• 한국항공운항학회지
• /
• 제26권4호
• /
• pp.101-109
• /
• 2018

In order to predict the future needs of the aircraft repair parts, each military group develops and applies various techniques to their characteristics. However, the aircraft and the equipped weapon systems are becoming increasingly advanced, and there is a problem in improving the hit rate by applying the existing demand prediction technique due to the change of the aircraft condition according to the long term operation of the aircraft. In this study, we propose a new prediction model based on the conventional time-series analysis technique to improve the prediction accuracy of aircraft repair parts by using machine learning model. And we show the most effective predictive method by demonstrating the change of hit rate based on actual data.

• 품질경영학회지
• /
• 제51권4호
• /
• pp.497-514
• /
• 2023

Purpose: This study aims to estimate the demand for various public parking lots in Seoul by clustering similar demand types of parking lots and predicting the demand for new public parking lots. Methods: We examined real-time parking information data and used time series clustering analysis to cluster public parking lots with similar demand patterns. We also performed various regression analyses of parking demand based on diverse heterogeneous data that affect parking demand and proposed a parking demand prediction model. Results: As a result of cluster analysis, 68 public parking lots in Seoul were clustered into four types with similar demand patterns. We also identified key variables impacting parking demand and obtained a precise model for predicting parking demands. Conclusion: The proposed prediction model can be used to improve the efficiency and publicity of public parking lots in Seoul, and can be used as a basis for constructing new public parking lots that meet the actual demand. Future research could include studies on demand estimation models for each type of parking lot, and studies on the impact of parking lot usage patterns on demand.

• 신재생에너지
• /
• 제18권2호
• /
• 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.

• 도시과학
• /
• 제7권1호
• /
• pp.45-54
• /
• 2018

The purpose of this study is to find the factors that reduce prediction error in traffic volume using highway traffic volume data. The ARIMA model was used to predict the day, and it was confirmed that weekday and weekly characteristics were distinguished by prediction error. The forecasting results showed that weekday characteristics were prominent on Tuesdays, Wednesdays, and Thursdays, and forecast errors including MAPE and MAE on Sunday were about 15% points and about 10 points higher than weekday characteristics. Also, on Friday, the forecast error was high on weekdays, similar to Sunday's forecast error, unlike Tuesday, Wednesday, and Thursday, which had weekday characteristics. Therefore, when forecasting the time series belonging to Friday, it should be regarded as a weekly characteristic having characteristics similar to weekend rather than considering as weekday.

• 대한전기학회논문지
• /
• 제32권6호
• /
• pp.191-198
• /
• 1983

This paper describes the aplication of different model which can be used for short-term load prediction. The model is based on Bohlin's approach to first develop a load profile model representing the nominal load component and the Box-Jenkins approach is used to predict residuals. An on-line algorithm using Kalman Filter and Time Series is implemented for and hour-ahead prediction. In the Kalman Filter system equation and measurement equation were fixed and parameters of Time Series were varied week after week. A set of data for Korea Electric Power Corporation from April to June 1981 was used for the evaluation of the model. As the result of this simulation 1.2% rms error was acquired.

• 전력전자학회논문지
• /
• 제27권4호
• /
• pp.316-324
• /
• 2022

This paper uses seasonal auto-regressive integrated moving average (S-ARIMA), which is efficient in seasonality between time-series models, to predict the degradation tendency for lithium-ion batteries and study a method for improving the predictive performance. The proposed method analyzes the degradation tendency and extracted factors through an electrical characteristic experiment of lithium-ion batteries, and verifies whether time-series data are suitable for the S-ARIMA model through several statistical analysis techniques. Finally, prediction of battery aging is performed through S-ARIMA, and performance of the model is verified through error comparison of predictions through mean absolute error.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2022년도 학술발표회
• /
• pp.150-150
• /
• 2022

