• Ocean Systems Engineering
• /
• 제7권4호
• /
• pp.319-328
• /
• 2017

Higher prediction efficacy is a very challenging task in any field of engineering. Due to global warming, there is a considerable increase in the global sea level. Through this work, an attempt has been made to find the sea level variability due to climate change impact at Haldia Port, India. Different statistical downscaling techniques are available and through this paper authors are intending to compare and illustrate the performances of three regression models. The models: Wavelet Neural Network (WNN), Minimax Probability Machine Regression (MPMR), Feed-Forward Neural Network (FFNN) are used for projecting the sea level variability due to climate change at Haldia Port, India. Model performance indices like PI, RMSE, NSE, MAPE, RSR etc were evaluated to get a clear picture on the model accuracy. All the indices are pointing towards the outperformance of WNN in projecting the sea level variability. The findings suggest a strong recommendation for ensembled models especially wavelet decomposed neural network to improve projecting efficiency in any time series modeling.

• Steel and Composite Structures
• /
• 제33권4호
• /
• pp.583-594
• /
• 2019

In the areas highly exposed to earthquakes, concrete-filled steel tube columns (CFSTCs) are known to provide superior structural aspects such as (i) high strength for good seismic performance (ii) high ductility (iii) enhanced energy absorption (iv) confining pressure to concrete, (v) high section modulus, etc. Numerous studies were reported on behavior of CFSTCs under axial compression loadings. This paper presents an analytical model to predict ultimate load capacity of CFSTCs with circular sections under axial load by using multivariate adaptive regression splines (MARS). MARS is a nonlinear and non-parametric regression methodology. After careful study of literature, 150 comprehensive experimental data presented in the previous studies were examined to prepare a data set and the dependent variables such as geometrical and mechanical properties of circular CFST system have been identified. Basically, MARS model establishes a relation between predictors and dependent variables. Separate regression lines can be formed through the concept of divide and conquers strategy. About 70% of the consolidated data has been used for development of model and the rest of the data has been used for validation of the model. Proper care has been taken such that the input data consists of all ranges of variables. From the studies, it is noted that the predicted ultimate axial load capacity of CFSTCs is found to match with the corresponding experimental observations of literature.

• Journal of the Korean Data and Information Science Society
• /
• 제20권4호
• /
• pp.615-627
• /
• 2009

본 연구의 목적은 효과적인 마케팅전략 수립에 도움이 되는 정보를 제공하는 데 있다. 이를 위하여 화장품구매 자료로부터 고객 구매형태와 재구매 간의 관계를 분석하여 고객충성도 예측모형을 개발하였다. 고객충성도는 재구매 가능성으로 측정하였다. 본 연구에서 사용된 자료는 국내의 한 화장품회사 고객들의 2000년부터 2008년까지 9년간의 구매자료 (432,528명, 2,440,107건)이다. 예측모형의 목표변수는 재구매 유무이고, 설명변수는 구매수량, 구매액, 휴면기간 등의 기본변수와 구매횟수와 거래 일자를 이용한 가공변수들이다. 충성도 예측모형은 데이터마이닝 기법인 로지스틱회귀, 의사결정나무 및 신경망모형을 사용하였다. 예측모형평가의 측도로는 하이드게 점수를 사용하였으며, 최대의 하이드게 점수를 가지는 분계점을 선택하였다. 각예측모형에서 선택된 변수는 유사하며, 모형비교 결과 세 모형의 효율과 평가측도의 차이는 크지 않았다. 정분류율이 다소 높고 해석과 활용이 쉬운 의사결정나무모형을 최종모형으로 선택했다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 하계종합학술대회 논문집
• /
• pp.865-868
• /
• 1999

In this paper, indoor propagation characteristics are analyzed for various environments such as corridors, walls and corners. In order to present the statistical model for indoor environments the loss factors of each case are obtained by linear regression analysis method with the function of logarithmic distance between transmitter and receiver.

• 한국압력기기공학회 논문집
• /
• 제12권2호
• /
• pp.40-49
• /
• 2016

Flow accelerated corrosion (FAC) of the carbon steel piping has been a significant problem in nuclear power plants. FAC occurs under certain hydrodynamic, environmental, and material conditions, and extensive research into the factors of FAC has been conducted. The basic process of FAC is now relatively well understood; however, a full mechanistic model has not yet been established. Recently, the Korea Atomic Energy Research Institute (KAERI) has built a large experiment loop system for FAC. To produce significant experimental results using this system, the factors affecting on FAC should be analyzed quantitatively, and a model needs to be developed. In this work, a statistical modeling methodology to develop an empirical model is described in detail, and a preliminary model is suggested. Firstly, FAC data were collected from the research literature in Japan and the results of domestic experiments. The flow rate, water temperature, pH at room temperature, and the Cr content are selected as major factors, and nonlinear regression is used to find the best fit of the available data. An iterative procedure between suggesting and evaluating a model is used until an optimum model is obtained. The developed model gives the FAC rate comparable to the measured FAC rate. The developed model is going to be refined using additional laboratory data in the future.

