• Journal of the Korea Society of Computer and Information
• /
• v.26 no.7
• /
• pp.1-7
• /
• 2021

In this paper, we propose a feature selection technique for multi-label classification. Many existing feature selection techniques have selected features by calculating the relation between features and labels such as a mutual information scale. However, since the mutual information measure requires a joint probability, it is difficult to calculate the joint probability from an actual premise feature set. Therefore, it has the disadvantage that only a few features can be calculated and only local optimization is possible. Away from this regional optimization problem, we propose a feature selection technique that constructs a low-rank space in the entire given feature space and selects features with sparsity. To this end, we designed a regression-based objective function using Nuclear norm, and proposed an algorithm of gradient descent method to solve the optimization problem of this objective function. Based on the results of multi-label classification experiments on four data and three multi-label classification performance, the proposed methodology showed better performance than the existing feature selection technique. In addition, it was showed by experimental results that the performance change is insensitive even to the parameter value change of the proposed objective function.

• Journal of Platform Technology
• /
• v.8 no.4
• /
• pp.20-28
• /
• 2020

In this paper, a voice, object, and optical character recognition platform including voice recognition-based smart wearable devices, smart devices, and web AI servers was proposed as an appropriate technology to help the visually impaired to live independently by learning the life cycle of the visually impaired in advance. The wearable device for the visually impaired was designed and manufactured with a reverse neckband structure to increase the convenience of wearing and the efficiency of object recognition. And the high-sensitivity small microphone and speaker attached to the wearable device was configured to support the voice recognition interface function consisting of the app of the smart device linked to the wearable device. From experimental results, the voice, object, and optical character recognition service used open source and Google APIs in the web AI server, and it was confirmed that the accuracy of voice, object and optical character recognition of the service platform achieved an average of 90% or more.

• Journal of Convergence for Information Technology
• /
• v.10 no.12
• /
• pp.9-14
• /
• 2020

Currently, NTIS (National Technology Information Service) is building an interactive search service based on artificial intelligence technology. In order to understand users' search intentions and provide R&D information, an interactive search service is built based on deep learning models and morpheme analyzers. The deep learning model learns based on the log data loaded when using NTIS and interactive search services and understands the user's search intention. And it provides task information through step-by-step search. Understanding the search intent makes exception handling easier, and step-by-step search makes it easier and faster to obtain the desired information than integrated search. For future research, it is necessary to expand the range of information provided to users.

• The Mathematical Education
• /
• v.60 no.1
• /
• pp.41-59
• /
• 2021

The purpose of this study is to synthesize a comprehensive and general conclusion about the effects of mathematics classes using peer tutoring on the cognitive (mathematics learning achievement) and affective domains. For this purpose, a total of 61 individual studies were meta-analyzed in this study to calculate the effect size, measuring the strength of the relationship between mathematics classes using peer tutoring and either the cognitive or affective domain. As a result of this study, it was confirmed that mathematics classes using peer tutoring generally have a medium effect size in both cognitive and affective domains. Also, it was found that level of school, type of student, learning location, class time, tutor education or prior training are significant variables that affect the impact of mathematics classes using peer tutoring on the cognitive and affective domains. These results suggest specific ideas on how to design and operate peer tutoring in school mathematics classes on the basis of different variables.

• Journal of the Korean Society for Library and Information Science
• /
• v.55 no.1
• /
• pp.541-565
• /
• 2021

The study is aimed at designing an effective edutech platform based on online remote classes, and clarifying the effect of empathy competence of youths through the operation linked with the empathic reading program focusing on reading. To this end, after constructing the environment for education and drawing a class model based on components of edutech for remote classes on the basis of previous studies and elaborating the empathic reading education program, this study has been conducted for one semester for 107 students in 4 classes in their 1st grade at S middle school, Gyeonggi-do in order to apply them to fields. As a result of the study, the empathy reading program that a remote class model was applied has shown a meaningful difference among groups in cognitive empathy and emotional empathy, and it was found that there was a statistically meaningful difference between the two groups in total scores. Besides, the effect and meaning of adolescents' empathy competence have been verified through the remote empathy reading education and the empirical analysis, and the direction to develop the empathy reading program has been suggested for a solution to settle differences in students' learning due to COVID-19.

