• Journal of Korea Multimedia Society
• /
• v.13 no.4
• /
• pp.496-503
• /
• 2010

Speech recognition system is developed of standalone, In case of a mobile terminal using that low recognition rate represent because of limitation of memory size and audio compression. This study suggest vocabulary recognition highest performance improvement system for separate acoustic search and lexical search. Acoustic search is carry out in mobile terminal, lexical search is carry out in server processing system. feature vector of speech signal extract using GMM a phoneme execution, recognition a phoneme list transmission server using Lexical Tree Search algorithm lexical search recognition execution. System performance as a result of represent vocabulary dependence recognition rate of 98.01%, vocabulary independence recognition rate of 97.71%, represent recognition speed of 1.58 second.

• Journal of radiological science and technology
• /
• v.39 no.4
• /
• pp.509-516
• /
• 2016

A dental panoramic radiography which usually uses low level X-rays is subject to the Nuclear Safety Act when it is installed for the purpose of education. This paper measures radiation dose and spatial dose rate by usage and thereby aims to verify the effectiveness of radiation safety equipment and provide basic information for radiation safety of radiation workers and students. After glass dosimeter (GD-352M) is attached to direct exposure area, the teeth, and indirect exposure area, the eye lens and the thyroid, on the dental radiography head phantom, these exposure areas are measured. Then, after dividing the horizontal into a $45^{\circ}$, it is separated into seven directions which all includes 30, 60, 90, 120 cm distance. The paper shows that the spatial dose rate is the highest at 30 cm and declines as the distance increases. At 30 cm, the spatial dose rate around the starting area of rotation is $3,840{\mu}Sv/h$, which is four times higher than the lowest level $778{\mu}Sv/h$. Furthermore, the spatial dose rate was $408{\mu}Sv/h$ on average at the distance of 60 cm where radiation workers can be located. From a conservative point of view, It is possible to avoid needless exposure to radiation for the purpose of education. However, in case that an unintended exposure to radiation happens within a radiation controlled area, it is still necessary to educate radiation safety. But according to the current Medical Service Act, in medical institutions, even if they are not installed, the equipment such as interlock are obliged by the Nuclear Safety Law, considering that the spatial dose rate of the educational dental panoramic radiography room is low. It seems to be excessive regulation.

• Journal of Korean Society for Geospatial Information Science
• /
• v.4 no.2 s.8
• /
• pp.137-147
• /
• 1996

In this paper, the performances between maximum likelihood classifier based on statistical classification and multilayer perceptrons based on neural network approaches were compared and evaluated Experimental results from both neural network method and statistical method are presented. In addition, the nature of two different approches are analyzed based on the experiments.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.04a
• /
• pp.273-276
• /
• 2005

본 논문은 고유얼굴 방법을 이용한 얼굴인식 시스템의 성능을 분석하였다. 제안한 고유얼굴을 이용한 얼굴인식 방법은 훈련집합의 얼굴 이미지 사이의 중요한 변화를 가지고 있는 특징공간으로 투영시키면서 이루어진다. 중요한 특징들은 얼굴집합의 고유벡터(주성분)들이기 때문에 고유얼굴이라 한다. 특징 공간으로의 투영은 고유얼굴의 가중치의 합으로 입력얼굴을 기술할 수 있으며, 입력 얼굴의 인식은 훈련집합의 가중치와 입력 영상의 가중치를 비교하면서 이루어진다. 본 논문에서는 제안된 방법의 검증을 위해서 Harvard 데이터베이스를 이용하였으며, 시스템의 성능 분석을 위하여 조명에 대한 인식성능의 변화, 사용한 고유얼굴의 수에 대한 인식률의 변화, 전처리를 통하여 얻을 수 있는 인식률의 변화, 인식 거부 곡선을 통하여 시스템의 적용 가능성에 대한 실험을 수행하여 분석한다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.460-460
• /
• 2017

본 연구에서는 규모가 비슷한 두 개 댐의 홍수조절 경향성과 영향을 시공간적으로 분석하고 하류에 미친 영향에 대해 조사하였다. 이를 위해 낙동강 유역의 안동댐과 임하댐을 선정하였다. 댐 하류에 위치하여 직접적인 영향을 받는 성주 수위관측소를 기준으로 하였다. 성주 수위관측소의 시작은 1995년 3월로, 이를 기준으로 2010까지의 31개 홍수 사상에 대해 홍수조절 능력과 영향을 검토하였다. 홍수사상의 관측치를 기준으로 한강홍수통제소에서 사용하고 있는 저류함수법을 활용하였다. 관측치에 대한 모의를 통해 매개변수를 최적화하고 이를 기준으로 자연상태의 홍수 발생량을 측정하였다. 성주 수위관측소를 중심으로 홍수 조절에 대한 댐 영향을 유역면적의 비와 홍수저감률의 관계로 분석하였으며 수위관측소의 평균저감률과 유역면적의 비와 비교하였다. 댐 운영에 따른 Resevoir Index (RI)를 활용하여 댐에 따른 하류지점에서의 영향성을 분석하였으며 홍수저감 효과를 분석하고 이를 한강유역에서 분석한 자료와 비교 분석하여 분석의 유사성을 통해 다른 유역에 대한 적용 가능성을 제시하고자 한다.

