• Title/Summary/Keyword: Estimation factor

Search Result 2,237, Processing Time 0.038 seconds

Estimation of Road Surface Condition during Summer Season Using Machine Learning (기계학습을 통한 여름철 노면상태 추정 알고리즘 개발)

  • Yeo, jiho;Lee, Jooyoung;Kim, Ganghwa;Jang, Kitae
    • The Journal of The Korea Institute of Intelligent Transport Systems
    • /
    • v.17 no.6
    • /
    • pp.121-132
    • /
    • 2018
  • Weather is an important factor affecting roadway transportation in many aspects such as traffic flow, driver 's driving patterns, and crashes. This study focuses on the relationship between weather and road surface condition and develops a model to estimate the road surface condition using machine learning. A road surface sensor was attached to the probe vehicle to collect road surface condition classified into three categories as 'dry', 'moist' and 'wet'. Road geometry information (curvature, gradient), traffic information (link speed), weather information (rainfall, humidity, temperature, wind speed) are utilized as variables to estimate the road surface condition. A variety of machine learning algorithms examined for predicting the road surface condition, and a two - stage classification model based on 'Random forest' which has the highest accuracy was constructed. 14 days of data were used to train the model and 2 days of data were used to test the accuracy of the model. As a result, a road surface state prediction model with 81.74% accuracy was constructed. The result of this study shows the possibility of estimating the road surface condition using the existing weather and traffic information without installing new equipment or sensors.

Estimation of SO2 emissions in large point sources at Dangjin City using airborne measurements (항공관측 결과를 활용한 당진시 대형사업장에서의 황산화물 배출량 평가)

  • Kim, Yong Pyo;Kim, Saewung;Kim, Jongho;Lee, Taehyoung
    • Particle and aerosol research
    • /
    • v.16 no.4
    • /
    • pp.107-117
    • /
    • 2020
  • Based on the airborne measurement results over a coal fired power plant and steel work in Dangjin city, SO2 emission amounts of each site are estimated (top-down emission). Airborne measurements were carried out on May-June and October-November 2019. The estimated SO2 emission in 2019 for the power plant was 1502.1 kg/hr and that for the steel work was 2850.5 kg/hr, higher as much as a factor of 2.5 and 2.0, respectively, than the emission amounts provided by both facilities (bottom-up emission). The outcomes strongly illustrates that well designed airborne observations can serve a quantitative diagnostic tool for bottom-up emission estimates. Further research direction to improve the reliability of the top-down emission estimates is suggested.

Drought evaluation using unstructured data: a case study for Boryeong area (비정형 데이터를 활용한 가뭄평가 - 보령지역을 중심으로 -)

  • Jung, Jinhong;Park, Dong-Hyeok;Ahn, Jaehyun
    • Journal of Korea Water Resources Association
    • /
    • v.53 no.12
    • /
    • pp.1203-1210
    • /
    • 2020
  • Drought is caused by a combination of various hydrological or meteorological factor, so it is difficult to accurately assess drought event, but various drought indices have been developed to interpret them quantitatively. However, the drought indexes currently being used are calculated from the lack of a single variable, which is a problem that does not accurately determine the drought event caused by complex causes. Shortage of a single variable may not be a drought, but it is judged to be a drought. On the other hand, research on developing indices using unstructured data, which is widely used in big data analysis, is being carried out in other fields and proven to be superior. Therefore, in this study, we intend to calculate the drought index by combining unstructured data (news data) with weather and hydrologic information (rainfall and dam inflow) that are being used for the existing drought index, and to evaluate the utilization of drought interpretation through verification of the calculated drought index. The Clayton Copula function was used to calculate the joint drought index, and the parameter estimation was used by the calibration method. The analysis showed that the drought index, which combines unstructured data, properly expresses the drought period compared to the existing drought index (SPI, SDI). In addition, ROC scores were calculated higher than existing drought indices, making them more useful in drought interpretation. The joint drought index calculated in this study is considered highly useful in that it complements the analytical limits of the existing single variable drought index and provides excellent utilization of the drought index using unstructured data.

A study on estimation of lowflow indices in ungauged basin using multiple regression (다중회귀분석을 이용한 미계측 유역의 갈수지수 산정에 관한 연구)

  • Lim, Ga Kyun;Jeung, Se Jin;Kim, Byung Sik;Chae, Soo Kwon
    • Journal of Korea Water Resources Association
    • /
    • v.53 no.12
    • /
    • pp.1193-1201
    • /
    • 2020
  • This study aims to develop a regression model that estimates a low-flow index that can be applied to ungauged basins. A total of 30 midsized basins in South Korea use long-term runoff data provided by the National Integrated Water Management System (NIWMS) to calculate average low-flow, average minimum streamflow, and low-flow index duration and frequency. This information is used in the correlation analysis with 18 basin factors and 3 climate change factors to identify the basin area, average basin altitude, average basin slope, water system density, runoff curve number, annual evapotranspiration, and annual precipitation in the low-flow index regression model. This study evaluates the model's accuracy by using the root-mean-square error (RMSE) and the mean absolute error (MAE) for 10 ungauged, verified basins and compares them with the previous model's low-flow calculations to determine the effectiveness of the newly developed model. Comparative analysis indicates that the new regression model produces average low-flow, attributed to the consideration of varied basin and hydrologic factors during the new model's development.

