• Journal of Energy Engineering
• /
• v.25 no.4
• /
• pp.190-197
• /
• 2016

Flash point is the one of the important properties for the safe handling of inflammable liquid solution. In this paper, flash points of binary liquid solutions, water+1-propanol and water+2-propanol, were been measured by using Seta flash closed cup aparatus. Flash point was estimated using regression analysis method. Flash points were also estimated by the method based on Raoul's law and the method optimizing the binary parameters of van Laar equation. Experimental results were compared with the calculated results. The regression analysis method is able to estimate the flash point fairly well for water+1-propanol and water+2-propanol mixture.

• Journal of the Korean Data and Information Science Society
• /
• v.7 no.2
• /
• pp.203-210
• /
• 1996

A linear neural unit with a modified anti-Hebbian learning rule has been shown to be able to optimally fit curves, surfaces, and hypersurfaces by adaptively extracting the minor component of the input data set. In this paper, we study how to use the robust version of this neural fitting method for linear regression analysis. Furthermore, we compare this method with other methods when data set is contaminated by outliers.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.49 no.3
• /
• pp.63-68
• /
• 2007

The LRA(Logistic Regression Analysis) conducts a quantitative analysis by collecting a lot of samples and the AHP(Analytic Hierarchy Program) makes use of expert decision influenced by subjective judgment to a certain degree. This study is to suggest a combination method in mapping landslide hazard by giving equal weight for the result of LRA and AHP. Topographic factors(slope, aspect, elevation), soil dram, soil depth and land use were adopted to classify landslide hazard areas. The three methods(LRA, AHP, the combined approach) was applied to a $520km^2$ region located in the middle of South Korea which have occurred 39 landslides during 1999 and 2003. The suggested method showed 58.9% matching rate for the real landslide sites comparing with the classified areas of high-risk landslide While LRA and AHP Showed 46.1% and 48.7% matching rates respectively. Further studies are recommended to find the optimal combining weight of LRA and AHP with more landslide data.

• Proceedings of the KSME Conference
• /
• 2003.11a
• /
• pp.1430-1435
• /
• 2003

Satellite upper platform is optimized by response surface method which has non-gradient, semi-glogal, discrete and fast convergency characteristics. Sampling points are extracted by design of experiments using Central Composite Method and Factorial Design. Also response surface is generated by the various regression functions. Structure analysis is execuated with regard for static and dynamic environment in launching stage. As a result response surface method is superior to other optimization method with respect to optimum value and cost of computation time. Also a confidence is varified in the various regression models.

• Journal of Computing Science and Engineering
• /
• v.11 no.4
• /
• pp.121-129
• /
• 2017

Feature selection has been widely established as an efficient technique for microarray data analysis. Feature selection aims to search for the most important feature/gene subset of a given dataset according to its relevance to the current target. Unsupervised feature selection is considered to be challenging due to the lack of label information. In this paper, we propose a novel method for unsupervised feature selection, which incorporates embedded learning and $l_{2,1}-norm$ sparse regression into a framework to select genes in microarray data analysis. Local tangent space alignment is applied during embedded learning to preserve the local data structure. The $l_{2,1}-norm$ sparse regression acts as a constraint to aid in learning the gene weights correlatively, by which the proposed method optimizes for selecting the informative genes which better capture the interesting natural classes of samples. We provide an effective algorithm to solve the optimization problem in our method. Finally, to validate the efficacy of the proposed method, we evaluate the proposed method on real microarray gene expression datasets. The experimental results demonstrate that the proposed method obtains quite promising performance.

• Journal of Digital Contents Society
• /
• v.19 no.7
• /
• pp.1357-1363
• /
• 2018

In addition to advances in information technology, machine learning approach is applied to a variety of applications, and is expanding to a variety of areas. In this paper, we propose a software analysis method that applies linear regression to analyse software similarity from the code distribution of the software. The characteristics of software can be expressed by instructions contained within the program, so the distribution information of instructions is used as learning data. In addition, a learning procedure with the learning data generates a linear regression model for software similarity analysis. The proposed method is evaluated with real world Java applications. The proposed method is expected to be used as a basic technique to determine similarity of software. It is also expected to be applied to various software analysis techniques through machine learning approaches.

