• KIPS Transactions on Computer and Communication Systems
• /
• v.8 no.4
• /
• pp.79-86
• /
• 2019

This paper describes a time-series data prediction based on artificial neural networks (ANN). In this study, a batch based ANN model and a stochastic ANN model have been implemented using TensorFlow libraries. Each model are evaluated by comparing training and testing errors that are measured through experiment. To train and test each model, tax dataset was used that are collected from the government website of indiana state budget agency in USA from 2001 to 2018. The dataset includes tax incomes of individual, product sales, company, and total tax incomes. The experimental results show that batch model reveals better performance than stochastic model. Using the batch scheme, we have conducted a prediction experiment. In the experiment, total taxes are predicted during next seven months, and compared with actual collected total taxes. The results shows that predicted data are almost same with the actual data.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.172-172
• /
• 2022

분산계수는 하천에서 오염물질의 혼합능을 파악할 수 있는 대표적인 인자이다. 특히 하수처리장 방류수 혼합예측과 같이 횡 방향 혼합에 대한 예측이 중요한 경우, 하천의 지형적, 수리학적 특성을 고려한 2차원 횡 분산계수의 결정이 필요하다. 2차원 횡 분산계수의 결정을 위해 기존 연구에서는 추적자실험결과로부터 경험식을 만들어 횡 분산계수 산정에 사용해왔다. 회귀분석을 통한 경험식 산정을 위해서는 충분한 데이터가 필요하지만, 2차원 추적자 실험 건수가 충분치 않아 신뢰성 높은 경험식 산정이 어려운 상황이다. 따라서 본 연구에서는 SMOTE기법을 이용하여 횡분산계수 실험데이터를 증폭시켜 이로부터 횡 분산계수 경험식을 산정하고자 한다. 또한 다중선형회귀분석을 통해 도출된 경험식의 한계를 보완하기 위해 다양한 머신러닝 기법을 적용하고, 횡 분산계수 산정에 적합한 머신러닝 기법을 제안하고자 한다. 기존 추적자실험 데이터로부터 하폭 대 수심비, 유속 대 마찰유속비, 횡 분산계수 데이터 셋을 수집하였으며, SMOTE 알고리즘의 적용을 통해 회귀분석과 머신러닝 기법 적용에 필요한 데이터그룹을 생성했다. 새롭게 생성된 데이터 셋을 포함하여 다중선형회귀분석을 통해 횡 분산계수 경험식을 결정하였으며, 새로 제안한 경험식과 기존 경험식에 대한 정확도를 비교했다. 또한 다중선형회귀분석을 통해 결정된 경험식은 횡 분산계수 예측범위에 한계를 보였기 때문에 머신러닝기법을 적용하여 다중선형회귀분석에 대한 예측성능을 평가했다. 이를 위해 머신러닝 기법으로서 서포트 벡터 머신 회귀(SVR), K근접이웃 회귀(KNN-R), 랜덤 포레스트 회귀(RFR)를 활용했다. 세 가지 머신러닝 기법을 통해 도출된 횡 분산계수와 경험식으로부터 결정된 횡 분산계수를 비교하여 예측 성능을 비교했다. 이를 통해 제한된 실험데이터 셋으로부터 2차원 횡 분산계수 산정을 위한 데이터 전처리 기법 및 횡 분산계수 산정에 적합한 머신러닝 절차와 최적 학습기법을 도출했다.

• Journal of Energy Engineering
• /
• v.25 no.1
• /
• pp.69-75
• /
• 2016

Bubble size is a key parameter for an accurate prediction of bubble behaviours in the multi-dimensional two-phase flow. In the current STAR CCM+ CFD code, a mechanistic bubble size model $S{\gamma}$ is available for the prediction of bubble size in the flow channel. As another model, Yun model is developed based on DEBORA that is subcooled boiling data in high pressure. In this study, numerical simulation for the gas-liquid two-phase flow was conducted to validate and confirm the performance of $S{\gamma}$ model and Yun model, using the commercial CFD code STAR CCM+ ver. 10.02. For this, local bubble models was evaluated against the air-water data from DEDALE experiments (1995) and Hibiki et al. (2001) in the vertical pipe. All numerical results of $S{\gamma}$ model predicted reasonably the two-phase flow parameters and Yun model is needed to be improved for the prediction of air-water flow under low pressure condition.

