• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.36 no.6
• /
• pp.749-756
• /
• 2003

Hydroacoustic and open-closing zooplankton net survey were conducted to understand the characteristics of the sound scattering layer (SSL) and to estimate the density of an euphausiid (Euphausia pacifica) in the SSL, in the northwestern part of the East China Sea. The survey was carried out during July 6-9 2002 at 8 sampling stations for zooplankton. The virtual echogram technique was used to identify E. pacifica from all acoustic scatters. Mean volume backscattering strength difference $(MVBS_{120kHz-38kHz})$ and target strength equation for E. pacifica were derived from the Distorted-wave Born Approximation (DWBA) model. Although vertical migration of the SSL is similar to the general pattern, dispersion at night shows some differences. Estimated mean density using acoustic data ranged from $20.4-221.4\;mg/m^3$ over the whole depth, and $87.1-553.5\;mg/m^3$ in the SSL. The density using the zooplankton net ranged from $0.2-362.4\;mg/m^3$ and was not related to net deploying method. The results from the acoustic and net survey suggest that E. pacifica might be an important zooplankton community in the northwestern part of the East China Sea.

• 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.

• Tunnel and Underground Space
• /
• v.22 no.6
• /
• pp.373-382
• /
• 2012

Cessation of dewatering usually results in groundwater rebound after closing an underground coal mine because the mine voids and surrounding strata flood up to the levels of decant points such as shafts and drifts. Several numerical models have been developed to predict the timing, magnitude and location of discharges resulting from groundwater rebound. This study reviews the numerical models such as VSS-NET, GRAM and MODFLOW, and compares their scopes of assessment at different spatial and time scales. In particular, the GRAM model was reviewed in details to implement it. This paper describes the implementation of GRAM model and its application to the Dongwon coal mine in Korea. The application showed that the groundwater level modeled at the shaft of Dongwon coal mine using the GRAM model is similar to the observed one in the field.

• Nuclear Engineering and Technology
• /
• v.48 no.5
• /
• pp.1280-1290
• /
• 2016

This paper presents an advanced estimation method for obtaining the probability density functions of a damage parameter for valve leakage detection in a reciprocating pump. The estimation method is based on a comparison of model data which are simulated by using a mathematical model, and experimental data which are measured on the inside and outside of the reciprocating pump in operation. The mathematical model, which is simplified and extended on the basis of previous models, describes not only the normal state of the pump, but also its abnormal state caused by valve leakage. The pressure in the cylinder is expressed as a function of the crankshaft angle, and an additional volume flow rate due to the valve leakage is quantified by a damage parameter in the mathematical model. The change in the cylinder pressure profiles due to the suction valve leakage is noticeable in the compression and expansion modes of the pump. The damage parameter value over 300 cycles is calculated in two ways, considering advance or delay in the opening and closing angles of the discharge valves. The probability density functions of the damage parameter are compared for diagnosis and prognosis on the basis of the probabilistic features of valve leakage.

• Nuclear Engineering and Technology
• /
• v.48 no.1
• /
• pp.114-128
• /
• 2016

The development of operational performance indicators is of utmost importance for nuclear power plants, since they measure, track, and trend plant operation. Leading indicators are ideal for reducing the likelihood of consequential events. This paper describes the operational data analysis of the information contained in the Corrective Action Program. The methodology considers human error and organizational factors because of their large contribution to consequential events. The results include a tool developed from the data to be used for the identification, prediction, and reduction of the likelihood of significant consequential events. This tool is based on the resilience curve that was built from the plant's operational data. The stress is described by the number of unresolved condition reports. The strain is represented by the number of preventive maintenance tasks and other periodic work activities (i.e., baseline activities), as well as, closing open corrective actions assigned to different departments to resolve the condition reports (i.e., corrective action workload). Beyond the identified resilience threshold, the stress exceeds the station's ability to operate successfully and there is an increased likelihood that a consequential event will occur. A performance indicator is proposed to reduce the likelihood of consequential events at nuclear power plants.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.56 no.2
• /
• pp.259-264
• /
• 2023

Day-night vertical euphausiid distribution was investigated at three stations in the East Sea using a Multiple Opening/Closing Net and Environmental Sensing System (MOCNESS). Three euphausiid species were recognized. Euphausia pacifica was more dominant than Thysanoessa longipes. Euphausiids were collected at Station 1 at night, Station 2 at sunset, and Station 3 during the daytime. At Station 1, calyptopis and furcilia stages were concentrated from the surface to 30 m and 20-40 m, respectively. Juveniles and E. pacifica were distributed in strata shallower than 30 m. At Station 2, calyptopis and furcilia stages were dominant in strata from the surface to 40 m. Juveniles were not recorded in strata at 30-100 m. However, E. pacifica occurred in these strata. At Station 3, calyptopis and furcilia stages occurred in the upper 40 m of strata. E. pacifica was distributed deeper than 100 m and rarely occurred above 100 m. The furcilia stages weakly migrated, whereas the calyptopis stages did not. Juveniles and E. pacifica showed a clear migration pattern. Vertical distribution of euphausiids in the northern East Sea varied by life stage and time of day.