• Communications for Statistical Applications and Methods
• /
• v.16 no.2
• /
• pp.317-323
• /
• 2009

Recently not even government polices but small town decisions are based on the survey data/information, so the most of government agencies/organizations demand various sample surveys in each fields for more detail information. However in conducting the sample survey, nonresponse problem rises very often and it becomes a major issue on judging the accuracy of survey. For that matters, one solution ran be using the administration data. However unfortunately most of administration data are restricted to the common users. The other solution can be the imputation. Therefore several method, of imputation are studied in various fields. In this study, in stead of the simple regression imputation method which is commonly used, factor score regression method is applied specially to the incomplete data which have the unit and item misting values in survey data. Here for simulation study, Consumer Expenditure Surveys in Korea are used.

• Proceedings of the KSRS Conference
• /
• 2006.03a
• /
• pp.202-205
• /
• 2006

The objective of this study is to analyze the hazard-areas for landslide using GIS and RS. LRA (Logistic Regression Analysis) and AHP (Analytic Hierarchy Program) methods were used for evaluation of the hazard-areas by six topographic factors (slope, aspect, elevation, soil drain, soil depth, land use). These methods were applied to Anseong-si where frequent landslides were occurred mainly by the regional heavy rainfall. A landslide hazard-map of Anseong-si could describe into 7 hazard-grades. As results, LRA method was underestimated in higher grades areas, while AHP method was underestimated in lower grades areas. In order to evaluate the hazard-areas for landslides with accuracy, these results of each method were overlapped and the results of suggested method were compared with the historical landslide hazard records of KFRI (Korea Forest Research Institute).

• Korean Journal of Applied Biomechanics
• /
• v.31 no.2
• /
• pp.148-153
• /
• 2021

Objective: It is to extract training items that have a high relationship with the improvement of weightlifting records through correlation and regression analysis between training methods used commonly in the field and Snatch records and jerk records. Through this, it is intended to promote training efficiency to improve the records of weightlifters. Method: For 90 elite weightlifters of the professional teams, 4 groups (lightweight (30 people): 61 kg, 67 kg, 73 kg., middleweight (30 people): 81 kg, 89 kg, 96 kg., heavyweight (30 people): 102 kg, 109 kg, +109 kg., the whole group (90 people)) were divided. At the significance level of 0.05, correlation analysis and linear regression analysis were performed between record of training methods used widely in the field and Snatch records and Jerk records. Results: First, the better the record in Jerk, the better the Snatch record. Second, the three training methods HS, ForceS and WP performed in the field were all found to be important factors related to the improvement of Snatch record. Third, In the jerk where there are more types of training than Snatch, three training methods (HC, ForceS, BPP) appeared to be an important training method for improving the jerk record. Conclusion: While many training methods have been devised and carried out in the field, 3 types of training (HS, ForceS, WP) for improving Snatch record and 3 types of training (HC, ForceS, BPP) for improving Jerk record was found to be the most influential training method. Since all of them showed a large value of explanatory power by regression analysis, it is considered that this study is meaningful in that it can promote training efficiency by simplifying although there are many types of training for athletes.

• Journal of the Korean Society of Costume
• /
• v.54 no.3
• /
• pp.73-85
• /
• 2004

The purpose of this study was to investigate the characteristic and sensibility of Japanism fashion designs which represented by Japanese designers and Western designers. The stimulus were 29 pictures of contemporary fashion designs which represented the Japanism style fashion designs from fashion collections. The data were analyzed by Cluster analysis, Factor analysis, Multidimensional Scaling Method and Regression Analysis. The specific objectives were as follows ; 1) As result of design analysis, Japanism fashion sensibility is unique and good-looking. 2) As result of the factor analysis. 4 factors which are Attractiveness, Attention, Maturity and Hardness and softness. 3) According to sensibility positioning, The Japanism fashion design was classified by Decorative-Simple, Hard-Soft. 4) As result of the Regression Analysis, The preference of Japanism fashion design was related to attractive factor. 5) As result of the Regression Analysis. The buying desirable of Japanism fashion design was related to attractive, attentive and mature factor.