• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.289-294
• /
• 2022

의존구문분석은 문장을 의존관계(의존소-지배소)로 분석하는 구문분석 방법론이다. 현재 사전학습모델을 사용한 전이 학습의 딥러닝이 좋은 성능을 보이며 많이 연구되지만, 데이터셋에 의존적이며 그로 인한 자료부족 문제와 과적합의 문제가 발생한다는 단점이 있다. 본 논문에서는 언어학적 지식에 기반한 강화된 지배소-의존소 제약규칙 에지 알고리즘을 심층학습과 결합한 모델을 제안한다. TTAS 표준 가이드라인 기반 모두의 말뭉치로 평가한 결과, 최대 UAS 96.28, LAS 93.19의 성능을 보였으며, 선행연구 대비 UAS 2.21%, LAS 1.84%의 향상된 결과를 보였다. 또한 적은 데이터셋으로 학습했음에도 8배 많은 데이터셋 학습모델 대비 UAS 0.95%의 향상과 11배 빠른 학습 시간을 보였다. 이를 통해 심층학습과 언어지식의 결합이 딥러닝의 문제점을 해결할 수 있음을 확인하였다.

• Journal of the Korean Society of Safety
• /
• v.32 no.5
• /
• pp.88-95
• /
• 2017

As the safety fields are expanding to a variety of industrial fields, safety technology has been developed by convergence between industrial safety fields such as mechanics, ergonomics, electronics, chemistry, construction, and information science. As the technology convergence is facilitating recently advanced safety technology, it is important to explore the trends of safety technology for understanding which industrial technologies have been integrated thus far. For studying the trends of technology, the patent is considered one of the useful sources that has provided the ample information of new technology. The patent has been also used to identify the patterns of technology convergence through various quantitative methods. In this respect, this study aims to identify the convergence patterns and fields of safety technology using association rule mining(ARM)-based patent co-classification(co-class) analysis. The patent co-class data is especially useful for constructing convergence network between technological fields. Through linkages between technological fields, the core and hub classes of convergence network are explored to provide insight into the fields of safety technology. As the representative method for analyzing patent co-class network, the ARM is used to find the likelihood of co-occurrence of patent classes and the ARM network is presented to visualize the convergence network of safety technology. As a result, we find three major convergence fields of safety technology: working safety, medical safety, and vehicle safety.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.18 no.3
• /
• pp.83-95
• /
• 2022

A technology can be newly formed through technological convergence achieved by the intersection of two or more technological fields. As the complexity of technology development increases, related interest is increasing. Researches have been carried out on the concept, related indicators and analysis of technology convergence including method of social networks. This paper intends to suggest an analysis method of technology convergence using social networks based on the company's possessing technologies. According to the similarity of technologies among companies, a social network was constructed and the technology convergence was analyzed using k-core, a social network subgroup method. Using the result of k-core, base and element technologies for convergence was identified with their relations. Using the suggested method, technology convergence was analyzed on real technology data of defense-industry companies. When the minimum technology similarity is 0, the overall technology convergence relations between technology elements can be identified. In the scope of data in this paper, technologies of defense S/W, aircraft structure and structural materials are identified as important base technology for convergence.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.934-936
• /
• 2022

현재 사회적인(COVID-19) 영향으로 메타버스에 대한 수요가 급증하였지만, 메타버스 플랫폼 진입을 지원하는 XR(AR/VR) 장비의 높은 가격대와 전문성 요구로 폭넓은 수요층을 포괄하기 어려운 상황이다. 본 논문에서는 이러한 수요층의 어려움을 개선하고자 웹 캠이나 스마트폰 카메라로 생성된 개인의 사진 이미지를 StyleGAN 딥러닝 기술과 접목시켜 캐릭터를 생성해 Mediapipe를 활용하여 모션 측정 및 제어를 처리하는 서비스를 제안하여 메타버스 시장의 대중화에 기여하고자 한다.

