• 한국융합학회논문지
• /
• 제10권12호
• /
• pp.29-34
• /
• 2019

유전 알고리즘에서 해의 적합도를 계산하는 시간이 오래 걸린다면 메타모델을 만드는 것은 필수적이다. 이에 메타모델의 성능을 높여 유전 알고리즘이 더 좋을 해를 찾게 하기 위한 연구가 진행되어 왔다. 본 연구에서 우리는 이산적인 도메인에서 이산 월시 변환을 사용해 메타모텔의 성능을 높이고자 하였다. 이산 월시 변환을 통해 해의 기저를 변환했고 변환된 해를 사용해 메타모델을 만들었다. 의사-불리언 함수의 대표적인 함수인 NK 모형을 대상으로 실험했고 제안된 모델의 성능에 대한 실증적인 증거를 제공했다. 제안된 모델을 사용해 유전 알고리즘을 수행했을 때, 유전알고리즘이 더 좋은 해를 찾음을 확인했다. 특히, 선행 연구인 유사도 함수를 이산적인 도메인에 적합하게 수정한 방사기저 함수 네트워크보다 좋은 성능을 보였다.

• 대한영상의학회지
• /
• 제84권1호
• /
• pp.240-252
• /
• 2023

목적 소아 환자에서 두부 컴퓨터단층촬영(이하 CT)에 대한 딥러닝 이미지 재구성(deep learning image reconstruction; 이하 DLIR; TrueFidelity; GE Healthcare, Milwaukee, WI, USA)의 효과를 평가하고자 한다. 대상과 방법 총 126개의 소아 두부 CT 이미지를 수집했으며, adaptive statistical iterative reconstruction (이하 ASiR)-V를 사용한 반복적 재구성 및 세 가지 수준의 DLIR을 사용한 재구성을 시행하였다. 각 이미지 세트 그룹은 환자의 연령에 따라 4개의 그룹으로 구분하였으며 각 연령군의 임상 및 방사선량 관련 데이터를 검토하였다. 양적 매개 변수에는 signal to noise ratio (이하 SNR) 및 contrast to noise ratio (이하 CNR)가 포함되었으며 질적 매개 변수로 영상의 잡음(noise), 회백질의 구분 정도, 선명도, 인공물 및 수용 가능성(acceptability), 영상의 질감이 포함되었고 이에 대한 평가와 비교를 시행하였다. 결과 모든 연령 그룹의 모든 수준의 SNR 및 CNR은 높은 수준의 DLIR 사용 시 증가하였다. ASiR-V와 비교했을 때 높은 수준의 DLIR은 SNR 및 CNR이 개선되었다(p < 0.05). 그리고 DLIR의 수준이 증가될수록 순차적인 잡음 감소, 회백질 구분 개선, 선명도 개선이 나타났다. 이러한 변수들에서 높은 수준의 DLIR 사용 시 ASiR-V와 유사한 정도의 수치가 측정되었다. 인공물과 수용 가능성의 경우에 적용된 DLIR 수준 간에 큰 차이를 보이지 않았다. 결론 소아 두부 CT에 고수준 DLIR을 적용하면 영상의 노이즈를 줄일 수 있으나 인공물 처리에 대한 개선이 필요하다.

