• International Journal of Reliability and Applications
• /
• v.3 no.1
• /
• pp.37-50
• /
• 2002

Simultaneous estimation of accuracy and probability corresponding to a prediction interval is considered in this study. Traditional application of confidence interval forecasting consists in evaluation of interval limits for a given significance level. The wider is this interval, the higher is probability and the lower is the forecast precision. In this paper a measure of stochastic forecast accuracy is introduced, and a procedure for balanced estimation of both the predicting accuracy and confidence probability is elaborated. Solution can be obtained in an optimizing approach. Suggested method is applied to constructing confidence intervals for parameters estimated by normal and t distributions

• KEPCO Journal on Electric Power and Energy
• /
• v.6 no.4
• /
• pp.399-404
• /
• 2020

There are many attempts to apply AI technology to diagnose facilities or improve the work efficiency of the power industry. The emergence of new machine learning technologies, such as deep learning, is accelerating the digital transformation of the power sector. The problem is that traditional power systems face security risks when adopting state-of-the-art AI systems. This adoption has convergence characteristics and reveals new cybersecurity threats and vulnerabilities to the power system. This paper deals with the security measures and implementations of the power system using machine learning. Through building a commercial facility operations forecasting system using machine learning technology utilizing power big data, this paper identifies and addresses security vulnerabilities that must compensated to protect customer information and power system safety. Furthermore, it provides security guidelines by generalizing security measures to be considered when applying AI.

• International Area Studies Review
• /
• v.21 no.2
• /
• pp.3-20
• /
• 2017

Traditional co-integration analysis method is known to be difficult to clearly determine the relationship between the cointegrated variables. This study utilizes a fractional cointegation method and a causal analysis of time and frequency domain among the exchange rates of Korea, China and Japan. The results show that even though traditional cointegration methods did not clarify the existence of cointegration, exchange rates were fractionally cointegrated. Causal analysis of time domain and frequency domain provided somewhat different results, but the yen/dollar was useful for forecasting won/dollar and yuan/dollar. Proper use of causal analysis of frequency domain and fractional cointegration emthods may provide useful information that can not be explained from the traditional method.

• International Commerce and Information Review
• /
• v.18 no.1
• /
• pp.81-105
• /
• 2016

Recently, master plan on the Far East three provinces in China as well as the Russian Far East coupling with 'Eurasia Initiatives' of our government is doubling its importance. It should take advantage of Zarubino port for the hub of Eurasia Logistics Network. This study forecasts the volume demand and whether the expected items of cargo traffic of Zarubino port with O/Ds for the region including the Far East three provinces in China. Input data and the existing basic unit of Korea were utilized in order to overcome the absence of the relevant information to the region. It was derived by them confined to the industrial complex facility in Jilin Sheng on behalf of the Far East three provinces in China as a pilot study. Suitable for the transport sector as a basis for traditional traffic demand, four-step method for estimating the proposed modifications, complementing methodologies. This study is determined that the contribution to the implications on the region's logistics policies of our government has a commitment with raising awareness of the region's Logistics system.

• Korean Journal of Remote Sensing
• /
• v.23 no.5
• /
• pp.393-400
• /
• 2007

We present in this paper a novel power load prediction method using temporal pattern mining from AMR(Automatic Meter Reading) data. Since the power load patterns have time-varying characteristic and very different patterns according to the hour, time, day and week and so on, it gives rise to the uninformative results if only traditional data mining is used. Also, research on data mining for analyzing electric load patterns focused on cluster analysis and classification methods. However despite the usefulness of rules that include temporal dimension and the fact that the AMR data has temporal attribute, the above methods were limited in static pattern extraction and did not consider temporal attributes. Therefore, we propose a new classification method for predicting power load patterns. The main tasks include clustering method and temporal classification method. Cluster analysis is used to create load pattern classes and the representative load profiles for each class. Next, the classification method uses representative load profiles to build a classifier able to assign different load patterns to the existing classes. The proposed classification method is the Calendar-based temporal mining and it discovers electric load patterns in multiple time granularities. Lastly, we show that the proposed method used AMR data and discovered more interest patterns.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.5
• /
• pp.187-194
• /
• 2019

