• Journal of the Korean earth science society
• /
• v.32 no.4
• /
• pp.388-401
• /
• 2011

Asian dust was observed a total of 66 times in the springtime during the period from 2002 to 2010, with 26 cases in March, 23 cases in April and 17 cases in May. This study investigates a Asian dust episode that occurred during the period from 22 to 25 May 2010, based on synoptic weather patterns, wind vector at 850 hPa, relative humidity at 1000 hPa, Jet streams and wind vector at 300 hPa, PM10 concentration in Korea and satellite imagery. In this case, Asian dust originated on 22 May along the rear of a developing low pressure system in Mongolia. The Asian dust was then transported southeastward and bypassed the Korea peninsula from 23 to 24 May, before reaching Japan on 25 May. Jet streams on 24 May bypassed the Korean peninsula and induced the development of a surface low pressure centered over the peninsula. The resulting air flow was critical to the trajectory of the Asian dust, which likewise bypassed the Korean peninsula. 72-hour backward trajectory data reveal that the Shandong Peninsula and the East China Sea were the points of origin for the air flows that swept through the Japanese sites where Asian dust was observable to the naked eay. The Asian dust pathway is ascertained by horizontal distribution of the Asian dust of RGB imagery from MODIS satellites which captured the Asian dust moving over the Shandong Peninsula, the East China Sea, and northwest of the Kyushu region in Japan. Since the synoptic pattern and the transport way of the Asian dust case are far from typical ones, which Asian dust forecasting technique has long been based on, this study can be good example of exceptional Asian dust pattern and it will be used for more accurate Asian dust forecasting.

• The Journal of Bigdata
• /
• v.4 no.2
• /
• pp.1-12
• /
• 2019

As Artificial Intelligence (AI) technology develops, it is applied to various fields such as image, voice, and text. AI has shown fine results in certain areas. Researchers have tried to predict the stock market by utilizing artificial intelligence as well. Predicting the stock market is known as one of the difficult problems since the stock market is affected by various factors such as economy and politics. In the field of AI, there are attempts to predict the ups and downs of stock price by studying stock price patterns using various machine learning techniques. This study suggest a way of predicting stock price patterns based on the Convolutional Neural Network(CNN) among machine learning techniques. CNN uses neural networks to classify images by extracting features from images through convolutional layers. Therefore, this study tries to classify candlestick images made by stock data in order to predict patterns. This study has two objectives. The first one referred as Case 1 is to predict the patterns with the images made by the same-day stock price data. The second one referred as Case 2 is to predict the next day stock price patterns with the images produced by the daily stock price data. In Case 1, data augmentation methods - random modification and Gaussian noise - are applied to generate more training data, and the generated images are put into the model to fit. Given that deep learning requires a large amount of data, this study suggests a method of data augmentation for candlestick images. Also, this study compares the accuracies of the images with Gaussian noise and different classification problems. All data in this study is collected through OpenAPI provided by DaiShin Securities. Case 1 has five different labels depending on patterns. The patterns are up with up closing, up with down closing, down with up closing, down with down closing, and staying. The images in Case 1 are created by removing the last candle(-1candle), the last two candles(-2candles), and the last three candles(-3candles) from 60 minutes, 30 minutes, 10 minutes, and 5 minutes candle charts. 60 minutes candle chart means one candle in the image has 60 minutes of information containing an open price, high price, low price, close price. Case 2 has two labels that are up and down. This study for Case 2 has generated for 60 minutes, 30 minutes, 10 minutes, and 5minutes candle charts without removing any candle. Considering the stock data, moving the candles in the images is suggested, instead of existing data augmentation techniques. How much the candles are moved is defined as the modified value. The average difference of closing prices between candles was 0.0029. Therefore, in this study, 0.003, 0.002, 0.001, 0.00025 are used for the modified value. The number of images was doubled after data augmentation. When it comes to Gaussian Noise, the mean value was 0, and the value of variance was 0.01. For both Case 1 and Case 2, the model is based on VGG-Net16 that has 16 layers. As a result, 10 minutes -1candle showed the best accuracy among 60 minutes, 30 minutes, 10 minutes, 5minutes candle charts. Thus, 10 minutes images were utilized for the rest of the experiment in Case 1. The three candles removed from the images were selected for data augmentation and application of Gaussian noise. 10 minutes -3candle resulted in 79.72% accuracy. The accuracy of the images with 0.00025 modified value and 100% changed candles was 79.92%. Applying Gaussian noise helped the accuracy to be 80.98%. According to the outcomes of Case 2, 60minutes candle charts could predict patterns of tomorrow by 82.60%. To sum up, this study is expected to contribute to further studies on the prediction of stock price patterns using images. This research provides a possible method for data augmentation of stock data.