• 한국보건간호학회지
• /
• 제19권1호
• /
• pp.74-94
• /
• 2005

The purpose of this study was to compare the effect of education between CAI(Computer Assisted Instruction) and lectures for smoking cessation among male students who attended vocational high schools. Conducted from February 24th to April 26th, 2003, the study design was quasi-experimental with nonequivalent control group pretest-posttest design. The study subjects were 60 male students in K vocational high school in Daegu city, who were present smokers and had more than 7.0 ppm concentration level of carbon monoxide. Thirty students were randomly chosen as the experimental group which applied CAI education method for smoking cessation. The other 30 students served as the control group which received lecture education method of 40 minutes on four consecutive days. CAI education for smoking cessation was composed of ready-made individual learning contents, counseling by using cyber-communication, writing a letter to stop smoking, and writing a written agreement for smoking cessation. Lecture education for smoking cessation was composed of a ready-prepared lecture for the group, writing a letter to stop smoking, and writing a written agreement for smoking cessation. To measure smoking related knowledge, Jeong Ree Roh(1996)'s smoking related knowledge scale$(Cronbach's\;{\alpha}=0.84)$ was modified and used by the researcher. To measure smoking related attitude, Jeong Ree Roh(1996)'s smoking related attitude scale$(Cronbach's\;{\alpha}=0.91)$ was modified and used by the researcher. Smoking related knowledge scale's Cronbach's $\alpha$ was 0.83 in the pilot study and 0.93 in this study. Smoking related attitude scale's Cronbach's a was 0.80 in the pilot study and 0.98 in this study. To determine the smoking amount, the number of cigarettes smoked per day was checked. The concentration level of CO in the exhaled breath was measured (Micro CO Cat. No. MCO2, UK). Data was analyzed by $x^2-test$, t-test, repeated measures ANOVA. simple main effects, and time contrast test with SPSS/Win 11.0 program. The results of this study were as follows: 1. The first hypothesis. that 'Smoking-related knowledge score in the experimental group by using CAI education for smoking cessation will be higher than that in the control group by using lecture education for smoking cessation', was not supported. 2. The second hypothesis, that 'Smoking-related attitude in the experimental group by using CAI education for smoking cessation will be higher than that in the control group by using lecture education for smoking cessation'. was supported(F=6490.79. p=0.000). 3. The third hypothesis. that 'Smoking amount in the experimental group by using CAI education for smoking cessation will be less than that in the control group by using lecture education for smoking cessation'. was supported. 1) The third-1st sub-hypothesis. that 'The number of cigarettes smoked per day in the experimental group by using CAI education for smoking cessation will be less than that in the control group by using lecture education for smoking cessation'. was supported(F=134.19. p=0.000). 2) The third-2nd sub-hypothesis. that 'The concentration level of CO by ppm per one exhaled breath in the experimental group by using CAI education for smoking cessation will be lower than that in the control group by using lecture education for smoking cessation"' was supported(F=268.55. p=0.000). From the above results. CAI education can be an effective intervention to improve smoking-related knowledge and attitude. and to reduce the number of cigarettes smoked per day and the concentration level of CO by ppm per one exhaled breath. Lecture education can be effective to improve smoking-related knowledge. In the future, when CAI education and lecture education for smoking cessation are applied on the school nursing field. the students can gain a comprehensive understanding of smoking cessation, changes in smoking-related knowledge. smoking-related attitude and reducing smoking amount. Furthermore, CAI education for smoking cessation could be developed as an individual self initiative program and could give a guideline to apply CAI education for smoking cessation in other field.

• Korean Journal of Radiology
• /
• 제22권1호
• /
• pp.131-138
• /
• 2021

Objective: Iterative reconstruction degrades image quality. Thus, further advances in image reconstruction are necessary to overcome some limitations of this technique in low-dose computed tomography (LDCT) scan of the chest. Deep-learning image reconstruction (DLIR) is a new method used to reduce dose while maintaining image quality. The purposes of this study was to evaluate image quality and noise of LDCT scan images reconstructed with DLIR and compare with those of images reconstructed with the adaptive statistical iterative reconstruction-Veo at a level of 30% (ASiR-V 30%). Materials and Methods: This retrospective study included 58 patients who underwent LDCT scan for lung cancer screening. Datasets were reconstructed with ASiR-V 30% and DLIR at medium and high levels (DLIR-M and DLIR-H, respectively). The objective image signal and noise, which represented mean attenuation value and standard deviation in Hounsfield units for the lungs, mediastinum, liver, and background air, and subjective image contrast, image noise, and conspicuity of structures were evaluated. The differences between CT scan images subjected to ASiR-V 30%, DLIR-M, and DLIR-H were evaluated. Results: Based on the objective analysis, the image signals did not significantly differ among ASiR-V 30%, DLIR-M, and DLIR-H (p = 0.949, 0.737, 0.366, and 0.358 in the lungs, mediastinum, liver, and background air, respectively). However, the noise was significantly lower in DLIR-M and DLIR-H than in ASiR-V 30% (all p < 0.001). DLIR had higher signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) than ASiR-V 30% (p = 0.027, < 0.001, and < 0.001 in the SNR of the lungs, mediastinum, and liver, respectively; all p < 0.001 in the CNR). According to the subjective analysis, DLIR had higher image contrast and lower image noise than ASiR-V 30% (all p < 0.001). DLIR was superior to ASiR-V 30% in identifying the pulmonary arteries and veins, trachea and bronchi, lymph nodes, and pleura and pericardium (all p < 0.001). Conclusion: DLIR significantly reduced the image noise in chest LDCT scan images compared with ASiR-V 30% while maintaining superior image quality.

• 보건행정학회지
• /
• 제24권2호
• /
• pp.164-171
• /
• 2014

Background: Safety of drugs has become a major issue in public healthcare. Spontaneous reporting of adverse drug reaction (ADR) is the cornerstone in management of drug safety. We aimed to investigate the awareness and knowledge of spontaneous ADR reporting in general public of Korea. Methods: A total of 1,500 study subjects aged 19-69 years were interviewed with a questionnaire for their awareness and knowledge related to spontaneous ADR reporting. Computer assisted telephone interview was performed from 27th February 2013 to 4th March 2013. Target population was selected with quota sampling, using age, sex, and residence area. Healthcare professionals such as physicians, pharmacists, and nurses were excluded. The survey questions included awareness of spontaneous ADR reporting, opinions on ways to activate ADR reporting, and sociodemographic characteristics. Results: Overall awareness of spontaneous ADR reporting system was 8.3% (${\pm}2.53%$) among general population of Korea. Major source from which people got the information regarding ADR reporting was television/radio (69.9%), followed by internet (19.3%), and poster/brochure (6.1%). Awareness level differed between age groups (p<0.0001) and education levels (p<0.0001). Upon learning about the ADR reporting system, 88.5% of study subjects agreed on the necessity of ADR reporting system, while 46.6% thought promotion through internet and mass media as an effective way to activate ADR reporting. Conclusion: The overall awareness of spontaneous ADR reporting should be enhanced in order to establish a firm national system for drug safety. Adequate promotions should be performed targeting lower awareness groups, as well as various publicity activities via effective channels for the general population.

