• The Journal of the Korea Contents Association
• /
• v.15 no.7
• /
• pp.655-663
• /
• 2015

The purpose of this study is to inquiry 'instructive fairy tale story making' teaching model developed in Russia to cultivate creativity and character and to present implementation idea in Korea. Fairy tale story is one of first tasks to spread his and her creativity and latent ability, and good genre to identify and express his and her feeling and to accomplish through these experience for children. In process of this teaching model, they are able to recognize and compare good literary works, to know 'instructive fairy tale story making' algorithm and to do 'instructive fairy tale story making' personally. As a result, students' imagination, creativity and linguistic performance would be developed more through 'instructive fairy tale story making', at the same time they will examine closely and apply moral and ethical contents in daily life and internalize.

• Journal of the Korean Society for information Management
• /
• v.22 no.4 s.58
• /
• pp.173-195
• /
• 2005

The purpose of this study is to clarify whether readability formulas based on linguistic factors are suitable for secondary and older primary age texts. A comparison among fomulas for primary age texts, some for both primary and secondary age, and some for secondary age revealed that exclusive ones for narrow age range were more effective. A model estimating readability scores from the average number of sentences in paragraphs or a model with two factors, the average number of sentences and paragraphs in texts was found to be good one for secondary age. While a model based on total number of unique syllables or a model from total number of unique syllables and new syllable occurrence ratio was good for primary age.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.5
• /
• pp.489-494
• /
• 2015

The purpose of this paper is to analyse outcomes of Korean Pro-basketball games using regression models. Both Classic Fuzzy Regression Model and Fuzzy Regression Model applying linguistic variables were used to meet the purpose of the paper. In General Regression Analysis, in which the results of games are expressed and analyzed through score differences, a regression model is proposed considering influential variables for the score differences of the two teams. In Fuzzy Regression Analysis, the results are sorted into six different literal expressions, 'win with large margin, win with moderate margin, win with narrow margin, defeat with narrow margin, defeat with moderate margin, and defeat with large margin'. Athletic performances and team work of each teams were expressed in fuzzy number to analyse how much athletic performances and team work affect results of games. This paper referred back to 2013-2014 season data provided by KBL(Korean Basketball League) and professional columns on Korean basketball analysis.

• Journal of the Korea Convergence Society
• /
• v.13 no.2
• /
• pp.21-29
• /
• 2022

Based on the importance of dialect research, preservation, and communication, this paper conducted a study on machine translation of Korean dialects for dialect users who may be marginalized. For the dialect data used, AIHUB dialect data distributed based on the highest administrative district was used. We propose a many-to-one dialect machine translation that promotes the efficiency of model distribution and modeling research to improve the performance of the dialect machine translation by applying Copy mechanism. This paper evaluates the performance of the one-to-one model and the many-to-one model as a BLEU score, and analyzes the performance of the many-to-one model in the Korean dialect from a linguistic perspective. The performance improvement of the one-to-one machine translation by applying the methodology proposed in this paper and the significant high performance of the many-to-one machine translation were derived.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.165-184
• /
• 2023

Recently, Deep learning analysis of unstructured text data using language models, such as Google's BERT and OpenAI's GPT has shown remarkable results in various applications. Most language models are used to learn generalized linguistic information from pre-training data and then update their weights for downstream tasks through a fine-tuning process. However, some concerns have been raised that privacy may be violated in the process of using these language models, i.e., data privacy may be violated when data owner provides large amounts of data to the model owner to perform fine-tuning of the language model. Conversely, when the model owner discloses the entire model to the data owner, the structure and weights of the model are disclosed, which may violate the privacy of the model. The concept of offsite tuning has been recently proposed to perform fine-tuning of language models while protecting privacy in such situations. But the study has a limitation that it does not provide a concrete way to apply the proposed methodology to text classification models. In this study, we propose a concrete method to apply offsite tuning with an additional classifier to protect the privacy of the model and data when performing multi-classification fine-tuning on Korean documents. To evaluate the performance of the proposed methodology, we conducted experiments on about 200,000 Korean documents from five major fields, ICT, electrical, electronic, mechanical, and medical, provided by AIHub, and found that the proposed plug-in model outperforms the zero-shot model and the offsite model in terms of classification accuracy.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.39 no.2
• /
• pp.138-149
• /
• 2016

