• Journal of KIISE:Software and Applications
• /
• v.32 no.6
• /
• pp.542-553
• /
• 2005

Recommendation systems analyze user preferences and recommend items to a user by predicting the user's preference for those items. Among various kinds of recommendation methods, collaborative filtering(CF) has been widely used and successfully applied to practical applications. However, collaborative filtering has two inherent problems: data sparseness and the cold-start problems. If there are few known preferences for a user, it is difficult to find many similar users, and therefore the performance of recommendation is degraded. This problem is more serious when a new user is first using the system. In this paper we propose a method of integrating additional feature information of users and items into CF to overcome the difficulties caused by sparseness and improve the accuracy of recommendation. In our method, we first fill in unknown preference values by using the probability distribution of feature values, then generate the top-N recommendations by applying collaborative filtering on the modified data. We call this method of filling unknown preference values as data blurring. Several experimental results that show the effectiveness of the proposed method are also presented.

• Journal of Digital Convergence
• /
• v.12 no.11
• /
• pp.339-348
• /
• 2014

As future society will be strengthened by interdisciplinary study and education, we have to prepare general education curriculum which provide critical thinking, problem-solving, creativity, communication abilities. Those curriculum will help to nurture students who lead our future society. Now we prepare new curriculum to train students to understand the computer science and software needed to create their own, and we could cultivate students having ability to create interdisciplinary study by using programming skill. So we ran a computer programming class during a semester for the freshmen's capacity building on computing-thinking ability using the Python language. We analyzed the effectiveness and showed that student's curiosity and motivation to want to learn computer programming occurred, their various skills for interdisciplinary ability were improved.

• Journal of Industrial Convergence
• /
• v.18 no.1
• /
• pp.35-43
• /
• 2020

This study aimed to evaluate the reliability and validity of the Korean version of Student Evidence-Based Practice Questionnaire (S-EBPQ) which developed by Upton, Scurlock-Evans, and Upton. Data were collected from 209 nursing students with previous experience of education in evidence-based practice and clinical placement. Using SPSS 25.0, construct validity, concurrent validity and reliability were evaluated. The Korean version of S-EBPQ consisted of 21 items in four domains. The measurement explained 67.0% and the reliability using Cronbach's alpha was .927. The Korean version of S-EBPQ can be used to evaluate the ability of evidence-based practice among nursing students. The tool could be also used to examine the effectiveness of educational programs for evidence-based practice which would contribute to improving the quality of nursing education in Korea.

• Journal of Digital Convergence
• /
• v.16 no.10
• /
• pp.453-463
• /
• 2018

This study investigated the effects of an Augmented Reality(AR) implemented book on flow of reading, interest in history, and acquisition of history knowledge. Perceptions of AR infused books were investigated as well. Researchers provided a history book implementing AR and the same book without any AR content respectively to an experiment group(n=15) and a control group(n=15) composed of $3^{rd}$ and $4^{th}$ grade elementary school children. Results indicate that AR implemented reading had a positive effect on the flow of reading and interest in history, but not on acquisition of history knowledge. Also, AR-based contents were attractive to learners due to its amusing characters, sound, realistic visual motions, and vivid three-dimensional effects. Lastly, students preferred amusing interesting characters, lengthier animations and subtitles, and AR that could be seen without holding smart devices for a long while.

• Journal of Korea Game Society
• /
• v.15 no.4
• /
• pp.189-198
• /
• 2015

This paper is about a serious game controlled by EEG and motion capture. We developed our game for 2 users competitive and its method is as follows. One player uses a controlling interface using EEG signals based on the premise that the player's facial movements are a depiction of the player's emotion and intensity throughout the game play. The other player uses a controlling interface using kinect's motion capture technology which captures the player's vertical and lateral movements as well as state of running. The game shows the first player's EEG as a real-time graphic along the map on the game screen. The player will then be able to pace himself based on these visualization graphics of his brain activities. This results in higher concentration for the player throughout the game for a better score in the game. In addition, the second player will be able to improve his physical abilities since the game action is based on real movements from the player.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.6
• /
• pp.876-880
• /
• 2008

Outliers are the observations which are very larger or smaller than most observations in the given data set. These are shown by some sources. The result of the analysis with outliers may be depended on them. In general, we do data analysis after removing outliers. But, in data mining applications such as fraud detection and intrusion detection, outliers are included in training data because they have crucial information. In regression models, simple and multiple regression models need to eliminate outliers from given training data by standadized and studentized residuals to construct good model. In this paper, we use support vector regression(SVR) based on statistical teaming theory to analyze data with outliers in regression. We verify the improved performance of our work by the experiment using synthetic data sets.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.727-730
• /
• 2016

TSC means classifying time series data based on pattern. Time series data is quite common data type and it has high potential in many fields, so data mining and machine learning have paid attention for long time. In traditional approach, distance and dictionary based methods are quite popular. but due to time scale and random noise problems, it has clear limitation. In this paper, we propose a novel approach to deal with these problems with CNN and data mutation. CNN is regarded as proven neural network model in image recognition, and could be applied to time series pattern recognition by extracting pattern. Data mutation is a way to generate mutated data with different methods to make CNN more robust and solid. The proposed method shows better performance than traditional approach.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38C no.2
• /
• pp.213-218
• /
• 2013

One of the most popular approaches to parameter adaptation in hidden Markov model (HMM) based systems is the maximum likelihood linear regression (MLLR) technique. In our previous study, we proposed factored MLLR (FMLLR) where each MLLR parameter is defined as a function of a control vector. We presented a method to train the FMLLR parameters based on a general framework of the expectation-maximization (EM) algorithm. Using the proposed algorithm, supplementary information which cannot be included in the models is effectively reflected in the adaptation process. In this paper, we apply the FMLLR algorithm to a pitch sequence as well as spectrum parameters. In a series of experiments on artificial generation of expressive speech, we evaluate the performance of the FMLLR technique and also compare with other approaches to parameter adaptation in HMM-based speech synthesis.

• Journal of the Korean School Mathematics Society
• /
• v.10 no.4
• /
• pp.471-485
• /
• 2007

In this study, a 27 class hour prescribed program for the fourth grade students is to be developed and applied by extracting the contents associated with basic operations studied prior to the fourth grade level of mixed calculations. After analyzing the results of the research, the following conclusions are obtained. First, the prescribed program for mixed calculations brought about the improvement in the mixed calculation problem solving ability of the students. Second, applying the prescribed program for mixed calculation resulted in an increase in students' interest and concentration on problem solving. In synthesis of the above conclusions, the development and application of the prescribed program for mixed calculation improved the students' concentration on the problem and the students' problem solving ability.

• Journal of the Korean School Mathematics Society
• /
• v.17 no.2
• /
• pp.275-290
• /
• 2014

This study aims to examine how secondary mathematics teachers perceive and how they use constructed-response assessment in their mathematics classrooms. For this purpose, we conducted a survey in Seoul, Inchun, and Gyeonggi-do; 189 teachers participated in the survey. Results from the data analysis suggest as follows: a) the secondary mathematics teachers participated in the survey seem to consider the primary goals of assessment through constructed-response items as evaluating student achievement and the development of students' thinking and creativity; b) the teachers perceive that constructed-response assessment would promote students' mathematical thinking and problem solving skills; c) in general, constructed-response items were included in both performance assessment(less than 20 percent) and paper-and-pencil test(20 to 40 percent); and d) constructed-response items were primarily used as a part of regular examination, rather than as an independent assessment.