• The Journal of the Korea Contents Association
• /
• v.20 no.6
• /
• pp.695-704
• /
• 2020

Recently, There has been an increasing of utilization IT, and studies have been conducted on predicting learning results. In this study, Learning activity data were collected that could affect learning outcomes by using learning analysis. The survey was conducted at a university in South Chung-Cheong Province from October to December 2018, with 1,062 students taking part in the survey. First, A Hierarchical regression analysis was conducted by organizing a model of individual, academic, and behavioral factors for learning results to ensure the validity of predictors in machine learning. The model of hierarchical regression was significant, and the explanatory power (R²) was shown to increase step by step, so the variables injected were appropriate. In addition, The linear regression analysis method of machine learning was used to determine how predictable learning outcomes are, and its error rate was collected at about 8.4%.

• Journal of Korea Multimedia Society
• /
• v.11 no.3
• /
• pp.353-363
• /
• 2008

A multi-agent system has a longer learning period and larger state-spaces than a sin91e agent system. In this paper, we suggest a new method to reduce the learning time of Nash Q-learning in a multi-agent environment. We apply Macro-actions to Nash Q-learning to improve the teaming speed. In the Nash Q-teaming scheme, when agents select actions, rewards are accumulated like Macro-actions. In the experiments, we compare Nash Q-learning using Macro-actions with general Nash Q-learning. First, we observed how many times the agents achieve their goals. The results of this experiment show that agents using Nash Q-learning and 4 Macro-actions have 9.46% better performance than Nash Q-learning using only 4 primitive actions. Second, when agents use Macro-actions, Q-values are accumulated 2.6 times more. Finally, agents using Macro-actions select less actions about 44%. As a result, agents select fewer actions and Macro-actions improve the Q-value's update. It the agents' learning speeds improve.

• Journal of Korea Multimedia Society
• /
• v.17 no.2
• /
• pp.232-239
• /
• 2014

As online texts have been rapidly growing, their automatic classification gains more interest with machine learning methods. Nevertheless, comparatively few research could be found, aiming for Korean texts. Evaluating them with statistical methods are also rare. This study took a sample of tweets and used machine learning methods to classify emotions with features of morphemes and n-grams. As a result, about 76% of emotions contained in tweets was correctly classified. Of the two methods compared in this study, Support Vector Machines were found more accurate than Na$\ddot{i}$ve Bayes. The linear model of SVM was not inferior to the non-linear one. Morphological features did not contribute to accuracy more than did the n-grams.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.8
• /
• pp.39-47
• /
• 2011

Ergezinger's method, one of the layer-by-layer algorithms used for multilyer perceptrons, consists of an output node and can make premature saturations in the output's weight because of using linear least squared method in the output layer. These saturations are obstacles to learning time and covergence. Therefore, this paper expands Ergezinger's method to be able to use an output vector instead of an output node and introduces a learning rate to improve learning time and convergence. The learning rate is a variable rate that reflects the correlation coefficient between new weight and previous weight while updating hidden's weight. To compare the proposed method with Ergezinger's method, we tested iris recognition and nonlinear approximation. It was found that the proposed method showed better results than Ergezinger's method in learning convergence. In the CPU time considering correlation coefficient computation, the proposed method saved about 35% time than the previous method.

• Journal of The Korean Association of Information Education
• /
• v.16 no.4
• /
• pp.489-502
• /
• 2012

Today computer education puts an emphasis on algorithm education. There are little researches about how to express the given problem in algorithm and how to interpret the expressed algorithm. In this study play-based learning methods dealing with flow chart which is one of the expressing tools of algorithm are developed for lower graders of elementary school. Then we diagnosed the learning possibility of the tool after applying the methods in a classroom environment. There are four types of learning game activities; sequential play, selective play, repetitive play and puzzle play. Puzzle play is a game that students need to reconstruct the learned content to a real flow chart by using flow chart cards. The result of an achievement test after teaching students flow chart showed that the group who took the play-based lesson got their average score with about 7.5% higher than the group who took the ICT-based lesson. Both the groups got their average scroe of more than 9 out of 10 after the lesson. This result shows that flow chart lessons are adaptable for the lower graders of elementary school. It also shows that play-based education can be exceptionally effective.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.8
• /
• pp.66-74
• /
• 2014