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권14호
• /
• pp.5883-5888
• /
• 2014

Background: Breast cancer is the most common cancers in female populations. The exact cause is not known, but is most likely to be a combination of genetic and environmental factors. Log-logistic model (LLM) is applied as a statistical method for predicting survival and it influencing factors. In recent decades, artificial neural network (ANN) models have been increasingly applied to predict survival data. The present research was conducted to compare log-logistic regression and artificial neural network models in prediction of breast cancer (BC) survival. Materials and Methods: A historical cohort study was established with 104 patients suffering from BC from 1997 to 2005. To compare the ANN and LLM in our setting, we used the estimated areas under the receiver-operating characteristic (ROC) curve (AUC) and integrated AUC (iAUC). The data were analyzed using R statistical software. Results: The AUC for the first, second and third years after diagnosis are 0.918, 0.780 and 0.800 in ANN, and 0.834, 0.733 and 0.616 in LLM, respectively. The mean AUC for ANN was statistically higher than that of the LLM (0.845 vs. 0.744). Hence, this study showed a significant difference between the performance in terms of prediction by ANN and LLM. Conclusions: This study demonstrated that the ability of prediction with ANN was higher than with the LLM model. Thus, the use of ANN method for prediction of survival in field of breast cancer is suggested.

• Journal of the Korean Wood Science and Technology
• /
• 제26권3호
• /
• pp.16-25
• /
• 1998

This study was carried out to compare vibrational properties and adsorption among shellac, cashew finished plate and untreated plate of Sitka spruce(Picea sitchensis Carr). By the method of statistical regression modeling, the fundamental resonance frequency of finished plate was higher than that of untreated plate. The fundamental resonance frequency of cashew finished plate was higher than that of shellac finished plate. By the method of modal analysis, mode frequency ratio of cashew finished plate was higher than that of shellac finished plate. Amounts of adsorption of finished plate was lower than that of untreated plate, and amount of adsorption of cashew finished plate was lower than that of shellac finished plate. It was clarified that the vibrational properties and adsorption of finished plate were superior to those of untreated plate. The vibrational properties and adsorption of cashew finished plate was superior to those of shellac finished plate.

• 한국펄프종이공학회:학술대회논문집
• /
• 한국펄프종이공학회 2006년도 PAN PACIFIC CONFERENCE vol.2
• /
• pp.365-372
• /
• 2006

In this paper, the possibility of statistical modeling from the pulp and peroxide bleaching condition variables to predict optical properties of a bleached chemimechanical pulp used in a newsprint paper machine at Mazandaran Wood and Paper Industries Company (MWPI) was studied. Due to the variations in the opacity and the brightness of the bleached pulp at MWPI and to tackle this problem, it was decided to study the possibility of modeling the bleaching process. To achieve this purpose, Multi-variate Regression Analysis was used for model building and it was found that there is a relationship between independent variables and pulp brightness as well as pulp opacity, consequently, two models were constructed. Then, model validation was carried out using new data set in the bleaching plant at MWPI to test model predictive ability and its performance.

• Journal of Forest and Environmental Science
• /
• 제28권3호
• /
• pp.170-178
• /
• 2012

Dipterocarps or Dipterocarpaceae is a commercially important timber producing and dominant keystone tree family in the rain forests of Borneo. Borneo's landscape is changing at an unprecedented rate in recent years which affects this important biodiversity. This paper attempts to model the natural occurrence (distribution including those areas with natural forests before being converted to other land uses as opposed to current distribution) of dipterocarp species in Sarawak which is important for forest biodiversity conservation and management. Local modeling method of Inverse Distance Weighting was compared with commonly used statistical method (Binary Logistic Regression) to build the best natural distribution models for three genera (12 species) of dipterocarps. Database of species occurrence data and pseudoabsence data were constructed and divided into two halves for model building and validation. For logistic regression modeling, climatic, topographical and edaphic parameters were used. Proxy variables were used to represent the parameters which were highly (p>0.75) correlated to avoid over-fitting. The results show that Inverse Distance Weighting produced the best and consistent prediction with an average accuracy of over 80%. This study demonstrates that local interpolation method can be used for the modeling of natural distribution of dipterocarp species. The Inverse Distance Weighted was proven a better method and the possible reasons are discussed.

• Communications for Statistical Applications and Methods
• /
• 제13권1호
• /
• pp.177-190
• /
• 2006

The aim of this study is to propose a Bayesian model for fitting mortality rate of colon cancer. For the analysis of mortality rate of a disease, factors such as age classes of population and spatial characteristics of the location are very important. The model proposed in this study allows the age class to be a random effect in addition to its conventional role as the covariate of a linear regression, while the spatial factor being a random effect. The model is fitted using Metropolis-Hastings algorithm. Posterior expected predictive deviances, standardized residuals, and residual plots are used for comparison of models. It is found that the proposed model has smaller residuals and better predictive accuracy. Lastly, we described patterns in disease maps for colon cancer.