http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
라즈베리파이를 사용한 신경망 학습기반 한국어 음성인식 시스템
김상홍(Sanghong Kim),이보원(Bowon Lee) 대한전자공학회 2018 대한전자공학회 학술대회 Vol.2018 No.11
This paper proposes an embedded system for neural network based automatic speech recognition using Raspberry pi equipped with ARM-v8 quad core processor. This system consists of Cirrus Logic Audio Card, and 7 inch touch screen. The proposed system does not need any internet connection for Korean speech recognition. Kaldi (written in C++ code) is adopted as speech recognition toolkit for the proposed system.
조동현(Cho Donghyun),이상홍(Lee Sanghong),홍원화(Hong Wonhwa) 한국주거학회 2004 한국주거학회 논문집 Vol.15 No.6
This study proposes the direction of planning and designing for the media related facilities through the future concepts of media-center even though the concept and environment of the media-center are developed mealy at elementary schools in Korea. This study investigates and analyzes whether the present facilities are ready for the efficient education and improved facilities through comparison between after and before the 7th education program of systems of the academic support facilities. Therefore this study proposes the direction of developing and designing media-center through the field survey, make-up questionaries and analyzing architectural drawings of media related facilities for the future.
도심 오피스의 주거 전환에 대응하는 주차공간 계획 연구 - 대구 구도심(중구)의 오피스를 중심으로 -
김은광(Kim, Eunkwang),이상홍(Lee, Sanghong) 대한건축학회 2021 대한건축학회논문집 Vol.37 No.11
To revitalize the declining downtown, it is necessary to improve the settlement conditions and increase the settlement population. Consequently, this paper proposed a plan for urban regeneration to convert the vacancy of the city office into urban housing and analyzed the solution for securing the legal parking space for the conversion. For the analysis, seven plan prototypes were set up by classifying all offices in the old downtown of Daegu by the number of floors, slenderness ratio, core type, and typical floor area. Based on this, if the entire office vacancy is converted into urban housing, it is required an additional 15-30% of parking, and if it is impossible to expand additional parking within the site, parking space should be secured by utilizing existing urban assets such as underground urban parks and public parking lots. Meanwhile, if an office vacancy is converted into a complex facility that combines residential, neighborhood facilities, office(SOHO), and community facilities, legal parking is satisfied with existing parking space without further expansion. To this end, the parking expansion plan required for the converted housing is necessary for sustainable urban regeneration by facilitating the universal applicability of the office-to-residential conversion and increasing the urban housing rate.
이청용(Qinglong Li),전상홍(Sanghong Jeon),이창재(Changjae Lee),김재경(Jae Kyeong Kim) 한국IT서비스학회 2021 한국IT서비스학회지 Vol.20 No.3
Recently, online job websites have been activated as unemployment problems have emerged as social problems and demand for job openings has increased. However, while the online job platform market is growing, users have difficulty choosing their jobs. When users apply for a job on online job websites, they check various information such as job contents and recruitment conditions to understand the details of the job. When users choose a job, they focus on various details related to the job rather than simply viewing and supporting the job title. However, existing online job websites usually recommend jobs using only quantitative preference information such as ratings. However, if recommendation services are provided using only quantitative information, the recommendation performance is constantly deteriorating. Therefore, job recommendation services should provide personalized services using various information about the job. This study proposes a recommended methodology that improves recommendation performance by elaborating on qualitative preference information, such as details about the job. To this end, this study performs a topic modeling analysis on the job content of the user profile. Also, we apply LDA techniques to explore topics from job content and extract qualitative preferences. Experiments show that the proposed recommendation methodology has better recommendation performance compared to the traditional recommendation methodology.