Recently a variety of study of Korean parsing system is carried out by many software engineers and linguists. The parsing system mainly uses the method of machine learning or symbol processing paradigm. But the parsing system using machine learning has long training time because the data of Korean sentence is very big. And the system shows the limited recognition rate because the data has self error. In this thesis we design system using feature module which can reduce training time and analyze the recognized rate each the number of training sentences and repetition times. The designed system uses the separated modules and sorted table for binary search. We use the refined 36,090 sentences which is extracted by Sejong Corpus. The training time is decreased about three hours and the comparison of recognized rate is the highest as 84.54% when 10,000 sentences is trained 50 times. When all training sentence(32,481) is trained 10 times, the recognition rate is 82.99%. As a result it is more efficient that the system is used the refined data and is repeated the training until it became the steady state.

• The Journal of Korean Association of Computer Education
• /
• v.7 no.6
• /
• pp.117-128
• /
• 2004

Compared with traditional face-to-face instruction, online learning causes learners to experience more severe feeling of isolation and results in higher dropout rate. This is due to the lack of interaction, sense of belonging, membership, interdependency, cooperation among members and social environment that enables persistence in online learning. Therefore, it is very important for grouping e-learning community to lower the dropout rate and eliminate feeling of isolation. In this paper, the research has been done on the inclination test list to be applied for grouping the desirable learning community. And on the basis of this research, the grouping system for e-learning community(GSE) based on intelligent multi agents for an inclination test using homogeneous and heterogeneous items has been developed. GSE system has such properties that construct a personalized user profile by an agent, and then make groupings according to users' inclination. When this system was evaluated, about 88% of learners were satisfied, and they wanted the group not to be disorganized but to be maintained.

• The Journal of Korean Association of Computer Education
• /
• v.7 no.4
• /
• pp.121-129
• /
• 2004

If we followed to be based on the result of survey for researching on the actual condition about e-Learning of the MOE(2004), the critical problem has been suggested managing the quality of teaching and learning materials(37.68%(1775/4717)). If we also reviewed the research of the KICE(2002), the superior material's rate of 70,000 teaching and learning materials of the web site, the educational organization, and teachers was 8.7%. There was some suggestions about the quality problem of the teaching and learning material, but there wasn't the alternative policy: there wasn't the systemic program for managing the message quality of teaching and learning materials. The purpose of this study was to develop the alternative system for managing the message quality of teaching and learning materials. The alternative system of this study's result will be the basic to build the system for managing the message quality of teaching and learning materials. I expect that my system will be the useful tool for managing the message quality of teaching and learning materials.

• Journal of the Korea Convergence Society
• /
• v.11 no.10
• /
• pp.45-51
• /
• 2020

Recently, many games provide data related to the users' game play, and there have been a few studies that predict opponent move by combining machine learning methods. This study predicts opponent move using match data of a real-time strategy game named ClashRoyale and a multi-label classification based on machine learning. In the initial experiment, binary card properties, binary card coordinates, and normalized time information are input, and card type and card coordinates are predicted using random forest and multi-layer perceptron. Subsequently, experiments were conducted sequentially using the next three data preprocessing methods. First, some property information of the input data were transformed. Next, input data were converted to nested form considering the consecutive card input system. Finally, input data were predicted by dividing into the early and the latter according to the normalized time information. As a result, the best preprocessing step was shown about 2.6% improvement in card type and about 1.8% improvement in card coordinates when nested data divided into the early.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.12
• /
• pp.197-204
• /
• 2011

In this paper, There is a study of a smartphone-based App for e-learning when the process control of manufacturing. First, That is obtained the control limit lines after inputted by the measured data and able to look up the assignable causes and then can display those causes. A User of this App can access the record about assignable causes using the record menu and can use with an e-Learning tool. Because that were provided in the form of a control process theory and bulletin announcements. Helped to exchange information. In addition, the user's guide how to use this App. The result of this process control is provided by charts. The alarm message to the alertsymbol, depending on the level of color clearly was designed to UI which displays the results. After the questionnaire responses with respect to satisfaction of Utilization and satisfaction of the learning experience. The Utilization' satisfaction results Appeared that 82% of the participants were satisfied. And The learning's satisfaction results Appeared that 90% of the participants were satisfied.