high contribution to the increase/decrease in overall cargo volume at Incheon Port. In addition, in the view point of nationwide, LNG is the one of the most important key resource to supply the gas and generate electricity. Thus, it is very essential to identify the factors that have impact on the demand fluctuation and build the appropriate forecasting model, which present the basic information to make balance between supply and demand of LNG and establish the plan for power generation. In this study, different to previous research based on macroscopic annual data, the weekly demand of LNG is converted from the cargo volume unloaded by LNG carriers. We have identified the periodicity and correlations among internal and external factors of demand variability. We have identified the input factors for predicting the LNG demand such as seasonality of weekly cargo volume, the peak power demand, and the reserved capacity of power supply. In addition, in order to predict LNG demand, considering the characteristics of the data, time series prediction with weekly LNG cargo volume as a dependent variable and prediction through an artificial neural network model were made, the suitability of the predictions was verified, and the optimal model was established through error comparison between performance and estimates.

• Journal of Ocean Engineering and Technology
• /
• v.25 no.1
• /
• pp.49-55
• /
• 2011

The EG/AD/S model ice, originally developed by Timco (1986), was selected as the primary model ice material for the newly built MOERI Ice Model Basin in Korea. However, the existence of a sugar component in the EG/AD/S mixture may cause a serious maintenance problem, as described in certain references. This study focuses on the tests of the mechanical properties of the EG/AD/S and the EG/AD model ice. In order to understand the influence of sugar in the original EG/AD/S model ice and to find a possible substitute for sugar, a series of tests with the EG/AD model ice were performed, and the results were compared to those of the EG/AD/S model ice. The relatively large size of the MOERI Ice Model Basin made it difficult to control the initial strength of model ice, so it took a much longer time to achieve the target strength. In order to obtain a lower strength and stiffness for the model ice, the amount of chemical additives may be varied to achieve the desired strength level. This paper is a preliminary study aimed at seeking a possible substitute for the original EG/AD/S model ice for utilization in a large-scale ice tank. To understand the influence of sugar in the original EG/AD/S model ice, the mechanical properties of the EG/AD/S and EG/AD model ice, such as flexural strength, compressive strength, and elastic modulus, were tested in the laboratory condition and compared to each other. The warm-up procedure seems to be an important factor to reduce ice strength in the tests, so it is discussed in detail.

• Journal of Ship and Ocean Technology
• /
• v.11 no.3
• /
• pp.1-13
• /
• 2007

A semi-submersible drilling rig is regarded as one of the typical offshore structures operated in the field with moderate environments such as the Gulf of Mexico, Brazil, and West Africa. Its typical roll and pitch natural periods are around 30 seconds, which avoids prevailing regions of the wave energy spectrum, and their responses in waves are quite acceptable for common operation conditions. But large roll and pitch motions can be induced by wave difference frequency energy spectrum if the metacentric heights of a semi-submersible decrease to small values in some loading conditions, and it is because the roll and pitch natural periods increase and approach to the region where the spectral density of the low frequency wave drift moment has significant value. This paper describes the low frequency roll motion of a semi-submersible that are excited by the wave 2nd order difference frequency energy by a series of model experiments. From the model tests with several different initial metacentric heights (GM), it was observed that a semi-submersible can experience large roll motion due to the wave group spectrum.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.4 no.2
• /
• pp.130-137
• /
• 1992

The previous model of Inchon Bay (Choi 1980) was refined to hindcast/forecast the tides in the Inchon Bay by prescribing the 8 tidal constituents at the open boundaries. A series of hindcast was performed for the period of meterologically calm condition and the simulated results were compared with limited observation showing the reasonable agreements. Preliminary stage of real-time tidal prediction over the whole Inchon Bay were briefly outlined for practical purposes. The established model were further improved by dynamically interfacing, a one dimensional representation of the Han River system. With this model the tidal propagation in the Han River were computed and simulation of recent September. 1990 flood were performed. Discussion for further model development are also described.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.14 no.2
• /
• pp.91-97
• /
• 2014

Chaotic dynamics is an active research area in fields such as biology, physics, sociology, psychology, physiology, and engineering. Interest in chaos is also expanding to the social sciences, such as politics, economics, and societal events prediction. Most people pursue happiness, both spiritual and physical in many cases. However, happiness is not easy to define, because people differ in how they perceive it. Happiness can exist in mind and body. Therefore, we need to be happy in both simultaneously to achieve optimal happiness. To do this, we need to synchronize mind and body. In this paper, we propose a chaotic synchronization method in a mathematical model of happiness organized by a second-order ordinary differential equation with external force. This proposed mathematical happiness equation is similar to Duffing's equation, because it is derived from that equation. We introduce synchronization method from our mathematical happiness model by using the derived Duffing equation. To achieve chaotic synchronization between the human mind and body, we apply an idea of mind/body unity originating in Oriental philosophy. Of many chaotic synchronization methods, we use only coupled synchronization, because this method is closest to representing mind/body unity. Typically, coupled synchronization can be applied only to non-autonomous systems, such as a modified Duffing system. We represent the result of synchronization using a differential time series mind/body model.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.9 no.1
• /
• pp.131-136
• /
• 2014

In this paper, we develop a fashion products demand forecasting algorithm using ARIMA model and Wavelet Neural Networks model. To show effectiveness of the proposed method, we analyzed characteristics of time-series data collected in "H" company during 2008-2012 and then performed the proposed method through various analyses. As noted in experimental results, the performance of three types model such as ARIMA, Wavelet Neural Networks and ARIMA + Wavelet Neural Networks show 5.179%, 4.553%, and 4.448.% with respect to MAPE(Mean Absolute Percentage Error), respectively. Thus, it is noted that the proposed method can be used to predict fashion products demand for efficient of operation.

• Steel and Composite Structures
• /
• v.37 no.3
• /
• pp.371-390
• /
• 2020

One of the most common strategies for retrofitting as-built reinforced concrete (RC) columns is to enlarge the existing section through the application of a new concrete layer reinforced by both steel transverse and longitudinal reinforcements. The present study was dedicated to developing a comprehensive model to predict the seismic behavior of as-built RC jacketed columns. For this purpose, a new sectional model was developed to perform moment-curvature analysis coupled by the plastic hinge method. In this analysis-oriented model, new methodologies were suggested to address the impacts of axial, flexural and shear mechanisms, variable confining pressure, eccentric loading, longitudinal bar buckling, and varying axial load. To consider the effective interaction between core and jacket, the monolithic factor approach was adopted to extent the response of the monolithic columns to that of a respective RC jacket strengthened column. Next, parametric studies were implemented to examine the effectiveness of the main parameters of the RC jacket strategy in retrofitting as-built RC columns. Ultimately, the reliability of the developed analytical model was validated against a series of experimental results of as-built and retrofitted RC columns.