• Proceedings of the Korean Society of Computer Information Conference
• /
• 2018.07a
• /
• pp.141-142
• /
• 2018

기존 데이터의 패턴 예측에는 통계를 기반으로 한 수학적 모델이 주로 사용되었으나 새로운 데이터에 대한 피드백이 부족하기 때문에 장기간의 데이터 예측에 한계가 있다. 또한 데이터의 특성이 다양하고 복잡한 경우에는 수학적 모델의 결합 및 계산과정이 어려워진다. 따라서 본 논문에서는 데이터의 학습 및 예측에 기존 정적 모델이 아닌 기계학습 중 시계열 데이터 분석 (Time Series Analysis) 을 기반으로 연구를 진행하였다. 기계학습은 복잡한 특성을 가진 데이터를 학습하여 미래의 데이터 값을 예측하거나 분류하는데 있어서 정확도 및 처리시간 측면에서의 성능을 향상시킬 수 있다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.224-227
• /
• 2000

In this Paper, we prepose a method of constructing neural networks using bio-inspired emergent and evolutionary concepts. This method is algorithm that is based on the characteristics of the biological DNA and growth of plants. Here is, we propose a constructing method to make a DNA coding method for production rule of L-system. L-system is based on so-called the parallel rewriting mechanism. The DNA coding method has no limitation in expressing the production rule of L-system. Evolutionary algorithms motivated by Darwinian natural selection are population based searching methods and the high performance of which is highly dependent on the representation of solution space. In order to verify the effectiveness of our scheme, we apply it to one step ahead prediction of Mackey-Glass time series, Sun spot data and KOSPI data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.3
• /
• pp.528-550
• /
• 2024

Warehousing demand prediction is an essential part of the supply chain, providing a fundamental basis for product manufacturing, replenishment, warehouse planning, etc. Existing forecasting methods cannot produce accurate forecasts since warehouse demand is affected by external factors such as holidays and seasons. Some aspects, such as consumer psychology and producer reputation, are challenging to quantify. The data can fluctuate widely or do not show obvious trend cycles. We introduce a new model for warehouse demand prediction called MAGRU, which stands for Multi-layer Attention with GRU. In the model, firstly, we perform the embedding operation on the input sequence to quantify the external influences; after that, we implement an encoder using GRU and the attention mechanism. The hidden state of GRU captures essential time series. In the decoder, we use attention again to select the key hidden states among all-time slices as the data to be fed into the GRU network. Experimental results show that this model has higher accuracy than RNN, LSTM, GRU, Prophet, XGboost, and DARNN. Using mean absolute error (MAE) and symmetric mean absolute percentage error(SMAPE) to evaluate the experimental results, MAGRU's MAE, RMSE, and SMAPE decreased by 7.65%, 10.03%, and 8.87% over GRU-LSTM, the current best model for solving this type of problem.

• Journal of IKEEE
• /
• v.25 no.4
• /
• pp.766-769
• /
• 2021

In order to perform tasks such as design, control, optimization, and prediction of flight vehicle trajectories based on machine learning techniques including deep learning, a certain amount of flight vehicle trajectory data is required. However, there are cases in which it is difficult to secure more than a certain amount of flight vehicle trajectory data for various reasons. In such cases, synthetic data generation could be one way to make machine learning possible. In this paper, to explore this possibility, we generated and evaluated synthetic flight vehicle trajectory data using time-series generative adversarial neural network. In addition, various ablation studies (comparative experiments) were performed to explore the possibility of using synthetic data in the aircraft trajectory prediction task. The experimental results presented in this paper are expected to be of practical help to researchers who want to conduct research on the possibility of using synthetic data in the generation of synthetic flight vehicle trajectory data and the work related to flight vehicle trajectories.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.11
• /
• pp.13-20
• /
• 2023

In this paper, we propose a water temperature prediction method using feature extraction and reconstructed data based on LSTM-Autoencoder. We used multivariate time series data such as sea surface water temperature in the Naksan area of the East Sea where the cold water zone phenomenon occurred, and wind direction and wind speed that affect water temperature. Using the LSTM-Autoencoder model, we used three types of data: feature data extracted through dimensionality reduction of the original data combined with multivariate data of the original data, reconstructed data, and original data. The three types of data were trained by the LSTM model to predict sea surface water temperature and evaluated the accuracy. As a result, the sea surface water temperature prediction accuracy using feature extraction of LSTM-Autoencoder confirmed the best performance with MAE 0.3652, RMSE 0.5604, MAPE 3.309%. The result of this study are expected to be able to prevent damage from natural disasters by improving the prediction accuracy of sea surface temperature changes rapidly such as the cold water zone.