• 한국해양학회지
• /
• v.30 no.6
• /
• pp.550-564
• /
• 1995

The temporal and spatial characteristics of wind fields over the neighbouring seas of the Korean peninsula are investigated using 10-years daily wind data during 1978${\sim}$1987 which have been spatially smoothed and low-pass filtered. Long term annual and monthly means are examined for synoptic patterns and spectral analyses are made for temporal variability and spatial coherence. Spatial patterns of the annual mean wind stress and curl have a strong resemblance with those of monthly means during the winter season. Two outstanding periodicities are observed at 1 and 2 cycles per year. The synoptic winds over the study area are highly coherent at both the annual and semi-annual periodicities. However, each basin has its own characteristic spatial pattern. For instance, the prevailing wind during the winter season is northerIy over the northern East Sea (ES), Yellow Sea (YS), and northern East China Sea (ECS), while it is northwesterly over the southern ES and northesterly over the northern ES and southern ECS. At the same time, the wind stress curl is positive over the northern ES and southern ECS, while it is negative over the southern ES, YS and northern ECS. On the other hand, the wind field during the summer season, with its strength being much reduced, is completely different from that during the winter season, and frequent passage of tropical storms provokes large temporal variability over ECS. One remarkable point is that the annual cycle, dominated by the Siberian High, tends to propagate from northeast to southwest, i.e., from northern 25 toward southern ES, YS and ECS, while the semi-annual cycle propagates in the opposite direction, from southwest to northeast. The semi-annual periodicity may reflect development of extratropical cyclones in spring and fall which frequently cross the Korean peninsula. In higher frequencies, there are no dominant periodicities, but local winds over YS and ES are highly correlated for frequencies larger than 0.1 cycles per day and phase difference increases linearly with frequency. This linear increase of phase corresponds to phase speed of 550 and 730 km/d at 0.1 and 0.3 cpd, respectively, The phase speed is apparently coincident with moving speed of extratropical cyclones across the Korean peninsula in the west-east direction.

• Geophysics and Geophysical Exploration
• /
• v.13 no.3
• /
• pp.243-248
• /
• 2010

Two suspicious events, which were claimed as underground nuclear tests by North Korea, were detected in the northern Korean Peninsula on October 9, 2006 and May 25, 2009. The KIGAM and Korea-China Joint seismic stations are distributed uniformly along the boundaries between North Korea and adjacent countries. In this study, the data from broadband stations with the distance of 200 to 550 km from the test site are used to analyze and compare two nuclear tests of North Korea. By comparing the time differences of the Pn-wave arrival times of 1st and 2nd tests at multiple stations, the relative locations of two test sites could be calculated precisely. From the geometrical calculation with the velocity of Pn wave $V_{Pn}$ = 8 km/s, the 2nd test site is estimated to move in the WNW direction from 1st one with the distance of 2 km. Body wave magnitude, mb of the 2nd test, which was announced officially as the network average of 4.5, varies widely with the directional location of stations from 4.1 to 5.2. The magnitude obtained from Lg wave, $m_b$(Lg), shows less variation between 4.3 to 4.7 with the average of 4.6. The moving-window spectra of time traces of 1st and 2nd tests show very similar pattern with different scale level. In addition, the corner frequencies of P wave of 1st and 2nd tests at each station show no or negligible difference. This indicates the burial depths of two tests might be very similar. The relative yield amount of the 2nd test is estimated 8 times larger than that of the 1st from the weighted average of ground-velocity amplitude ratios.

