Loading [MathJax]/jax/output/CommonHTML/jax.js
  • Title/Summary/Keyword: Prediction of variables

Search Result 1,887, Processing Time 0.032 seconds

Non-destructive quality prediction of domestic, commercial red pepper powder using hyperspectral imaging

  • Sang Seop Kim;Ji-Young Choi;Jeong Ho Lim;Jeong-Seok Cho
    • Food Science and Preservation
    • /
    • v.30 no.2
    • /
    • pp.224-234
    • /
    • 2023
  • We analyzed the major quality characteristics of red pepper powders from various regions and predicted these characteristics nondestructively using shortwave infrared hyperspectral imaging (HSI) technology. We conducted partial least squares regression analysis on 70% (n=71) of the acquired hyperspectral data of the red pepper powders to examine the major quality characteristics. Rc2 values of ≥0.8 were obtained for the ASTA color value (0.9263) and capsaicinoid content (0.8310). The developed quality prediction model was validated using the remaining 30% (n=35) of the hyperspectral data; the highest accuracy was achieved for the ASTA color value (Rp2=0.8488), and similar validity levels were achieved for the capsaicinoid and moisture contents. To increase the accuracy of the quality prediction model, we conducted spectrum preprocessing using SNV, MSC, SG-1, and SG-2, and the model's accuracy was verified. The results indicated that the accuracy of the model was most significantly improved by the MSC method, and the prediction accuracy for the ASTA color value was the highest for all the spectrum preprocessing methods. Our findings suggest that the quality characteristics of red pepper powders, even powders that do not conform to specific variables such as particle size and moisture content, can be predicted via HSI.

PREDICTION OF DIAMETRAL CREEP FOR PRESSURE TUBES OF A PRESSURIZED HEAVY WATER REACTOR USING DATA BASED MODELING

  • Lee, Jae-Yong;Na, Man-Gyun
    • Nuclear Engineering and Technology
    • /
    • v.44 no.4
    • /
    • pp.355-362
    • /
    • 2012
  • The aim of this study was to develop a bundle position-wise linear model (BPLM) to predict Pressure Tube (PT) diametral creep employing the previously measured PT diameters and operating conditions. There are twelve bundles in a fuel channel, and for each bundle a linear model was developed by using the dependent variables, such as the fast neutron fluences and the bundle coolant temperatures. The training data set was selected using the subtractive clustering method. The data of 39 channels that consist of 80 percent of a total of 49 measured channels from Units 2, 3, and 4 of the Wolsung nuclear plant in Korea were used to develop the BPLM. The data from the remaining 10 channels were used to test the developed BPLM. The BPLM was optimized by the maximum likelihood estimation method. The developed BPLM to predict PT diametral creep was verified using the operating data gathered from Units 2, 3, and 4. Two error components for the BPLM, which are the epistemic error and the aleatory error, were generated. The diametral creep prediction and two error components will be used for the generation of the regional overpower trip setpoint at the corresponding effective full power days. The root mean square (RMS) errors were also generated and compared to those from the current prediction method. The RMS errors were found to be less than the previous errors.

Clustering of Seoul Public Parking Lots and Demand Prediction (서울시 공영주차장 군집화 및 수요 예측)

  • Jeongjoon Hwang;Young-Hyun Shin;Hyo-Sub Sim;Dohyun Kim;Dong-Guen Kim
    • Journal of Korean Society for Quality Management
    • /
    • v.51 no.4
    • /
    • pp.497-514
    • /
    • 2023
  • Purpose: This study aims to estimate the demand for various public parking lots in Seoul by clustering similar demand types of parking lots and predicting the demand for new public parking lots. Methods: We examined real-time parking information data and used time series clustering analysis to cluster public parking lots with similar demand patterns. We also performed various regression analyses of parking demand based on diverse heterogeneous data that affect parking demand and proposed a parking demand prediction model. Results: As a result of cluster analysis, 68 public parking lots in Seoul were clustered into four types with similar demand patterns. We also identified key variables impacting parking demand and obtained a precise model for predicting parking demands. Conclusion: The proposed prediction model can be used to improve the efficiency and publicity of public parking lots in Seoul, and can be used as a basis for constructing new public parking lots that meet the actual demand. Future research could include studies on demand estimation models for each type of parking lot, and studies on the impact of parking lot usage patterns on demand.

