• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.1
• /
• pp.123-131
• /
• 2020

There have been a lot of studies in the past for the method of predicting the failure of a machine, and recently, a lot of researches and applications have been generated to diagnose the physical condition of the machine and the parts and to calculate the remaining life through various methods. Survival models are also used to predict plant failures based on past anomaly cycles. In particular, special machine that reflect the fluid flow and process characteristics of chemical plants are connected to hundreds or thousands of sensors, so there are not many factors that need to be considered, such as process and material data as well as application of derivative variables. In this paper, the data were preprocessed through time series anomaly detection based on unsupervised learning to predict the abnormalities of these special machine. Next, clustering results reflecting clustering-based data characteristics were applied to produce additional variables, and a learning data set was created based on the history of past facility abnormalities. Finally, the prediction methodology based on the supervised learning algorithm was applied, and the model update was confirmed to improve the accuracy of the prediction of facility failure. Through this, it is expected to improve the efficiency of facility operation by flexibly replacing the maintenance time and parts supply and demand by predicting abnormalities of machine and extracting key factors.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.204-206
• /
• 2021

Real-time drilling parameters prediction is a considerably important study from the viewpoint of maximizing drilling efficiency. Among the methods of maximizing drilling, the method of improving the drilling speed is common, which is related to the rate of penetration, drillstring rotational speed, weight on bit, and drilling mud flow rate. This study proposes a method of predicting the drilling rate, one of the real-time drilling parameters, using a recurrent neural network-based deep learning model, and compares the existing physical-based drilling rate prediction model with a prediction model using deep learning.

• International Journal of Ocean System Engineering
• /
• v.3 no.3
• /
• pp.116-130
• /
• 2013

The prediction of ocean currents in real time over the warning times of a few hours or days is required in planning many operation-related activities in the ocean. Traditionally this is done through numerical models which are targeted toward producing spatially distributed information. This paper discusses a complementary method to do so when site-specific predictions are desired. It is based on the use of a recurrent type of neural network as well as the statistical tool of model tree. The measurements made at a site in Indian Ocean over a period of 4 years were used. The predictions were made over 72 time steps in advance. The models developed were found to be fairly accurate in terms of the selected error statistics. Among the two modeling techniques the model tree performed better showing the necessity of using distributed models for different sub-domains of data rather than a unique one over the entire input domain. Typically such predictions were associated with average errors of less than 2.0 cm/s. Although the prediction accuracy declined over longer intervals, it was still very satisfactory in terms of theselected error criteria. Similarly prediction of extreme values matched with that of the rest of predictions. Unlike past studies both east-west and north-south current components were predicted fairly well.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.11
• /
• pp.310-318
• /
• 2018

Recently, the importance of big data analysis is increasing as a large amount of data is generated by various devices connected to the Internet with the advent of Internet of Things (IoT). Especially, it is necessary to analyze various large-scale IoT streaming sensor data generated in real time and provide various services through new meaningful prediction. This paper proposes a real-time indoor PM10 concentration prediction LSTM model based on streaming data generated from IoT sensor using AWS. We also construct a real-time indoor PM10 concentration prediction service based on the proposed model. Data used in the paper is streaming data collected from the PM10 IoT sensor for 24 hours. This time series data is converted into sequence data consisting of 30 consecutive values from time series data for use as input data of LSTM. The LSTM model is learned through a sliding window process of moving to the immediately adjacent dataset. In order to improve the performance of the model, incremental learning method is applied to the streaming data collected every 24 hours. The linear regression and recurrent neural networks (RNN) models are compared to evaluate the performance of LSTM model. Experimental results show that the proposed LSTM prediction model has 700% improvement over linear regression and 140% improvement over RNN model for its performance level.

• Journal of Korea Water Resources Association
• /
• v.54 no.5
• /
• pp.301-309
• /
• 2021

In this study, we tried to improve the performance of the existing U-net-based deep learning rainfall prediction model, which can weaken the meaning of time series order. For this, ConvLSTM2D U-Net structure model considering temporal consistency of data was applied, and we evaluated accuracy of the ConvLSTM2D U-Net model using a RainNet model and an extrapolation-based advection model. In addition, we tried to improve the uncertainty in the model training process by performing learning not only with a single model but also with 10 ensemble models. The trained neural network rainfall prediction model was optimized to generate 10-minute advance prediction data using four consecutive data of the past 30 minutes from the present. The results of deep learning rainfall prediction models are difficult to identify schematically distinct differences, but with ConvLSTM2D U-Net, the magnitude of the prediction error is the smallest and the location of rainfall is relatively accurate. In particular, the ensemble ConvLSTM2D U-Net showed high CSI, low MAE, and a narrow error range, and predicted rainfall more accurately and stable prediction performance than other models. However, the prediction performance for a specific point was very low compared to the prediction performance for the entire area, and the deep learning rainfall prediction model also had limitations. Through this study, it was confirmed that the ConvLSTM2D U-Net neural network structure to account for the change of time could increase the prediction accuracy, but there is still a limitation of the convolution deep neural network model due to spatial smoothing in the strong rainfall region or detailed rainfall prediction.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.1
• /
• pp.173-180
• /
• 2009

