• Journal of the Korean Society of Marine Environment & Safety
• /
• v.18 no.6
• /
• pp.545-550
• /
• 2012

Wind resource assessment is necessary when designing wind farm. To get the assessment, we must use a long term(20 years) observed wind data but it is so hard. so that we usually measured more than a year on the planned site. From the wind data, we can calculate wind energy related with the wind farm site. However, it calculate wind energy to collect the long term data from Met-mast(Meteorology Mast) station on the site since the Met-mast is unstable from strong wind such as Typhoon or storm surge which is Non-periodic. To solve the lack of the long term data of the site, we usually derive new data from the long term observed data of AWS(Automatic Weather Station) around the wind farm area using mathematical interpolation method. The interpolation method is called MCP(Measure-Correlative-Predict). In this study, based on the MCP Regression Model proposed by us, we estimated the wind energy at Handong site using AEP(Annual Energy Production) from Gujwa AWS data in Jeju. The calculated wind energy at Handong was shown a good agreement between the predicted and the measured results based on the linear regression MCP. Short term AEP was about 7,475MW/year. Long term AEP was about 7,205MW/year. it showed an 3.6% of annual prediction different. It represents difference of 271MW in annual energy production. In comparison with 20years, it shows difference of 5,420MW, and this is about 9 months of energy production. From the results, we found that the proposed linear regression MCP method was very reasonable to estimate the wind resource of wind farm.

• 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.

• Transactions of the Korean hydrogen and new energy society
• /
• v.32 no.6
• /
• pp.592-611
• /
• 2021

In this study a rarely available high-throughput cycling data set of 124 commercial lithium iron phosphate/graphite cells cycled under fast-charging conditions, with widely varying cycle lives ranging from 150 to 2,300 cycles including in-cycle temperature and per-cycle IR measurements. We worked out own Python codes which reproduced the various data plots and machine learning approaches for cycle life prediction using early cycles and more details not presented in the article and the supplementary information. Particularly, we applied regularized ridge, lasso and elastic net linear regression models using features extracted from capacity fade curves, discharge voltage curves, and other data such as internal resistance and cell can temperature. We found that due to the limitation in the quantity and quality of the data from costly and lengthy battery testing a careful hyperparameter tuning may be required and that model features need to be extracted based on the domain knowledge.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.513-515
• /
• 2022

Manufacturing data collected using IoT devices in a smart factory environment is generally reliable except for noises caused by external factors. However, unlike manufacturing data that is collected mechanically, process data manually recorded by field-workers can cause problems such as the misspelled entries or the missing entries. Therefore, process data must be validated before being used as training data for artificial intelligence models. In this paper, based on the fact that which is a linear relationship between the power consumption of the MCT machine and the production of the product recorded by the field-workers, we detect anomalous records of the workers using robust linear regression.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 1995.04a
• /
• pp.147-152
• /
• 1995

실험에 의한 모우드 해석 방법들은 1980년대부터 활발히 연구되어 많은 새로운 방법들이 개발되어 발표되었다. 그러나 개발된 대부분의 방법들은 측정된 데이타를 일괄처리하는 밸치(또는 off-line) 방법들이다. 최근에는 시간에 따라서 변하는 구조물의 동특성을 규명하는 분야에 모우드 해석 방법이 응용되어 사용되고 있다. 이러한 응용분야에서는 모우드 변수들의 변화되는 값을 새로운 데이타가 샘플링 될 때마다 그 값들을 수정하면서 추정할 수 있는 회귀적인(recursive 또는 on-line) 방법을 사용하여야 한다. Davies와 Hammond[1]는 회귀적 선형 자승법(Recursive Least Squares : RLS)을 이용하여 모우드 변수를 구하고 이를 벧치방법인 Instrumental Variable 방법과 Fourier 방법의 결과와 비교하였다. 그러나, 그 결과에서 보여준것처럼 RLS 방법은 잡음 대 시호비가 낮을 때에만 모우드 변수 값들을 정확하게 추정할 수 있었다. Sundararajan과 Montgomrey[2]는 회귀적 선형 최소자승 격자필터(lattice filter)를 이용하여 구조물의 차수(order)와 고유진동형, 그리고 진폭을 결정한 후 이를 토대로 회귀적 gradient형태의 방정식 오차 규명 방법(equation-error identification algorithm)에 의하여 모우드 변수들을 추정하였다. 이 방법은 2차원 격자구조물의 모우드 변수 추정에 사용되었으며, 또한 적응모우드제어에도 성공적으로 이용되었다. 그러나, 이 방법도 잡음 대 신호비가 낮은 환경에서만 사용할 수 있다는 단점이 있다. 위에서 언급한 방법들은 모두 RLS 방법을 기초로 하여 개발되었으나, RLS 방법은 전형적인 결정적(deterministic)방법으로서 잡음이 섞인 데이타를 처리하기에는 부적절한 방법임이 널리 알려진 사실이다[3]. 최근에 Ben Mrad와 Fassois[4]는 신호에 잡음이 존재하여도 이를 잘 처리할 수 있는 확률적(stochastic) 방법을 개발하여 기존의 결정적 방법들과 그 결과를 비교하였다. 그러나, 개발된 방법은 응답 신호에 백색잡음(white noise)이 섞이는 특수한 경우에만 사용할 수 있게 만들어져서 이 방법의 실질적인 적용에는 어려움이 있다. 본 연구에서는 기존의 방법들의 단점을 극복할 수 있는 새로운 회귀적 모우드 변수 규명 방법을 개발하였다. 이는 Fassois와 Lee가 ARMAX모델의 계수를 효율적으로 추정하기 위하여 개발한 뱉치방법인 Suboptimum Maximum Likelihood 방법[5]를 기초로 하여 개발하였다. 개발된 방법의 장점은 응답 신호에 유색잡음이 존재하여도 모우드 변수들을 항상 정확하게 구할 수 있으며, 또한 알고리즘의 안정성이 보장된 것이다.

