• Journal of KIISE:Software and Applications
• /
• v.30 no.3_4
• /
• pp.316-325
• /
• 2003

A user preference prediction method using an exiting collaborative filtering technique has used the nearest-neighborhood method based on the user preference about items and has sought the user's similarity from the Pearson correlation coefficient. Therefore, it does not reflect any contents about items and also solve the problem of the sparsity. This study suggests the preference prediction system using the similarity weight granted Bayesian estimated value and the associative user clustering to complement problems of an exiting collaborative preference prediction method. This method suggested in this paper groups the user according to the Genre by using Association Rule Hypergraph Partitioning Algorithm and the new user is classified into one of these Genres by Naive Bayes classifier to slove the problem of sparsity in the collaborative filtering system. Besides, for get the similarity between users belonged to the classified genre and new users, this study allows the different estimated value to item which user vote through Naive Bayes learning. If the preference with estimated value is applied to the exiting Pearson correlation coefficient, it is able to promote the precision of the prediction by reducing the error of the prediction because of missing value. To estimate the performance of suggested method, the suggested method is compared with existing collaborative filtering techniques. As a result, the proposed method is efficient for improving the accuracy of prediction through solving problems of existing collaborative filtering techniques.

• Fashion & Textile Research Journal
• /
• v.9 no.2
• /
• pp.229-236
• /
• 2007

Many researchers have focused on consumers' clothes purchase behavior, These researches could not reflect the characteristics of the single consumers' clothes purchase behavior. In addition, little has been written on the single consumer. The purposes of this study are to identify the concept and psychologic characteristics of single consumer and investigate the effects of single consumers' psychologic characteristic and susceptibility to interpersonal influence on clothes shopping pursuing value. Also, It was analyzed how single consumer' pursuing values are different based on the type of single motivation. To test research problems, Data were collected by means of a survey questionnaire, which was sent to 300 single in Pusan and Ulsan. In total, 274 were returned and 14 were unusable because of unacceptable levels of missing data. The Results were summarized as follows: First, self-efficacy, informative and normative influence were positively related to utilitarian pursuing value employee satisfaction. Also, self-efficacy, variety seeking, innovativeness and informative influence had a positive effect on hedonic pursuing value. Second, voluntary single and nonvoluntary single group had different perceptions about self-efficacy, variety seeking, innovativeness, informative influence, and hedonic pursuing value.

• Korea Journal of Hospital Management
• /
• v.27 no.4
• /
• pp.13-21
• /
• 2022

Purpose: The purpose of this study was to analyze the association between single-person households & Beneficiary of National Basic Livelihood and recommendation on alcohol consumption, and counseling on drinking problems for adults 19 years of age or older. Methods: In this study, excluding missing values, the association between the single-person household & Beneficiary of National Basic Livelihood and recommendation to refrain drinking alcohol, counseling for drinking problems was analyzed by using the chi-squre test and logistic regression analysis. Results: In the case of non-single person households, compared to single-person households, the recommendation rate to refrain drinking alcohol was 1.519 OR (Odds Ratio [OR]: 1.159 , p-value <.0001). meanwhile, in the case of Beneficiary of National Basic Livelihood, the recommendation rate to refrain alcohol consumption was higher by 1.414 OR (OR: 1.414, p-value: 0.011), and the drinking problem counseling rate was also higher by 2.257 OR (OR: 2.257, p-value: 0.026) compared to non-beneficiary group. Discussion & Conclusion: Based on the 2016-2019 National Health and Nutrition Survey, this study investigated the associaiton between single households & Beneficiary of National Basic Livelihood and recommendations to refrain alcohol, and counseling on drinking problems. Compared to the Beneficiary of National Basic Livelihood group, single-person household group has recently been classified as a socially vulnerable group, but it is not applicable in the policy category. If policy and institutional measures for treatment are provided, it is expected that the problem of alcohol abuse can be reduced.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.1
• /
• pp.696-701
• /
• 2017

This paper proposes an improved de-interlacing method that converts interlaced images into progressive images from one field. First, it calculates inter-pixel values applying third-order spline interpolation for the horizontal direction from four upper lower pixel values of missing pixels. From inter-pixel values obtained from spline interpolation and upper lower pixels with value, the proposed method makes an accurate estimate of the direction by applying the correlation between upper and lower pixels. The correlation between upper and lower pixels is calculated in nine directions of a missing pixel by using values obtained from spline interpolation and pixels with value. The direction of an edge is determined as the direction in which the correlation between upper and lower pixels is at its minimum. Thus, a missing pixel is calculated by taking the average of upper lower pixels obtained from the predicted direction of an edge. From the simulation results, there are problems in that it takes a bit more time for processing, but it is expected that the time problem will be improved by increasing CPU processing speed. As for image quality, it is shown that the proposed method improves both subjective and objective image quality and quantitatively improves picture signal-to-noise ratio (PSNR) in the range between 0.1 dB to 0.5 dB, as compared with previously presented de-interlacing methods.

• The Journal of Bigdata
• /
• v.5 no.1
• /
• pp.227-239
• /
• 2020

This paper introduces a method for predicting the maximum power demand despite communication errors in industrial sites. Due to the recent policy of de-nuclearization in Korea, the price of electricity is inevitable, and the amount of electricity used and maximum load management for the management of power demand are becoming important issues. Accordingly, it is important to predict and manage peak power. However, problems such as loss and modulation of measured power data occur at industrial sites due to noise generated by various facilities and sensors. It is difficult to predict the exact value when measured effective power data are lost. The study presents a model for predicting and correcting anomalies and missing values when measured effective power data are lost. The models used in this study are expected to be useful in predicting peak power demand in the event of communication errors at industrial sites.

