• 대한치과교정학회지
• /
• 제51권2호
• /
• pp.77-85
• /
• 2021

Objective: To evaluate the accuracy of a multi-stage convolutional neural network (CNN) model-based automated identification system for posteroanterior (PA) cephalometric landmarks. Methods: The multi-stage CNN model was implemented with a personal computer. A total of 430 PA-cephalograms synthesized from cone-beam computed tomography scans (CBCT-PA) were selected as samples. Twenty-three landmarks used for Tweemac analysis were manually identified on all CBCT-PA images by a single examiner. Intra-examiner reproducibility was confirmed by repeating the identification on 85 randomly selected images, which were subsequently set as test data, with a two-week interval before training. For initial learning stage of the multi-stage CNN model, the data from 345 of 430 CBCT-PA images were used, after which the multi-stage CNN model was tested with previous 85 images. The first manual identification on these 85 images was set as a truth ground. The mean radial error (MRE) and successful detection rate (SDR) were calculated to evaluate the errors in manual identification and artificial intelligence (AI) prediction. Results: The AI showed an average MRE of 2.23 ± 2.02 mm with an SDR of 60.88% for errors of 2 mm or lower. However, in a comparison of the repetitive task, the AI predicted landmarks at the same position, while the MRE for the repeated manual identification was 1.31 ± 0.94 mm. Conclusions: Automated identification for CBCT-synthesized PA cephalometric landmarks did not sufficiently achieve the clinically favorable error range of less than 2 mm. However, AI landmark identification on PA cephalograms showed better consistency than manual identification.

• 문화기술의 융합
• /
• 제10권1호
• /
• pp.579-584
• /
• 2024

현재 우리나라는 지하철 선로를 인접하여 대규모, 대심도 굴착시공이 이루어지고 있다. 인접굴착공사 시 흙막이 구조물 및 지하구조물의 안전성 확보가 매우 중요하므로 자동화계측 시스템을 도입하여 지하철에 대한 안전성을 관리하고 있다. 인접굴착공사 시 지하철 궤도 변형은 열차주행안정성에 영향을 미칠 수 있으며, 이는 열차 탈선사고와 연결될 수 있는 인자이다. 그러나 현재 자동화계측 시스템을 이용한 지하철 궤도 안전성평가는 측정된 데이터의 최댓값에만 의존하여, 이상거동을 과소, 과대평가할 수 있는 기법이다. 따라서 자동화계측 시스템 결과의 활용도를 개선시킬 수 있는 방법이 필요한 실정이다. 이에 본 연구에서는 방대한 양의 지하철 궤도 변형 측정결과를 정량적으로 평가할 수 있는 기법인 가우시안 확률밀도함수 분석기법을 이용하여 분석하였다. 방대한 양의 데이터를 확률통계 분석기법을 이용하여 인접굴착공사에 따른 지하철 궤도 변형에 대한 안전성평가를 수행하였다.

• 한국지진공학회논문집
• /
• 제20권4호
• /
• pp.269-276
• /
• 2016

Seismic performance evaluation of existing building usually needs much time and man power, especially in case of nonlinear analysis. Many data interaction steps for model transfer are needed and engineers should spend much time with simple works like data entry. Those time-consuming steps could be reduced by applying computerized and automated modules. In this study, computational platform for seismic performance evaluation was made with several computerized modules. StrAuto and floor load transfer module offers a path that can transfer most linear model data to nonlinear analysis model so that engineers can avoid a lot of repetitive work for input information for the nonlinear analysis model. And the new nonlinear property generator also helps to get the nonlinear data easily by importing data from structural design program. To evaluate the effect of developed modules on each stages, seismic performance evaluation of example building was carried out and the lead time was used for the quantitative evaluation.

