• Proceedings of the Korean Statistical Society Conference
• /
• 2004.11a
• /
• pp.229-236
• /
• 2004

This article presents a multiple comparison ranking procedure for several products of the Poisson rates. A preference probability matrix that warrants the optimal comparison ranking is introduced. Using a Bayesian Monte Carlo method, we develop simulation-based procedure to estimate the matrix and obtain the optimal ranking via a row-sum scores method. Necessary theory and two illustrative examples are provided.

• Proceedings of the Korean Statistical Society Conference
• /
• 2003.05a
• /
• pp.85-90
• /
• 2003

In this paper we develop a method for finding optimal ordering of K statistical models. This is based on a dependent paired comparison experimental arrangement whose results can naturally be represented by a completely oriented graph (also so called tournament graph). Introducing preference probabilities, strong transitivity conditions, and an optimal criterion to the graph, we show that a Hamiltonian path obtained from row sum ranking is the optimal ordering. Necessary theories involved in the method and computation are provided. As an application of the method, generalized variances of K multivariate normal populations are compared by a Bayesian approach.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.61 no.2
• /
• pp.92-97
• /
• 2016

This experiment aimed to compare the sensory ability of experts and untrained to evaluate three rice varieties by using five sensory evaluation methods. All panelists showed significant differences in their sensory abilities to distinguish among Haiami, Chucheong, and Dasan 1 rice varieties when using the duo-trio test and triangle test. The expert panelists showed a clear preference in the following order: Haiami > Chucheong > Dasan 1, when using the paired comparison test, ranking test, and multiple comparison test. However, the untrained panelists showed no significant differences in their sensory ability to distinguish between the Haiami and Chucheong varieties when using the multiple comparison test. The results indicate that, for sensory evaluation of cooked rice by untrained panelists, the paired comparison test is suitable for evaluating two samples and the ranking test is suitable for evaluating more than two samples.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.4
• /
• pp.1-10
• /
• 2022

Attempts to interpret human perspectives using computer vision have been developed in various fields. In this paper, we propose a method for evaluating the walking environment through semantic segmentation results of images from road images. First, the Kakao Map API was used to collect road images, and four-way images were collected from about 50,000 points in JeonJu. 20% of the collected images build datasets through crowdsourcing-based paired comparisons, and train various regression models using paired comparison data. In order to derive the walkability score of the image data, the ranking score is calculated using the Trueskill algorithm, which is a ranking algorithm, and the walkability and analysis using various regression models are performed using the constructed data. Through this study, it is shown that the walkability of Jeonju can be evaluated and scores can be derived through the correlation between pixel distribution classification information rather than human vision.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.5
• /
• pp.1-11
• /
• 2022

With the development of deep learning technology, various research and development are underway to estimate preference rankings through learning, and it is used in various fields such as web search, gene classification, recommendation system, and image search. Approximation algorithms are used to estimate deep learning-based preference ranking, which builds more than k comparison sets on all comparison targets to ensure proper accuracy, and how to build comparison sets affects learning. In this paper, we propose a k-disjoint comparison set generation algorithm and a k-chain comparison set generation algorithm, a novel algorithm for generating paired comparison sets for crowd-sourcing-based deep learning affinity measurements. In particular, the experiment confirmed that the k-chaining algorithm, like the conventional circular generation algorithm, also has a random nature that can support stable preference evaluation while ensuring connectivity between data.

• Korean journal of food and cookery science
• /
• v.7 no.3
• /
• pp.29-36
• /
• 1991

Analysis of major nutritional components and Sensory evaluation in two kinds of beef bone stocks (White & Brown) have been Carried out in this study, these stocks were prepared with four different parts of beef bone (Knee bone, Rumpbone, Legbone, Backbone). White bone stocks were made of each beef bone boiling in water & hours, while brown bone stocks were prepared with roasted beef bone in the oven at $230^{\circ}C$ for half an hour and boiled 8 hours with water. Fatty acids were determined by GLC (Gas Lipids Chromatogram), the minerals were analysed by Automic spectrometer. The results of these analysis were obtained as followes; 1. Neutral lipids was gradually becreased, and glycolipids phospholipids were increased in quantity in Brown stocks for 8 hours. Unsaturated fatty accid of Brown stocks was highly decreased due to roasting of bores in the oven at 23$0^{\circ}C$ for half an hour. But they appeared in large quantity in white stocks. 2. The minerals also contained of high percentage in almost Brown stock except backbone Stock 3. Four materials (Kneebone, Rumpbone, Legbone, and backbone) were used for this study and the paired comparison of flavor test presented the recognition of different flavor at 5% level of Least Significant Difference (LSD) on brown stocks (Kneebone, and Legbone). Ranking preference test showed that white Kneebone stock and brown legbone stock had good taste.