• Journal of electromagnetic engineering and science
• /
• v.15 no.2
• /
• pp.76-81
• /
• 2015

This paper presents a design of a transmission line negative group delay (NGD) circuit with multiple pole characteristics. By inserting an additional transmission line into a conventional NGD circuit, the proposed circuit provides further design parameters to obtain wideband group delay (GD) and to help reduce signal attenuation. As a result, the number of gain compensating amplifiers can be reduced, which can contribute to stable operation when integrated into RF systems. The multiple pole characteristics can provide wider NGD bandwidth and can be obtained by connecting resonators with slightly different center frequencies separated by quarter-wavelength transmission lines. For experimental validation, an NGD circuit with two poles GD characteristic is designed, simulated, and measured.

• Proceedings of the Korea Contents Association Conference
• /
• 2016.05a
• /
• pp.343-344
• /
• 2016

최근 3D 기술의 이슈는 안경을 사용하지 않고 고화질 3D를 볼 수 있도록 하는 것이며, 그 기술로 집적영상시스템이 대표적으로 사용된다. 본 논문에서는 고화질의 3D 영상 생성에 대한 기법의 하나로 저해상도의 깊이영상을 고해상도로 확장시켜 고해상도 요소영상을 생성하는 기법을 제안한다. 제안 기법을 적용한 결과 질 좋은 요소 영상을 생성하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.1001-1004
• /
• 2021

Pain is an unpleasant experience for the patient. The recognition and assessment of pain help tailor the treatment to the patient, and they are also challenging in the medical. In this paper, we propose an approach for pain recognition through a deep neural network applied to pre-processed physiological. The proposed approach applies the idea of shortcut connections to concatenate the spatial information of a convolutional neural network and the temporal information of a recurrent neural network. In addition, our proposed approach applies the attention mechanism and achieves competitive performance on the BioVid Heat Pain dataset.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.459-461
• /
• 2024

본 논문은 국내 정보보안 분야 학술 연구에서 참고문헌 인용행태를 파악하고자 해당 분야 대표 학술지의 인용문헌 현황 및 패턴을 분석하였다. 실험데이터는 "정보보호학회논문지"를 대상으로 수록된 모든 논문과 참고문헌 정보를 수집하고 개별 학술지 및 학술대회의 식별 과정을 통해 구축하였다. 이를 기반으로 참고문헌 현황, 인용나이 통계 분석 결과와 동시출현네트워크 (학술지 및 학술대회)의 생성을 통한 네트워크 중심성 및 시각화 지도를 제시하였다.

• Journal of Digital Convergence
• /
• v.10 no.11
• /
• pp.279-285
• /
• 2012

This study classified the categorization process of convergence products as a rule-based and a similarity-based categorization process. And we examined that how the categorization process was determined according to information types(visual vs. visual + verbal) about the components of two prototypes before convergence and thinking styles(holistic vs. analytic). The result of this study showed: (1) The rule-based categorization process appeared more in case of visual information with verbal information than only visual information. (2) Analytic thinkers chose a rule-based categorization process more than holistic thinkers. These findings provide the theoretical and practical implications to comprehend the categorization process of convergence products and the judgement for consideration set from various convergence products.

• Journal of Convergence for Information Technology
• /
• v.10 no.7
• /
• pp.122-130
• /
• 2020

The purpose of this study is to identify current states and trends of convergence researches by conducting a bibliometric analysis of the papers in the Convergence Society for SMB. After 792 papers from 2012 to 2019 were collected, we analyzed network analysis by using centrality through extracting of nouns and compound nouns with text mining and 3 times of pre-processing and purification processing. According to the results, first, quantitative and qualitative aspects of the researches since 2016 improved, studies focused on words such as influence, convergence, mediating effect, satisfaction, and effect. Second, in the first half (2012-2015), engineering and technical studies were intensively conducted based on topics such as information, system, and security. Third, in the period of the second half (2016-2019), the research scope was expanded to college students, parents, teenagers under the topics of job, self-efficacy, education, satisfaction, depression, and stress. The results of this study are meaningful in identifying existing research trends and in providing information which requires the expansion of new research areas.