• Journal of Digital Convergence
• /
• v.11 no.11
• /
• pp.367-372
• /
• 2013

In general, Levenshtein distance algorithm have a problem with not distinguish the consideration of vacabulary retrieve, because Levenshtein methode is used to vocabulary order are not defined. In this paper, we propose a improved Levenshtein methode, it effectively manage the vocabulary retrieve by frequency use of a vocabulary, and it gives the weight number which have a order between vocabularies. Therefore proposed methode have a advantage of solve the defect of perception rate in the case of increase the vocabulary, improve the recognition time become higher and it can be effectively retrieval space management.. System performance as a result of represent vocabulary dependence recognition rate of 97.81%, vocabulary independence recognition rate of 96.91% in indoor environment. Also, vocabulary dependence recognition rate of 91.11%, vocabulary independence recognition rate of 90.01% in outdoor environment.

• The KIPS Transactions:PartD
• /
• v.11D no.1
• /
• pp.23-30
• /
• 2004

In order to approximate the spatial query result size we partition the input rectangles into subsets and estimate the query result size based on the partitioned spatial area. In this paper we examine query result size estimation in skewed data. We examine the existing spatial partitioning techniques such as equi-area and equi-count partitioning, which are analogous to the equi-width and equi-height histograms used in relational databases, and examine the other partitioning techniques based on spatial indexing. In this paper we propose a new spatial partitioning technique based on the Hilbert space filling curve. We present a detailed experimental evaluation comparing the proposed technique and the existing techniques using synthetic as well as real-life datasets. The experiments showed that the proposed partitioning technique based on the Hilbert space filling curve achieves better query result size estimation than the existing techniques for space query size, bucket numbers, skewed data, and spatial data size.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.23 no.6
• /
• pp.577-587
• /
• 2021

Room and Pillar method is an underground facility construction method that maximizes the strength of the in-situ ground. In order to secure the safety of the underground space, it is necessary to secure the safety of the room actually used in addition to the safety of pillar of the room and Pillar method. In this study, the evaluation method for the safety of the room and rock pillar in the room and pillar method was studied through numerical analysis. Numerical analysis was performed for a total of 125 cases using ground conditions, pillar width, and room width as parameters, and the results were derived. As for the safety factor of the pillar, it was confirmed that the safety factor increased when the strength of the ground increased, and it was confirmed that the increment in the safety factor decreased when the width of the pillar was widened. The room strain was evaluated by applying the Critical strain. As the width of the pillar became narrower, the Critical strain was higher, and as the width of the room became smaller, the Critical strain was smaller. As a result of the correlation analysis between the safety factor of the pillar and the room strain, it was possible to derive the upper limit of the room strain that can secure the standard safety factor of the pillar according to the width of the pillar. It is judged that the results derived from this study can be used as a guideline to secure the safety of the room when the actual design is performed in consideration of the ground conditions and room width.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.11a
• /
• pp.1523-1526
• /
• 2005

본 논문에서는 현실 세계에서 사용되고 있는 디지털 오디오 파일들을 사용하여 전통적인 파일시스템에서의 클러스터 크기들이 파일시스템의 입출력 처리시간 및 공간 사용률 등의 성능 요소에 미치는 영향들을 분석하고 이를 디지털 오디오 파일의 특성에 맞게 개선함으로써, 임베디드 오디오 파일시스템의 클러스터 크기에 관한 개선된 디자인을 제시하고자 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.11a
• /
• pp.824-826
• /
• 2010

컴퓨터의 활용도가 높아지면서 자연스럽게 컴퓨터에 따른 입력 장치도 사용이 잦아지고 있는 추세이다. 본 논문에서 다루고 있는 핸드 트랙킹 인터랙션 시스템(Hand-Tracking Interaction System)이란 캠에 사람의 손을 인식시켜 손의 모션에 기능을 부여하는 또 다른 차세대 입력 장치이다. 본 논문에서는 현재 사용하고 있는 마우스와 키보드 같은 입력 장치의 공간 제약성 이라는 단점을 보완하기 위해 핸드 트랙킹 인터랙션 시스템 (Hand-Tracking Interaction System) 을 개발하였고, 빛과 그림자의 영향을 쉽게 받아 손 인식률이 낮아지는 단점을 해결하기 위해 캠 대신 적외선카메라를 이용하여 인식률을 높임에 힘썼다. 또 핸드 트랙킹 인터랙션 시스템을 효율적으로 사용할 수 있는 새로운 어플리케이션을 함께 개발하였다.