• Journal of Korean Society of Environmental Engineers
• /
• v.27 no.8
• /
• pp.852-858
• /
• 2005

Modeling techniques for air quality are useful tools in air quality management. Especially, the air quality in urban area is significantly influenced by local surroundings such as buildings and traffic. When considering the air quality in a street canyon, which is usually filmed by a series of consecutive buildings and a street, currently available air dispersion model have a number of limitations to predict the air quality properly. In this study, it is aimed to propose an empirical model for the air quality in urban street canyons. A series of wind tunnel tests, followed by statistical analysis, were conducted. In conclusion, it is found that a wide street canyon and a perpendicular external wind to the street canyon are beneficial to achieve an enhanced air quality in street canyon environment. The model prediction using the proposed model also shows reliable correlations to the wind tunnel test results.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.4
• /
• pp.13-20
• /
• 2023

In this paper, the actual data of VOC reduction facilities was analyzed through a model that detects and predicts data anomalies. Using the USAD model, which shows stable performance in the field of anomaly detection, anomalies in real-time data are detected and sensors that cause anomalies are searched. In addition, we propose a method of predicting and warning, when abnormalities that time will occur by predicting future outliers with an auto-regressive model. The experiment was conducted with the actual data of the VOC reduction facility, and the anomaly detection test results showed high detection rates with precision, recall, and F1-score of 98.54%, 89.08%, and 93.57%, respectively. As a result, averaging of the precision, recall, and F1-score for 8 sensors of detection rates were 99.64%, 99.37%, and 99.63%. In addition, the Hamming loss obtained to confirm the validity of the detection experiment for each sensor was 0.0058, showing stable performance. And the abnormal prediction test result showed stable performance with an average absolute error of 0.0902.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.40 no.1
• /
• pp.105-110
• /
• 2020

This study provides a method and data for predicting the flight initiation wind speed of wind-borne debris. From the force equilibrium acting on debris including aerodynamic and inertia forces, the equation for predicting the flight initiation wind speeds are presented. Wind tunnel tests were carried out to provide necessary aerodynamic data in the equation for the debris with various aspect ratios. The proposed equation for flight initiation wind speeds was validated from free flying tests in the wind tunnel. The flights of debris were mostly initiated by slip when width to thickness was less than 10, otherwise overturning were dominant. The actual flight initiation speeds were lower than that of the computed ones. The surface boundary layer flow and the gap between the debris and surface might affect the prediction error.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.35 no.2
• /
• pp.124-129
• /
• 2007

Prediction methods for a rotor averaged inflow in forward flight are investigated in this study. The investigated methods are Drees linear inflow model, Mangler & Squire model and free vortex wake(FVW) method. Predictions have been performed for a four-blade rotor operating at three different advance ratios i.e. 0.15, 0.23 and 0.30, at which experimental data are available. According to results, Drees model has a limitation for the inflow non-uniformity prediction due to an inherent linear characteristics. Mangler & Squire model has a reasonable accuracy except the disk edge region. KARI FVW method has very good accuracy and has better accuracy than the other FVW method especially in inboard region. However, there are some discrepancies in retreating side due to the dynamic stall effect and in near hub region due to the fuselage upwash effect.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.4
• /
• pp.161-167
• /
• 2019

Recently, demand forecasting techniques have been actively studied due to interest in stable power supply with surging power demand, and increase in spread of smart meters that enable real-time power measurement. In this study, we proceeded the deep learning prediction model experiments which learns actual measured power usage data of home and outputs the forecasting result. And we proceeded pre-processing with moving average method. The predicted value made by the model is evaluated with the actual measured data. Through this forecasting, it is possible to lower the power supply reserve ratio and reduce the waste of the unused power. In this paper, we conducted experiments on three types of networks: Multi Layer Perceptron (MLP), Recurrent Neural Network (RNN), and Long Short Term Memory (LSTM) and we evaluate the results of each scheme. Evaluation is conducted with following method: MSE(Mean Squared Error) method and MAE(Mean Absolute Error).

• Environmental engineer
• /
• v.18 s.196
• /
• pp.52-57
• /
• 2002

통계적인 상관관계 분석이나, 과학적인 실험계획 등을 통하여 결과를 예측하고, 예측된 결과가 개선효과로 나타남으로써 시그마 추진에 대한 신뢰도가 향후 더욱 높아질 것으로 기대된다.

• Proceedings of the Korean Institute of Industrial Safety Conference
• /
• 1998.05a
• /
• pp.101-106
• /
• 1998

현대사회가 급속한 발전을 이룩하면서 화재의 발생은 증가추세에 있다. 화재의 예방과 진압장비의 개발을 위해서는 실내화재현상에 대한 연구와 이해가 필요하다. 대부분의 실내화재 관련 현상에 대하여서는 많은 연구가 이루어졌고, 이러한 연구를 바탕으로 컴퓨터 시뮬레이션과 같은 화재 현상의 예측기법을 발전 시켜왔으며, 거의 실제에 가깝게 발전하고 있으나, 아직까지도 규명이 확연히 되지 않고 있는 부분은 창유리의 파괴현상이다. 본 연구는 구획화재시 창유리의 파괴현상을 실제에 근접한 시나리오를 설정한 후 실험을 통해 고찰하고자한다. 또한 파괴시간 예측 프로그램인 BREAKl의 분석 결과와 실험치의 비교도 아울러 실시하여 그 적용성을 판단해보자 한다. (중략)