• Journal of Korea Port Economic Association
• /
• v.29 no.2
• /
• pp.239-253
• /
• 2013

Changes of a port's market share in the exports of domestic ports result from many interrelated factors. Therefore, the analysis of the export performance of a port should be put in perspective by analysing long periods to identify trends. This paper aims to show the development of competitiveness, product and geographical structure of the Busan Port's merchandise exports from 1995 to 2012 using constant-market shares (CMS) analysis. This article is relevant for Busan port because its export market shares have been showing disappointing path. The dynamic consideration of the CMS analysis, which the static indicators have been replaced by time series, helps to track all changes in the export structure and competitiveness of the Busan port over time. The long-term trend of the indicators suggests that it may be very hard for the Busan port to maintain its market share in the global environment. The advantage in competitiveness of the Busan port has vanished and the product and geographical structure effects show negative trends after 1995, pointing to vulnerability in the Busan port's exports.

• Journal of the Korean GEO-environmental Society
• /
• v.21 no.5
• /
• pp.5-11
• /
• 2020

Outliers detection and elimination included in field monitoring datum are essential for effective foundation of unusual movement, long and short range forecast of stability and future behavior to various structures. Integrated outlier analysis system for assessing long term time series data was developed in this study. Outlier analysis could be conducted in two step of primary analysis targeted at single dataset and second multi datasets analysis using synthesis value. Integrated outlier analysis system presents basic information for evaluating stability and predicting movement of structure combined with real-time safety management platform. Field application results showed increased correlation between synthesis value including similar sort of sensor showing constant trend and each single dataset. Various monitoring data in case of showing different trend can be used to analyse outlier through correlation-weighted value.

• Journal of Energy Engineering
• /
• v.23 no.4
• /
• pp.88-94
• /
• 2014

In this paper, Thermal Shock tests were performed varying the composition of the solder and ribbon thickness (A-type:0.2mm/60Sn40Pb, B-type:0.25mm/60Sn40Pb, C-type:0.2 /62Sn36Ag2Pb, D-type:0.25mm/62Sn36Ag2Pb) for evaluating the long-term reliability about Ribbon junction of Silicon solar cells. Thermal Shock test condition was performed during the 600cycles having $-40^{\circ}C{\sim}85^{\circ}C$ temperature range each 15 minutes; One cycle time was 30min. As a result, the initial efficiency of the A-type, B-type, and C, D-type were showed 15.0%, 15.4% and 15.8% respectively. After thermal shock test, the efficiency decreasing-rate of each type were as follow that A-type was 13.8%, B-Type was 15.4%. C-Type and D-Type was 15.3% and 16.2%, respectively. Also, degradation of surface changes and I-V characteristic curves were showed that the series resistance of the A, C-type was increased. Also, current lowering starting point of C-type shown 0.05volt[v] earlier than that of A-type. And B, D-type shown characteristics of composite lowering efficiency such as increase of series resistance, decrease of parallel resistance and cell damage. Therefore Initial solderability and efficiency of specimens using the solder with SnAgPb were superior. But, It has inferior the long-term reliability. The test was confirmed that as the ribbon thickness increases, long-term reliability of solar cell will decrease.

• Korean Journal of Remote Sensing
• /
• v.38 no.3
• /
• pp.265-282
• /
• 2022

Sea surface temperature (SST) is a factor that greatly influences ocean circulation and ecosystems in the Earth system. As global warming causes changes in the SST near the Korean Peninsula, abnormal water temperature phenomena (high water temperature, low water temperature) occurs, causing continuous damage to the marine ecosystem and the fishery industry. Therefore, this study proposes a methodology to predict the SST near the Korean Peninsula and prevent damage by predicting abnormal water temperature phenomena. The study area was set near the Korean Peninsula, and ERA5 data from the European Center for Medium-Range Weather Forecasts (ECMWF) was used to utilize SST data at the same time period. As a research method, Long Short-Term Memory (LSTM) algorithm specialized for time series data prediction among deep learning models was used in consideration of the time series characteristics of SST data. The prediction model predicts the SST near the Korean Peninsula after 1- to 7-days and predicts the high water temperature or low water temperature phenomenon. To evaluate the accuracy of SST prediction, Coefficient of determination (R²), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE) indicators were used. The summer (JAS) 1-day prediction result of the prediction model, R²=0.996, RMSE=0.119℃, MAPE=0.352% and the winter (JFM) 1-day prediction result is R²=0.999, RMSE=0.063℃, MAPE=0.646%. Using the predicted SST, the accuracy of abnormal sea surface temperature prediction was evaluated with an F1 Score (F1 Score=0.98 for high water temperature prediction in summer (2021/08/05), F1 Score=1.0 for low water temperature prediction in winter (2021/02/19)). As the prediction period increased, the prediction model showed a tendency to underestimate the SST, which also reduced the accuracy of the abnormal water temperature prediction. Therefore, it is judged that it is necessary to analyze the cause of underestimation of the predictive model in the future and study to improve the prediction accuracy.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.9
• /
• pp.1224-1230
• /
• 2020