• 한국정밀공학회지
• /
• 제13권1호
• /
• pp.38-44
• /
• 1996

The CAD system for design and drawing of limit gauges was constructed and developed. This system was made by Visual Basic program. Using this system, drawings together with concerned data for the manufacturing of limit gauges are generated on the screen, file and printer. The data base was constructed by referring handbooks, textbooks, relevant standards and regulations. This system was proved a powerful tool for design and drawing of limit gauges by actual applications. The output drawings from this system are in good agreement with the drawings and data of the concerned standards and regulations.

• 대한지역사회영양학회지
• /
• 제4권2호
• /
• pp.149-156
• /
• 1999

This study was due to investigate the dietary intakes, serum lipids and other hematological indices in female adolescent smokers. The subjects were 85 smokers, whose average pack-year(smoking years on the basis of one pack of cigarettes per day) was 1.26 and 87 nonsmokers who were female high school students in Seoul. An anthropometric measreument was performed and % body fat was also analyzed by the Bioelectrical Impedance Fatness Analyzer(GIF-891). Dietary intakes and food habits were examined through questionnaires and nutrient intakes were analyzed by the Computer Aided. Nutritional analysis program for professional(CAN-pro). Serum TG, HDL-cholesterol and total-cholesterol levels were measured with test kits. Serum glucose, albumin, GOT and GPT were measured by automated dry chemistry system, SPOTCHEM 4410. Hemoglobin, hematocrit, RBC, WBC and MCV were determined by Semi Automated Microcell Counter(F-520). All data were statistically analyzed by SAS PC package program. There was no significant difference in the anthropometric measurements between smokers and nonsmokers. The caloric intake in adolescent smokers tended to be higher than that of nonsmokers but the difference was not statistically significant. In addition, there was no significant difference between smokers and nonsmokers in biochemical indices. Analysis of serum lipids showed that the serum levels of total-cholesterol and LDL-cholesterol of nonsmokers were unexpectedly significantly higher(p<0.05) than those of smokers. Overall results indicate that smoking itself with short pack-year in healthy female adolescent did not seem to influence apparent health and nutritional status.

• Journal of Welding and Joining
• /
• 제14권4호
• /
• pp.33-42
• /
• 1996

In recent years there has been a significant growth in the use of the automated and/or robotic welding system, carried out as a means of improving productivity and quality, reducing product costs and removing the operator from tedious and potentially hazardous environments. One of the major difficulties with the automated and/or robotic welding process is the inherent lack of mathematical models for determination of suitable welding process parameters. Partial-penetration, single-pass bead-on-plate welds were fabricated in 12mm AS 1204 mild steel flats employing five different welding process parameters. The experimental results were used to develop three empirical equations: curvilinear; polynomial; and linear equations. The results were also employed to find the best mathematical equation under weld bend width to assist in the process control algorithms for the Gas Metal Arc Welding(GMAW) process and to correlate welding process parameters with weld bead width of bead-on-plates deposited. With the help of a standard statistical package program. SAS, multipe regression analysis was undertaken for investigating and modeling the GMAW process, and significance test techniques were applied for the interpretation of the experimental data.

• 말소리와 음성과학
• /
• 제10권4호
• /
• pp.1-10
• /
• 2018

This study introduces an automated Praat script allowing optimal formant analysis for children's vowels. Using Burg's algorithm in Praat, formants can be extracted by setting the maximum formant value and the number of formants. The optimal formant setting was determined by identifying the two conditions, F1 and F2, with minimum standard deviations. When applying the optimal formant setting determined by the script, the results of normality tests were not significant among all vowels except /e/ for the maximum formant value, and among the vowels /a/, /e/, /i/, /o/, /u/ and /ʌ/ for the number of formants. This indicates that when analyzing the formants of children's vowel sounds, the unilateral application of a parameter setting (the maximum formant value and the number of formants) to all vowels is problematic. The performance of the optimal formant setting script was evaluated along with 3 different algorithm in order to determine whether it properly extracts formants for children's vowels. To this end, Korean monophghongs of 6-year-old children were collected and the Praat scripts were applied to the data. Resultant Formant plots and statistical analysis showed that optimum_script and qtone_script, which links to the perceptual unit, performed very well in formant extraction compared to the remaining 2 scripts.