Quality function deployment (QFD) is a widely adopted customer-oriented product development methodology by translating customer requirements (CRs) into technical attributes (TAs), and subsequently into parts characteristics, process plans, and manufacturing operations. A main activity in QFD planning process is the determination of the target levels of TAs of a product so as to achieve a high level of customer satisfaction using the data or information included in the houses of quality (HoQ). Gathering the information or data for a HoQ may involve various inputs in the form of linguistic data which are inherently vague, or human perception, judgement and evaluation for the information and data. This research focuses on how to deal with this kind of impreciseness in QFD optimization. In this paper, it is assumed as more realistic situation that the values of TAs are taken as discrete, which means each TA has a few alternatives, as well as the customer satisfaction level acquired by each alternative of TAs and related cost are determined based on subjective or imprecise information and/or data. To handle these imprecise information and/or data, an approach using some basic definitions of fuzzy sets and the signed distance method for ranking fuzzy numbers is proposed. An example of a washing machine under two-segment market is provided for illustrating the proposed approach, and in this example, the difference between the optimal solution from the fuzzy model and that from the crisp model is compared as well as the advantage of using the fuzzy model is drawn.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.1
• /
• pp.37-43
• /
• 2016

Recently, it is emphasized importance of family. The new family organize including husband and wife are created by caused marriage, they organize new family including wife's home and husband's home. As a result, they may experience about conflict or peace between new family and previous family. The research of family mainly have been studied in the social science side. However, because researchers of social science deals with linguistic emotion status, there is no mathematical modeling for family relationship. In this paper, one of the nonlinear research for social subject, we modify love model of Romeo and Juliet. Then we propose novel family relationship model for parent-in-law and daughter (or son)-in- law relation. We also confirm chaotic behavior or nonlinear behavior by time series and phase portrait.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.7
• /
• pp.71-80
• /
• 1999

Sign-language communication can be a useful way of exchanging message between people who using different languages. In this paper, we report an experimental survey on the construction of a Korean-Japanese sign-language communication system using 3D model. For real-time communication, we introduced an intelligent communication method and built the system as a client-server architecture on the Internet. A character model is stored previously in the clients and a series of animation parameters are sent instead of real image data. The input-sentence is converted into a series of parameters of Korean sign language or Japanese sign language at server. The parameters are transmitted to clients and used for generating the animation. We also employ the emotional expressions, variable frames allocation method, and a cubic spline interpolation for the purpose of enhancing the reality of animation. The proposed system is implemented with Visual $C^{++}$ and Open Inventor library on Windows platform. Experimental results show a possibility that the system could be used as a non-verbal communication means beyond the linguistic barrier.

• Journal of Broadcast Engineering
• /
• v.24 no.1
• /
• pp.77-86
• /
• 2019

This paper proposes using machine-learning technology to analyze and classify historical collected documents based on them. Data is collected based on keywords associated with a specific domain and the non-conceptuals such as special characters are removed. Then, tag each word of the document collected using a Korean-language morpheme analyzer with its nouns, verbs, and sentences. Embedded documents using Doc2Vec model that converts documents into vectors. Measure the similarity between documents through the embedded model and learn the document classifier using the machine running algorithm. The highest performance support vector machine measured 0.83 of F1-score as a result of comparing the classification model learned.

• Journal of Broadcast Engineering
• /
• v.24 no.1
• /
• pp.58-66
• /
• 2019

Recognition of named entity such as proper nouns in conversation sentences is the most fundamental and important field of study for efficient conversational information prediction. The most important part of a task-oriented dialogue system is to recognize what attributes an object in a conversation has. The named entity recognition model carries out recognition of the named entity through the preprocessing, word embedding, and prediction steps for the dialogue sentence. This study aims at using user - defined dictionary in preprocessing stage and finding optimal parameters at word embedding stage for efficient dialogue information prediction. In order to test the designed object name recognition model, we selected the field of daily chemical products and constructed the named entity recognition model that can be applied in the task-oriented dialogue system in the related domain.