• 무역학회지
• /
• 제46권6호
• /
• pp.191-209
• /
• 2021

In this paper, various time series analysis models and machine learning models are presented for long-term prediction of export growth rate, and the prediction performance is compared and reviewed by RMSE and MAE. Export growth rate is one of the major economic indicators to evaluate the economic status. And It is also used to predict economic forecast. The export growth rate may have a negative (-) value as well as a positive (+) value. Therefore, Instead of using the ReLU function, which is often used for time series prediction of deep learning models, the PReLU function, which can have a negative (-) value as an output value, was used as the activation function of deep learning models. The time series prediction performance of each model for three types of data was compared and reviewed. The forecast data of long-term prediction of export growth rate was deduced by three forecast methods such as a fixed forecast method, a recursive forecast method and a rolling forecast method. As a result of the forecast, the traditional time series analysis model, ARDL, showed excellent performance, but as the time period of learning data increases, the performance of machine learning models including LSTM was relatively improved.

• International Journal of Air-Conditioning and Refrigeration
• /
• 제10권2호
• /
• pp.65-71
• /
• 2002

The objective of this study is to evaluate the design parameters and to develop the cooling and heating load prediction equations of office buildings. The building load calculation simulation was carried out using the DOE-2.1E program. The results of the simulation were used as data for multiple regression analysis which could develop the load prediction equations.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.1343-1346
• /
• 2005

In the cold rolling mill, coil breakage that generated in rolling process makes the various types of troubles such as the degradation of productivity and the damage of equipment. Recent researches were done by the mechanical analysis such as the analysis of roll chattering or strip inclining and the prevention of breakage that detects the crack of coil. But they could cover some kind of breakages. The prediction of Coil breakage was very complicated and occurred rarely. We propose to build effective prediction modes for coil breakage in rolling process, based on data mining model. We proposed three prediction models for coil breakage: (1) decision tree based model, (2) regression based model and (3) neural network based model. To reduce model parameters, we selected important variables related to the occurrence of coil breakage from the attributes of coil setup by using the methods such as decision tree, variable selection and the choice of domain experts. We developed these prediction models and chose the best model among them using SEMMA process that proposed in SAS E-miner environment. We estimated model accuracy by scoring the prediction model with the posterior probability. We also have developed a software tool to analyze the data and generate the proposed prediction models either automatically and in a user-driven manner. It also has an effective visualization feature that is based on PCA (Principle Component Analysis).

• 한국건축시공학회지
• /
• 제21권2호
• /
• pp.105-112
• /
• 2021

국내 해체시장 규모는 꾸준히 증가되고 있는 반면, 해체공사비 예측 연구는 미흡한 실정이다. 이에 본 연구에서는 해체공사비 변동에 영향을 미치는 다양한 속성을 반영한 공사비 예측 모델을 제시하고자 하였다. 이를 위하여 기존 문헌고찰과 전문가 자문을 바탕으로 13개의 영향요인과 실적공사비 데이터를 수집하였으며, 회귀분석을 통해 2개의 예측모델을 구축하고 예측정확도를 평가하였다. 그 결과, 약 6~12%의 평균 오차율을 보였으며, 예측 모델로서의 활용 가능성을 모색할 수 있었다. 본 연구 결과는 향후 국내 해체공사의 적정 공사비산정 및 관련 기준 정비에 기여할 수 있을 것이다.

• 한국IT서비스학회지
• /
• 제13권3호
• /
• pp.221-233
• /
• 2014

Because people's interest of the stock market has been increased with the development of economy, a lot of studies have been going to predict fluctuation of stock prices. Latterly many studies have been made using scientific and technological method among the various forecasting method, and also data using for study are becoming diverse. So, in this paper we propose stock prices prediction models using sentiment analysis and machine learning based on news articles and SNS data to improve the accuracy of prediction of stock prices. Stock prices prediction models that we propose are generated through the four-step process that contain data collection, sentiment dictionary construction, sentiment analysis, and machine learning. The data have been collected to target newspapers related to economy in the case of news article and to target twitter in the case of SNS data. Sentiment dictionary was built using news articles among the collected data, and we utilize it to process sentiment analysis. In machine learning phase, we generate prediction models using various techniques of classification and the data that was made through sentiment analysis. After generating prediction models, we conducted 10-fold cross-validation to measure the performance of they. The experimental result showed that accuracy is over 80% in a number of ways and F1 score is closer to 0.8. The result can be seen as significantly enhanced result compared with conventional researches utilizing opinion mining or data mining techniques.

