• Journal of Information Processing Systems
• /
• v.16 no.5
• /
• pp.1074-1082
• /
• 2020

Recently, research has been actively conducted to create artificial intelligence agents that learn games through reinforcement learning. There are several factors that determine performance when the agent learns a game, but using any of the activation functions is also an important factor. This paper compares and evaluates which activation function gets the best results if the agent learns the game through reinforcement learning in the 2D racing game environment. We built the agent using a reinforcement learning algorithm and a neural network. We evaluated the activation functions in the network by switching them together. We measured the reward, the output of the advantage function, and the output of the loss function while training and testing. As a result of performance evaluation, we found out the best activation function for the agent to learn the game. The difference between the best and the worst was 35.4%.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.14 no.1
• /
• pp.1-14
• /
• 2018

The purpose of this study is to learn the current perception of Total Smart Mirror Display devised with IoT, focused on Hair beauty industry. In detail, this study is to analyze domestic and foreign precedented case studies and conditions of Smart Mirror in beauty industry, and to learn, through survey, the real condition of use of Hair Smart Mirror, which is devised and applied according to the actual state of our country. First, the mean comparison for Total Smart Mirror by gender showed that Function1, Technology 2 and 3 had differences. Second, the mean comparison each by age, external design, function, marketing and technologies showed that Function 4, Marketing 1 to 3, Technology 1 and 3 had differences.

• Journal of Educational Research in Mathematics
• /
• v.9 no.1
• /
• pp.121-132
• /
• 1999

We have compared Korean and American mathematics curriculums in 5 areas: whole number(concepts and its operations); geometry; pattern and relations; measurements; statistics and probability. We have found significant differences in geometry area. Korean curriculums contain simple planar figures (circles, triangles, rectangles, and squres) and some of the spatial figures until 3rd grades. But in America they learn various planar and spatial fugures(cone, pyramid, triangular prism, etc) since the 1st grade starts. They also start the 1st grade by dealing with topological concepts like open/closed, inside/outside, order, etc. As the grade goes on, students learn other geometrical concepts like congruence, symmetry, 3-dimensional views. We also found that American curriculum focuses on students' activities and courages communication through projects, groupwork, journal writing, etc. It's also superior in respects of motivation, and connections with real life and other subjects. Korean curriculum needs more improvements in these aspects. Furthermore for lower graders reviewing sections need to be enhanced for feedback.

• Journal of the Semiconductor & Display Technology
• /
• v.7 no.4
• /
• pp.13-18
• /
• 2008

This paper explores a content-based image retrieval framework with relevance feedback based on genetic algorithm (GA). This framework adopts GA to learn the user preferences using the similarity functions defined for all available descriptors. The objective of the GA-based learning methods is to learn the user preferences using the similarity functions and to find a descriptor combination function that best represents the user perception. Experiments were performed to validate the proposed frameworks. The experiments employed the natural image databases and color and texture descriptors to represent the content of database images. The proposed frameworks were compared with the other two relevance feedback methods regarding effectiveness in image retrieval tasks. Experiment results demonstrate the superiority of the proposed method.

• Journal of information and communication convergence engineering
• /
• v.11 no.4
• /
• pp.258-267
• /
• 2013

New incremental learning algorithm using extended data expression, based on probabilistic compounding, is presented in this paper. Incremental learning algorithm generates an ensemble of weak classifiers and compounds these classifiers to a strong classifier, using a weighted majority voting, to improve classification performance. We introduce new probabilistic weighted majority voting founded on extended data expression. In this case class distribution of the output is used to compound classifiers. UChoo, a decision tree classifier for extended data expression, is used as a base classifier, as it allows obtaining extended output expression that defines class distribution of the output. Extended data expression and UChoo classifier are powerful techniques in classification and rule refinement problem. In this paper extended data expression is applied to obtain probabilistic results with probabilistic majority voting. To show performance advantages, new algorithm is compared with Learn++, an incremental ensemble-based algorithm.

• Journal of Institute of Control, Robotics and Systems
• /
• v.9 no.7
• /
• pp.527-535
• /
• 2003

A behavior-based control and learning architecture is proposed, where reinforcement learning is applied to learn proper associations between stimulus and response by using two types of memory called as short Term Memory and Long Term Memory. In particular, to solve delayed-reward problem, a knowledge-propagation (KP) method is proposed, where well-designed or well-trained S-R(stimulus-response) associations for low-level sensors are utilized to learn new S-R associations for high-level sensors, in case that those S-R associations require the same objective such as obstacle avoidance. To show the validity of our proposed KP method, comparative experiments are performed for the cases that (ⅰ) only a delayed reward is used, (ⅱ) some of S-R pairs are preprogrammed, (ⅲ) immediate reward is possible, and (ⅳ) the proposed KP method is applied.

• International Journal of Advanced Culture Technology
• /
• v.8 no.2
• /
• pp.209-215
• /
• 2020

Russia has an interesting history as a donor, recipient and re-emerging donor in international development assistance (IDA). This article introduces the history, policy and challenges of Russian IDA, and provides suggestions for such challenges. The main barrier to Russian IDA is the absence of a central government agency and Russia can learn from other country's experience. Concerning lack of data on the provision of assistance to each sector of IDA and the large number of recipient countries, Russia can learn from Korea particularly in education sector. With respect to building a system ensuring the efficiency of the Russian IDA works, a tool for analysis of the effect of the Russian IDA programmes may be drawn in consultation with international institutions or successful programmes of other donor countries.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.87-90
• /
• 2002

This paper analyzes statistically the relationship between size and balance of text corpus by evaluation of the effect of interview sentences in language model for Korean broadcast news transcription system. Our Korean broadcast news transcription system's ultimate purpose is to recognize not interview speech, but the anchor's and reporter's speech in broadcast news show. But the gathered text corpus for constructing language model consists of interview sentences a portion of the whole, $15\%$ approximately. The characteristic of interview sentence is different from the anchor's and the reporter's in one thing or another. Therefore it disturbs the anchor and reporter oriented language modeling. In this paper, we evaluate the effect of interview sentences in language model for Korean broadcast news transcription system and analyze statistically the relationship between size and balance of text corpus by making an experiment as the same procedure according to varying the size of corpus.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 2003.11a
• /
• pp.721-727
• /
• 2003

This study designed and implemented a system to extract of vowel from a word. The system is comprised of a voice feature extraction module and a neutral network module. The voice feature extraction module use a LPC(Linear Prediction Coefficient) model to extract a voice feature from a word. The neutral network module is comprised of a learning module and voice recognition module. The learning module sets up a learning pattern and builds up a neutral network to learn. Using the information of a learned neutral network, a voice recognition module extracts a vowel from a word. A neutral network was made to learn selected vowels(a, eo, o, e, i) to test the performance of a implemented vowel extraction recognition machine. Through this experiment, could confirm that speech recognition module extract of vowel from 4 words.

• Industrial Engineering and Management Systems
• /
• v.10 no.4
• /
• pp.264-271
• /
• 2011

It is necessary for humans who have been facing environmental problems to build a sustainable society in which economic activities coexist with nature. To realize such goals, it is essential to promote and enhance environmental education, and to raise global awareness of environmental issues. As a preceding study, a board game "Ecopoly" based on the Kyoto protocol and the estate dealings game, was developed and the validity of environmental education was verified. This study further aims to develop a computer game "Ecopoly", based on the board game which enables us to learn the relationship between environmental problems and economic activities, and to learn more about environmental problems. This computer game enables to concentrate on it by automatic complicated calculations, and to get a higher visual effect compared with the board game. Experimental testing of the game was conducted with 13 college student subjects, and the validity of the game was verified.