Predicting and Interpreting Quality of CMP Process for Semiconductor Wafers Using Machine Learning (머신러닝을 이용한 반도체 웨이퍼 평탄화 공정품질 예측 및 해석 모형 개발)

  • Ahn, Jeong-Eon;Jung, Jae-Yoon
    • The Journal of Bigdata
    • /
    • v.4 no.2
    • /
    • pp.61-71
    • /
    • 2019
  • Chemical Mechanical Planarization (CMP) process that planarizes semiconductor wafer's surface by polishing is difficult to manage reliably since it is under various chemicals and physical machinery. In CMP process, Material Removal Rate (MRR) is often used for a quality indicator, and it is important to predict MRR in managing CMP process stably. In this study, we introduce prediction models using machine learning techniques of analyzing time-series sensor data collected in CMP process, and the classification models that are used to interpret process quality conditions. In addition, we find meaningful variables affecting process quality and explain process variables' conditions to keep process quality high by analyzing classification result.

  • PDF

Study on Single-Phase Heat Transfer, Pressure Drop Characteristics and Performance Prediction Program in the Oblong Shell and Plate Heat Exchanger (Oblong 셀 앤 플레이트 열교환기에서의 단상 열전달, 압력강하 특성 및 성능예측 프로그램 개발에 관한 연구)

  • 권용하;김영수;박재홍
    • Journal of Advanced Marine Engineering and Technology
    • /
    • v.28 no.6
    • /
    • pp.1026-1036
    • /
    • 2004
  • In this study, single-phase heat transfer experiments were conducted with Oblong Shell and Plate heat exchanger using water. An experimental water loop has been developed to measure the single-phase heat transfer coefficient and pressure drop in a vertical Oblong Shell and Plate heat exchanger. Downflow of hot water in one channel receives heat from the cold water upflow of water in the other channel. Similar to the case of a plate heat exchanger, even at a very low Reynolds number, the flow in the Oblong Shell and Plate heat exchanger remains turbulent. The present data show that the heat transfer coefficient and pressure drop increase with the Reynolds number. Based on the present data, empirical correlations of the heat transfer coefficient and pressure drop in terms of Nusselt number and friction factor were proposed. Also, performance prediction analyses for Oblong Shell and Plate heat exchanger were executed and compared with experiments. ε-NTU method was used in this prediction program. Independent variables are flow rates and inlet temperatures. Compared with experimental data, the accuracy of the program is within the error bounds of ±5% in the heat transfer rate.

Market Prediction Methodology for a Medical 3D Printing Business : Focusing on Dentistry (의료분야 3D프린팅 비즈니스 시장규모 예측 연구 : 치과 분야를 중심으로)

  • Kim, Min Kwan;Lee, Jungwoo;Kim, Young Myung;Lee, Kikwang;Han, Chang Hee
    • Journal of Information Technology Applications and Management
    • /
    • v.23 no.2
    • /
    • pp.263-277
    • /
    • 2016
  • Recently, 3D printing technology has been considered as a core applicable technology because it brings many improvements such as the development of medical technology, medical customization, and reducing production cost and shortening treatment period. This research suggests a market prediction framework for medical 3D printing business. As an immature market situation, it is important to control some uncertainty for market prediction such as a customers' conversion rate. So we adopt decision making tree (DMT) model which used to choose an optimal decision making among diverse pathway. Among medical industries this paper just focuses on dentistry business. For predicting a 5 year period trend expected market size, we identified some replaceable denture procedure by 3D printing, collected related data, controlled uncertain variables. The result shows that medical 3D printing business could be a market of 28.2 billion won at 1st year and in the end of fifth year it could become on a scale of 61.1 billion won market.

Impact of SAPHIR Data Assimilation in the KIAPS Global Numerical Weather Prediction System (KIAPS 전지구 수치예보모델 시스템에서 SAPHIR 자료동화 효과)

  • Lee, Sihye;Chun, Hyoung-Wook;Song, Hyo-Jong
    • Atmosphere
    • /
    • v.28 no.2
    • /
    • pp.141-151
    • /
    • 2018
  • The KIAPS global model and data assimilation system were extended to assimilate brightness temperature from the Sondeur Atmosphˊerique du Profil dHumiditˊe Intertropicale par Radiomˊetrie (SAPHIR) passive microwave water vapor sounder on board the Megha-Tropiques satellite. Quality control procedures were developed to assess the SAPHIR data quality for assimilating clear-sky observations over the ocean, and to characterize observation biases and errors. In the global cycle, additional assimilation of SAPHIR observation shows globally significant benefits for 1.5% reduction of the humidity root-mean-square difference (RMSD) against European Centre for Medium-Range Weather Forecasts (ECMWF) Integrated Forecast System (IFS) analysis. The positive forecast impacts for the humidity and temperature in the experiment assimilating SAPHIR were predominant at later lead times between 96- and 168-hour. Even though its spatial coverage is confined to lower latitudes of 30S30N and the observable variable is humidity, the assimilation of SAPHIR has a positive impact on the other variables over the mid-latitude domain. Verification showed a 3% reduction of the humidity RMSD with assimilating SAPHIR, and moreover temperature, zonal wind and surface pressure RMSDs were reduced up to 3%, 5% and 7% near the tropical and mid-latitude regions, respectively.

