• Journal of The Korean Society of Agricultural Engineers
• /
• v.65 no.4
• /
• pp.33-43
• /
• 2023

In this study, it was developed and verified an application method of fuzzy-logic theory to the rating process of agricultural fill dam safety. A fuzzy-logic is very famous logical system when some decision making is made on the status of a lack of information. Three proxies were selected and configured membership functions (MFs) and these MFs were activated in the process of fuzzification procedures. Fuzzified vlaues were passed through the rule-based inference system, then fire strength could classified among cases of the rule-based inference system. To obtain final results, Mandani-type was adapted in the defuzzification process. As the results, it was shown the developed system can give a correct results that was compared with Matlab - fuzzy inference function. More ever it could perform the detailed analysis and improvement on the infrastructure safety rating process using classical diagnosis method.

• Science of Emotion and Sensibility
• /
• v.17 no.1
• /
• pp.71-78
• /
• 2014

We propose the sentiment pattern as a novel sentiment feature for more accurate text sentiment analysis, and introduce the rating inference of movie reviews using it. The text sentiment analysis is a task that recognizes and classifies sentiment of text whether it is positive or negative. For that purpose, the sentiment feature is used, which includes sentiment words and phrase pattern that have specific sentiment like positive or negative. The previous researches for the sentiment analysis, however, have a limit to understand accurately total sentiment of either a sentence or text because they consider the sentiment of sentiment words and phrase patterns independently. Therefore, we propose the sentiment pattern that is defined by arranging semantically all sentiment in a sentence, and use them as a new sentiment feature for the rating inference that is one of the detail subjects of the sentiment analysis. In order to verify the effect of proposed sentiment pattern, we conducted experiments of rating inference. Ratings of test reviews is inferred by using a probabilistic method with sentiment features including sentiment patterns extracted from training reviews. As a result, it is shown that the result of rating inference with sentiment patterns are more accurate than that without sentiment patterns.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.19 no.1
• /
• pp.91-107
• /
• 2023

With the recent expansion of the commerce ecosystem, a large number of user evaluations have been produced. Accordingly, attempts to create business insights using user evaluation data have been actively made. However, since user evaluation can change after the user experiences the product, it is difficult to say that the analysis based only on reviews immediately after purchase fully reflects the user's evaluation of the product. Moreover, studies conducted so far on user evaluation have overlooked the fact that the length of time a user has used a product can affect the user's product evaluation. Therefore, in this study, we build a model that predicts the direction of change in the user's rating after use from the user's rating and reviews immediately after purchase. In particular, the proposed model reflects the product's period of use in predicting the change direction of the star rating. However, since the posterior information on the duration of product use cannot be used as input in the inference process, we propose a structure that utilizes information about the product's period of use using an auxiliary classifier. As a result of an experiment using 599,889 user evaluation data collected from the shopping platform 'N' company, we confirmed that the proposed model performed better than the existing model in terms of accuracy.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.8
• /
• pp.3636-3643
• /
• 2011

To prevent the electrical accidents in the laboratory, we identify problems for periodic inspections of the electric field and develop a fuzzy inference system that can be practically applied to check items. Focusing on electrical safety in the lab environment, we draw check items that can be applied in common and develop a standard checklist that is consistent with the laboratory electrical safety and the periodic inspections. Using the standard checklist we select the items that may contain a linguistic ambiguity and define the membership functions for these items. We also have a safety rating defined by the membership function. Using these fuzzy variables we form the fuzzy rules in the form of 'If-Then' and develop a fuzzy inference system through the fuzzy engine. From this, electrical accidents could be prevented in advance continuously by managing the intelligent and efficient inspection and electrical safety to prevent the electrical accidents in the laboratory.

• Journal of KIISE:Software and Applications
• /
• v.37 no.9
• /
• pp.659-668
• /
• 2010

Collaborative filtering systems grasp behaviors for a new user and need new information for the user in order to recommend interesting items to the user. For the purpose of acquiring the information the collaborative filtering systems learn behaviors for users based on the previous data and can obtain new information from the results. In this paper, we propose an inductive inference method to obtain new information for users and rank items by using the new information in the proposed method. The proposed method clusters users into groups by learning users through NMF among inductive machine learning methods and selects the group features from the groups by using chi-square. Then, the method classifies a new user into a group by using the bayesian probability model as one of inductive inference methods based on the rating values for the new user and the features of groups. Finally, the method decides the ranks of items by applying the Rocchio algorithm to items with the missing values.

• Journal of Digital Contents Society
• /
• v.18 no.3
• /
• pp.535-542
• /
• 2017

The ubiquitous computing made it happen to easily take cognizance of context, which includes user's location, status, behavior patterns and surrounding places. And it allows providing the catered service, designed to improve the quality and the interaction between the provider and its customers. The personalized recommendation service needs to obtain logical reasoning to interpret the context information based on user's interests. We researched a model that connects to the practical value to users for their daily life; information about restaurants, based on several mobile contexts that conveys the weather, time, day and location information. We also have made various approaches including the accurate rating data review, the equation of Naïve Bayes to infer user's behavior-patterns, and the recommendable places pre-selected by preference predictive algorithm. This paper joins a vibrant conversation to demonstrate the excellence of this approach that may prevail other previous rating method systems.