Development of a Software for Re-Entry Prediction of Space Objects for Space Situational Awareness (우주상황인식을 위한 인공우주물체 추락 예측 소프트웨어 개발)

  • Choi, Eun-Jung
    • Journal of Space Technology and Applications
    • /
    • v.1 no.1
    • /
    • pp.23-32
    • /
    • 2021
  • The high-level Space Situational Awareness (SSA) objective is to provide to the users dependable, accurate and timely information in order to support risk management on orbit and during re-entry and support safe and secure operation of space assets and related services. Therefore the risk assessment for the re-entry of space objects should be managed nationally. In this research, the Software for Re-Entry Prediction of space objects (SREP) was developed for national SSA system. In particular, the rate of change of the drag coefficient is estimated through a newly proposed Drag Scale Factor Estimation (DSFE), and is used for high-precision orbit propagator (HPOP) up to an altitude of 100 km to predict the re-entry time and position of the space object. The effectiveness of this re-entry prediction is shown through the re-entry time window and ground track of space objects falling in real events, Grace-1, Grace-2, Tiangong-1, and Chang Zheng-5B Rocket body. As a result, through analysis 12 hours before the final re-entry time, it is shown that the re-entry time window and crash time can be accurately predicted with an error of less than 20 minutes.

Measurement uncertainty analysis of radiophotoluminescent glass dosimeter reader system based on GD-352M for estimation of protection quantity

  • Kim, Jae Seok;Park, Byeong Ryong;Yoo, Jaeryong;Ha, Wi-Ho;Jang, Seongjae;Jang, Won Il;Cho, Gyu Seok;Kim, Hyun;Chang, Insu;Kim, Yong Kyun
    • Nuclear Engineering and Technology
    • /
    • v.54 no.2
    • /
    • pp.479-485
    • /
    • 2022
  • At the Korea Institute of Radiological and Medical Sciences, physical human phantoms were developed to evaluate various radiation protection quantities, based on the mesh-type reference computational phantoms of the International Commission on Radiological Protection. The physical human phantoms were fabricated such that a radiophotoluminescent glass dosimeter (RPLGD) with a Tin filter, namely GD-352M, could be inserted into them. A Tin filter is used to eliminate the overestimated signals in low-energy photons below 100 keV. The measurement uncertainty of the RPLGD reader system based on GD-352M should be analyzed for obtaining reliable protection quantities before using it for practical applications. Generally, the measurement uncertainty of RPLGD systems without Tin filters is analyzed for quality assurance of radiotherapy units using a high-energy photon beam. However, in this study, the measurement uncertainty of GD-352M was analyzed for evaluating the protection quantities. The measurement uncertainty factors in the RPLGD include the reference irradiation, regression curve, reproducibility, uniformity, energy dependence, and angular dependence, as described by the International Organization for Standardization (ISO). These factors were calculated using the Guide to the Expression of Uncertainty in Measurement method, applying ISO/ASTM standards 51261(2013), 51707(2015), and SS-ISO 22127(2019). The measurement uncertainties of the RPLGD reader system with a coverage factor of k = 2 were calculated to be 9.26% from 0.005 to 1 Gy and 8.16% from 1 to 10 Gy. A blind test was conducted to validate the RPLGD reader system, which demonstrated that the readout doses included blind doses of 0.1, 1, 2, and 5 Gy. Overall, the En values were considered satisfactory.

Estimation of the Hydrological Design Frequency of Local Rivers Using Bayesian Inference and a Sensitivity Analysis of Evaluation Factors (평가인자 가중치에 대한 베이지안 추론과 민감도 분석을 통한 적정 하천설계빈도 결정)

  • Ryu, Jae Hee;Kim, Ji Eun;Lee, Jin-Young;Park, Kyung-Woon;Kim, Tae-Woong
    • KSCE Journal of Civil and Environmental Engineering Research
    • /
    • v.42 no.5
    • /
    • pp.617-626
    • /
    • 2022
  • In Korea, annual precipitation and its variability have gradually increased since modern meteorological observations began, and the risk of disasters has also been increasing due to significant regional variations and recent abnormal climate conditions. Given that damage from storms and floods mainly occurs around rivers, it is crucial to determine the appropriate design frequency for river-related projects. This study examined existing design practices used to determine hydrological design frequencies and suggested a new method to determine appropriate design frequencies. The study collected available data pertaining to seven evaluation factors, specifically the basin areas, shape parameters, channel slopes, stream orders, backwater effect reaches, extreme rainfall frequencies, and urbanized flood inundation areasfor 413 local rivers in Chungcheongnam-do in Korea. The estimated weights for areas of extreme rainfall frequencies and urbanized flood inundation were found to be 18, having a great effect on determining the design frequency. Compared with the established design frequency in previous government reports, the estimated design frequency increased for 255 rivers and decreased for 158 rivers.