• Journal of Navigation and Port Research
• /
• v.37 no.5
• /
• pp.493-498
• /
• 2013

This paper is aimed to priority evaluation of preliminary cases for IMO -IMS(International Maritime Organization- Information Management System) using fuzzy TOPSIS(Technique for Order Performance by Similarity to Ideal Solution) and AHP(Analytic Hierarchy Process). To this solve, therefore, this paper extract 24 preliminary cases and select 4 major preliminary alternative cases after analysing the structure of its alternative cases using FSM(Fuzzy Structure Modeling). Also, the weights of evaluation factors determine using AHP which able to keep the consistency when decision-makers assess. In AHP method, but, the numbers of paired comparison incerase as much as the numbers of the comparison items increase and because this evaluation have the many of vagueness, the decision of final ranking is used to fuzzy TOPSIS method which is included TOPSIS and Fuzzy Set Theory. The result are developed as order as Management of IMO Convention Information, Delivery of IMO Convention Information, Total IMO Database, Knowledge Hub of IMO Convention Information in IMO-IMS.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.19 no.3
• /
• pp.471-482
• /
• 1995

Using the acetate velvet and viscose velvet whose pile lengths were sheared as 1.45, 1.55, 1 65, 1.75, 1.85, 1.90mm under the condition equating the weaving process of ground fabric, the conclusions were as follows through the results of the sensory assessments estimated by women students in our university and the physical properties, H. V and T. H. V obtained by KES-F system. 1. In the sensory assessments estimated by the method of paired comparison and ranking of samples, the longer pile length was, the more the hand values of smoothness, softness, thickness, heaviness increased on the whole. 2. The H V. and T. H. V. measured by KES-F system were as follows; Kohi increased to pile length 1.85mm and then decreased a little at 1.90mm. hummer increased as pile length was longer. Fukurami increased to pile length 1.75mm and then decreased gradually as pile length was longer. Total hand value increased gradually from 1. 45mm to 1.85mm, had the top value at 1.85mm, and then decreased a little at 1.90mm. 3. In the results of summarizing $\ulcorner$the physical properties correlated closely with the H. V obtained by sensory assessments$\lrcorner$ and tithe Physical properties correlated closely with the H. V. and T. H. V obtained by KES-F systems, it showed that all the sensory properties correlated closely with compressive energy, flexural rigidity, thickness, weight and pile ratio in the former and that the physical properties correlated closely with each H V and T. H. V were different in the latter. 4. It showed that factor 1 was related to compressive energy, thickness, weight, pile ratio, factor 2 was related to recovery energy, compressive resilience, compressive index, and factor 3 was related to compressive recovery ratio in the result of factor analysis. 5. In the multiple repression analysis, the expressions of all sensory properties had compressive ratio, frictional coefficient in the regression expressions of $\ulcorner$H. V. obtained by sensory assessments$\lrcorner$, while the expressions of each H. V. and different physical properties in the regression expressions of $\ulcorner$H. V. obtained by KES-F system$\lrcorner$.

• Journal of the Korean Home Economics Association
• /
• v.28 no.4
• /
• pp.1.1-13
• /
• 1990

Authors have performed the sensory evaluation tests according to each given items after selecting various lines in order to assess the visual effects by the lines in cloth designing. The evaluations were done by means of ranking tests followed by paired comparison tests. The results obtained were as follows : 1. In the item in than "Shoulder width looks wide", the design C3 showed the best visual effect, and then B1, F8, and A5 comes in order. In "Shoulder width looks narrow", they were A2, F5, F7, and B2 in order. 2. In "Bust looks big", the effect was best in F9, and then B1, F5, C3, and A5 and order. "Bust looks small" item showed A3, C1, and F1 in order. 3. In "Waist looks thick", they were B2, D1, and F7 while in "Waist looks thin", they were B3, F8, and D6 in order. 4. In the item in that "Hip looks big", the best effect was in F9, and then E3, C2, and B4 in order. In "Hip looks small", the best one was C1, and then comes. E1, F6, and F8. 5. In "Upper body looks thick", they were D2, D4, F8, C3 and A5 in order whild in "Upper body looks thin", they were A1, F5, and D7 in order. 6. In the item "Lower body lookds thick", they were F9, C2, E3, B3, and D3 in order. In "Lower body looks thin", the best one was C1, and then D1, E2, F6, and F8 comes in order. 7. In "whole body looks thick", they were F9, F3, D3, and A5, and in "Whole body looks thin", they were F5, A1, C1, and D6 in order. 8. In "Height looks tall", the effects were in order of A4, D6, E1, and F7 while in "Height looks short", they were E3, F9, B4, D2, and D1. 8. In "Height looks tall", the effects were in order of A4, D6, E1, and F7 while in "Height looks short", they were E3, F9, B4, D2, and D1. F9, B4, D2, and D1.

• The Journal of the Acoustical Society of Korea
• /
• v.37 no.3
• /
• pp.147-155
• /
• 2018

In this paper, we tried to find out sound quality metrics to express discomfort of overload excavator noise and to develop sound quality indexes through multiple regression analysis by using them. For this purpose, the interior noise of cabin under overload condition was recorded for six excavator models with different noise properties and Jury test was carried out by PCM (Paired Comparison Method) and MEM (Magnitude Estimation Method). Jury test result with low consistency was classified into two groups with different preference tendencies by cluster analysis and multiple regression analysis was conducted in order to find out which sound quality metrics have significant effects on discomfort(low preference). As a result, we figured out that the sound quality metrics to express the discomfort were the partial loudness (= $PN_{10Bark}$) between 0 and 10 Bark in case of group1 and the difference between engine noise(= $dB_{EG}$) and hydraulic system noise ($dB_1$) in case of group2. Using the results of preference ranking and tendency analysis of PCM followed by the correlation analysis between PCM and MEM, the more reliable results were adopted by excluding the data with low consistency obtained from Jury test via MEM.