Since the spread of smart phones, interest in wearable devices has increased and diversified, and is closely related to the lives of users, and has been used as a method for providing personalized services. In this paper, we propose a method to detect the user's behavior by applying information from a 3-axis acceleration sensor and a 3-axis gyro sensor embedded in a smartphone to a convolutional neural network. Human behavior differs according to the size and range of motion, starting and ending time, including the duration of the signal data constituting the motion. Therefore, there is a performance problem for accuracy when applied to a convolutional neural network as it is. Therefore, we proposed a Time-Division Feature Fusion Convolutional Neural Network (TDFFCNN) that learns the characteristics of the sensor data segmented over time. The proposed method outperformed other classifiers such as SVM, IBk, convolutional neural network, and long-term memory circulatory neural network.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.21 no.3
• /
• pp.135-145
• /
• 2019

Analysis of a long cycle or a trend of time series data based on a long-term observation would require comparability between data observed in the past and the present. In the present study, we proposed an approach to ensure the compatibility among the instruments used for the long-term observation, which would allow to secure continuity of the data. An open-path gas analyzer (Model LI-7500, LI-COR, Inc., USA) has been used for eddy covariance flux measurement in the Gwangneung deciduous forest for more than 10 years. The open-path gas analyzer was replaced by an enclosed-path gas analyzer (Model EC155, Campbell Scientific, Inc., USA) in July 2015. Before completely replacing the gas analyzer, the carbon dioxide ($CO_2$) and latent heat fluxes were collected using both gas analyzers simultaneously during a five-month period from August to December in 2015. It was found that the $CO_2$ fluxes were not significantly different between the gas analyzers under the condition that the daily mean temperature was higher than $0^{\circ}C$. However, the $CO_2$ flux measured by the open-path gas analyzer was negatively biased (from positive sign, i.e., carbon source, to 0 or negative sign, i.e., carbon neutral or sink) due to the instrument surface heating under the condition that the daily mean temperature was lower than $0^{\circ}C$. Despite applying the frequency response correction associated with tube attenuation of water vapor, the latent heat flux measured by the enclosed-path gas analyzer was on average 9% smaller than that measured by the open-path gas analyzer, which resulted in >20% difference of the sums over the study period. These results indicated that application of the additional air density correction would be needed due to the instrument heat and analysis of the long-term observational flux data would be facilitated by understanding the underestimation tendency of latent heat flux measurements by an enclosed-path gas analyzer.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.2 no.2
• /
• pp.69-78
• /
• 1999

In this paper, a neural network approach to forecast Korean regional precipitation is presented. We first analyze the characteristics of the conventional models for time series prediction, and then propose a new model and its learning method for the precipitation forecast. The proposed model is a layered network in which the outputs of a layer are buffered within a given period time and then fed fully connected to the upper layer. This study adopted the dual connections between two layers for the model. The network behavior and learning algorithm for the model are also described. The dual connection structure plays the role of the bias of the ordinary Multi-Layer Perceptron(MLP), and reflects the relationships among the features effectively. From these advantageous features, the model provides the learning efficiency in comparison with the FIR network, which is the most popular model for time series prediction. We have applied the model to the monthly and seasonal forecast of precipitation. The precipitation data and SST(Sea Surface Temperature) data for several decades are used as the learning pattern for the neural network predictor. The experimental results have shown the validity of the proposed model.