• 한국지능시스템학회논문지
• /
• 제24권3호
• /
• pp.251-258
• /
• 2014

신경계 영상 해석의 목적은 움직이는 미토콘드리아들을 추적하여 그 속도와 이동 방향 등을 추출하는 것인데, 미토콘드리아의 움직임은 축삭돌기 상에서만 이루어지는 특징이 있다. 축삭돌기 추출 작업은 일반적으로 수작업을 동반한 처리 과정을 통해 이루어지고 있는데, 본 논문에서는 자동화된 축삭돌기 추출 기법을 제안한다. 우선 전체 비디오 프레임 영상에서 각 픽셀의 최대값을 취해 통합영상을 구한다. 통합 영상에서 축삭돌기는 능선 구조를 보이는데, 능선을 검출하기 위해 본 연구에서는 능선 강화 필터링과 피크 검출 과정을 적용하였다. 또한 검출된 능선점에서 나타난 오류를 제거하기 위해 대해 각 능선점 주위에서 신뢰도 함수를 사용한 필터링을 적용한다. 실제 영상을 이용한 실험을 통해 제안된 방식은 높은 검출률과 정확도를 나타내는 것을 확인하였다.

• 정보처리학회논문지D
• /
• 제14D권5호
• /
• pp.517-530
• /
• 2007

최근 웹 어플리케이션은 급속도로 성장하였으며, 점점 더 복잡해지고 있다. 웹 어플리케이션이 복잡해질수록 품질에 관련된 다양한 요구사항이 증가하고 있다. 그러나 웹 어플리케이션의 테스트에 관한 연구 및 도구는 매우 부족하다. 이에 본 논문에서는 웹 어플리케이션에 대한 테스트 자동화 기법을 제안한다. 이를 위해 본 논문에서는 HTML 코드와 소스 코트로부터 분석 모델을 생성하고, 이 모델을 기반으로 테스트 대상을 파악하며, 테스트 케이스를 추출한다. 또한 테스트 드라이버와 테스트 데이터를 자동으로 생성하고, 그것들을 서버 내에 자동으로 배치함으로써 매우 쉽게 테스트 환경을 구축한다. 본 논문에서 제안하는 방법은 웹 어플리케이션에 대한 테스트의 전반적인 과정을 자동화하며, 이러한 자동화 방법은 기존의 연구에 비해 웹 어플리케이션의 기능 테스트의 효과를 높일 수 있다는 장점이 있다.

• 융합정보논문지
• /
• 제9권1호
• /
• pp.116-122
• /
• 2019

최근 중소기업은 세계적인 경쟁력을 갖추기 위해서 공정/품질/에너지 데이터 집계가 자동 또는 실시간으로 처리할 수 있는 산업 구조로 급격하게 변화하고 있다. 특히, 중소기업 생산 공정에서 생산되는 실시간 정보 분석은 중소기업의 유의미한 성과들을 분석, 예측, 처방 및 이행하는 새로운 공정 프로세스 형태로 진화해 가고 있다. 본 논문에서는 중소기업에서 생상되는 데이터를 고도화할 수 있도록 중소기업의 자동화 생산 정보 시스템을 빅데이터화 할 수 있는 플랫폼 구축 모델을 제안한다. 제안 모델은 스마트한 중소기업의 데이터 수집을 위해 중소기업에서 생산되는 제품의 기본 정보에 대한 다양한 데이터를 활용해 중소기업의 운영 효율화(컨설팅 및 교육 등) 및 전략적 의사결정을 지원할 수 있는 기능이 있다. 또한, 제안 모델은 종소기업의 정보 공유 및 시스템 연계가 원활하게 서로 다른 지역적 특성 및 분야를 가지는 중소기업들간에 긴밀한 협조가 가능한 것이 특징이다.