Traditional demand forecasting methods are difficult to meet the needs of companies due to rapid changes in the market and the diversification of individual consumer needs. In a diversified production environment, the right demand forecast is an important factor for smooth yield management. Many of the existing predictive models commonly used in industry today are limited in function by little. The proposed model is designed to overcome these limitations, taking into account the part where each model performs better individually. In this paper, variables are extracted through Gray Relational analysis suitable for dynamic process analysis, and statistically predicted data is generated that includes characteristics of historical demand data produced through ARIMA forecasts. In combination with the LSTM model, demand forecasts can then be calculated by reflecting the many factors that affect demand forecast through an architecture that is structured to avoid the long-term dependency problems that the neural network model has.

• Journal of the Korea Society for Simulation
• /
• v.30 no.4
• /
• pp.1-8
• /
• 2021

Deep learning is one of the most widely accepted methods for the forecasting of time series data which have the complexity and non-linear behavior. In this paper, we investigate the modification of a state-of-art WaveNet deep learning architecture and walk forward validation (WFV) in order to forecast electric power consumption data 24-hour-ahead. WaveNet originally designed for raw audio uses 1D dilated causal convolution for long-term information. First of all, we propose a modified version of WaveNet which activates real numbers instead of coded integers. Second, this paper provides with the training process with tuning of major hyper-parameters (i.e., input length, batch size, number of WaveNet blocks, dilation rates, and learning rate scheduler). Finally, performance evaluation results show that the prediction methodology based on WFV performs better than on the traditional holdout validation.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.40 no.6
• /
• pp.563-569
• /
• 2020

Presenting the impact of meteorological disasters departs from the traditional weather forecasting approach for meteorological phenomena. It is important to provide impact forecasts so that precautions against disruption and damage can be taken. Countries such as the United States, the U.K., and France already conduct impact forecasting for heavy rain, heavy snow, and cold weather. This study improves and applies forecasts of the impact of heavy rain among various weather phenomena in accordance with domestic conditions. A total of 33 impact factors for heavy rain were constructed per 1 km grids, and four impact levels (minimal, minor, significant, and severe) were calculated using standard normal distribution. Estimated criteria were used as indicators to estimate heavy rain risk impacts for 6 categories (residential, commercial, utility, community, agriculture, and transport) centered on people, facilities, and traffic.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.2
• /
• pp.201-207
• /
• 2023

In this paper, we propose an optimal model for mid to long-term price prediction of agricultural products using LGBM, MLP, LSTM, and GRU to compare and analyze the three strategies of the Multi-Step Time Series. The proposed model is designed to find the optimal combination between the models by selecting methods from various angles. Prior agricultural product price prediction studies have mainly adopted traditional econometric models such as ARIMA and LSTM-type models. In contrast, agricultural product price prediction studies related to Multi-Step Time Series were minimal. In this study, the experiment was conducted by dividing it into two periods according to the degree of volatility of agricultural product prices. As a result of the mid-to-long-term price prediction of three strategies, namely direct, hybrid, and multiple outputs, the hybrid approach showed relatively superior performance. This study academically and practically contributes to mid-to-long term daily price prediction by proposing an effective alternative.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.6B
• /
• pp.543-550
• /
• 2009

The traditional simple extrapolation type short term quantitative rainfall forecast can not realize the evolution of rainfall generating weather system. To overcome the drawback of the linear extrapolation type rainfall forecasting model, the history of a weather system from sequential weather radar information and a polynomial regression technique were used to generate forecast fileds of x-directional, y-directional velocities and radar reflectivity which considered the nonlinear behavior related to the evolution of weather systems. Results demonstrated that test statistics of forecasts using the developed model is better than that of 2-CAPPI forecast. However there is still a large room to improve the forecast of spatial and temporal evolution of local storms since the model is not based on a fully physical approach but a statistical approach.