• Journal of Conservation Science
• /
• v.32 no.2
• /
• pp.273-291
• /
• 2016

Some ceramic artifacts representing time-wise from comb pattern pottery in the Neolithic Age to white porcelain in Joseon Dynasty were selected from 7 sites in the north and south area of Charyeong Mountain Range in order to making techniques interpretation and development process of ancient ceramics through physicochemical and mineralogical quantitative analysis. Studied pottery samples in the Prehistoric times showed trace of ring piling in soft-type, and pottery in the Three Kingdoms Period had both soft and hard-type but kettle-ware and storage-ware were made with ring piling, but table-ware was made by wheel spinning. Different from pottery after the Three Kingdom Period when refinement of source clay was high, pottery in the Neolithic Age and in the Bronze Age exhibited highly mineral content in sandy source clay, which showed a lot of larger temper than source clay. Groundmass of celadon and white porcelain almost did not reveal primary minerals but had high content of minerals by high temperature firing. Ceramic samples showed some different in major and minor elements according to sites irrespective of times. Geochemical behaviors are very similar indicating similar basic characteristics of source clay. However, loss-on-ignition showed 0.01 to 12.59wt.% range with a large deviation but it rapidly decreased moving from the Prehistoric times to the Three Kingdom Period. They have correlation with the weight loss due to firings, according to burning degree of source clay and detection of high temperature minerals, estimated firing temperatures are classified into 5 groups. Pottery in the Neolithic Age and in the Bronze Age belongs from 750 to $850^{\circ}C$ group; pottery in the Three Kingdom Period are variously found in 750 to $1,100^{\circ}C$ range of firing temperature; and it is believed celadon and white porcelain were baked in high temperature of 1,150 to $1,250^{\circ}C$. It seems difference between refinement of source clay and firing temperature based on production times resulted from change in raw material supply and firing method pursuant to development of production skill. However, there was difference in production methods even at the same period and it is thought that they were utilized according to use purpose and needs instead of evolved development simply to one direction.

• Journal of the Economic Geographical Society of Korea
• /
• v.21 no.1
• /
• pp.20-33
• /
• 2018

Population distribution in urban space varies with transportation flow changing along time of day. Transportation flow is directly affected by the activities of urbanites and the distribution of related facilities, since the flow is the result of moving to the point where the facilities associated with their activities are located. It is thus necessary to analyze the spatio-temporal characteristics of the urban population distribution by integrating the distribution of activity spaces related to the daily life of urbanites and the flow of transportation. The purpose of this study is to analyze the population distribution in urban space with daily and weekly time bases using the building database and T-card database in the city of Seoul, which is rich in information on land use and transportation flow. For a time-based analysis that is difficult to grasp by general statistical techniques, a four-dimensional visualization method combining time and space using a Java program is devised. Dynamic visualization in the four-dimensional space and time allows intuitive analysis and makes it possible to understand more effectively the spatio-temporal characteristics of population distribution. For this purpose, buildings are classified into three activity groups: residential, working, and commercial according to their purpose, and the number of passengers traveling to and from each stop site of bus and subway networks in the T-card database for one week is calculated in one-minute increments, Visualizing these and integrating transportation and land use, we analyze spatio-temporal characteristics of the population distribution in Seoul. As a result, it is found that the population distribution of Seoul displays distinct spatio-temporal characteristics according to land use. In particular, there is a clear difference in the population distribution pattern along the time axis according to the mixed aspects of working, commercial, and residential activities. The results of this study can be very useful for transportation and location planning of city facilities.