• The KIPS Transactions:PartB
• /
• v.10B no.3
• /
• pp.287-296
• /
• 2003

There has been much research focused on collaborative filtering technique in Recommender System. However, these studies have shown the First-Rater Problem and the Sparsity Problem. The main purpose of this Paper is to solve these Problems. In this Paper, we suggest the user's predicting preference method using Bayesian estimated value and the associative user clustering for the recalculation of preference. In addition to this method, to complement a shortcoming, which doesn't regard the attribution of item, we use Representative Attribute-Neighborhood method that is used for the prediction when we find the similar neighborhood through extracting the representative attribution, which most affect the preference. We improved the efficiency by using the associative user's clustering analysis in order to calculate the preference of specific item within the cluster item vector to the collaborative filtering algorithm. Besides, for the problem of the Sparsity and First-Rater, through using Association Rule Hypergraph Partitioning algorithm associative users are clustered according to the genre. New users are classified into one of these genres by Naive Bayes classifier. In addition, in order to get the similarity value between users belonged to the classified genre and new users, and this paper allows the different estimated value to item which user evaluated through Naive Bayes learning. As applying the preference granted the estimated value to Pearson correlation coefficient, it can make the higher accuracy because the errors that cause the missing value come less. We evaluate our method on a large collaborative filtering database of user rating and it significantly outperforms previous proposed method.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.13 no.3
• /
• pp.78-88
• /
• 2014

Now, UTIS collects and provides traffic information by building RSE 1,150(unit) and OBE about 51,000(vehicle). it's inevitable to enlarge traffic information sources which use to improve quality of UTIS traffic information for Stabilizing UTIS's service. but there are missing data sections. And, In this study as a way to overcome these problems, based on BIS(Bus information system) installed and operating in the capital area to develop normal vehicle's link transit time estimation model which is used realtime collecting BMS data, we'll utilize the model to provide missing data section's information. For these problem, we selected partial section of suwon-city, anyang-city followed by drive only way or not and conducted model estimating and verification each of BMS data and UTIS traffic information. Consequently, Case2,4,6,8 presented highly credibility between UTIS communication data and estimated value but In the Case 3,5 we determined to replace communication data of UTIS' missing data section too hard for large error. So we need to apply high credibility model formula adjusting road managing condition and the situation of object section.

• Journal of the Korean School Mathematics Society
• /
• v.16 no.4
• /
• pp.719-743
• /
• 2013

Proportional reasoning is considered as a difficult concept to most elementary school students and might be connect to functional thinking, algebraic thinking, and mathematical thinking later. The purpose of this study is to analyze the sixth graders' development level of proportional reasoning so that children's problem solving processes on different proportional problem items were investigated in a way how the problem type of proportion and the degree of ill-structured affect to their levels. Results showed that the greater part of participants solved problems on the level of proportional reasoning and various development levels according to type of problem. In addition, they showed highly the level of transition and proportional reasoning on missing value problems rather than numerical comparison problems.

• Transactions of Materials Processing
• /
• v.27 no.2
• /
• pp.115-122
• /
• 2018

Most domestic and international standards on the forming limit diagram (FLD) including ISO 12004-2, use a 'position-dependent method,' which determines the forming limit from a strain distribution measured on the specimen after necking or fracture. However, the position-dependent method has inherent problems such as the incidence of asymmetry of a strain distribution, the estimation of missing data near fracture, the termination time of test, and the deformation due to the new stress equilibrium after a fracture, which is blamed for causing sometimes a significant lab-to-lab variation. The 'time-dependent method,' which is anticipated to be a new international standard for evaluating the forming limit, is expected to greatly improve these intrinsic disadvantages of the position-dependent method. It is because the time-dependent method makes it possible to identify and accurately determine the forming limit, just before the necking point from the strain data as continuously measured in a short time interval. In this study, we propose a new time-dependent method based on a Gaussian fitting of strain acceleration with the introduction of 'normalized correlation coefficient.' It has been shown in this study that this method can determine the forming limit very stably and gives a higher value, which is in comparison with the results of the previously studied position-dependent and time-dependent methods.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.35 no.4
• /
• pp.248-252
• /
• 2009

Purpose: This retrospective study was performed to analyze the relationship between complications of the posterior mandibular single crowns and distance from the adjacent teeth to the implant. Subjects and Methods: Of the patients who presented Ewha Womans University Mokdong Hospital & Yonsei University Dental Hospital with missing of the posterior mandibular molar and restored with implant-supported 18 Single crowns between 1996 thru 2007, 115 patients had been followed after crown delivery. The subjects were divided into complication-followed group and a control without any problems. The distance from the most distal tooth to the implant were measured. The prosthetic & biologic complications were reviewed by the cantilever distance and analyzed by abutment type, age & gender statistically using SAS version 9.1 (SAS Inc., USA). Results and Conclusion The results were as follows; 1) The posterior mandibular single crown with cantilever showed higher incidence of follow-up complications upon logistic analysis (p<0.05). 2) The prosthetic and biologic complications are related with the cantilever distance with 2.1 odds ratio and 3.39 cut-off value of specificity & sensitivity by SPSS 12.0. 3) The complications are neither significant in abutment types nor age & gender.