• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.46 no.2
• /
• pp.186-194
• /
• 2013

We compiled and analyzed long-term time-series data collected in Korea to evaluate changes in oceanographic conditions and marine ecosystems near Jeju Island ($33^{\circ}00^{\prime}-34^{\circ}00^{\prime}\;N$, $125^{\circ}30^{\prime}-127^{\circ}30^{\prime}\;E$) from 1981 to 2010. Environmental data included depth-specific time series of temperature and salinity that have been measured bimonthly since 1961 in water columns at 175 fixed stations along 22 oceanographic lines in Korean waters by the National Fisheries Research & Development Institute, and time series of estimated volume transport of the Tsushima Warm Current (TWC) and Korea Strait Bottom Cold Water (KSBCW) for the period from 1961 to 2008. We analyzed the species composition in terms of biomass of fish species caught by Korean fishing vessels in the waters near Jeju Island (1981-2010). Data were summarized and related to environmental changes using canonical correspondence analysis (CCA). The CCA detected major shifts in fish community structure between 1982 and 1983 and between 1990 and 1992; the dominant species were a filefish during 1981-1992 and chub mackerel from 1992 to 2007. CCA suggested that water temperature and salinity in the mixed layer and the volume transport of the TWC and the KSBCW were significantly related to the long-term changes in the fish community in the waters off Jeju Island. Fish community shifts seemed to be related to the well-established 1989 regime shift in the North Pacific. Further studies are required to elucidate the mechanisms driving climate change effects on the thermal windows and habitat ranges of commercial species to develop fisheries management plans based on reliable projections of long-term changes in the oceanographic conditions in waters off Jeju Island.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2017.11a
• /
• pp.50-53
• /
• 2017

Not only growth of importance to understanding economic trends, but also the prediction to overcome the uncertainty is coming up for long-term maritime recession. This paper discussed about the prediction of BDI with artificial neural networks (ANN). ANN is one of emerging applications that can be the finest solution to the knotty problems that may not easy to achieve by humankind. Proposed a prediction by implementing neural networks that have recurrent architecture which are a Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM). And for the reason of comparison, trained Multi Layer Perceptron (MLP) from 2009.04.01 to 2017.07.31. Also made a comparison with conventional statistics, prediction tools; ARIMA. As a result, recurrent net, especially RNN outperformed and also could discover the applicability of LSTM to specific time-series (BDI).

• Korean Journal of Remote Sensing
• /
• v.36 no.4
• /
• pp.515-525
• /
• 2020

This study investigates the potential of bidirectional long short-term memory (Bi-LSTM) for efficient modeling of temporal information in crop classification using multitemporal remote sensing images. Unlike unidirectional LSTM models that consider only either forward or backward states, Bi-LSTM could account for temporal dependency of time-series images in both forward and backward directions. This property of Bi-LSTM can be effectively applied to crop classification when it is difficult to obtain full time-series images covering the entire growth cycle of crops. The classification performance of the Bi-LSTM is compared with that of two unidirectional LSTM architectures (forward and backward) with respect to different input image combinations via a case study of crop classification in Anbadegi, Korea. When full time-series images were used as inputs for classification, the Bi-LSTM outperformed the other unidirectional LSTM architectures; however, the difference in classification accuracy from unidirectional LSTM was not substantial. On the contrary, when using multitemporal images that did not include useful information for the discrimination of crops, the Bi-LSTM could compensate for the information deficiency by including temporal information from both forward and backward states, thereby achieving the best classification accuracy, compared with the unidirectional LSTM. These case study results indicate the efficiency of the Bi-LSTM for crop classification, particularly when limited input images are available.

• Journal of Korean Academy of Nursing Administration
• /
• v.20 no.1
• /
• pp.95-105
• /
• 2014

Purpose: The purpose of this study was to examine trends in number of nursing staff and skill mix. Methods: Nursing staff and skill mix were measured using the number of nursing staff including nurse aids and registered nurses per bed. Descriptive and panel data regression analyses were conducted using data on long-term care hospitals which included yearly series data from 2006 to 2010 for 119 hospitals. Results: The number of nursing staff per bed increased significantly but percentage of registered nurses decreased significantly from 2007 to 2010. The regression model explained this variation as much as 34.9% and 43.8%. Conclusion: The results showed that in long-term care hospitals there were more nurse aids employed instead of registered nurses after the implemention of differentiated inpatient nursing fees. Thus clarifying the job descriptions for nurses and nurse aids is needed and appropriate hospital incentive policies should be implemented.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.12
• /
• pp.7018-7024
• /
• 2014

This study examined the squared returns and absolute returns of KOSPI 200 with GPH (Geweke and Porter-Hudak, 1983) estimators. GPH was estimated by the long-term memory preserving time series parameter d in linear regression. This called the GPH estimator, which depends on a bandwidth m. m was decided by confirming the stable section of the point estimate by validating the track of the GPH estimator according to the value of m. The result suggests that by satisfying 0< d <0.5, the squared returns and absolute returns of KOPI 200 retains long-term memory.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2005.03a
• /
• pp.561-568
• /
• 2005

