• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.5
• /
• pp.2082-2102
• /
• 2018

In recent years, social network related applications such as WeChat, Facebook, Twitter and so on, have attracted hundreds of millions of people to share their experience, plan or organize, and attend social events with friends. In these operations, plenty of valuable information is accumulated, which makes an innovative approach to explore users' preference and overcome challenges in traditional recommender systems. Based on the study of the existing social network recommendation methods, we find there is an abundant information that can be incorporated into probability matrix factorization (PMF) model to handle challenges such as data sparsity in many recommender systems. Therefore, the research put forward a unified social network recommendation framework that combine tags, trust between users, ratings with PMF. The uniformed method is based on three existing recommendation models (SoRecUser, SoRecItem and SoRec), and the complexity analysis indicates that our approach has good effectiveness and can be applied to large-scale datasets. Furthermore, experimental results on publicly available Last.fm dataset show that our method outperforms the existing state-of-art social network recommendation approaches, measured by MAE and MRSE in different data sparse conditions.

• The Korean Journal of Applied Statistics
• /
• v.21 no.1
• /
• pp.95-107
• /
• 2008

Survey on the rural living indicators was the statistic approved from National Statistical Office and the survey executed by rural resources development institute. This study was used the raw data of survey on the rural living indicators in 2005. After editing procedure for raw data, we were studied 1,582 households which is acquired through elimination of case included nonresponses, and imputed a nonresponses of 15 item selected from 146 item. The imputation methods and efficiency of imputation for simulation was adapted differently from type of data. For continuous data, we imputed the nonresponses with mean imputation, regression imputation, adjusted grey-based k-NN imputation(DU, DW, WU, WW) and compared the results with RMSE. For categorical data, we imputed the nonresponses with mode method, probability imputation, conditional mode method, conditional probability method, hot-deck imputation, and compared the results with Accuracy. By the results, regression imputation and adjusted grey-based k-NN imputation appropriated for continuous data and hot-deck imputation appropriated for categorical data.

• The Journal of Korean Association of Computer Education
• /
• v.23 no.1
• /
• pp.29-36
• /
• 2020

Various items were used as evaluation tools that identify the student's abilities accurately to confirm the completion of learning. Among them, the multiple choice item has the advantages of high objectivity and reliability in scoring, but it cannot remove the factor of guessing. In this paper, the multiple choice items are classified into two types according to the relationship between the questionnaire and the choices. One is the type used in the classical test theory with the probability of guessing 1/k for k choices and the other is the novel proposed type which introduces the concept of partial knowledge. In the proposed type, the probability of guessing when the number of knowledge i is (i+1)/k for k choices. Based on the assumptions of the previous theories about multiple choice items, we derive the guessing parameter about the proposed type. And we analyzed the effect of the guess on the correct answer in the existing type and the proposed type. This shows that the proposed type has more question guessing than the existing type.

• Journal of KIISE:Databases
• /
• v.36 no.1
• /
• pp.30-43
• /
• 2009

Broadcast in the wireless environment has drawn much attention because it is capable of sending data to clients regardless of the number of clients. Most previous researches have aimed at obtaining an independent data item in a minimum time. But, they have not been researched on simultaneously receiving dependent data items in a query. In addition, these papers have only researched allocation problem that have not been came out data items in a query in same time and different channels. The access probability of each data item based on query request probability have not been reflected. This paper proposes a new method of allocating data items and simultaneously minimizing average response time required in receiving all the dependent data items in a query. Our performance analysis shows that our proposed method gives better average response time over the existing methods.

• Journal of Science Education
• /
• v.47 no.2
• /
• pp.211-224
• /
• 2023

The purpose of this study is to suggest how to investigate the reliability of the assessment, which consists of items generated by automatic item generation using empirical example data. To achieve this, we analyzed the illustrative assessment data by applying the multivariate generalizability theory, which can reflect the design of responding to different items for each student and multiple error sources in the assessment score. The result of the G-study showed that, in most designs, the student effect corresponding to the true score of the classical test theory was relatively large after residual effects. In addition, in the design where the content domain was fixed, the ranking of students did not change depending on the item types or items. Similarly, in the design where the item format was fixed, the difficulty showed little variation depending on the content domains. The result of the D-study indicated that the original assessment data achieved a sufficient level of reliability. It was also found that higher reliability than the original assessment data could be obtained by reducing the number of items in the content domains of operation, geometry, and probability and statistics, or by assigning higher weights to the domains of letters and formulas, and function. The efficient measurement conditions presented in this study are limited to the illustrative assessment data. However, the method applied in this study can be utilized to determine the reliability and to find efficient measurement conditions for the various assessment situations using automatic item generation based on measurement traits.

• Journal of Educational Research in Mathematics
• /
• v.19 no.1
• /
• pp.99-121
• /
• 2009

This study analyzed the difficulty trend of item which are common with TIMSS 1999, 2003, 2007 and are released since TIMSS 2007. The results show that the 7th curriculum has positive effects on the students' achievement in the domain such as spatial sense of rotation, ratio proportion percent, pattern, calculation of decimal numbers, concept of angle, area of triangle, and qualitative approach to graph. And the results leaved the consideration for the process of scoring, teaching method of statistical probability concept, and making table as a problem solving method.

