• Korean Journal of Radiology
• /
• v.25 no.2
• /
• pp.126-133
• /
• 2024

Large language models (LLMs) have revolutionized the global landscape of technology beyond natural language processing. Owing to their extensive pre-training on vast datasets, contemporary LLMs can handle tasks ranging from general functionalities to domain-specific areas, such as radiology, without additional fine-tuning. General-purpose chatbots based on LLMs can optimize the efficiency of radiologists in terms of their professional work and research endeavors. Importantly, these LLMs are on a trajectory of rapid evolution, wherein challenges such as "hallucination," high training cost, and efficiency issues are addressed, along with the inclusion of multimodal inputs. In this review, we aim to offer conceptual knowledge and actionable guidance to radiologists interested in utilizing LLMs through a succinct overview of the topic and a summary of radiology-specific aspects, from the beginning to potential future directions.

• STI Policy Review
• /
• v.1 no.2
• /
• pp.1-18
• /
• 2010

The development and maintenance of human capacity in economies is critical to long term competitiveness, but also for the overall health and environment of regions. Yet, human science and technology-based capacity is multidimensional and has interrelated characteristics which present certain policy challenges. This paper addresses a range of issues specific to a discussion on human capacity in S&T. First, the paper emphasizes the importance of acknowledging the complexity of human capacity issues and how they evolve along the STEM (science, technology, engineering, and mathematics) pipeline. The pipeline is an often used reference to describe the training and development in STEM disciplines, from early childhood education, to more advanced training, and finally to professional collaboration and interaction and serves as a useful organizing framework for the discussion of capacity along the career evolution process. Second, the paper offers an organizing framework for discussion of policy mechanisms that have been developed to address issues and gaps that occur along this STEM pipeline. Specifically, it contrasts the traditional mechanisms of building human capacity in STEM areas with newer "gap filling" and integrated approached to addressed human capacity disparities and priorities. Third, the paper addresses core challenges in human capacity in STEM, including the education and training, participation of women and underrepresented groups, brain drain/brain circulation issues, and the globalization of science. The paper concludes with a discussion of policy implication for the development of human capacity.

• The Journal of the Korea Contents Association
• /
• v.18 no.2
• /
• pp.320-333
• /
• 2018

The study introduced an actual American university program student's learning outcomes in instructional technology integration knowledge in order to acknowledge implication considering the current status of relevant Korean teacher training programs. With utilizing complete sampling (students enrolled in a master's program in Instructional Systems Technology at the N University in Fall 2015), the survey was conducted on knowledge, strategies and performance in instructional technology integration, and interview assessed deeper understanding of students' relevant competencies in their specific professional setting. The results and findings based on triangulation of the data confirmed that the students gained sufficient knowledge, and applied the relevant knowledge and competencies into their work setting. For future research, the implications were offered on reviewing Korean teacher training programs in professional competency development related to technology integration in teaching and learning.

• Journal of Information Technology Applications and Management
• /
• v.30 no.2
• /
• pp.1-18
• /
• 2023

Recently, as technology development has accelerated and product life cycles have been shortened, it is necessary to derive key product features from customers in the R&D planning and evaluation stage. More companies want differentiated competitiveness by providing consumer-tailored products based on big data and artificial intelligence technology. To achieve this, the need to correctly grasp the required quality, which is a requirement of consumers, is increasing. However, the existing methods are centered on suppliers or domain experts, so there is a gap from the actual perspective of consumers. In other words, product attributes were defined by suppliers or field experts, but this may not consider consumers' actual perspective. Accordingly, the demand for deriving the product's main attributes through reviews containing consumers' perspectives has recently increased. Therefore, we propose a review data analysis-based required quality methodology containing customer requirements. Specifically, a pre-training language model with a good understanding of Korean reviews was established, consumer intent was correctly identified, and key contents were extracted from the review through a combination of KeyBERT and topic modeling to derive the required quality for each product. RevBERT, a Korean review domain-specific pre-training language model, was established through further pre-training. By comparing the existing pre-training language model KcBERT, we confirmed that RevBERT had a deeper understanding of customer reviews. In addition, all processes other than that of selecting the required quality were linked to the automation process, resulting in the automation of deriving the required quality based on data.

• Journal of Korean society of Dental Hygiene
• /
• v.19 no.1
• /
• pp.19-31
• /
• 2019

Objectives: The aim of this study was to propose a standardized guideline for clinical training courses among dental hygiene departments of colleges in Korea. This study comparatively evaluated periods and durations of the curricula and specific domains, credits and hours of clinical training classes, and institutions providing practical lessons, and calculated the total credits and hours. Methods: From August 15 to September 15, 2017, a literature review was conducted in dental hygiene departments of 82 schools around the country in order to investigate the current conditions of clinical training in each educational system. Furthermore, 5 colleges were selected from each type of educational system, and their credits and hours for clinical training were analyzed in subjects of practical training for clinical dental hygiene, practical training for dental clinic, practical training for local community dental health, clinical training, and pre-clinical level practical training. The total credits and hours were calculated on the basis of analysis results. Results: The findings revealed that the hours of clinical training classes and hours per credit for practical training in the dental hygiene departments as well as the practical training institutions varied between the colleges. In some cases, the hours of practical training were not indicated. Standardized clinical training in the dental hygiene department was allotted 675 hours, whereas practical training in local community dental health studies was allotted 105 hours, which totaled to 780 allotted hours. Conclusions: There was a significant difference among the colleges in terms of the current conditions of clinical training in the dental hygiene department. The literature review revealed that a total of 780 hours was allotted to clinical training, and this was significantly more than the standard (500 hours) set by the. Moreover, these clinical training hours were lower than in advanced countries or other health and medical treatment occupations. Therefore, efficient improvement is required in order to provide a timely guideline for clinical training.

