• Structural Engineering and Mechanics
• /
• 제83권4호
• /
• pp.515-535
• /
• 2022

The strength models for fiber-reinforced polymer (FRP)-confined normal strength concrete (NC) cylinders available in the literature have been suggested based on small databases using limited variables of such structural members portraying less accuracy. The artificial neural network (ANN) is an advanced technique for precisely predicting the response of composite structures by considering a large number of parameters. The main objective of the present investigation is to develop an ANN model for the axial strength of FRP-confined NC cylinders using various parameters to give the highest accuracy of the predictions. To secure this aim, a large experimental database of 313 FRP-confined NC cylinders has been constructed from previous research investigations. An evaluation of 33 different empirical strength models has been performed using various statistical parameters (root mean squared error RMSE, mean absolute error MAE, and coefficient of determination R²) over the developed database. Then, a new ANN model using the Group Method of Data Handling (GMDH) has been proposed based on the experimental database that portrayed the highest performance as compared with the previous models with R²=0.92, RMSE=0.27, and MAE=0.33. Therefore, the suggested ANN model can accurately capture the axial strength of FRP-confined NC cylinders that can be used for the further analysis and design of such members in the construction industry.

• Genomics & Informatics
• /
• 제21권4호
• /
• pp.50.1-50.9
• /
• 2023

Vaccine development is one of the key efforts to control the spread of coronavirus disease 2019 (COVID-19). However, it has become apparent that the immunity acquired through vaccination is not permanent, known as the waning effect. Therefore, monitoring the proportion of the population with immunity is essential to improve the forecasting of future waves of the pandemic. Despite this, the impact of the waning effect on forecasting accuracies has not been extensively studied. We proposed a method for the estimation of the effective immunity (EI) rate which represents the waning effect by integrating the second and booster doses of COVID-19 vaccines. The EI rate, with different periods to the onset of the waning effect, was incorporated into three statistical models and two machine learning models. Stringency Index, omicron variant BA.5 rate (BA.5 rate), booster shot rate (BSR), and the EI rate were used as covariates and the best covariate combination was selected using prediction error. Among the prediction results, Generalized Additive Model showed the best improvement (decreasing 86% test error) with the EI rate. Furthermore, we confirmed that South Korea's decision to recommend booster shots after 90 days is reasonable since the waning effect onsets 90 days after the last dose of vaccine which improves the prediction of confirmed cases and deaths. Substituting BSR with EI rate in statistical models not only results in better predictions but also makes it possible to forecast a potential wave and help the local community react proactively to a rapid increase in confirmed cases.

• Journal of Positioning, Navigation, and Timing
• /
• 제13권1호
• /
• pp.111-115
• /
• 2024

This study builds a machine learning model optimized for clocks among various techniques in the field of artificial intelligence and applies it to clock stabilization or synchronization technology based on atomic clock noise characteristics. In addition, the possibility of providing stable source clock data is confirmed through the characteristics of machine learning predicted values during holdover of atomic clocks. The proposed machine learning model is evaluated by comparing its performance with the AutoRegressive Integrated Moving Average (ARIMA) model, an existing statistical clock prediction model. From the results of the analysis, the prediction model proposed in this study (MSE: 9.47476) has a lower MSE value than the ARIMA model (MSE: 221.2622), which means that it provides more accurate predictions. The prediction accuracy is based on understanding the complex nature of data that changes over time and how well the model reflects this. The application of a machine learning prediction model can be seen as a way to overcome the limitations of the statistical-based ARIMA model in time series prediction and achieve improved prediction performance.

• 지질공학
• /
• 제32권3호
• /
• pp.327-338
• /
• 2022

산사태 발생지역에서 측정된 토층심도 자료를 토대로 경험적 내지 통계적으로 토층심도를 예측하기 위하여 지형고도 기반의 Z-model과 확률론적 통계모델을 활용하여 산사태 발생구간에 대한 토층심도를 산정하고, 이를 토대로 강우사상에 따라 토층 내로 강우의 침투특성을 반영하여 분석할 수 있는 토층에 대한 포화깊이비 개념을 접목하여 산사태위험도 분석을 수행하였다. 그 결과, Z-model로 예측된 토층심도가 확률론적 통계모델로 산정된 결과보다는 본 연구지역에서 측정된 토층심도와 비교적 유사하게 산정된 것으로 나타났다. 이를 토대로 산사태 발생지역에 대해 확률론적 통계모델로 예측된 토층심도를 적용해 분석한 결과가 Z-model로 산정된 결과보다 산사태위험도 1등급 분포 비율이 2.5배 이상 높게 나타났다. 이는 토층심도가 직접적으로 산사태위험도 평가에 영향을 주는 것을 의미하는 것으로 산사태위험도 분석을 위해서는 대상지역의 토층심도 자료의 획득 및 적용이 중요함을 의미한다.

• Membrane and Water Treatment
• /
• 제1권1호
• /
• pp.49-60
• /
• 2010

In this study, response surface methodology (RSM) was performed in NF membrane process to evaluate the separation efficiency of membrane in the removal of salt and reactive dye by varying different variables such as pressure, temperature, pH, dye concentration and salt concentration. The significant level of both the main effects and the interaction were observed by analysis of variance (ANOVA) approach. Based on the statistical analysis, the results have provided valuable information on the relationship between these variables and the performances of membrane. The rejection of salt was found to be greatly influenced by pressure, pH and salt concentration whereas the dye rejection was relatively constant in between 96.22 and 99.43% regardless of the changes in the variables. The water flux on the other hand was found to be affected by the pressure and salt concentration. It is also found that the model predictions were in good agreement with the experimental data, indicating the validity of these models in predicting membrane performances prior to the real filtration process.