• Journal of Navigation and Port Research
• /
• v.34 no.10
• /
• pp.781-786
• /
• 2010

In this study, a new concept of ocean transport system, called the mobile harbor serving for a short distance transport of containers with cargo handling cranes between mother containerships and coastal ports, is introduced. Instead of direct berthing a very large containership at the coastal port, Mobile Harbor is moving to the offshore mooring basin with enough water depth condition. Therefore, investigation of the coastal environment, technical condition and limitation of the domestic trade ports for the application of Mobile Harbor, is essential process. To figure out the accessibility of mobile harbor, the environmental conditions, the cargo handling capacity and marine traffic volume and flow pattern has been analyzed with the tools for marine traffic simulation and virtual navigation aids system. The most proper Mobile Harbor mooring areas among trade ports of the south and east coast are selected by analyzing the obtained information and evaluating its application: (1) Under natural environmental conditions such as air and sea weather, three candidate areas are selected such as Masan port, Ulsan port, and Busan(New port) port. (2) Under marine traffic and appropriateness of water facilities, three candidate areas are selected as Mokpo port, Busan(New port) port, and Donghae & Mookho port (3) For a region-based analysis considering handling capacity and the local managed trade ports in vicinity, three candidate areas are selected as Busan region, Yosu & KwangYang region, and Mokpo region. Through this study, the basic guideline for selection of optimum trade port and offshore mooring basin for mothership and Mobile Harbor is recommended. In order to apply the Mobile Harbor to the real water, navigaton aids as the virtual route identification with AIS must be introduced for maritime safety in the vicinity of Mobile Harbor area which berthing and cargo handling is being conducted.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.24 no.1
• /
• pp.16-25
• /
• 2012

To calculate the total mass flux that change in dry and flood season in the Yeomha Channel of Gyeonggi Bay, the 13 hour bottom tracking observation was performed from the southern extremity. The value of the total mass flux(Lagrange flux) was calculated as the sum of the Eulerian flux value and stroke drift value and the tidal residual flow was harmonically analyzed through the least-squares method. Moreover, the average during the tidal cycle is essential to calculate the mass flux and the tidal residual flow and there is the need to equate the grid of repeatedly observed data. Nevertheless, due to the great differences in the studied region, the number of vertical grid tends to change according to time and since the horizontal grid differs according to the transport speed of the ship as a characteristic of the bottom tracking observation, differences occur in the horizontal and vertical grid for each hour. Hence, the present study has vertically and horizontally normalized(sigma coordinate) to equate the grid per each hour. When compared to the z-level coordinate system, the Sigma coordinate system was evaluated to have no irrationalities in data analysis with 5% of error. As a result of the analysis, the tidal residual flow displayed the flow pattern of sagging in the both ends in the main waterway direction of dry season. During flood season, it was confirmed that the tidal residual flow was vertical 2-layer flow. As a result of the total mass flux, the ebb properties of 359 cm/s and 261 cm/s were observed during dry and flood season, respectively. The total mass flux was moving the intertidal region between Youngjong-do and Ganghwa-do.

• Journal of Intelligence and Information Systems
• /
• v.20 no.2
• /
• pp.59-71
• /
• 2014