• Journal of Intelligence and Information Systems
• /
• v.17 no.3
• /
• pp.187-201
• /
• 2011

KOSPI200 index is the Korean stock price index consisting of actively traded 200 stocks in the Korean stock market. Its base value of 100 was set on January 3, 1990. The Korea Exchange (KRX) developed derivatives markets on the KOSPI200 index. KOSPI200 index futures market, introduced in 1996, has become one of the most actively traded indexes markets in the world. Traders can make profit by entering a long position on the KOSPI200 index futures contract if the KOSPI200 index will rise in the future. Likewise, they can make profit by entering a short position if the KOSPI200 index will decline in the future. Basically, KOSPI200 index futures trading is a short-term zero-sum game and therefore most futures traders are using technical indicators. Advanced traders make stable profits by using system trading technique, also known as algorithm trading. Algorithm trading uses computer programs for receiving real-time stock market data, analyzing stock price movements with various technical indicators and automatically entering trading orders such as timing, price or quantity of the order without any human intervention. Recent studies have shown the usefulness of artificial intelligent systems in forecasting stock prices or investment risk. KOSPI200 index data is numerical time-series data which is a sequence of data points measured at successive uniform time intervals such as minute, day, week or month. KOSPI200 index futures traders use technical analysis to find out some patterns on the time-series chart. Although there are many technical indicators, their results indicate the market states among bull, bear and flat. Most strategies based on technical analysis are divided into trend following strategy and non-trend following strategy. Both strategies decide the market states based on the patterns of the KOSPI200 index time-series data. This goes well with Markov model (MM). Everybody knows that the next price is upper or lower than the last price or similar to the last price, and knows that the next price is influenced by the last price. However, nobody knows the exact status of the next price whether it goes up or down or flat. So, hidden Markov model (HMM) is better fitted than MM. HMM is divided into discrete HMM (DHMM) and continuous HMM (CHMM). The only difference between DHMM and CHMM is in their representation of state probabilities. DHMM uses discrete probability density function and CHMM uses continuous probability density function such as Gaussian Mixture Model. KOSPI200 index values are real number and these follow a continuous probability density function, so CHMM is proper than DHMM for the KOSPI200 index. In this paper, we present an artificial intelligent trading system based on CHMM for the KOSPI200 index futures system traders. Traders have experienced on technical trading for the KOSPI200 index futures market ever since the introduction of the KOSPI200 index futures market. They have applied many strategies to make profit in trading the KOSPI200 index futures. Some strategies are based on technical indicators such as moving averages or stochastics, and others are based on candlestick patterns such as three outside up, three outside down, harami or doji star. We show a trading system of moving average cross strategy based on CHMM, and we compare it to a traditional algorithmic trading system. We set the parameter values of moving averages at common values used by market practitioners. Empirical results are presented to compare the simulation performance with the traditional algorithmic trading system using long-term daily KOSPI200 index data of more than 20 years. Our suggested trading system shows higher trading performance than naive system trading.

• Advances in environmental research
• /
• v.2 no.3
• /
• pp.203-227
• /
• 2013

Global demand for dwelling energy and implications of changing climatic conditions on buildings confront the built environment to build sustainable dwellings. This study investigates the variability of future climatic conditions on newly built detached dwellings in the UK. Series of energy modelling and simulations are performed on ten detached houses to evaluate and predict the impact of varying future climatic patterns on five building performance indicators. The study identifies and quantifies a consistent declining trend of building performance which is in consonance with current scientific knowledge of annual temperature change prediction in relations to long term climatic variation. The average percentage decrease for the annual energy consumption was predicted to be 2.80, 6.60 and 10.56 for 2020s, 2050s and 2080s time lines respectively. A similar declining trend in the case of annual natural gas consumption was 4.24, 9.98 and 16.1, and that for building emission rate and heating demand were 2.27, 5.49 and 8.72 and 7.82, 18.43 and 29.46 respectively. The study further analyse future heating and cooling demands of the three warmest months of the year and ascertain future variance in relative humidity and indoor temperature which might necessitate the use of room cooling systems to provide thermal comfort.

• Structural Monitoring and Maintenance
• /
• v.7 no.2
• /
• pp.109-124
• /
• 2020

Benefiting from the massive monitoring data collected by the Structural health monitoring (SHM) system, scholars can grasp the complex environmental effects and structural state during structure operation. However, the monitoring data is often missing due to sensor faults and other reasons. It is necessary to study the recovery method of missing monitoring data. Taking the structural temperature monitoring data of Nanjing Dashengguan Yangtze River Bridge as an example, the long short-term memory (LSTM) network-based recovery method for missing structural temperature data is proposed in this paper. Firstly, the prediction results of temperature data using LSTM network, support vector machine (SVM), and wavelet neural network (WNN) are compared to verify the accuracy advantage of LSTM network in predicting time series data (such as structural temperature). Secondly, the application of LSTM network in the recovery of missing structural temperature data is discussed in detail. The results show that: the LSTM network can effectively recover the missing structural temperature data; incorporating more intact sensor data as input will further improve the recovery effect of missing data; selecting the sensor data which has a higher correlation coefficient with the data we want to recover as the input can achieve higher accuracy.