• Fisheries and Aquatic Sciences
• /
• v.1 no.2
• /
• pp.168-179
• /
• 1998

Circulation in the Jinhae Bay in the southern sea of Korea is examined using the Princeton Ocean Model (POM) with a free surface in a sigma coordinate, governed by primitive equations. The model well corresponds to the time series of the observed velocities at several layers obtained from a long-term mooring observation. In the residual velocity field of the model, persistent downward flow fields are formed along the central deep regions in the bay, and they are caused by bottom topographic effect. In addition, a comparison between a depth-averaged (2D) model and the POM is given, and a dependance of the results on bottom drag coefficient is also examined.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.6 no.2
• /
• pp.19-27
• /
• 2010

Historical archived traffic data management system enables a long term time-series analysis and provides data necessary to acquire the constantly changing traffic conditions and to evaluate and analyze various traffic related strategies and policies. Such features are provided by maintaining highly reliable traffic data through scientific and systematic management. Now, the management systems for massive traffic data have a several problems such as, the storing and management methods of a large volume of archive data. In this paper, we describe how to storing and management for the massive traffic data and, we propose methodology for logical and physical architecture, collecting and storing, database design and implementation, process design of massive traffic data.

• Genomics & Informatics
• /
• v.13 no.3
• /
• pp.90-92
• /
• 2015

Biological diversity, also known as biodiversity, is an important criterion for measuring the value of an ecosystem. As biodiversity is closely related to human welfare and quality of life, many efforts to restore and maintain the biodiversity of species have been made by government agencies and non-governmental organizations, thereby drawing a substantial amount of international attention. In the fields of biological research, biodiversity is widely measured using traditional statistical indices such as the Shannon-Wiener index, species richness, evenness, and relative dominance of species. However, some biologists and ecologists have difficulty using these indices because they require advanced mathematical knowledge and computational techniques. Therefore, we developed VBioindex, a user-friendly program that is capable of measuring the Shannon-Wiener index, species richness, evenness, and relative dominance. VBioindex serves as an easy to use interface and visually represents the results in the form of a simple chart and in addition, VBioindex offers functions for long-term investigations of datasets using time-series analyses.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2010.05a
• /
• pp.1640-1644
• /
• 2010

In this study the wetness/dryness in Geum river basin are classified by dint of cumulative probability density function of monthly moisture index and the long term changes of them are analyzed based on climatic water balance concept. The drought events in Geum river basin are selected through evaluation of monthly moisture index and the various hydrological properties of them are investigated in detail. Also the trends of time-series of climatic water balance components are examined by Seasonal Kendall test and the variability of hydrological cycle in Geum river basin during the recent decade is inquired. It is judged that the results of this study can be contributed to establishment of the counter plan against the future drought events as the fundamental information.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.18 no.4
• /
• pp.379-385
• /
• 2000

In order to evaluate the stability of permanent GPS arrays for obtaining high precision coordinates, spectral analysis uses the least square spectrum analysis to the coordinate variations of Suwon, Tsukuba and Sanghai stations. Permanent GPS observations at Suwon, Tsukuba and Sanghai have been more or less continuously carried out since 1994. Time series of the resulting coordinate variations are analyzed for long term repeatability and periodic behaviour.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.398-402
• /
• 2018

비정상(non-stationary) 장기 시계열 안에서도, 단기적으로 추세의 변화가 일시적인 것인지, 아니면 구조적으로 변한 것인지를 적시에 판단하는 것은 중요하다. 이는 시계열 추세의 변화를 상시 감지하여, 변화에 맞는 적정한 수준의 대응을 할 필요가 있기 때문이다. 본 연구에서는 장기 시계열이 주어진 상황에서, 단위근 검정법을 기반으로 단기적으로 구조변화를 감지하여, 이러한 변화가 얼마나 지속될 것인지를 시각적으로 판단할 수 있는 방법을 제시하고자 한다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.32-32
• /
• 2019

본 연구에서는 다양한 시계열 예측에서 우수한 성과를 보이고 있는 딥러닝 알고리즘 LSTM(Long & Short Term Memory) 모형의 수문시계열 분석에 있어서의 적용성을 검토하고, 모형의 활용가능성과 한계점을 제시하는 것을 목적으로 한다. 이를 위해 물리적 강우-유출 모형과의 비교 검토, 일반하천 및 감조하천에서의 수위 예측, 월강수량 및 댐방류량을 활용한 갈수량 예측 등에 LSTM 모형을 적용하고, 결과분석을 통해 모형의 장 단점을 요약하였다. 상기 목적을 위한 모형적용 결과, LSTM 모형은 수문시계열 예측에 있어 우수한 예측능력을 보이고 있으며, 이는 양적/질적 수문자료가 충분히 확보되었지만, 수문해석 모형구축에 제약이 있는 유역에 대해서 보완적 수단으로 사용이 가능할 것으로 판단된다.

• The Journal of Industrial Distribution & Business
• /
• v.13 no.12
• /
• pp.33-39
• /
• 2022

Purpose: This research investigates the paths of some important economic variables: government domestic product (GDP), capital accumulation, unemployment rates. Decreasing GDP, declining capital accumulation and higher unemployment affect to South Korea economy. The macroeconomic policies discussed are all capital financed accumulation policy and an enactment of unemployment regulation. Research design, data and methodology: The GDP, capital accumulation rates and unemployment rates are the main macroeconomic issues in the South Korea. This research studies the correlations of the GDP, capital accumulation, and unemployment rates by time series data from 2000 to 2005 in a Vector Autoregressive (VAR). Results: The first, GDP relates a positive effect between the GDP and capital accumulation in the long term. The second, there is the negative relationship between GDP and unemployment rates. Economic growth was strongly supported by employment growth and by declining unemployment. The third, There is positive relationship between unemployment rates and capital accumulation. Conclusions: This research provides that fiscal policy introduce to increasing GDP, private investments and employment rates. The GDP should be major on capital accumulation to increase employment rates in South Korea.

• New & Renewable Energy
• /
• v.18 no.2
• /
• pp.18-25
• /
• 2022

In this study, we propose a wind power generation prediction system that applies machine learning and data mining to predict wind power generation. This system increases the utilization rate of new and renewable energy sources. For time-series data, the data set was established by measuring wind speed, wind generation, and environmental factors influencing the wind speed. The data set was pre-processed so that it could be applied appropriately to the model. The prediction system applied the CNN (Convolutional Neural Network) to the data mining process and then used the LSTM (Long Short-Term Memory) to learn and make predictions. The preciseness of the proposed system is verified by comparing the prediction data with the actual data, according to the presence or absence of data mining in the model of the prediction system.

• International Journal of Computer Science & Network Security
• /
• v.22 no.1
• /
• pp.55-60
• /
• 2022

Churn prediction is a critical long-term problem for many business like music, games, magazines etc. The churn probability can be used to study many aspects of a business including proactive customer marketing, sales prediction, and churn-sensitive pricing models. It is quite challenging to design machine learning model to predict the customer churn accurately due to the large volume of the time-series data and the temporal issues of the data. In this paper, a parallel artificial neural network is proposed to create a highly-accurate customer churn model on a large customer dataset. The proposed model has achieved significant improvement in the accuracy of churn prediction. The scalability and effectiveness of the proposed algorithm is also studied.