• 한국컴퓨터정보학회논문지
• /
• 제26권12호
• /
• pp.11-18
• /
• 2021

본 논문에서는 함포 사격 정확도를 향상시키기 위해 표적 위치 예측과 사격 오차 도출에서의 딥러닝 알고리즘 적용 가능성을 연구하였다. 표적 위치 예측 시 딥러닝 알고리즘의 하나인 LSTM 모델과 RN 구조를 적용했을 때 좀 더 정밀한 표적 위치를 예측할 수 있다는 가능성을 확인하고 모델을 설계하였다. 사격 오차 도출 시 사격제원 계산에 영향을 끼치는 요소들을 데이터 셋으로 관리하며, GAN을 사용하여 데이터 셋을 생성 후 강화 학습을 진행하여 사격 오차를 줄일 수 있는 모델을 설계하였다. 2가지 모델을 결합하여 사격 정확도를 향상시키기 위한 딥러닝 기반의 사격제원 계산 모델을 설계하였다.

• 한국항공우주학회지
• /
• 제39권9호
• /
• pp.839-847
• /
• 2011

이 논문에서는 포탄의 정밀도 향상을 위한 새로운 유도기법을 제안한다. 미사일 연구에서 널리 사용되고 있는 비례항법 유도기법은 몇 가지의 문제점 때문에 포탄에 적용하기는 힘들다. 비행 중 발생하는 시선각의 변화 때문에 탄착 오차가 없는 경우에도 가속도 명령을 생성하며, 가속도 명령에 의해 만들어지는 비행경로 또한 포탄에 적용이 불가능하다. 이러한 문제를 해결하기 위해 표적과 포탄의 탄착점 오차를 이용하여 유도 기법을 구성하였다. 기본 구성은 비례항법 유도기법과 유사하지만 시선각 변화 대신 경로 수정각을 사용한다. 경로 수정각은 현재 속도와 표적을 향하는 속도의 사이각이며 탄착점 오차로 추정할 수 있다. 탄착점 예측 속도와 정확도를 높이기 위해 신경회로망을 사용하였으며 비례항법 유도기법 결과와 비교하여 이 유도 기법의 적합성을 검증하였다.

• International Journal of Knowledge Content Development & Technology
• /
• 제5권2호
• /
• pp.75-101
• /
• 2015

In this paper, we investigate the notion of error correction memory applied to technical texts. The main purpose is to introduce flexibility and context sensitivity in the detection and the correction of errors related to Constrained Natural Language (CNL) principles. This is realized by enhancing error detection paired with relatively generic correction patterns and contextual correction recommendations. Patterns are induced from previous corrections made by technical writers for a given type of text. The impact of such an error correction memory is also investigated from the point of view of the technical writer's cognitive activity. The notion of error correction memory is developed within the framework of the LELIE project an experiment is carried out on the case of fuzzy lexical items and negation, which are both major problems in technical writing. Language processing and knowledge representation aspects are developed together with evaluation directions.

• 대한원격탐사학회지
• /
• 제33권4호
• /
• pp.445-454
• /
• 2017

The performance of spatial downscaling models depends on the quality of input coarse scale products. Thus, the impact of intrinsic errors contained in coarse scale satellite products on predictive performance should be properly assessed in parallel with the development of advanced downscaling models. Such an assessment is the main objective of this paper. Based on a synthetic satellite precipitation product at a coarse scale generated from rain gauge data, two synthetic precipitation products with different amounts of error were generated and used as inputs for spatial downscaling. Geographically weighted regression, which typically has very high explanatory power, was selected as the trend component estimation model, and area-to-point kriging was applied for residual correction in the spatial downscaling experiment. When errors in the coarse scale product were greater, the trend component estimates were much more susceptible to errors. But residual correction could reduce the impact of the erroneous trend component estimates, which improved the predictive performance. However, residual correction could not improve predictive performance significantly when substantial errors were contained in the input coarse scale data. Therefore, the development of advanced spatial downscaling models should be focused on correction of intrinsic errors in the coarse scale satellite product if a priori error information could be available, rather than on the application of advanced regression models with high explanatory power.

• 환경영향평가
• /
• 제14권5호
• /
• pp.247-254
• /
• 2005

Road traffic noise has increasing broader effects on urban areas as well as rural areas because of rapidly increasing traffic volume and newly-constructed roads. 10 sites in building development areas were selected and the noise level were measured by the apartment floors and by the various block plans of apartment complex. Analysis result, about correction factor, in the case of right angle arrangement, apply - 2.5dB(A). In the case of apartment house correlation of each floor apply 1st floors 0dB(A), 2st floors 1.2dB(A), 3st floors 2.1dB(A), 4st floors 2.6dB(A), 5st floors 2.7dB(A), 6st floors 2.7dB(A), 7st floors 2.4dB(A), 8st floors 2.0dB(A), 9st floors 1.6dB(A), 10st floors 1.1dB(A), 13st floors 0.2dB(A), 15st floors 0.5dB(A). The level of road traffic noise in the arrangement construction of right angle was about 3.0dB(A) at N-4 point and 2.1dB(A) at N-6 point lower than that of a plan figure, respectively. The results suggested that application of correction coefficient obtained by the apartment floor and by the arrangement construction can be improved in road traffic noise. The results suggested that application of correction coefficient obtained by the apartment floor and by the arrangement construction can be improved in road traffic noise.

