• Smart Structures and Systems
• /
• 제26권1호
• /
• pp.23-33
• /
• 2020

Majority of the damage in engineering structures is nonlinear. Damage sensitive features (DSFs) extracted by traditional methods from linear time series models cannot effectively handle nonlinearity induced by structural damage. A new DSF is proposed based on vector space cosine similarity (VSCS), which combines K-means cluster analysis and Bayesian discrimination to detect nonlinear structural damage. A reference autoregressive moving average (ARMA) model is built based on measured acceleration data. This study first considers an existing DSF, residual standard deviation (RSD). The DSF is further advanced using the VSCS, and then the advanced VSCS is classified using K-means cluster analysis and Bayes discriminant analysis, respectively. The performance of the proposed approach is then verified using experimental data from a three-story shear building structure, and compared with the results of existing RSD. It is demonstrated that combining the linear ARMA model and the advanced VSCS, with cluster analysis and Bayes discriminant analysis, respectively, is an effective approach for detection of nonlinear damage. This approach improves the reliability and accuracy of the nonlinear damage detection using the linear model and significantly reduces the computational cost. The results indicate that the proposed approach is potential to be a promising damage detection technique.

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 1990년도 춘계공동학술대회논문집; 한국과학기술원; 28 Apr. 1990
• /
• pp.125-139
• /
• 1990

This paper presents a forecasting method for domestic demand of electric home appliances. Because of lack of data, some popular methods such as time series analysis may not be appropriate to forecast such a demand domestically. We suggest a systematic and practical method by considering structural parameters and variables which determine the actual demand. We use this model to forecast the demand of color TV. Since the parameters in our model may be variant according to the change of economic environment, our model leads the user to develop a dynamic model to be used in the well-known System Dynamics Approach.

• 한국방재학회:학술대회논문집
• /
• 한국방재학회 2008년도 정기총회 및 학술발표대회
• /
• pp.669-673
• /
• 2008

In this study, the new methodology which combines Kohonen self-organizing map(KSOM) neural networks model and the conventional neural networks models such as feedforward neural networks model and generalized neural networks model is introduced to forecast flood stage in Nakdong river, Republic of Korea. It is possible to train without output data in KSOM neural networks model. KSOM neural networks model is used to classify the input data before it combines with the conventional neural networks model. Four types of models such as SOM-FFNNM-BP, SOM-GRNNM-GA, FFNNM-BP, and GRNNM-GA are used to train and test performances respectively. From the statistical analysis for training and testing performances, SOM-GRNNM-GA shows the best results compared with the other models such as SOM-FFNNM-BP, FFNNM-BP, and GRNNM-GA and FFNNM-BP shows vice-versa. From this study, we can suggest the new methodology to forecast flood stage and construct flood warning system in river basin.

• 한국정보시스템학회지:정보시스템연구
• /
• 제29권1호
• /
• 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.

• 한국대기환경학회지
• /
• 제25권2호
• /
• pp.167-174
• /
• 2009

The AIRWARE System was developed from one of the EUREKA PROJECT E!3266-EUROENVIRON WEBAIR System. The AIRWARE can nowcast and forecast the air quality of Seoul and Gyeonggi-do regions. To nowcast and forecast concentration of pollutants, MM5, AERMOD/CAMx, and SMOKE Models were used for each meteorologic data, measured data, and emission data. All DB were constructed for 2001 year. The episode analysis and time series analysis were accomplished to analyze the AIRWARE reliability. The simulated results were very well agreed with measured result for measured pollutants and meteorological data. The developed AIRWARE system can analyze with real-time, support web-based air quality information. This information can used with policy data to manage the air quality and prepare reduction plan in air impact assessment or air environmental plan.

• 한국컴퓨터정보학회논문지
• /
• 제23권5호
• /
• pp.9-14
• /
• 2018

For an efficient management of electricity market and power systems, accurate forecasts for electricity demand are essential. Since there are many factors, either known or unknown, determining the realized loads, it is difficult to forecast the demands with the past time series only. In this paper we perform a cluster analysis on electricity demand data collected from Jan. 2000 to Dec. 2017. Our purpose of clustering on electricity demand data is that each cluster is expected to consist of data whose latent variables are same or similar values. Then, if properly clustered, it is possible to develop an accurate forecasting model for each cluster separately. To validate the feasibility of this approach for building better forecasting models, we clustered data with t-SNE. To apply t-SNE to time series data effectively, we adopt the dynamic time warping as a similarity measure. From the result of experiments, we found that several clusters are well observed and each cluster can be interpreted as a mix of well-known factors such as trends, seasonality and holiday effects and other unknown factors. These findings can motivate the approaches which build forecasting models with respect to each cluster independently.