• Journal of Mechanical Science and Technology
• /
• 제18권8호
• /
• pp.1428-1434
• /
• 2004

This paper presents the mean streamline analysis using the empirical loss correlations for performance prediction of cross-flow fans. Comparison of overall performance predictions with test data of a cross-flow fan system with a simplified vortex wall scroll casing and with the published experimental characteristics for a cross-flow fan has been carried out to demonstrate the accuracy of the proposed method. Predicted performance curves by the present mean streamline analysis agree well with experimental data for two different cross-flow fans over the normal operating conditions. The prediction method presented herein can be used efficiently as a tool for the preliminary design and performance analysis of general-purpose cross-flow fans.

• Tribology and Lubricants
• /
• 제26권1호
• /
• pp.37-43
• /
• 2010

Precise prediction of rotordynamic coefficients for annular type seal of turbomachinery is necessary for enhancing their vibrational stability and various prediction methods have been developed. As the seal passage is designed complicatedly, the analysis based on Bulk-flow concept which has been mainly used in predicting seal dynamics is limited. In order to improve the seal rotordynamic prediction, full Navier-Stokes Equations with turbulent model derived in the seal flow passage have to be solved. In this study, 3D CFD(Computational Fluid Dynamics) analysis has been performed for predicting rotordynamic coefficients of non-contact type annular plain seal using FLUENT. Comparing with the results of Bulk-flow model analysis, the result of 3D CFD analysis shows good agreement.

• 한국유체기계학회 논문집
• /
• 제9권3호
• /
• pp.14-21
• /
• 2006

Leakage reduction through annular type seals of turbomachinery is necessary for enhancing their efficiency and the precise prediction method of seal leakage is needed. The analysis based on Bulk-flow concept has been mainly used in predicting seal leakage. However, full Navier-Stokes Equations with turbulent model derived in the seal flow passage have to be solved for improving the prediction of seal leakage. FLUENT 6 which is commercial CFD(Computational Fluid Dynamics) code based on FVM(Finite Volume Method) and SIMPLE algorism has been used to analyze leakage of various non-contact-type seals in this presentation. Comparing with the results of Bulk-flow model analysis and experiment, the result of CFD analysis shows good agreement with that of existing theoretical analysis for the incompressible grooved seal and compressive plain and staggered seal. The CFD analysis also shows improvement on the leakage prediction of the incompressible plain seal and compressive see-through-type labyrinth seal.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2001년도 추계학술대회논문집B
• /
• pp.670-675
• /
• 2001

This paper describes aerodynamic preliminary design performance prediction and flow analysis for turbine of the marine middle engine turbocharger. The performance characteristics of turbocharger turbine are investigated at various operating conditions using mass flow rate and computational flow analysis for rotor and nozzle at design point are performed. Preliminary design results are performed by applying mean line and radial equilibrium theory. Performance prediction and flow analysis results show good agreement with experiments. From 3 dimensional flow analysis result, efficiency is 0.6% greater than design point. Therefore, this design approach is useful for preliminary design, and helps to increase the design capability for optimized rotor blade.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2000년도 춘계학술대회논문집
• /
• pp.849-854
• /
• 2000

Statistical energy analysis is suitable for shipboard noise prediction in many respects. It could effectively model the large and complicated ship structures for noise analysis. This paper introduces the procedure of SEA for shipboard noise analysis gained from author's experiences in the past few years. Also, prediction accuracies of shipboard noise analysis using statistical energy analysis are discussed. It is found that the prediction results could be much improved when using the actual measured data of source levels and material properties such as loss factors, absorption coefficients and etc.