• Journal of the Korean Data and Information Science Society
• /
• v.24 no.4
• /
• pp.689-699
• /
• 2013

This paper studies the partial credibility application method by assuming the empirical prior or noninformative prior informations in auto insurnace business where intensive rating segmentation is expanded because of premium competition. Expanding of rating factor segmetation brings the increase of pricing cells, as a result, the number of cells for partial credibility application will increase correspondingly. This study is trying to suggest more accurate estimation method by considering the Bayesian framework. By using empirically well-known or noninformative information, inducing the proper posterior distribution and applying the Bayes estimate which is minimizing the error loss into the credibility method, we will show the advantage of Bayesian inference by comparison with current approaches. The comparison is implemented with square root rule which is a widely accepted method in insurance business. The convergence level towarding to the true risk will be compared among various approaches. This study introduces the alternative way of redcuing the error to the auto insurance business fields in need of various methods because of more segmentations.

• Korean Journal of Psychosomatic Medicine
• /
• v.25 no.1
• /
• pp.63-72
• /
• 2017

Objectives : Attention-deficit hyperactivity disorder(ADHD) is characterized by significant impairments in executive functions, with a prevalence of approximately 3-5% of all children worldwide. The goal of this study was to examine the relationship between executive functions and electrophysiological activities in children and adolescents with ADHD. Methods : In 31 patients with ADHD, resting-state EEG was recorded, and Comprehensive Attention Test(CAT), Stroop Color-Word Inference Test(Stroop CWIT), Trail Making Test(TMT), and Wisconsin Card Sorting Test(CST) were administered. Korean version of the ADHD Rating Scale(K-ARS) was assessed. Results : Alpha and beta power positively correlated with the Attention Quotient(AQ), while delta power negatively correlated with AQ from CAT. In the Stroop CWIT, decreased delta power and increased beta power were related to higher performance. Power of the alpha band increased with higher TMT performance. Moreover, delta power negatively correlated with good performance on the CST, while alpha and high gamma band showed a positive correlation. Correlation with the parent-rating of ADHD symptoms showed a negative correlation between alpha power and higher scores on the K-ARS. Conclusions : These findings indicate that relative power in higher frequency bands of EEG is related to the higher executive function in children and adolescents with ADHD, while the association with the relative power in lower frequency bands of EEG seem to be vice versa. Furthermore, the findings suggest that QEEG may be a useful adjunctive tool in assessing patients with ADHD.

• Journal of Technology Innovation
• /
• v.23 no.3
• /
• pp.373-396
• /
• 2015

This study analyzed the determinants of high-growth firms using the technology appraisal data of the Korea Technology Finance Corporation. This study is differentiated from previous studies for three reasons. First, it analyzed the determinants of firms that will grow into high-growth firms in the future, not the characteristics of current high-growth firms. Second, it analyzed high-growth firms by dividing them in two aspects: sales and employment. In other words, they were divided into three types: the case in which a firm achieves high growth in both sales increase and creation of jobs, the case in which a firm achieves high growth in creation of jobs but low growth in sales increase, and the case in which a firm achieves high growth in only sales increase but low growth in creation of jobs. Third, this study applied the technology appraisal indicators of Kibo Technology Rating System(KTRS) by the Korea Technology Finance Corporation as the explanatory variable. As a result of analysis, it was found that a firm achieved high growth in both sales and employment if the position in the technology life cycle was appropriate and the technology readiness level was high. However, it turned out that the management system of technical manpower had conflicting effects on high growth of employment and sales. In other words, a firm that had well managed its technical manpower achieved high growth in terms of employment, but rather showed low growth in terms of sales. This result suggests the inference that firms showing high growth in employment may appear mainly in the high-tech industry where management of technical manpower is important. Accordingly, as a result of adding dummy variables that represent whether or not firms are in the high-tech industry, it was found that the result supported the inference, as firms in the high-tech industry were highly likely to achieve high growth in employment.

• Journal of Internet Computing and Services
• /
• v.16 no.2
• /
• pp.41-48
• /
• 2015

On movie review sites, movie ratings are determined by netizens' subjective judgement. This means that inconsistency between ratings and opinions from netizens often occurs. To solve this problem, this paper proposes sentiment sentence sets which affect movie evaluation, and apply sets to comments to infer ratings. Creation of sentiment sentence sets is consisted of two stages, construction of sentiment word dictionary and creation of sentiment sentences for sentiment estimation. Sentiment word dictionary contains sentimental words and its polarities included in reviews. Elements of sentiment sentences are combined with movie related noun and predicate from words sentiment word dictionary. In this study, to make correspondence between polarity of sentiment sentence and sentiment word dictionary, sentiment sentences which have different polarity with sentiment word dictionary are removed. The scores of comments are calculated by applying averages of sentiment sentences elements. The result of experiment shows that sentence scores from sentiment sentence sets are closer to reflect real opinion of comments than ratings by netizens'.