• 환경영향평가
• /
• 제20권6호
• /
• pp.879-890
• /
• 2011

The GOSAT (Greenhouse gases Observing SATellite) data provide new opportunities the most regionally complete and up-to-date assessment of $CO_2$. However, in practice, GOSAT records often suffer from missing data values mainly due to unfavorable meteorological condition in specific time periods of data acquisition. The aim of this research was to identify optimal spatial interpolation techniques to ensure the continuity of $CO_2$ from samples taken in the North East Asia. The accuracy among ordinary kriging (OK), universal kriging (UK) and simple kriging (SK) was compared based on the combined consideration of $R^2$ values, Root Mean Square Error (RMSE), Mean Error (ME) for variogram models. Cross validation for 1312 random sampling points indicate that the (UK) kriging is the best geostatistical method for spatial predictions of $CO_2$ in the East Asia region. The results from this study can be useful for selecting optimal kriging algorithm to produce $CO_2$ map of various landscapes. Also, data users may benefit from a statistical approach that would allow them to better understand the uncertainty and limitations of the GOSAT sample data.

• 농촌지도와개발
• /
• 제6권1호
• /
• pp.15-24
• /
• 1999

There have always been dilemmas between development and environmental conservation throughout the world. Gradually environmental contamination threatens sustainable development and conservation. we try to study on the sustainable development with environmental conservation. One of the instruments to get this goal is Environmental Impact Statement. Environmental Impact Statement has now become a standard tool of decision making in Environmentally Sound and Sustainable Development. The objectives of this study is to explore and suggest some suggestions for improvements of EIA. 1. Identify all criteria and standards that apply to physical and social environmental components and dynamics. 2. Giving attention to the purpose of the criterion and standard, with respect to resource use and quality. 3. Demonstrate the relevance legal, technical, and scientific authority by early planning through construction, operation and maintenance phases. 4. Implement rationales and protocols for the documentation of standard analytical methods, location of sampling points and statistical analysis of data. 5. Establish precise protocols by predictions of environmental impact relevant for established criteria and standards. Reviewing these protocols with relevant legal authorities prior to their implementation is important.

• Journal of Information Science Theory and Practice
• /
• 제3권3호
• /
• pp.75-80
• /
• 2015

Methods and Material: The PubMed database was used for retrieving data on 'cancer biology.' Articles were downloaded from the years 2000 to 2011. The articles were classified chronologically and transferred to a spreadsheet application for analysis of the data as per the objectives of the study. Statistical Method: To investigate the nature of growth of articles via exponential, linear, and logistics tests. Result: The year wise analysis of the growth of articles output shows that for the years 2000 to 2005 and later there is a sudden increase in output, during the years 2006 to 2007 and 2008 to 2011. The high productivity of articles during these years may be due to their significance in cancer biology literature, having received prominence in research. Conclusion: There is an obvious need for better compilations of statistics on numbers of publications in the years from 2000 to 2011 on various disciplines on a worldwide scale, for informed critical assessments of the amount of new knowledge contributed by these publications, and for enhancements and refinements of present Scientometric techniques (citation and publication counts), so that valid measures of knowledge growth may be obtained. Only then will Scientometrics be able to provide accurate, useful descriptions and predictions of knowledge growth.

• Advances in nano research
• /
• 제9권1호
• /
• pp.59-67
• /
• 2020

Filter cake formation during rotary drilling operation is an unavoidable scenario, hence there is need for constant improvement in the approaches used in monitoring the cake thickness growth in order to prevent drill-string sticking. This study proposes an improved model that predicts the growth of mud cake thickness overtime with the consideration of the addition of nanoparticles in the formulated drilling fluid system. Ferric oxide, titanium dioxide and copper oxide nanoparticles were used in varying amounts (2 g, 4 g and 6 g), and filtration data were obtained from the HPHT filtration test. The filter cakes formed were further analyzed with scanning electron microscope to obtain the morphological characteristics. The data obtained was used to validate the new filtrate loss model. This model specifically presents the concept of time variation in filter cake formation as against the previous works of constant and definite time. Regression coefficient which is a statistical measure was used to validate the new model and the predicted results were compared with the API model. The new model showed R² values of 99.9%, and the predictions from the proposed filtration model can be said to be more closely related to the experimental data than that predicted from the API model from the SSE and RMSE results.

• 지능정보연구
• /
• 제5권1호
• /
• pp.95-101
• /
• 1999

In this paper, a comparison between different methods to combine predictions from neural networks will be given. These methods are bagging, bumping, and balancing. Those are based on the analysis of the ensemble generalization error into an ambiguity term and a term incorporating generalization performances of individual networks. Neural Networks and AI machine learning models are prone to overfitting. A strategy to prevent a neural network from overfitting, is to stop training in early stage of the learning process. The complete data set is spilt up into a training set and a validation set. Training is stopped when the error on the validation set starts increasing. The stability of the networks is highly dependent on the division in training and validation set, and also on the random initial weights and the chosen minimization procedure. This causes early stopped networks to be rather unstable: a small change in the data or different initial conditions can produce large changes in the prediction. Therefore, it is advisable to apply the same procedure several times starting from different initial weights. This technique is often referred to as training ensembles of neural networks. In this paper, we presented a comparison of three statistical methods to prevent overfitting of neural network.