• Journal of Broadcast Engineering
• /
• v.27 no.2
• /
• pp.244-247
• /
• 2022

In this paper, the performance of the decoding schemes using linear MMSE filters in the frequency and time domains and the reinforcement Gauss-Seidel algorithm for the orthogonal time frequency space (OTFS) system that can improve robustness under high-speed mobile environments are compared. The reinforcement Gauss-Seidel algorithm can improve the bit error rate performance by suppressing the noise enhancement. The simulation results show that the performance of the decoding scheme using the linear MMSE filter in the frequency domain is severely degraded due to the effect of Doppler shift as the mobile speed increases. In addition, the decoding scheme using the reinforcement Gauss-Seidel algorithm under the channel environment with 120 km/h and 500 km/h speeds outperforms the decoding schemes using linear MMSE filters in the frequency and time domains.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.379-384
• /
• 2022

관계 추출은 두 개체 간의 관계를 식별하는 작업이며, 비정형 텍스트를 구조화시키는 역할을 하는 작업 중 하나이다. 현재 관계 추출에서 다양한 모델에 대한 연구들이 진행되고 있지만, 한국어 관계 추출 모델에 대한 연구는 영어에 비해 부족하다. 따라서 본 논문에서는 NE(Named Entity)태그 정보가 반영된 TEM(Typed Entity Marker)과 의존 구문 그래프를 이용한 한국어 관계 추출 모델을 제안한다. 모델의 학습과 평가 말뭉치는 KLUE에서 제공하는 관계 추출 학습 말뭉치를 사용하였다. 실험 결과 제안 모델이 68.57%의 F1 점수로 실험 모델 중 가장 높은 성능을 보여 NE태그와 구문 정보가 관계 추출 성능을 향상시킬 수 있음을 보였다.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.528-531
• /
• 2021

띄어쓰기에 대한 오류는 한국어 처리 전반에 영향을 주므로 자동 띄어쓰기는 필수적인 요소이다. 글쓴이의 대부분은 띄어쓰기 오류를 범하지 않으므로 글쓴이의 의도가 띄어쓰기 시스템에 반영되어야 한다. 그러나 대부분의 자동 띄어쓰기 시스템은 모든 띄어쓰기 정보를 제거하고 새로이 공백문자를 추가하는 방법으로 띄어쓰기를 수행한다. 이런 문제를 완화하기 위해서 본 논문에서는 기계학습에서 글쓴이의 의도가 반영된 자질을 추가하는 방법을 제안한다. 실험을 위해서 CRFs(Conditional Random Fields)를 사용하여 기존 시스템과 사용자의 의도를 반영한 띄어쓰기 시스템과의 성능을 비교하고 분석한다.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.536-539
• /
• 2021

본 논문은 한국어에서 형태소 복원을 위한 새로운 방법을 제안한다. 일반적으로 기계학습 기반 형태소 분석에서 형태소 복원은 기분석 사전과 약간의 경험규칙을 이용한다. 이와 같은 방법은 모호성을 해결하기 위해 사전에 모든 정보를 저장하는 것이 불가능할 뿐 아니라 단음절 이형태의 모호성을 해결할 수 없을 것이다. 이러한 문제를 완화하기 위해 본 논문에서는 생성된 모호성을 Viterbi 알고리즘을 이용해서 해소한다. 본 논문의 형태소 복원 과정은 기본적으로 기분석 사전과 약간의 경험규칙을 이용하여 형태소 복원 후보를 찾고 여러 후보가 있을 경우(모호성의 생성), 그 결과를 Viterbi 알고리즘으로 이형태를 결정한다. 실험을 위해 모두의 말뭉치(형태 분석)를 사용하고, 평가는 NER 방식으로 평가한다. 그 결과 품사 부착에 대해 96.28%정도의 성능을 보여주었다.

• Journal of Convergence for Information Technology
• /
• v.9 no.1
• /
• pp.28-37
• /
• 2019

Various fields are being combined and developed for the development of the country and industry. The purpose of this study is to examine the effects of interdisciplinary research on the technology commercialization of researchers in the national R&D project. For the purpose of empirical analysis, major research and development have been reviewed. Major research and development projects conducted by government-funded research institution in which various technological fields are integrated in order to commercialize technology. The research data is based on the major R&D project data for railway/public transportation/logistics fields technology in 2015-17, and 149 project were selected for analysis. As a result, it was found that diversity of participants' experts had significant positive effect on technology commercialization when R&D expense, The number of research participants, The number of participating organizations, TRL before R&D were controlled. It is expected that the results of this study will be used meaningfully when the R&D program plan, analysing the academic convergence factor of research topic.

• Journal of Broadcast Engineering
• /
• v.25 no.6
• /
• pp.870-881
• /
• 2020

This paper presents cell ID (cell identity) detection schemes using PSS/SSS (primary synchronization signal/secondary synchronization signal) for 5G NR (new radio) system and evaluates the detection performance. In this paper, we consider two cell ID detection schemes, i.e. two-stage detection and joint detection schemes. The two-stage detection scheme consists of two stages which estimate a channel gain between a transmitter and receiver and detect the PSS and SSS sequences. The joint detection scheme jointly detects the PSS and SSS sequences. In addition, this paper presents coherent and non-coherent combining schemes. The coherent scheme calculates the correlation value for the total length of the given PSS and SSS sequences, and the non-coherent combining scheme calculates the correlation within each group by dividing the total length of the sequence into several groups and then combines them non-coherently. For the detection schemes considered in this paper, the detection error rates of PSS, SSS and overall cell ID are evaluated and compared through computer simulations. The simulation results show that the joint detection scheme outperforms the two-stage detection scheme for both coherent and non-coherent combining schemes, but the two-stage detection scheme can greatly reduce the computational complexity compared to the joint detection scheme. In addition, the non-coherent combining detection scheme shows better performance under the additive white Gaussian noise (AWGN), fixed, and mobile environments.