• Journal of Korean Society of Forest Science
• /
• v.97 no.3
• /
• pp.348-356
• /
• 2008

There is the need of regulating chestnut production because of being expected with chestnut trees cultivation farmhouses to be in a difficult situation by means of FTA negotiation promotion hereafter in Korea. And this study is aim to establish compensation criteria and plan for depreciation of income of farmers who take part in chestnut production regulation. We surveyed one hundred and thirty three among chestnut trees cultivation farmhouses in chief producing districts Kyung-nam, Jeon-nam and Chung-nam in Korea. As the result of this study, this study showed compensation criteria and plans for depreciation of income for farmers's participate in chestnut production regulation and showed criteria for closing chestnut old tree orchard and working process of cutting chestnut old tree. Procedures in closing chestnut old tree orchard in a day per hecta were felling operation and crude manufacture of thirty trees per one man, five forklains in loading and unloading chestnut log from a truck and building of workroad, the two number of assistance persons in loading and unloading chestnut log from a truck, the 6.94 trucks in carrying chestnut log. After farmers close chestnut trees orchard, government cost of old trees cuts and net income decrease for 3 years in case of planting trees for landscape and environment preservation.

• Nuclear Engineering and Technology
• /
• v.41 no.1
• /
• pp.53-62
• /
• 2009

A set of experiments has been conducted on the performance sensitivity of the passive residual heat removal system (PRHRS) for an advanced integral type reactor, SMART, by using a high temperature and high pressure thermal-hydraulic test facility, the VISTA facility. In this paper the effects of the opening delay of the PRHRS bypass valves and the closing delay of the secondary system isolation valves, and the initial water level and the initial pressure of the compensating tank (CT) are investigated. During the reference test a stable flow occurs in a natural circulation loop that is composed of a steam generator secondary side, a secondary system, and a PRHRS; this is ascertained by a repetition test. When the PRHRS bypass valves are operated 10 seconds later than the secondary system isolation valves, the primary system is not properly cooled. When the secondary system isolation valves are operated 10 or 30 seconds later than the PRHRS bypass valves, the primary system is effectively cooled but the inventory of the PRHRS CT is drained earlier. As the initial water level of the CT is lowered to 16% of the full water level, the water is quickly drained and then nitrogen gas is introduced into the PRHRS, resulting in the deterioration of the PRHRS performance. When the initial pressure of the PRHRS is at 0.1MPa, the natural circulation is not performed properly. When the initial pressures of the PRHRS are 2.5 or 3.5 MPa, they show better performance than did the reference test.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.8
• /
• pp.31-39
• /
• 2022

Stock prices are influenced by a number of external factors, such as laws and trends, as well as number-based internal factors such as trading volume and closing prices. Since many factors affect stock prices, it is very difficult to accurately predict stock prices using only fragmentary stock data. In particular, since the value of a company is greatly affected by the perception of people who actually trade stocks, emotional information about a specific company is considered an important factor. In this paper, we propose a deep learning-based stock price prediction model using sentiment analysis with news data considering temporal characteristics. Stock and news data, two heterogeneous data with different characteristics, are integrated according to time scale and used as input to the model, and the effect of time scale and sentiment index on stock price prediction is finally compared and analyzed. Also, we verify that the accuracy of the proposed model is improved through comparative experiments with existing models.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.56 no.2
• /
• pp.221-227
• /
• 2023

The vertical distribution of snow crab Chionoecetes spp. larvae in the East Sea were investigated in April 2021 using the Multiple Opening/Closing Net and Environmental Sensing System (MOCNESS). The water temperature ranged from 0.86 to 17.2℃, and salinity from 34.0 to 34.7 psu. Zoea I and II occurred range from 29 to 1,982 inds.10³ m^-3 at 10 stations, and range from 4 to 11 inds.10³ m^-3 at 3 stations, separately. Therefore, Zoea I occurred in wider area and higher density than Zoea II at all stations. In the vertical distribution of larvae, all zoeal stages were mainly distributed in the 30-40 m strata, and the larvae showed nocturnal vertical migration similar to that of most zooplankton. Zoea I appeared in the range from 13.7 to 15.8℃ and occurred at the highest density of 1982 inds.10³ m^-3 at 14℃. And Zoea II appeared range from 13.4 to 14.5℃ and occurred in the highest density of 11 inds.10³ m^-3 at 13.4℃. In conclusion, the early larval stage (zoea I) occurred at a higher range of sea surface temperature than later larval stage (zoea II).