• 지적과 국토정보
• /
• 제47권1호
• /
• pp.5-14
• /
• 2017

급속한 도시화 과정을 거친 대한민국은 도시 공간의 형성 과정에서부터 시설물관리 안전 환경 교통 등 여러 분야에서 다양한 문제들을 직면하고 있다. 이러한 도시 내의 불만과 문제를 해결하기 위해 지방자치단체에서는 전자민원을 통해 이를 접수 처리하고 있지만 민원은 해를 거듭할수록 증가하고 있는 실정이다. 따라서 본 연구는 한국의 지방 중소도시인 진주시를 대상으로 최근 10년간의 전자민원 데이터를 수집하여 민원사유별로 분류하고 민원발생지점에 대한 위치데이터를 추출한 후 Geocoding을 통해 공간정보상에 나타내어 공간분포패턴분석 및 추이분석을 실시하였다. 그리고 ARIMA모형을 사용하여 시계열 예측분석을 통해 향후 2년간(2016년~2017년) 민원발생을 예측하였다. 그 결과 불법주차단속관련 민원이 가장 많이 발생하였고, 소음관련 민원이 두 번째로 많았으며, 불법쓰레기투기관련 민원이 세 번째로 많이 발생한 것으로 나타났다. 또한, 시 공간적 분포 패턴을 분석한 결과, 중심상업지역에서 매년 가장 큰 핫스팟을 형성한 것으로 나타났다. 불법주차단속관련 민원에 대해 시계열 예측분석을 실시한 결과, 해를 거듭하며 다소 증가하는 것으로 나타났으며 예측값과 실제 데이터를 비교한 결과, 매우 비슷한 패턴을 보이며 발생하는 것으로 나타났다. 이를 바탕으로 민원의 발생량 예측을 통해 문제시되는 민원을 찾고, 이에 대한 효과적인 대책을 수립하는데 이용될 수 있을 것으로 판단된다.

• 디지털융복합연구
• /
• 제15권2호
• /
• pp.165-172
• /
• 2017

본 논문에서는 전기자동차를 주제로 SCIE 및 SSCI 저널에 게재한 논문데이터를 활용한 시계열 분석과 국제특허분류(International patent classification, 이하 IPC) 별 특허 데이터를 활용한 시계열 분석과 노드엑셀을 활용한 네트워크 분석을 통해 2001년에서 2014년까지의 전기자동차의 기술 동향을 파악하고 특허와 논문 데이터의 상관관계 분석을 통하여 기술 동향을 분석하였다. 또한 예측기법 중 하나인 가중이동평균법으로 전기자동차의 유망 요소기술을 예측하였다. 본 연구의 결과 전기자동차 요소기술 중 배터리 기술이 유망한 기술로 나타났다.

• 천문학회지
• /
• 제53권6호
• /
• pp.139-147
• /
• 2020

The sunspot area is a critical physical quantity for assessing the solar activity level; forecasts of the sunspot area are of great importance for studies of the solar activity and space weather. We developed an innovative hybrid model prediction method by integrating the complementary ensemble empirical mode decomposition (CEEMD) and extreme learning machine (ELM). The time series is first decomposed into intrinsic mode functions (IMFs) with different frequencies by CEEMD; these IMFs can be divided into three groups, a high-frequency group, a low-frequency group, and a trend group. The ELM forecasting models are established to forecast the three groups separately. The final forecast results are obtained by summing up the forecast values of each group. The proposed hybrid model is applied to the smoothed monthly mean sunspot area archived at NASA's Marshall Space Flight Center (MSFC). We find a mean absolute percentage error (MAPE) and a root mean square error (RMSE) of 1.80% and 9.75, respectively, which indicates that: (1) for the CEEMD-ELM model, the predicted sunspot area is in good agreement with the observed one; (2) the proposed model outperforms previous approaches in terms of prediction accuracy and operational efficiency.

• 대한토목학회논문집
• /
• 제29권2B호
• /
• pp.163-171
• /
• 2009

수문시계열 분석과 예측을 위하여 통상적으로 기존의 선형적인 모형들을 이용하여 왔다. 그러나 최근 자연현상이나 수문시계열의 패턴 그리고 변동성에 비선형구조가 존재하고 있다는 것이 입증되고 있다. 따라서 기존의 선형적인 방법들에 의한 시계열분석이나 예측은 비선형 시스템에 대해서 적절하지 않을 것이다. 최근, 시계열의 비선형성 구조를 판단하기 위해 카오스 이론을 토대로 한 상관적분으로부터 BDS(Brock-Dechert-Scheinkman) 통계 기법이 유도되었다. BDS 통계는 시스템의 비선형구조와 무작위성 구조를 구별하는데 매우 효과적으로 이용되어 오고 있다. 또한 DVS(Deterministic Versus Stochastic) 알고리즘은 카오스와 추계학적 시스템을 구별하고 예측하는데 주로 이용되어 왔다. 그러나 본 연구에서는 DVS 알고리즘에 의해 시계열의 비선형성을 판별할 수 있음을 보이고자 한다. 따라서 본 연구에서는 추계학적 시계열과 수문학적 시계열들의 비선형성을 검사하고자 한다. ARMA 모형과 TAR(Threshold autoregressive) 모형으로부터로 발생시킨 추계학적 시계열, 미국 유타주 GSL 체적자료, 미국 플로리다 주 St. Johns 강 Cocoa 지점의 유출량 자료, 소양강 댐 일 유입량 자료 등의 수문시계열에 대해 비선형성 분석을 수행하고 그 결과를 비교하였다. 분석결과 BDS 통계가 선형 및 비선형 시계열을 구분하는데 매우 강력한 도구임을 보였고, DVS 알고리즘 또한 시계열의 비선형성을 구별하는데 효과적으로 이용될 수 있음을 보였다.