• Journal of Digital Convergence
• /
• v.19 no.3
• /
• pp.37-45
• /
• 2021

Since the Syrian Civil War in 2011, the number of refugees has been on the rise in Korea as well as worldwide. In addition to recognition of legal status for refugees, employment and education support, and qualification recognition are emerging as social issues. In this context, this study aims to compare the cases of Netherlands and Norway in terms of evaluation and recognition of refugees' qualifications. The findings of the study show that although there were concerns about the lack of official documents to verify the qualifications of refugees, the two countries have developed a special process for the evaluation and recognition for refugees respectively according to the Lisbon Recognition Convention. In addition, both countries have developed a recognition of prior learning system which has made the qualification recognition process flexible from a point of refugees. These experiences could be used as benchmarks for the Korean government which has a responsibility to develop its own qualification recognition system for refugees in the near future.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.6
• /
• pp.774-784
• /
• 2021

The object detection and recognition process is a very important task in the field of computer vision, and related research is actively being conducted. However, in the actual object recognition process, the recognition accuracy is often degraded due to the resolution mismatch between the training image data and the test image data. To solve this problem, in this paper, we designed and developed an integrated object recognition and super-resolution framework by proposing an image super-resolution technique to improve object recognition accuracy. In detail, 11,231 license plate training images were built by ourselves through web-crawling and artificial-data-generation, and the image super-resolution artificial neural network was trained by defining an objective function to be robust to the image flip. To verify the performance of the proposed algorithm, we experimented with the trained image super-resolution and recognition on 1,999 test images, and it was confirmed that the proposed super-resolution technique has the effect of improving the accuracy of character recognition.

• Journal of The Korean Association of Information Education
• /
• v.25 no.2
• /
• pp.289-300
• /
• 2021

SNS data was collected and analyzed by topic modeling techniques to examine recent trends in information education. By deriving keywords and topics for SW education and AI education, we not only attempted to discover insights ahead of the next revised curriculum but also suggested directions. According to the SNS data analysis, the contents of human resource development for software and the instructional method in schools are indicated as a high requirement. Meanwhile, SW education should be conducted through a separate curriculum from elementary school, and this was consistent with the opinion that it is necessary to be organized as a required subject. There was an opinion to support the schools since AI education is newly introduced in next revised national curriculum. The trends in SW education and AI education which are observed through SNS data analysis could be concluded to conduct the substantial operation of information education and curriculum organization.

• Journal of The Korean Association of Information Education
• /
• v.25 no.2
• /
• pp.367-375
• /
• 2021

This study developed and applied an artificial intelligence education program as an educational method for increasing computational thinking of elementary school students and verified its effectiveness. The educational program was designed based on the results of a demand analysis conducted using Google survey of 100 elementary school teachers in advance according to the ADDIE(Analysis-Design-Development-Implementation-Evaluation) model. Among Machine Learning for Kids, we use scratch for block-based programming and develop and apply textbooks to improve computational thinking in the programming process of learning the principles of artificial intelligence and solving problems directly by utilizing numerical data. The degree of change in computational thinking was analyzed through pre- and post-test results using beaver challenge, and the analysis showed that this study had a positive impact on improving computational thinking of elementary school students.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.242-263
• /
• 2021

This paper presents a method to implement a low-cost driving simulator for developing autonomous driving algorithms. This is implemented by using GTA V, a physical engine-based commercial game software, containing a function to emulate output and data of various sensors for autonomous driving. For this, NF of Script Hook V is incorporated to acquire GT data by accessing internal data of the software engine, and then, various sensor data for autonomous driving are generated. We present an overall function of the developed driving simulator and perform a verification of individual functions. We explain the process of acquiring GT data via direct access to the internal memory of the game engine to build up an autonomous driving algorithm development environment. And, finally, an example applicable to artificial neural network training and performance evaluation by processing the emulated sensor output is included.