• Journal of Gifted/Talented Education
• /
• v.25 no.6
• /
• pp.817-836
• /
• 2015

This research focuses on the development of gifted child behavior checklist which feasibly has application on the nation-wide gifted children observation-recommendation method. Corresponding measure has significance as it reflects actual observations of teachers teaching gifted children first-hand and involves measure of importance regarding each characteristic. An open survey on gifted children behavior characteristics lists and specific behavior patterns has been acquired from teachers in gifted education, and the checklist was developed through expert group review, pre-test, and confirmatory factor analysis process. The former checklists have shown several difficulties on application of observation-recommendation on the field due to behaviors that can't be observed in school, less important behaviors, and collide and duplicate behaviors etc. With regard to such problems, problematic clauses were removed based on the observation probability and importance of the behaviors. Ultimately, total of 32 behavior characteristic checklist consisting of ten sub factors(logical thinking, high achievement, originality, perfectionism, creative problem solving, curiosity, task commitment, conversation ability, creativity, passion) and two to three questions on each factor had been drawn. Through internal consistency test and item-total score correlation, each item of the measure has been analyzed to be consistently evaluating corresponding variables. In addition, the result of confirmatory factor analysis showed every item to be weighed appropriately on its sub-factor, strongly suggesting its feasibility on observation-recommendation of elementary gifted children as an appropriate checklist.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.30 no.2
• /
• pp.39-49
• /
• 2002

The purpose of this study is to propose an objective and rational methodology for the selection of proposed sites far the National Trust(NT), which is the new alterative proposal far the conservation of natural environments destroyed by injudicious land development and economic growth. That is to enforce many analysis for the effective estimation of rare ecological and landscape resources and to propose a model based on estimation and united indicators. Using the estimative model, we apply it to the selection of the proposed site in micro scale and simultaneously offer the basic methodology of effective and systematic land conservation in macro scale. The results of this study are as follows: 1) The results of analysis for the reliability of estimative items and indicators, presented no problem in that the coefficient of reliability was over 0.7. 2) The correlation measure of the estimative indicator indicated that 'succession'and 'regenerating restorability' were highly correlative in the item of plants. Another three items showed a tendency to be alike. 3) The results of factor analysis on the characteristics of indicators, classified plants into four categories including a stable factor. The item of animals was classified as a stable and rare factor. The item of landscape was classified as a physical and mental factor and the environment as a pollutional and conditional factor. 4) The model of estimation created through factor analysis was valid for the approval of the regression model because significant probability was 0.00. When we consider the NT proposed site as a complex body that is composed of diverse natural and manmade resources, certainly the synthetic methodology of estimation is needed. If these studies are carried out, NT sites will be selected more rationally and effectively than at present. Consequently, they have the potential to play a core role of natural ecosystem conservation in Korea.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.20 no.1
• /
• pp.113-127
• /
• 1996

In this study, the pattern was copied by the method of Tight Fitting Techinque, which resulted from the changed body by the upper limb motion-front-vertical motion(or vertical motion in front), side-vertical motion, and horizontal motion. And, this study analyzed the change of the pattern and the observed items dimension changed to the pattern. The results are as follows: 1. In the observation of the degree of the pattern change according to the motion of upper limb, the result provides that the motion change in the range of $135^{\circ}$ to $180^{\circ}$ is the largest in front-vertical motion, $45^{circ}~90^{\circ}$ in side-vertical motion, and $0^{circ}~45^{\circ}$ in horizontal motion respectively. 2. The probability test result of the items of the motion is more related with the horizontal width item rather than the vertical length item in the front and back pattern where the back pattern has more effect than the front pattern. And the upper limb-surrounding items are more related than any otheer item. 3. The change of the pattern according to the motion shows the decrese of the neck width and the shoulder legth, the rising of the point of shoulder (or shoulder point) and armpit point, the decrease of the pattern width and the increase of the pattern length. As the angle of the motion grows vertically motion. The change of the shoulder length in the horizontal motion is smaller than that vertical. But as the angle of the motion grows horizontally, it has a tendency of decreas in th width of the front patten and the length of the pattern, whereas the width of the back pattern is noticeably increases.

• Journal of Digital Contents Society
• /
• v.5 no.1
• /
• pp.7-11
• /
• 2004

There are many problems that must solve to construct next generation high-speed communication network. Among these, item that must consider basically is characteristics analysis of traffic that nows to network Traffic characteristics of many Internet services that is offered present have shown that network traffic exhibits at a wide range of scals-self-similarity. Self-similarity is expressed by long term dependency, this is contradictory concept with Poisson model that have relativity short term dependency. Therefore, first of all, for design and dimensioning of next generation communication network, traffic model that are reflected burstiness and self-similarity is required. Here self-similarity can be characterized by Hurst parameter. In this paper, the calculation equation is derived considering queueing delay and self-similarity of data traffic art compared with simulation results.