• Advanced Industrial SCIence
• /
• v.3 no.1
• /
• pp.17-22
• /
• 2024

History, which began with the emergence of mankind, has a means of recording. Today, we can check the past through data. Generated data may only be generated and stored at a certain moment, but it is not only continuously generated over a certain time interval from the past to the present, but also occurs in the future, so making predictions using it is an important task. In order to find out trends in the use of time series data among numerous data, this paper analyzes the concept of time series data, analyzes Recurrent Neural Network and Long-Short Term Memory, which are mainly used for time series data analysis in the machine learning field, and analyzes the use of these models. Through case studies, it was confirmed that it is being used in various fields such as medical diagnosis, stock price analysis, and climate prediction, and is showing high predictive results. Based on this, we will explore ways to utilize it in the future.

• Journal of Korean Society of Disaster and Security
• /
• v.12 no.2
• /
• pp.73-82
• /
• 2019

Recently, as the occurrence frequency of sudden floods due to climate change increased, the flood damage on riverside social infrastructures was extended so that there has been a threat of overflow. Therefore, a rapid prediction of potential flooding in riverside social infrastructure is necessary for administrators. However, most current flood forecasting models including hydraulic model have limitations which are the high accuracy of numerical results but longer simulation time. To alleviate such limitation, data driven models using artificial neural network have been widely used. However, there is a limitation that the existing models can not consider the time-series parameters. In this study the water surface elevation of the Hangang River bridge was predicted using the NARX model considering the time-series parameter. And the results of the ANN and RNN models are compared with the NARX model to determine the suitability of NARX model. Using the 10-year hydrological data from 2009 to 2018, 70% of the hydrological data were used for learning and 15% was used for testing and evaluation respectively. As a result of predicting the water surface elevation after 3 hours from the Hangang River bridge in 2018, the ANN, RNN and NARX models for RMSE were 0.20 m, 0.11 m, and 0.09 m, respectively, and 0.12 m, 0.06 m, and 0.05 m for MAE, and 1.56 m, 0.55 m and 0.10 m for peak errors respectively. By analyzing the error of the prediction results considering the time-series parameters, the NARX model is most suitable for predicting water surface elevation. This is because the NARX model can learn the trend of the time series data and also can derive the accurate prediction value even in the high water surface elevation prediction by using the hyperbolic tangent and Rectified Linear Unit function as an activation function. However, the NARX model has a limit to generate a vanishing gradient as the sequence length becomes longer. In the future, the accuracy of the water surface elevation prediction will be examined by using the LSTM model.

• Journal of the Korean Geosynthetics Society
• /
• v.21 no.2
• /
• pp.11-19
• /
• 2022

In this paper, we propose a GoogleNet transfer learning and CNN-LSTM combination method to improve the time-series prediction performance for crack detection using crack data captured inside the sewer pipes. LSTM can solve the long-term dependency problem of CNN, so spatial and temporal characteristics can be considered at the same time. The predictive performance of the proposed method is excellent in all test variables as a result of comparing the RMSE(Root Mean Square Error) for time series sections using the crack data inside the sewer pipe. In addition, as a result of examining the prediction performance at the time of data generation, the proposed method was verified that it is effective in predicting crack detection by comparing with the existing CNN-only model. If the proposed method and experimental results obtained through this study are utilized, it can be applied in various fields such as the environment and humanities where time series data occurs frequently as well as crack data of concrete structures.

• Journal of Positioning, Navigation, and Timing
• /
• v.9 no.2
• /
• pp.89-98
• /
• 2020

Prediction of clock behaviors is necessary to generate very high stable system time which is essential for a satellite navigation system. For the purpose, we applied the Auto-Regressive Integrated Moving Average (ARIMA) model to the prediction of two hydrogen masers' behaviors with respect to the rapid Coordinated Universal Time (UTCr). Using the packaged programming language R, we made an analysis and prediction of time series data of [UTCr - clocks]. The maximum variation width of the residuals which were obtained by the difference between the predicted and measured values, was 6.2 ns for 106 days. This variation width was just one-sixth of [UTCr-UTC (KRIS)] published by the BIPM for the same period. Since the two hydrogen masers were found to be strongly correlated, we applied the Vector Auto-Regressive Moving Average (VARMA) model for more accurate prediction. The result showed that the prediction accuarcy was improved by two times for one hydrogen maser.

• Journal of Convergence for Information Technology
• /
• v.11 no.3
• /
• pp.7-13
• /
• 2021

This study develops an artificial intelligence prediction system for Fine particulate Matter(PM2.5) based on the deep learning algorithm GAN model. The experimental data are closely related to the changes in temperature, humidity, wind speed, and atmospheric pressure generated by the time series axis and the concentration of air pollutants such as SO2, CO, O3, NO2, and PM10. Due to the characteristics of the data, since the concentration at the current time is affected by the concentration at the previous time, a predictive model for recursive supervised learning was applied. For comparative analysis of the accuracy of the existing models, CNN and LSTM, the difference between observation value and prediction value was analyzed and visualized. As a result of performance analysis, it was confirmed that the proposed GAN improved to 15.8%, 10.9%, and 5.5% in the evaluation items RMSE, MAPE, and IOA compared to LSTM, respectively.