System trading is becoming more popular among Korean traders recently. System traders use automatic order systems based on the system generated buy and sell signals. These signals are generated from the predetermined entry and exit rules that were coded by system traders. Most researches on system trading have focused on designing profitable entry and exit rules using technical indicators. However, market conditions, strategy characteristics, and money management also have influences on the profitability of the system trading. Unexpected price deviations from the predetermined trading rules can incur large losses to system traders. Therefore, most professional traders use strategy portfolios rather than only one strategy. Building a good strategy portfolio is important because trading performance depends on strategy portfolios. Despite of the importance of designing strategy portfolio, rule of thumb methods have been used to select trading strategies. In this study, we propose a SVM-based strategy portfolio management system. SVM were introduced by Vapnik and is known to be effective for data mining area. It can build good portfolios within a very short period of time. Since SVM minimizes structural risks, it is best suitable for the futures trading market in which prices do not move exactly the same as the past. Our system trading strategies include moving-average cross system, MACD cross system, trend-following system, buy dips and sell rallies system, DMI system, Keltner channel system, Bollinger Bands system, and Fibonacci system. These strategies are well known and frequently being used by many professional traders. We program these strategies for generating automated system signals for entry and exit. We propose SVM-based strategies selection system and portfolio construction and order routing system. Strategies selection system is a portfolio training system. It generates training data and makes SVM model using optimal portfolio. We make $m{\times}n$ data matrix by dividing KOSPI 200 index futures data with a same period. Optimal strategy portfolio is derived from analyzing each strategy performance. SVM model is generated based on this data and optimal strategy portfolio. We use 80% of the data for training and the remaining 20% is used for testing the strategy. For training, we select two strategies which show the highest profit in the next day. Selection method 1 selects two strategies and method 2 selects maximum two strategies which show profit more than 0.1 point. We use one-against-all method which has fast processing time. We analyse the daily data of KOSPI 200 index futures contracts from January 1990 to November 2011. Price change rates for 50 days are used as SVM input data. The training period is from January 1990 to March 2007 and the test period is from March 2007 to November 2011. We suggest three benchmark strategies portfolio. BM1 holds two contracts of KOSPI 200 index futures for testing period. BM2 is constructed as two strategies which show the largest cumulative profit during 30 days before testing starts. BM3 has two strategies which show best profits during testing period. Trading cost include brokerage commission cost and slippage cost. The proposed strategy portfolio management system shows profit more than double of the benchmark portfolios. BM1 shows 103.44 point profit, BM2 shows 488.61 point profit, and BM3 shows 502.41 point profit after deducting trading cost. The best benchmark is the portfolio of the two best profit strategies during the test period. The proposed system 1 shows 706.22 point profit and proposed system 2 shows 768.95 point profit after deducting trading cost. The equity curves for the entire period show stable pattern. With higher profit, this suggests a good trading direction for system traders. We can make more stable and more profitable portfolios if we add money management module to the system.

• Korean Journal of Ichthyology
• /
• v.18 no.3
• /
• pp.223-233
• /
• 2006

The annual and spatial changes in the species composition of catch off Yeosu were analyzed using the daily sales slip catch data by a set net in the inshore waters off Dolsan Islands in Yeosu from April to October 2001, off Yeon Islands of Yeosu from April to October 2002 and in the offshore waters off Dolsan Islands of Yeosu from April to December 2003, respectively. Scomberomorus niphonius, Seriola spp., Trichiurus lepturus, Engraulis japonicus, Sarda orientalis, Todarodes pacificus, Pampus echinogaster, Sardinella zunasi, Scomber japonicus, Lophius litulon and Loligo beka were dominant species in abundance, indicating that pelagic fish were mainly caught by a set net off Yeosu. S. zunasi, P. echinogaster, Platycephalus indicus and L. beka inhabited mainly in the inshore waters, and S. niphonius, Seriola spp., T. lepturus, P. echinogaster, T. pacificus, Takifugu porphyreus and Pagrus major resided mainly in the offshore waters as the pelagic resident species. E. japonicus was a representative dominant species moving between the inshore and the offshore waters seasonally. S. zunasi and E. japonicus occurred in the inshore waters, and E. japonicus, L. litulon and Seriola spp. begain to be caught in the deep offshore waters in spring. Total catch was high during the summer season by migration of the open sea species such as T. lepturus, S. niphonius, S. japonicus, Seriola spp., S. orientalis, P. echinogaster and T. pacificus. In fall, S. niphonius, E. japonicus, Sphyraena pinguis, Siganus fuscescens and Leiognathus nuchalis were dominant in the inshore waters, and S. niphonius, P. echinogaster, Hyporhamphus sajori, S. japonicus and T. lepturus continued to occur from summer in the offshore waters but total catch decreased, indicating the typical seasonal variation pattern of the temperate region. Most of catchable fishes by a set net were the pelagic species showing a significant temporal variation. Collection and analysis of daily catch data by large set nets can be used to determine seasonal variation in species composition of pelagic fish in a study area.