• Journal of Broadcast Engineering
• /
• v.26 no.6
• /
• pp.766-777
• /
• 2021

This paper presents an improved scheme for detection of the physical broadcast channel (PBCH) in long-term evolution (LTE)-based fifth-generation (5G) multimedia broadcast and multicast services (MBMS) and 5G new radio (NR) for cellular broadcast. In the time domain, by combining the correlations between the received signal and primary synchronization signal (PSS) within all SS/PBCH blocks, the frame synchronization and the start position of the SS/PBCH blocks can be obtained. In this paper, to improve the detection performance of PBCH for 5G NR, a combining scheme of PBCH signals within a frame is proposed. In addition, the performance of the proposed detection scheme is evaluated and the performance is compared with the conventional scheme for PBCH detection of LTE-based 5G MBMS. The simulation results show that the detection performance of PBCH for 5G NR is improved by combining the PBCH signals and outperforms LTE-based 5G MBMS under the additive white Gaussian noise (AWGN), fixed, and mobile environments.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.1
• /
• pp.147-156
• /
• 2022

The purpose of this study was to review various grounds and plans for the establishment of a convergence major in lifelong education for the disabled based on Daegu University, which establishes its status and identity as a base university for education and welfare for the disabled. Lifelong education for the disabled reflects the specificity of disability in common because it targets disabled learners, but since it constitutes two perspectives and characteristics of education and welfare, access to interdisciplinary convergence research in disabled-related fields is important. In the above dimension, Daegu University has an appropriate foundation to lead lifelong education for the disabled in Korea through various academic and practice-based infrastructures, and has sufficient leadership to improve the practical limitations of the lifelong education support system for the disabled. Accordingly, this study presented measures and related grounds to reflect lifelong education for the disabled in order to establish an interdisciplinary convergence major at Daegu University through literature review and expert advice. It was emphasized that lifelong education for the disabled, viewed as a new interdisciplinary convergence major, should be activated through professional competencies commonly accessible to the three fields rather than applied from a priority perspective between special education, rehabilitation science, and social welfare. As a result of the study, it was suggested that Korea, which failed to establish a lifelong education support system for the disabled, should gradually spread and spread to other universities starting with Daegu University's application model and plan. In addition, the necessity of systematically establishing a qualification development path for lifelong education professionals for the disabled through agreement between the three fields was also suggested.

• Journal of Engineering Education Research
• /
• v.16 no.6
• /
• pp.29-37
• /
• 2013

The necessity of convergence education is more emphasized based on the education policy for fostering creative men of talent. Inside universities, however, programs for training talented individuals are still at primary stage. Universities understanding the importance of convergence education and thus founding some major fields of convergence studies have experienced hosts of troubles. The paper discusses the necessary plans of supports from the government and the university to activate the convergence education in accord with the social demands. Twenty-eight professors in engineering colleges participated in the survey for reviewing the required factors for the convergence education. In addition, structured interviews were carried out with three specialists working in industry and academic area of convergence technology. The study could suggest the following activation plans based on the government supports: (1) establishing a support center of convergence education, (2) founding a major field of convergence, (3) developing curriculums and curriculum subjects, and (4) hosting related conferences and forums. Also, the study could suggest the following activation plans based on the university supports: (1) developing special programs on convergence education in accord with the industrial demands, (2) revising regulations and administrative systems more flexible for the convergence education, and (3) providing incentives to the participants in the convergence education.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.532-535
• /
• 2021

다양한 SNS 플랫폼이 등장하고, 이용자 수가 급증함에 따라 온라인에서 얻을 수 있는 정보의 활용 가치가 높아지고 있다. 문장은 자연어 처리 시스템의 기본적인 단위이므로 주어진 문서로부터 문장의 경계를 인식하는 작업이 필수적이다. 공개된 문장 경계 인식기는 SNS 문서에서 좋은 성능을 보이지 않는다. 본 논문에서는 문어체로 구성된 일반 문서뿐 아니라 SNS 문서에서 사용할 수 있는 문장 경계 인식기를 제안한다. 본 논문에서는 SNS 문서에 적용하기 위해 다음과 같은 두 가지를 개선한다. 1) 학습 말뭉치를 일반문서와 SNS 문서 두 영역으로 확장하고, 2) 이모티콘을 사용하는 SNS 문서의 특징을 반영하는 어절의 유형을 자질로 추가하여 성능을 개선한다. 실험을 통해서 추가된 자질의 기여도를 분석하고, 또한 기존의 한국어 문장 경계 인식기와 제안한 모델의 성능을 비교·분석하였다. 개선된 모델은 일반 문서에서 99.1%의 재현율을 보이며, SNS 문서에서 88.4%의 재현율을 보였다. 두 영역 모두에서 문장 경계 인식이 잘 이루어지는 것을 확인할 수 있었다.