• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.12
• /
• pp.485-496
• /
• 2018

So far, the deep learning, a field of artificial intelligence, has achieved remarkable results in solving problems from unstructured data. However, it is difficult to comprehensively judge situations like humans, and did not reach the level of intelligence that deduced their relations and predicted the next situation. Recently, deep neural networks show that artificial intelligence can possess powerful relational reasoning that is core intellectual ability of human being. In this paper, to analyze and observe the performance of Relation Networks (RN) among the neural networks for relational reasoning, two types of RN-based deep neural network models were constructed and compared with the baseline model. One is a visual question answering RN model using Sort-of-CLEVR and the other is a text-based question answering RN model using bAbI task. In order to maximize the performance of the RN-based model, various performance improvement experiments such as hyper parameters tuning have been proposed and performed. The effectiveness of the proposed performance improvement methods has been verified by applying to the visual QA RN model and the text-based QA RN model, and the new domain model using the dialogue-based LL dataset. As a result of the various experiments, it is found that the initial learning rate is a key factor in determining the performance of the model in both types of RN models. We have observed that the optimal initial learning rate setting found by the proposed random search method can improve the performance of the model up to 99.8%.

• Informatization Policy
• /
• v.25 no.4
• /
• pp.3-36
• /
• 2018

This article discusses the possibilities and limitations of ICT education by reviewing the previous research on its various aspects including educational goals, contents, methods, and evaluation. First, when it comes to its educational goal, the prior studies suggest that ICT education aims to nurture digital citizenship among students and to enable them to participate in different sectors of our society. ICT education characterizes the core capacities of its future learners as 'lifelong learners,' 'information producers/consumers,' and 'local/global citizens.' Second, in regard to the educational content of ICT education, researchers investigate SW education importantly: They develop the educational programs and examine the effectiveness of those programs. However, to ensure the relevancy of the educational contents to the future society, institutional support is imperative including facilitating educators' capacities and synchronizing ICT education with subject education. Third, as the educational methods, various ICTs such as flipped learning and augmented reality (AR) are being applied to actual classroom teaching. Research on the educational methods, which is the most vibrant area in the ICT education scholarship, is expected to improve the previous educational methods and to lead the qualitative development of ICT education. Fourth, the previous discussion on the educational evaluation focuses on computer-based evaluations. Educational evaluation using ICT will enable educators to assess the characteristics and achievement of an individual learner accurately and to lead them to apply a teaching-learning process effectively, which will ultimately enhance the effectiveness of educational evaluation. Along with the overall review on the possibilities of ICT education, this article discusses the limitations of the current ICT education and its implications for educational inequalities.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.05a
• /
• pp.665-667
• /
• 2014

Wellness is IT fused with the user manage and maintain the health of a service can help you. If you are using an existing Fitness Center to yourself by choosing appliances that fit with the risk of injury in order to learn how the efficient movement had existed for a long time was needed. To resolve, use the personal training but more expensive cost of people's problems, and shown again in the habit of exercising alone will have difficulty. This paper provides a variety of smart phones based on a hybrid app with compatibility with the platform and personalized training market system. Users of the Fitness Center is built into smart phones in the history of their movement sensors or transmits to the Web by typing directly. This is based on exercise programs tailored to users via the training market. Personal training marketplace has a variety of users, check the history of this movement he can recommend an exercise program for themselves can be applied by selecting the. This provides users with the right exercise program can do long-term exercise habits can be proactive and goal setting.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.981-984
• /
• 2014

Volumetric measurement of hippocampus using IBASPM, the 20's normal adults 10 people's brain images were acquired in order to assess the changes according to the type of the Atlas. Images was obtained using MPRAGE of a 3-D gradient echo pulse sequence on Head matrix coil of 1.5T MRI system. The results of Paired t-test using obtained volume of hippocampus depending on the type of the Atlas, Atlas69-Altas84, Atlas69-Atlas116(p=0.729, 0.729) in the left hippocampus and Atlas69-Atlas84, Atlas69-Atlas116(p=0.219, 0.219) in right hippocampal formation were no significant differences but in the area except this, there was significant difference(p=0.000). The volume of the hippocampus using Atlas84 and Atlas116, represented the same value and there was no significant difference. In the image analysis using the overlay of atlas image and original image, Atlas71 could be found that the area of hippocampus did mismatch. In the case of atlas used in this study, because it has been developed by the westerners, there are differences between brain of asian. It would be needed to development of new Atlas for high accuracy measurement of the volume of hippocampus.

• Journal of the Economic Geographical Society of Korea
• /
• v.22 no.2
• /
• pp.214-235
• /
• 2019

This study adopts the concept of social innovation cluster in which social economy organizations as one of the emerging axes of economic systems operate in collaboration with government agencies, investment institutions, intermediate supporting organizations and non-profit organizations, and investigates how the clusters of this kind grow in the context of the Korean socio-economic situation for the cases of Seongdong-gu and Eunpyeong-gu in Seoul, Korea. For this purpose, it has identified the actors of the clusters and their internal relations, and analyzed the process of cluster formation. A social network analysis of the partnerships between the actors has shown that Seongdong-gu has more diversified types of the network participation of universities, global networks and investment institutions than Eunpyeong-gu. It is interpreted that this pattern has resulted from the domination of private organizations in the former area, which is also confirmed by in-depth interviews with persons involved in the clusters. Although the facets of social innovation clusters are manifested in both areas, even in their initial stage, such factors as linkages between industrial actors and convergence with other clusters, which appear in the maturing stage of cluster formation, has yet to be found. It is suggested that the sustainable growth of social innovation clusters should be accompanied by information sharing and cooperation between the two areas on the future orientation of development.