The factors affecting the long-term design strength of geogrid can be classified into factors on creep deformation, installation damage, temperature, chemical degradation and biological degradation. Especially, creep deformation and installation damage are considered as main factors to determine the long-term design strength of geogrid. Current practice in the design of reinforced soil is to calculate the long-term design strength of a reinforcement damaged during installation by multiplying the two partial safety factors, $RF_{ID} and RF_{CR}$. This method assumes that there is no synergy effect between installation damage and creep deformation of geogrids. Therefore, this paper describes the results of a series of experimental study, which are carried out to assess the combined effect of installation damage and creep deformation for the long-term design strength of geogrid reinforcement. The results of this study show that the tensile strength reduction factors, RF, considering combined effect between installation damage and creep deformation is less than that calculated by the current design method.

• Smart Structures and Systems
• /
• v.21 no.2
• /
• pp.171-185
• /
• 2018

Maintenance of deteriorated bridge structures has always been one of the challenging issues in developing countries as it is directly related to daily life of people including trade and economy. An effective maintenance strategy is highly dependent on timely inspections on the bridge health condition. This study is intended to investigate an approach for detecting bridge damage for the long-term health monitoring by use of copula theory. Long-term measured data for the seven-span plate-Gerber bridge is investigated. Autoregressive time series models constructed for the observed accelerations taken from the bridge are utilized for the computation of damage indicator for the bridge. The copula model is used to analyze the statistical changes associated with the modal parameters. The changes in the modal parameters with the time are identified by the copula statistical properties. Applicability of the proposed method is also discussed based on a comparison study among other approaches.

• The Journal of Bigdata
• /
• v.7 no.2
• /
• pp.217-224
• /
• 2022

Since online shopping has become common, people can easily buy fashion goods anytime, anywhere. Therefore, consumers quickly respond to various environmental variables such as weather and sales prices. Therefore, utilizing big data for efficient inventory management has become very important in the fashion industry. In this paper, the changes in sales volume of fashion goods due to changes in temperature is analyzed via the proposed big data analysis algorithm by utilizing actual big data from Korean fashion company 'A'. According to the simulation results, it was confirmed that Bidirectional-LSTM(Bi-LSTM) compared to LSTM(Long Short-Term Memory) takes more simulation time about more than 50%, but the prediction accuracy of non-periodic time series data such as clothing product sales data is the same.

• Communications for Statistical Applications and Methods
• /
• v.31 no.2
• /
• pp.213-234
• /
• 2024

In recent decades, increasing research attention has been directed toward predicting the price of stocks in financial markets using deep learning methods. For instance, recurrent neural network (RNN) is known to be competitive for datasets with time-series data. Long short term memory (LSTM) further improves RNN by providing an alternative approach to the gradient loss problem. LSTM has its own advantage in predictive accuracy by retaining memory for a longer time. In this paper, we combine both supervised and unsupervised dimension reduction methods with LSTM to enhance the forecasting performance and refer to this as a dimension reduction based LSTM (DR-LSTM) approach. For a supervised dimension reduction method, we use methods such as sliced inverse regression (SIR), sparse SIR, and kernel SIR. Furthermore, principal component analysis (PCA), sparse PCA, and kernel PCA are used as unsupervised dimension reduction methods. Using datasets of real stock market index (S&P 500, STOXX Europe 600, and KOSPI), we present a comparative study on predictive accuracy between six DR-LSTM methods and time series modeling.

• Geomechanics and Engineering
• /
• v.11 no.4
• /
• pp.531-552
• /
• 2016

The greenschist in the Jinping II Hydropower Station in southwest China exhibits continuous creep behaviour because of the geological conditions in the region. This phenomenon illustrates the time-dependent deformation and progressive damage that occurs after excavation. In this study, the responses of greenschist to stress over time were determined in a series of laboratory tests on samples collected from the access tunnel walls at the construction site. The results showed that the greenschist presented time-dependent behaviour under long-term loading. The samples generally experienced two stages: transient creep and steady creep, but no accelerating creep. The periods of transient creep and steady creep increased with increasing stress levels. The long-term strength of the greenschist was identified based on the variation of creep strain and creep rate. The ratio of long-term strength to conventional strength was around 80% and did not vary much with confining pressures. A quantitative method for predicting the failure period of greenschist, based on analysis of the stress-strain curve, is presented and implemented. At a confining pressure of 40 MPa, greenschist was predicted to fail in 5000 days under a stress of 290 MPa and to fail in 85 days under the stress of 320 MPa, indicating that the long-term strength identified by the creep rate and creep strain is a reliable estimate.