• 정보관리연구
• /
• 제21권1호
• /
• pp.76-92
• /
• 1990

본고(本稿)는 서지(書誌) 데이터베이스제작(製作)과 정보검색관점(情報檢索觀點)에서 자동철자교정(自動綴字校正)에 대(對)하여 논(論)한다. 여기에는 흔히 발견되는 철자오류(綴字誤謬)의 유형(類型)과 서지(書誌) 데이터베이스내(內)의 철자오류(綴字誤謬)가 미치는 영향(影響)에 대하여 기술(記述)하고 있으며, 자동철자교정(自動綴字校正)시스템의 일반적 구성에 관해서는 문서(文書)의 정규화, 철자검증(綴字檢證), 철자교정(綴字校正), 사용자(使用者) 인터페이스로 나누어 기술(記述)하고 있다.

• 전자공학회논문지
• /
• 제50권7호
• /
• pp.231-235
• /
• 2013

Lens distortions have a significant impact on captured or projected image geometry. This paper proposes a lens distortion correction with gradient components for wide-angle lenses. In most cases, distortion coefficients are estimated using a distortion model by point correspondences. Corrected images using only point correspondences can be compensated excessively, therefore, producing bended lines into the opposite direction near the corners. To curtail these phenomena, we propose to adopt the gradient components in addition to positions to obtain the distortion coefficients. We verified the improved accuracy and the straightness of the proposed method through experimentation.

• Journal of Welding and Joining
• /
• 제11권1호
• /
• pp.42-51
• /
• 1993

In this study, investigations were conducted in calculating parameters of elastic-plastic fracture mechanics using single specimen. The validity of these testing methods was judged by the confirmation of multiple specimen method of stop block test. The results were as follows: In order to measure a fracture toughness using the instrumented impact test, two general requirement must be considered; One, setting up proper impact velocity considered the effect of loading and the other, the necessity of low blow test for obtaining true energy by the compliance correction. It was possible to detect a crack initiation point by calculating the compliance changing rate from a load-defection curve. Criterion of a stable crack growth, $T_{mat}$ could be estimated by using key-curve method for a base metal. and combining Kaiser's rebound compliance with Paris-Hutchison's $T_{appl}$ equation for the brittled zone of welding heat affected.at affected.d.

• 환경영향평가
• /
• 제15권2호
• /
• pp.93-100
• /
• 2006

In general, the verification to prediction formula in a national road and the main street of a town has been used recklessly in Korea. Therefore we investigated the validity of an existing prediction formula (NIER(87, 99), TR-Noise, KLC(2002)) with correction relationship which was based on both the prediction formular from apartment complex in the field and height 1.5m from the surface level. On the results of measuring the noise level form an isolated distance, the noise level showed that it was 4.5~5.5dB(A) by reason of becoming 2 folder far from a source. From the distribution of noise level measured by the apartment floors, the measurement point (1st floor) was 58.7~71.4dB(A) at its lowest level and the middle floors (3, 5, 7 and 10) were the highest distribution of noise level. From the analysis results on the application validity to an existing prediction formular (NIER(87, 99), TR-Noise, KLC(2002)) in the height 1.5m, the correction coefficients were 0.95~0.96 and the measured values were reasonably close to the predicted values, indicating the validity and adequacy of the predicted models. KLC(2002) model was found accurate within 3dB(A) with 36 data out of the total 42 data, showing the most accuracy among the predict models. However, the developed models have to improve the accuracy with a various of factors.

• 한국의학물리학회지:의학물리
• /
• 제15권3호
• /
• pp.149-155
• /
• 2004

목적: 전립선암의 세기조절 방사선 치료 시, 조직의 밀도보정 여부가 선량분포에 끼치는 영향을 연구한다. 재료 및 방법: 5명의 전립선 암 환자에 대하여 6 MV와 10 MV의 광자선에 대하여 각각 치료계획을 수립하였다. 각각 의 계획에서 7개의 조사선이 설정되었고, 선량계산 시에는 체조직의 밀도의 불균일성을 무시하였다. 선량 처방점인 회전중심점에서의 흡수선량과 계획표적용적(PTV)의 최대선량, 최소선량, 평균선량과 처방점선량의 95% 이상의 받는 부피(V>$_{p95%}$) 등을 측정하였다. 직장과 방광 내에서의 최대선량, 최소선량, 최방선량의 50%, 75%, 90% 이상을 받는 부피를 측정하였다. 동일한 조건에서 조직의 밀도 불균일성을 포함하여 선량분포를 재계산하고, 측정한 모든 물리량을 재 측정하였다. 결과: 밀도보정을 함으로써, 처방점에서의 흡수 선량은 6 MV에서 평균 4.9% 10 MV에서는 평균 4% 감소하였다. V>$_{p95%}$는 6 MV와 10 MV에서 각각 0.8%와 0.9% 감소하였다. PTV의 평균 흡수 선량은 6 MV와 10 MV에서 각각 4.2% 와 3.4% 감소하였다. 직장과 방광에서의 흡수선량은 약 l～2%의 차이를 보였다 결론: 전립선암의 세기변조 방사선치료시에 밀도보정을 무시하는 것은 표적에는 고려할 만한 선량의 차이를 유발하며, 주위의 위험장기에 미치는 영향은 미미하다.