• 산업경영시스템학회지
• /
• 제46권3호
• /
• pp.123-138
• /
• 2023

The Fourth Industrial Revolution and sensor technology have led to increased utilization of sensor data. In our modern society, data complexity is rising, and the extraction of valuable information has become crucial with the rapid changes in information technology (IT). Recurrent neural networks (RNN) and long short-term memory (LSTM) models have shown remarkable performance in natural language processing (NLP) and time series prediction. Consequently, there is a strong expectation that models excelling in NLP will also excel in time series prediction. However, current research on Transformer models for time series prediction remains limited. Traditional RNN and LSTM models have demonstrated superior performance compared to Transformers in big data analysis. Nevertheless, with continuous advancements in Transformer models, such as GPT-2 (Generative Pre-trained Transformer 2) and ProphetNet, they have gained attention in the field of time series prediction. This study aims to evaluate the classification performance and interval prediction of remaining useful life (RUL) using an advanced Transformer model. The performance of each model will be utilized to establish a health index (HI) for cutting blades, enabling real-time monitoring of machine health. The results are expected to provide valuable insights for machine monitoring, evaluation, and management, confirming the effectiveness of advanced Transformer models in time series analysis when applied in industrial settings.

• 한국환경과학회지
• /
• 제30권10호
• /
• pp.779-787
• /
• 2021

This study analyzes structural landscape changes over a time-series for a small and medium-sized city, Gangneung-Si, based on area and distribution patterns, and according to the type of land cover. Among the types of land cover, the area ratio of urbanized areas increased by 2.02% in the late 2010s as compared to the late 1980s, while there was a decrease of 2.69% in farmland and 0.69% in grassland areas. On analyzing the changes in land cover use by applying the Fragstats program, it was confirmed that landscape changes in urban and management areas were relatively severe according to the Landscape Shape Index, Largest Patch Index, and Aggregation Index. A pattern of concentrated expansion was also found around certain areas. In particular, from the analysis, it was established that the proportion of urbanized area had considerably increased and that the extent of farmland damage to management areas, including planned management areas, was large. Additionally, the Total Core Area generally indicated a reduction in the core areas of farmland and forest within urban and management areas. A medium-sized city showed significant changes besides large cities in terms of landscape structure. The developmental pressure on management areas, in particular, was quite high.

• 디지털산업정보학회논문지
• /
• 제14권2호
• /
• pp.19-25
• /
• 2018

With the development of IT technology, various services such as artificial intelligence and autonomous vehicles are being introduced, and many changes are taking place in our lives. However, if secure security is not provided, it will cause many risks, so the information security becomes more important. In this paper, we analyzed the research trends of main themes of information security over time. In order to conduct the research, 'Information Security' was searched in the Web of Science database. Using the abstracts of theses published from 1991 to 2016, we derived main research topics through topic modeling and time series regression analysis. The topic modeling results showed that the research topics were Information technology, system access, attack, threat, risk management, network type, security management, security awareness, certification level, information protection organization, security policy, access control, personal information, security investment, computing environment, investment cost, system structure, authentication method, user behavior, encryption. The time series regression results indicated that all the topics were hot topics.

• 한국경영과학회지
• /
• 제16권1호
• /
• pp.113-119
• /
• 1991

The author is currently assistant professor of Management Science at Korea Advanced Institute of Science and Technology, following a few years as assistant professor of Industrial Engineering at Kyung Hee University, Korea. He received his doctorate from the department of Industrial Engineering and Operations Research, University of California, Berkeley. His research interests are time series and forecasting modelling, Bayesian forecasting and the related software development. He is now teaching time series analysis and econometrics at the graduate level.

• 응용통계연구
• /
• 제32권5호
• /
• pp.671-681
• /
• 2019

최근에 부정맥 환자가 증가하면서 머신러닝을 이용한 부정맥을 예측하는 연구가 활발하게 진행되고 있다. 기존의 많은 연구들은 특정한 시점의 RR 간격 데이터에서 추출한 특징변수 다변량 데이터에 기반하여 부정맥을 예측하였다. 본 연구에서는 심장 상태가 시간에 따라 변해가는 패턴도 부정맥 예측에 중요한 정보가 될 수 있다고 생각하여 일정한 시간 간격을 두고 특징변수의 다변량 벡터를 추출하여 쌓음으써 얻어지는 다변량 시계열 데이터로 부정맥을 예측하는 것의 유용성에 대해 살펴보았다. 1-Nearest Neighbor 방법과 그것을 앙상블(ensemble)한 learner를 중심으로 비교했을 경우 시계열의 특징을 고려한 적절한 시계열 거리함수를 선택하여 시계열 정보를 활용한 다변량 시계열 데이터 기반 방법의 분류 성능이 더 좋게 나오는 것을 확인하였다.