Estimation of regional flow duration curve applicable to ungauged areas using machine learning technique (머신러닝 기법을 이용한 미계측 유역에 적용 가능한 지역화 유황곡선 산정)

  • Jeung, Se Jin;Lee, Seung Pil;Kim, Byung Sik
    • Journal of Korea Water Resources Association
    • /
    • v.54 no.spc1
    • /
    • pp.1183-1193
    • /
    • 2021
  • Low flow affects various fields such as river water supply management and planning, and irrigation water. A sufficient period of flow data is required to calculate the Flow Duration Curve. However, in order to calculate the Flow Duration Curve, it is essential to secure flow data for more than 30 years. However, in the case of rivers below the national river unit, there is no long-term flow data or there are observed data missing for a certain period in the middle, so there is a limit to calculating the Flow Duration Curve for each river. In the past, statistical-based methods such as Multiple Regression Analysis and ARIMA models were used to predict sulfur in the unmeasured watershed, but recently, the demand for machine learning and deep learning models is increasing. Therefore, in this study, we present the DNN technique, which is a machine learning technique that fits the latest paradigm. The DNN technique is a method that compensates for the shortcomings of the ANN technique, such as difficult to find optimal parameter values in the learning process and slow learning time. Therefore, in this study, the Flow Duration Curve applicable to the unmeasured watershed is calculated using the DNN model. First, the factors affecting the Flow Duration Curve were collected and statistically significant variables were selected through multicollinearity analysis between the factors, and input data were built into the machine learning model. The effectiveness of machine learning techniques was reviewed through statistical verification.

How to Improve Suitability of Irradiation Utilization in Development of Linear Regression Model for Estimating Paprika Productivity (파프리카 생산성 추정을 위한 선형 회귀모형 개발 시 외부광량 활용 적합성을 높이기 위한 방법)

  • Woo, Seung Mi;Kim, Ga Yeong;Kim, Ho Cheol
    • The Journal of the Convergence on Culture Technology
    • /
    • v.7 no.4
    • /
    • pp.779-783
    • /
    • 2021
  • The amount of sunlight (irradiation) acts as a very important factor for paprika (Capsicum annuum L.) productivity, but there are difficulties in developing a standard model for estimating paprika productivity using irradiation factors. This study was conducted to investigate how to increase the suitability of using irradiation as an independent variable when developing a standard model. In the linear regression analysis using the independent variable (cumulative irradiation) and the dependent variable (cumulative productivity) were classified as the average value of the total farm productivity (MTFP), and above and below (MHFP, MLFP) based on the average value, respectively. The RMSE value of the estimated linear regression model was 0.9418 kg·m-2 in the MHFP, which was significantly lower than 1.5468 kg·m-2 in the MTFP and 1.3812 kg·m-2 in the MLFP. And in due course of time (month), RMSE value was also the lowest in MHFP, below 1.0 kg·m-2 in all months. Therefore, when developing a regression model for estimating paprika productivity using irradiation, it is judged that it will improve the suitability of the estimation model by classifying and analyzing the difference in productivity of farms with an appropriate method.

The Structural Relationship among the Usefulness, Ease of Use, Intention to Use, and Learning Utilization of Smart Learning Devices Recognized by College Students (전문대학생이 인식한 스마트 학습기기의 유용성, 용이성, 사용의도 및 학습 활용의 구조적 관계)

  • Kim, Dae-Myung
    • The Journal of the Korea Contents Association
    • /
    • v.22 no.9
    • /
    • pp.667-677
    • /
    • 2022
  • The purpose of this study is to analyze the structural relationship among the usefulness, ease of use, use intention, and learning utilization of smart learning devices recognized by college students. In order to achieve this, the following problems were addressed: first, how do college students' recognition of ease and usefulness of smart learning devices? second, how do college students' recognition of ease and learning utilization? third, what mediating effects od use of smart learning devices and learning utilization? As for the research method, a survey of 350 students who participated in smart learning was conducted to conduct a home review, confirmatory factor analysis, and bootsrapping for structural equation estimation and mediating analysis. As a result of the analysis on this, first, it was found that the usefulness and ease of smart learning devices recognized by college students had an effect on the intention of use. Second, it was found that the perception of the usefulness and ease of smart devices perceived by college students had an effect on the use of smart learning device learning. Third, it was found that the intention to use smart devices perceived by college students mediated the relationship between usefulness and learning utilization, and it was found that it mediated the relationship between ease and learning utilization. The implications are that instructors can recognize and utilize the intention of using smart learning devices properly by allowing college students to recognize the usefulness and ease of using smart learning devices in the classroom, thereby increasing the learning utilization of smart learning devices in class. In addition, efforts are needed to enable college students to recognize the usefulness of smart devices and to expand the use of learning.