Prediction Models of Conflict and Intimacy in Teacher-Child Relationships: Investigation of Child Variables Based on Decision Tree Analysis (교사-유아 관계의 갈등 및 친밀감에 대한 예측 모형: 의사결정나무분석을 적용한 유아변인의 탐색)

  • Shin, Yoolim
    • Korean Journal of Childcare and Education
    • /
    • v.16 no.5
    • /
    • pp.69-86
    • /
    • 2020
  • Objective: The purpose of this research was to examine the prediction models of conflict and intimacy in teacher-child relationships based on decision tree analysis. Methods: The participants were 297 preschool children from ages three to five including 166 boys and 131 girls. Teacher-child relationships were measured by the Student-Teacher Relationship Scale(STRS). Physical aggression, relational aggression, social withdrawal, and prosocial behaviors were measured by teacher ratings. Moreover, ADHD-RS(Attentive Deficit Hyperactivity Disorder Rating Scale) was used to measure ADHD. The data was analyzed with decision tree analysis. Results: According to the prediction model for teacher-child conflict, the significant predictors were physical aggression and social withdrawal. According to the prediction model for teacher-child intimacy, the significant predictors were prosocial behaviors and relational aggression. However, children's age, gender and ADHD were not significant predictors. Conclusion/Implications: The findings suggest that social behaviors may be closely related with teacher-child relationships for preschool children. Based on the results of this study, intervention suggestions were made.

Financial Market Prediction and Improving the Performance Based on Large-scale Exogenous Variables and Deep Neural Networks (대규모 외생 변수 및 Deep Neural Network 기반 금융 시장 예측 및 성능 향상)

  • Cheon, Sung Gil;Lee, Ju Hong;Choi, Bum Ghi;Song, Jae Won
    • Smart Media Journal
    • /
    • v.9 no.4
    • /
    • pp.26-35
    • /
    • 2020
  • Attempts to predict future stock prices have been studied steadily since the past. However, unlike general time-series data, financial time-series data has various obstacles to making predictions such as non-stationarity, long-term dependence, and non-linearity. In addition, variables of a wide range of data have limitations in the selection by humans, and the model should be able to automatically extract variables well. In this paper, we propose a 'sliding time step normalization' method that can normalize non-stationary data and LSTM autoencoder to compress variables from all variables. and 'moving transfer learning', which divides periods and performs transfer learning. In addition, the experiment shows that the performance is superior when using as many variables as possible through the neural network rather than using only 100 major financial variables and by using 'sliding time step normalization' to normalize the non-stationarity of data in all sections, it is shown to be effective in improving performance. 'moving transfer learning' shows that it is effective in improving the performance in long test intervals by evaluating the performance of the model and performing transfer learning in the test interval for each step.

Daily PM2.5 Estimation using Multiple Linear Regression and Artificial Neural Networks Before 2015 (다중선형회귀와 인공신경망을 이용한 2015년 이전 PM2.5 일일 평균 수치 추정 방법론 제안)

  • Jin-Woo Huh;SeJoon Park
    • Journal of Industrial Technology
    • /
    • v.44 no.1
    • /
    • pp.1-7
    • /
    • 2024
  • Since 2015, the PM2.5 measurement data has been publicly available nationwide in South Korea, but its use is restricted to after 2015, unlike other air pollutants. To overcome this limitation, multiple linear regression and artificial neural network models were developed to predict the daily average PM2.5 values in South Korea before 2015. The daily data of air pollution measurement(SO2, CO, O3, NO2, PM10) and meteorological observation data (temperature, humidity, wind speed, atmospheric pressure, precipitation, snowfall) were used as input variables to develop regional prediction models for five regions(Seoul, Incheon, Gwangju, Daejeon, Ulsan) and a national prediction model. The models were developed and validated using the air pollution measurement data after 2015, and applied to predict PM2.5 values before 2015. The multiple linear regression model showed R2 values of 0.80 nationwide, 0.73 in Seoul, and 0.67 in Incheon, which enabled estimation of daily average PM2.5 values before 2015. The artificial neural network model showed good prediction power with R2 values of 0.79 in Gwangju, 0.81 in Daejeon, and 0.72 in Ulsan. The regional prediction models showed good prediction power in most regions, and both the multiple linear regression and artificial neural network models showed good prediction power.