• 한국시뮬레이션학회논문지
• /
• 제20권4호
• /
• pp.67-79
• /
• 2011

본 연구에서는 시계열 공정데이터 관리를 위한 모델모수 기반 이상 탐지방법을 제안한다. 일반적인 공정관리에 널리 쓰이는 전통적인 통계적 관리기법의 관리도(SPC chart)는 측정되는 데이터가 특정 분포를 따르며 상관관계가 없는 상황을 가정한다. 따라서 공정데이터 형태가 시계열데이터와 같이 특정분포를 따르지 않고, 자기상관관계를 갖는다면 전통적인 관리도로는 관리에 한계를 보인다. 본 연구는 시계열을 따르는 공정의 이상을 탐지를 위한 MPBC(Model Parameter Based Control-chart) 방법을 제안한다. 제안된 MPBC는 시계열공정을 모델링하고, 모델모수의 변화를 감지하여 공정의 이상을 탐지하는 방법이다. 시계열 공정은 ARMA(p,q) 모델을 가정하며, RLS(Recursive Least Square)를 이용하여 시계열 모델의 모수를 추정하고, 추정된 모수를 $K^2$관리도로 관리한다. 제안된 방법은 기존 알고리즘과 비교하여 시계열 공정 변화 탐지에 우수한 성능을 보였으며 시계열 데이터에 있어서 보다 효율적인 공정관리 방향을 제시한다.

• 품질경영학회지
• /
• 제48권3호
• /
• pp.511-520
• /
• 2020

Purpose: The purpose of this study was to devise an accurate machine learning model for predicting silica concentrations following the addition of impurities, through time series analysis of mining data. Methods: The mining data were preprocessed and subjected to time series analysis using the machine learning model. Through correlation analysis, valid variables were selected and meaningless variables were excluded. To reflect changes over time, dependent variables at baseline were treated as independent variables at later time points. The relationship between independent variables and the dependent variable after n point was subjected to Pearson correlation analysis. Results: The correlation (R2) was strongest after 3 hours, which was adopted as a dependent variable. According to root mean square error (RMSE) data, the proposed method was superior to the other machine learning methods. The XGboost algorithm showed the best predictive performance. Conclusion: This study is important given the current lack of machine learning studies pertaining to the domestic mining industry. In addition, using time series analysis in mining data will show further improvement. Before establishing a predictive model for the proposed method, predictions should be made using data with time series characteristics. After doing this work, it should also improve prediction accuracy in other domains.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2009년도 학술발표회 초록집
• /
• pp.1260-1264
• /
• 2009

Precipitation time series is a mixture of complicate fluctuation and changes. The monthly precipitation data of 61 stations during 36 years (1973-2008) in Korea are comprehensively analyzed using the EOFs technique and CSEOFs technique respectively. The main motivation for employing this technique in the present study is to investigate the physical processes associated with the evolution of the precipitation from observation data. The twenty-five leading EOF modes account for 98.05% of the total monthly variance, and the first two modes account for 83.68% of total variation. The first mode exhibits traditional spatial pattern with annual cycle of corresponding PC time series and second mode shows strong North South gradient. In CSEOF analysis, the twenty-five leading CSEOF modes account for 98.58% of the total monthly variance, and the first two modes account for 78.69% of total variation, these first two patterns' spatial distribution show monthly spatial variation. The corresponding mode's PC time series reveals the annual cycle on a monthly time scale and long-term fluctuation and first mode's PC time series shows increasing linear trend which represents that spatial and temporal variability of first mode pattern has strengthened. Compared with the EOFs analysis, the CSEOFs analysis preferably exhibits the spatial distribution and temporal evolution characteristics and variability of Korean historical precipitation.

• 응용통계연구
• /
• 제33권4호
• /
• pp.467-482
• /
• 2020

본 논문은 이분산성을 갖는 위치-척도 시계열 모형에서 모수의 변화에 대한 모니터링 절차를 연구한다. 모니터링 절차에서 수정된 잔차의 누적합을 이용한 탐지기를 소개하고 귀무가설과 대립가설 하에서 각각 모니터링 절차에 대한 점근적 성질을 규명한다. 그리고 모의실험과 사례 분석을 통하여 제안한 모니터링 방법의 성능이 우수함을 확인한다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume II
• /
• pp.764-767
• /
• 2006

It can be important framework data to monitor the change of land-use pattern of river boundary in design and management of river. This study analyzed the change of land-use pattern of Gab- and Yudeung River using time-series aerial images. To do this, we carried out radiation and geometric correction of image, and estimated land-use changes in inland and floodplain. As the analysis of inland, the ratio of residential, commercial, industrial, educational and public area, that is urbanized element, increases, but that of agricultural area shows a decline on the basis of 1990. Also, Minimum Distance Method, which is a kind of supervised classification method, is applied to extract water-body and sand bar layer in floodplain. As the analysis of land-use, the ratio of level-upped riverside land and water-body increases, but that of sand bar decreases. These time-series land use information can be important decision making data to evaluate the urbanization of river boundary, and especially it gives us goodness in river development project such as the composition of ecological habitat.