It is difficult to predict non-stationary or chaotic time series which includes the drift and/or the non-linearity as well as uncertainty. To solve it, we propose an effective prediction method which adopts data preprocessing and multiple model TS fuzzy predictors combined with model selection mechanism. In data preprocessing procedure, the candidates of the optimal difference interval are determined based on the correlation analysis, and corresponding difference data sets are generated in order to use them as predictor input instead of the original ones because the difference data can stabilize the statistical characteristics of those time series and better reveals their implicit properties. Then, TS fuzzy predictors are constructed for multiple model bank, where k-means clustering algorithm is used for fuzzy partition of input space, and the least squares method is applied to parameter identification of fuzzy rules. Among the predictors in the model bank, the one which best minimizes the performance index is selected, and it is used for prediction thereafter. Finally, the error compensation procedure based on correlation analysis is added to improve the prediction accuracy. Some computer simulations are performed to verify the effectiveness of the proposed method.

• The Journal of Information Systems
• /
• v.29 no.1
• /
• pp.241-265
• /
• 2020

Purpose Various machine learning techniques are used to implement for predicting corporate credit. However, previous research doesn't utilize time series input features and has a limited prediction timing. Furthermore, in the case of corporate bond credit rating forecast, corporate sample is limited because only large companies are selected for corporate bond credit rating. To address limitations of prior research, this study attempts to implement a predictive model with more sample companies, which can adjust the forecasting point at the present time by using the credit score information and corporate information in time series. Design/methodology/approach To implement this forecasting model, this study uses the sample of 2,191 companies with KIS credit scores for 18 years from 2000 to 2017. For improving the performance of the predictive model, various financial and non-financial features are applied as input variables in a time series through a sliding window technique. In addition, this research also tests various machine learning techniques that were traditionally used to increase the validity of analysis results, and the deep learning technique that is being actively researched of late. Findings RNN-based stateful LSTM model shows good performance in credit rating prediction. By extending the forecasting time point, we find how the performance of the predictive model changes over time and evaluate the feature groups in the short and long terms. In comparison with other studies, the results of 5 classification prediction through label reclassification show good performance relatively. In addition, about 90% accuracy is found in the bad credit forecasts.

• Journal of Information Processing Systems
• /
• v.13 no.4
• /
• pp.951-969
• /
• 2017

In this paper, we newly propose a traffic information service model that collects traffic information sensed by an individual vehicle in real time by using a smart device, and which enables drivers to share traffic information on all roads in real time using an application installed on a smart device. In particular, when the driver requests traffic information for a specific area, the proposed driver-personalized service model provides him/her with traffic information on the driving directions in advance by predicting the driving directions of the vehicle based on the learning of the driving records of each driver. To do this, we propose a traffic information management model to process and manage in real time a large amount of online-generated traffic information and traffic information requests generated by each vehicle. We also propose a road node-based indexing technique to efficiently store and manage location-based traffic information provided by each vehicle. Finally, we propose a driving learning and prediction model based on the hidden Markov model to predict the driving directions of each driver based on the driver's driving records. We analyze the traffic information processing performance of the proposed model and the accuracy of the driving prediction model using traffic information collected from actual driving vehicles for the entire area of Seoul, as well as driving records and experimental data.

• Journal of Navigation and Port Research
• /
• v.48 no.2
• /
• pp.116-124
• /
• 2024

Automatic docking of small planing ship is a critical aspect of maritime operations, requiring accurate prediction of motion states to ensure safe and efficient maneuvers. This study investigates the use of Artificial Neural Network (ANN) to predict motion state of a small planing ship to enhance navigation automation in port environments. To achieve this, simulation tests were conducted to control a small planing ship while docking at various heading angles in calm water and in waves. Comprehensive analysis of the ANN-based predictive model was conducted by training and validation using data from various docking situations to improve its ability to accurately capture motion characteristics of a small planing ship. The trained ANN model was used to predict the motion state of the small planning ship based on any initial motion state. Results showed that the small planing ship could dock smoothly in both calm water and waves conditions, confirming the accuracy and reliability of the proposed method for prediction. Moreover, the ANN-based prediction model can adjust the dynamic model of the small planing ship to adapt in real-time and enhance the robustness of an automatic positioning system. This study contributes to the ongoing development of automated navigation systems and facilitates safer and more efficient maritime transport operations.

• Journal of Astronomy and Space Sciences
• /
• v.32 no.1
• /
• pp.39-44
• /
• 2015

It is well known that the space radiation dose over the polar route should be carefully considered especially when the space weather shows sudden disturbances such as CME and flares. The National Meteorological Satellite Center (NMSC) and Korea Astronomy and Space Science Institute (KASI) recently established a basis for a space radiation service for the public by developing a space radiation prediction model and heliocentric potential (HCP) prediction model. The HCP value is used as a critical input value of the CARI-6 and CARI-6M programs, which estimate the aviation route dose. The CARI-6/6M is the most widely used and confidential program that is officially provided by the U.S. Federal Aviation Administration (FAA). The HCP value is given one month late in the FAA official webpage, making it difficult to obtain real-time information on the aviation route dose. In order to overcome this limitation regarding time delay, we developed a HCP prediction model based on the sunspot number variation. In this paper, we focus on the purpose and process of our HCP prediction model development. Finally, we find the highest correlation coefficient of 0.9 between the monthly sunspot number and the HCP value with an eight month time shift.