• Journal of Broadcast Engineering
• /
• v.24 no.1
• /
• pp.48-57
• /
• 2019

The purpose of this study is to understand the intention of the inquirer from the single text type question in Goal-oriented dialogue. Goal-Oriented Dialogue system means a dialogue system that satisfies the user's specific needs via text or voice. The intention analysis process is a step of analysing the user's intention of inquiry prior to the answer generation, and has a great influence on the performance of the entire Goal-Oriented Dialogue system. The proposed model was used for a daily chemical products domain and Korean text data related to the domain was used. The analysis is divided into a speech-act which means independent on a specific field concept-sequence and which means depend on a specific field. We propose a classification method using the word embedding model and the CNN as a method for analyzing speech-act and concept-sequence. The semantic information of the word is abstracted through the word embedding model, and concept-sequence and speech-act classification are performed through the CNN based on the semantic information of the abstract word.

• Journal of The Korean Association of Information Education
• /
• v.25 no.5
• /
• pp.847-857
• /
• 2021

Recently, domestic schools are increasingly interested in environmental education related to COVID-19 and the severe climate crisis, as well as artificial intelligence education related to the 4th industrial revolution that is rapidly approaching us. In particular, AI education is highly likely to be applied to 5th to 6th graders of elementary school, so measures related to connection with 1st to 4th graders are needed. There are many students who are not proficient in computers in the lower grades of elementary school, so there may be many restrictions in using the currently used teaching aids. Therefore, this study tried to develop an artificial intelligence education program for the lower grades of elementary school to secure the linkage of artificial intelligence education. The theme of the program was developed based on the topic of environmental education, which has recently increased in interest. As for the educational method, considering the developmental stage of the lower grades of elementary school, the STEAM education method was used, which was fused with various subjects and unplugged using play and games without a computer. of the program. For validity verification, Lawshe (1975)'s content validity ratio (CVR) calculation formula was used. The verification results were analyzed to be suitable for the purpose of development of all programs. In the future, it is necessary to measure the degree of effectiveness by applying the program proposed in this study to the lower grades of elementary school.

• Agribusiness and Information Management
• /
• v.13 no.1
• /
• pp.26-40
• /
• 2021

During the pandemic status of COVID-19 since 2019 December, demands and attention on various convergence services with non-contact technologies and social adoption are increasing. Along with these increased demands and attention, the digital divide issues should be concerned to understand the informatization degrees of rural area residences, the elderly, the disabled, and the low-income. Furthermore, rural area residences may be the elderly, the disabled, and the low-income also. It may mean that the rural area should be considered as in noticeable status of the digital divide. This study focuses on the policy alternatives to reduce the digital divide in rural areas with a literature review methodology and on the factors on informatization issues in rural areas. For the aims, this study analyzes the EU cases of informatization in rural areas to find out the advantages and disadvantages of the suggested policies. As the analysis result, it is clear that the EU countries try to enhance the economic and growth powers rather to reduce the digital divide gaps. Also, it can be considered that the EU countries focus on supporting the rural area to adopt the non-contact information services newly rather on maintaining the IT education services and the infrastructures in off-line environments.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.4
• /
• pp.105-112
• /
• 2021

In the era of big data, interest in data is exploding. In particular, the development of the Internet and social media has led to the creation of new data, enabling the realization of the era of big data and artificial intelligence and opening a new chapter in convergence technology. Also, in the past, there are many demands for analysis of data that could not be handled by programs. In this paper, an analysis model was designed and verified for classification of unstructured data, which is often required in the era of big data. Data crawled DBPia's thesis summary, main words, and sub-keyword, and created a database using KoNLP's data dictionary, and tokenized words through morpheme analysis. In addition, nouns were extracted using KAIST's 9 part-of-speech classification system, TF-IDF values were generated, and an analysis dataset was created by combining training data and Y values. Finally, The adequacy of classification was measured by applying three analysis algorithms(random forest, SVM, decision tree) to the generated analysis dataset. The classification model technique proposed in this paper can be usefully used in various fields such as civil complaint classification analysis and text-related analysis in addition to thesis classification.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.1
• /
• pp.570-575
• /
• 2021

Since humans live while feeling rich in their five senses, care must be taken not to damage their hearing in order to lead a happy life. Hearing damage suffered in a living environment is common in a partial band where a specific frequency band is first damaged. However, since the initial pain of hearing damage does not appear much, it is difficult to determine the symptoms in the early stages. In this paper, we proposed a high-speed measurement method that can easily and quickly self-measure hearing damage through a simple app. In this method, 9 pure tones compensated for gain for each voice soub-band are alternately heard in both ears, so that one's own hearing damage can be detected at high speed. When 18 tone pulses were heard for 30 seconds per person, 1 out of 12 subjects was identified as suspected of partial hearing damage. And when the test subjects were informed of the hearing determination method for the number of hearings, the participants themselves immediately determined whether their hearing was damaged. This measurement method simply judges the hearing of both ears within 30 seconds with a smart phone, so that hearing measurements that took more than 10 minutes in hospitals are relatively accurate, and it was found that hearing health can be maintained while reducing time and costs.