• Proceedings of the KSMRM Conference
• /
• 2001.11a
• /
• pp.173-173
• /
• 2001

목적： 1.5T 생체용 자기공명영상기기를 이용한 수소자기공명분광법으로 용액 내 물질의 정량분석에 대한 가능성을 알아보고자 하였다. 대상 및 방법： 0.01％에서 50％까지의 여러 농도를 갖는 포도당+증류수 혼합액의 모델용액을 만들어 생체용 자기공명영상기기와 시험관 nuclear magnetic resonance (NMR) 분광기에서 각각 수소 자기공명분광법을 시행하여 스펙트럼을 얻었다. 또한 12명의 당뇨환자에서 방광내의 소변에 대해 생체용 자기공명영상기기에서 스펙트럼을 얻고 소변을 추출하여 시험관 NMR 분광기에서 수소자기공명분광법을 시행하였다 각각의 방법으로 얻은 스펙트럼 상에서 포도당 농도에 따른 포도당/물 피크의 면적 비의 변화를 구하였고, 통계처리는 상관분석과 단순선형회귀분석을 시행하였고 회귀식을 산출하였다. 또한 생체용 자기공명영상기기를 이용하여 얻은 결과가 객관적인지 알아보기 위해 시험관 NMR 분광기에서 얻은 결과와의 상관관계를 분석하였다.

• Journal of Broadcast Engineering
• /
• v.19 no.6
• /
• pp.798-809
• /
• 2014

Video stabilization is performed to remove unexpected shaky and irregular motion from a video. It is often used as preprocessing for robust feature tracking and matching in video. Typical video stabilization algorithms are developed to compensate motion from surveillance video or outdoor recordings that are captured by a hand-help camera. However, since the vehicle video contains rapid change of motion and local features, typical video stabilization algorithms are hard to be applied as it is. In this paper, we propose a novel approach to compensate shaky and irregular motion in vehicle video using linear regression model and vertical projection histogram matching. Towards this goal, we perform vertical projection histogram matching at each sub region of an input frame, and then we generate linear regression model to extract vertical translation and rotation parameters with estimated regional vertical movement vector. Multiple binarization with sub-region analysis for generating the linear regression model is effective to typical recording environments where occur rapid change of motion and local features. We demonstrated the effectiveness of our approach on blackbox videos and showed that employing the linear regression model achieved robust estimation of motion parameters and generated stabilized video in full automatic manner.

• Journal of Korea Water Resources Association
• /
• v.30 no.6
• /
• pp.641-648
• /
• 1997

Mutual information is useful for analyzing nonlinear dependence in time series in much the same way as correlation is used to characterize linear dependence. We use multivariate kernel density estimators for the estimation of mutual information at different time lags for single and multiple time series. This approach is tested on a variety of hydrologic data sets, and suggested an appropriate delay time $ au$ at which the mutual information is almost zerothen multi-dimensional phase portraits could be constructed from measurements of a single scalar time series.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.6
• /
• pp.87-96
• /
• 2022

The traffic vulnerable, including elderly pedestrians, have a relatively low walking speed and slow cognitive response time due to reduced physical ability. Although a smart crossing system has been developed and operated to improve problem, it is difficult to operate a signal that reflects the appropriate walking speed for each pedestrian. In this study, a neural network model and a multiple regression model-based traversing speed estimation model were developed using image information collected in an area with a high percentage of traffic vulnerability. to support the provision of optimal walking signals according to real-time traffic weakness. actual traffic data collected from the urban traffic network of Paju-si, Gyeonggi-do were used. The performance of the model was evaluated through seven selected indicators, including correlation coefficient and mean absolute error. The multiple linear regression model had a correlation coefficient of 0.652 and 0.182; the neural network model had a correlation coefficient of 0.823 and 0.105. The neural network model showed higher predictive power.

• Journal of Service Research and Studies
• /
• v.13 no.3
• /
• pp.105-126
• /
• 2023

The domestic used car market continues to grow along with the used car online platform service. The used car online platform service discloses vehicle specifications, accident history, inspection history, and detailed options to service consumers. Most of the preceding studies were predictions of used car prices using vehicle specifications and some options for vehicles. As a result of the study, it was confirmed that there was a nonlinear relationship between used car prices and some specification variables. Accordingly, the researchers tried to solve the nonlinear problem by executing a Machine Learning model. In common, the Regression based Machine Learning model had the advantage of knowing the actual influence and direction of variables, but there was a disadvantage of low Cost Function figures compared to the Decision Tree based Machine Learning model. This study attempted to predict used car prices of six domestic brands by utilizing both vehicle specifications and vehicle options. Through this, we tried to collect the advantages of the two types of Machine Learning models. To this end, we sequentially conducted a regression based Machine Learning model and a decision tree based Machine Learning model. As a result of the analysis, the practical influence and direction of each brand variable, and the best tree based Machine Learning model were selected. The implications of this study are as follows. It will help buyers and sellers who use used car online platform services to predict approximate used car prices. And it is hoped that it will help solve the problem caused by information inequality among users of the used car online platform service.