This study investigates the roles of decomposition methods on high accuracy in daily rainfall prediction from light gradient boosting machine (LightGBM) algorithm. Here, empirical mode decomposition (EMD) and singular spectrum analysis (SSA) methods were considered to decompose and reconstruct input time series into trend terms, fluctuating terms, and noise components. The decomposed time series from EMD and SSA methods were used as input data for LightGBM algorithm in two hybrid models, including empirical mode-based light gradient boosting machine (EMDGBM) and singular spectrum analysis-based light gradient boosting machine (SSAGBM), respectively. A total of four parameters (i.e., temperature, humidity, wind speed, and rainfall) at a daily scale from 2003 to 2017 is used as input data for daily rainfall prediction. As results from statistical performance indicators, it indicates that the SSAGBM model shows a better performance than the EMDGBM model and the original LightGBM algorithm with no decomposition methods. It represents that the accuracy of LightGBM algorithm in rainfall prediction was improved with the SSA method when using multivariate dataset.

• 산업기술연구
• /
• 제29권B호
• /
• pp.9-15
• /
• 2009

In the case of traditional binary encoding technique, it takes long time to converge the optimal solutions and brings about complexity of the systems due to encoding and decoding procedures. However, the ROGAs (real-coded genetic algorithms) do not require these procedures, and the k-means clustering algorithm can avoid global searching space. Thus, this paper proposes a new approach by using their advantages. The proposed method constructs the multiple predictors using the optimal differences that can reveal the patterns better and properties concealed in non-stationary time series where the k-means clustering algorithm is used for data classification to each predictor, then selects the best predictor. After selecting the best predictor, the cluster centers of the predictor are tuned finely via RCGKA in secondary tuning procedure. Therefore, performance of the predictor can be more enhanced. Finally, we verifies the prediction performance of the proposed system via simulating typical time series examples.

• 한국해양공학회지
• /
• 제36권5호
• /
• pp.295-302
• /
• 2022

The initial response to a marine accident can play a key role to minimize the accident. Therefore, various decision support systems have been developed using sensors, simulations, and active response equipment. In this study, we developed an algorithm to predict damage locations using ship motion data with bidirectional long short-term memory (BiLSTM), a type of recurrent neural network. To reflect the low frequency ship motion characteristics, 200 time-series data collected for 100 s were considered as input values. Heave, roll, and pitch were used as features for the prediction model. The F1-score of the BiLSTM model was 0.92; this was an improvement over the F1-score of 0.90 of a prior model. Furthermore, 53 of 75 locations of damage had an F1-score above 0.90. The model predicted the damage location with high accuracy, allowing for a quick initial response even if the ship did not have flood sensors. The model can be used as input data with high accuracy for a real-time progressive flooding simulator on board.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제11권7호
• /
• pp.307-314
• /
• 2022

최근 전력수요를 예측하기 위해 통계기반 시계열 분석 기법을 대체하기 위해 딥러닝 기법을 활용한 연구가 활발히 진행되고 있다. 딥러닝 기반 전력수요 예측 연구 결과를 분석한 결과, LSTM 기반 예측 모델의 성능이 우수한 것으로 규명되었으나 장기간의 지역 범위 전력수요 예측에 대해 LSTM 기반 모델의 성능이 충분하지 않음을 확인할 수 있다. 본 연구에서는 기온 데이터를 반영하여 24시간 이전에 전력수요를 예측하는 WaveNet 기반 딥러닝 모델을 개발하여, 실제 사용하고 있는 통계적 시계열 예측 기법의 정확도(MAPE 값 2%)보다 우수한 예측 성능을 달성하는 모델을 개발하고자 한다. 먼저 WaveNet의 핵심 구조인 팽창인과 1차원 합성곱 신경망 구조를 소개하고, 전력수요와 기온 데이터를 입력값으로 모델에 주입하기 위한 데이터 전처리 과정을 제시한다. 다음으로, 개선된 WaveNet 모델을 학습하고 검증하는 방법을 제시한다. 성능 비교 결과, WaveNet 기반 모델에 기온 데이터를 반영한 방법은 전체 검증데이터에 대해 MAPE 값 1.33%를 달성하였고, 동일한 구조의 모델에서 기온 데이터를 반영하지 않는 것(MAPE 값 2.31%)보다 우수한 전력수요 예측 결과를 나타내고 있음을 확인할 수 있다.