• Journal of Information Science Theory and Practice
• /
• v.6 no.4
• /
• pp.28-38
• /
• 2018

Wikipedia is composed of millions of articles, each of which explains a particular entity with various languages in the real world. Since the articles are contributed and edited by a large population of diverse experts with no specific authority, Wikipedia can be seen as a naturally occurring body of human knowledge. In this paper, we propose a method to automatically identify key entities and relations in Wikipedia articles, which can be used for automatic ontology construction. Compared to previous approaches to entity and relation extraction and/or identification from text, our goal is to capture naturally occurring entities and relations from Wikipedia while minimizing artificiality often introduced at the stages of constructing training and testing data. The titles of the articles and anchored phrases in their text are regarded as entities, and their types are automatically classified with minimal training. We attempt to automatically detect and identify possible relations among the entities based on clustering without training data, as opposed to the relation extraction approach that focuses on improvement of accuracy in selecting one of the several target relations for a given pair of entities. While the relation extraction approach with supervised learning requires a significant amount of annotation efforts for a predefined set of relations, our approach attempts to discover relations as they occur naturally. Unlike other unsupervised relation identification work where evaluation of automatically identified relations is done with the correct relations determined a priori by human judges, we attempted to evaluate appropriateness of the naturally occurring clusters of relations involving person-artifact and person-organization entities and their relation names.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.3
• /
• pp.359-365
• /
• 2022

This study was to provide teaching and learning strategies to develop a creative sight-singing and ear-training program that aims to design student-centered education. Therefore, the characteristics of the sight-singing and ear-training as well as teaching and learning methods were analyzed through the literature review, and the following meaningful strategies were derived. First, a student-centered teaching environment was promoted by diversifying the teaching environment through small group activities and establishing a sustainable learning environment using MyEarTraining and Musescore applications. Second, teaching and learning strategies were proposed to improve sight-singing and ear-training skills by applying for various teaching and learning methods and cultivating the qualities of a pre-service teacher. This study is expected to be used as meaningful fundamental data in developing specific teaching and learning processes for a creative sight-singing and ear-training program.

• Journal of Internet Computing and Services
• /
• v.25 no.4
• /
• pp.23-37
• /
• 2024

Digital twin is an M&S (Modeling and Simulation) technology designed to solve or optimize problems in the real world by replicating physical objects in the real world as virtual objects in the digital world and predicting phenomena that may occur in the future through simulation. Digital twins have been elaborately designed and utilized based on data collected to achieve specific purposes in large-scale environments such as cities and industrial facilities. In order to apply this digital twin technology to real life and expand it into user-customized service technology, practical but sensitive issues such as personal information protection and personalization of simulations must be resolved. To solve this problem, this paper proposes a federated learning-based accelerated client training method (FACTS) for personalized digital twins. The basic approach is to use a cluster-driven federated learning training procedure to protect personal information while simultaneously selecting a training model similar to the user and training it adaptively. As a result of experiments under various statistically heterogeneous conditions, FACTS was found to be superior to the existing FL method in terms of training speed and resource efficiency.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.4
• /
• pp.193-202
• /
• 2023

In recent years, the outstanding performance of large language models (LLMs) trained on extensive datasets has become a hot topic. Since studies on LLMs are available on open-source approaches, the ecosystem is expanding rapidly. Models that are task-specific, lightweight, and high-performing are being actively disseminated using additional training techniques using pre-trained LLMs as foundation models. On the other hand, the performance of LLMs for Korean is subpar because English comprises a significant proportion of the training dataset of existing LLMs. Therefore, research is being carried out on Korean-specific LLMs that allow for further learning with Korean language data. This paper identifies trends of open source based LLMs and introduces research on Korean specific large language models; moreover, the applications and limitations of large language models are described.

• Proceedings of the KSPS conference
• /
• 2003.05a
• /
• pp.119-122
• /
• 2003

In general, triangular shape filters are used in the filter bank when we get the MFCCs from the spectrum of speech signal. In [1], a new feature extraction approach is proposed, which uses specific filter shapes in the filter bank that are obtained from the spectrum of training speech data. In this approach, principal component analysis technique is applied to the spectrum of the training data to get the filter coefficients. In this paper, we carry out speech recognition experiments, using the new approach given in [1], for a large amount of telephone speech data, that is, the telephone speech database of Korean connected digit released by SITEC. Experimental results are discussed with our findings.