• 정보교육학회논문지
• /
• 제1권1호
• /
• pp.92-101
• /
• 1997

컴퓨터 환경 및 교육 환경의 변화에 따라서 하이퍼미디어 교육용 소프트웨어의 필요성이 증대되고 있으나, 대부분의 제작도구가 다양한 기능을 가지고 있음에도 불구하고 하이퍼미디어 프로그램 지원 지능이 부족하거나 사용법이 불편하다. 또, 제작된 프로그램에서의 새로운 노드의 생성 및 데이터의 추가는 불가능하여, 교수-학습 과정에서 발생하는 각종 학습 자료 및 정보를 누적할 수 없다는 문제점이 있다. 따라서 본 연구에서는 간편하게 하이퍼미디어 교육 자료를 제작하여 교수-학습에 활용할 수 있는 하이퍼미디어 자료 편집기의 모델을 제시하고자 하였다. CAI와 관련된 교수 학습 이론과 하이퍼텍스트 및 하이퍼미디어 관련 이론을 고찰하고, 국내 외의 제작도구의 특징을 분석하여, 편집 모드와 실행 모드가 함께 제공되는 하이퍼미디어 자료편집기를 설계 구현하였다. 본 자료편집기는 자료제시형의 교육용 소프트웨어를 제작 할 수 있도록 설계되었으므로 학생들의 조사 학습을 위한 데이터베이스 구축에 사용될 수 있으며, 사회과 등에서의 활발한 사용이 기대된다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제37권2호
• /
• pp.129-136
• /
• 2010

본 논문에서는 영어 회화 교육을 위한 예제 기반 대화 시스템에 대해 논한다. 기존의 획일적인 멀티미디어 영어 학습에서 벗어나 자연어 처리 및 대화 기술을 이용하여 지능적인 일대일 영어 회화 교육 제공을 목적으로 한다. 본 시스템은 미숙한 학습자 발화를 이해할 수 있으므로 불완전한 언어 구사 능력으로도 대화를 참여할 수 있는 체험형 학습을 제공한다. 이를 통해 학습자에게 영어를 배우려는 흥미로운 동기를 부여한다. 또한 학습자의 표현력 향상을 위한 교육적인 도움 기능을 갖추고 있다. 이를 위해 우리는 학습자의 미숙한 표현을 이해하는 담화 상황 고려 발화의도 인식 모델, 도메인 확장성이 뛰어난 예제 기반 대화 관리 모델, 교육 및 평가 기능을 개발하였다. 실험 결과 학습자의 발화에 에러가 많아도 높은 발화의도 인식 성능을 보였으며 대화 상황에 적합한 피드백을 제공하여 학습자가 회화 연습을 끝까지 마치도록 도와 교육 효과에 이바지함을 알 수 있었다.

• 한국의학물리학회지:의학물리
• /
• 제30권4호
• /
• pp.94-103
• /
• 2019

Purpose: To evaluate the clinical feasibility of knowledge-based planning (KBP) for volumetric-modulated arc radiotherapy (VMAT) in spine stereotactic body radiotherapy (SBRT). Methods: Forty-eight VMAT plans for spine SBRT was studied. Two planning target volumes (PTVs) were defined for simultaneous integrated boost: PTV for boost (PTV-B: 27 Gy/3fractions) and PTV elective (PTV-E: 24 Gy/3fractions). The expert VMAT plans were manually generated by experienced planners. Twenty-six plans were used to train the KBP model using Varian RapidPlan. With the trained KBP model each KBP plan was automatically generated by an individual with little experience and compared with the expert plan (closed-loop validation). Twenty-two plans that had not been used for KBP model training were also compared with the KBP results (open-loop validation). Results: Although the minimal dose of PTV-B and PTV-E was lower and the maximal dose was higher than those of the expert plan, the difference was no larger than 0.7 Gy. In the closed-loop validation, D_1.2cc, D_0.35cc, and D_mean of the spinal cord was decreased by 0.9 Gy, 0.6 Gy, and 0.9 Gy, respectively, in the KBP plans (P<0.05). In the open-loop validation, only D_mean of the spinal cord was significantly decreased, by 0.5 Gy (P<0.05). Conclusions: The dose coverage and uniformity for PTV was slightly worse in the KBP for spine SBRT while the dose to the spinal cord was reduced, but the differences were small. Thus, inexperienced planners could easily generate a clinically feasible plan for spine SBRT by using KBP.

• 디지털융복합연구
• /
• 제18권2호
• /
• pp.285-290
• /
• 2020

본 연구는 워드프로세서를 사용하여 영어텍스트구문을 작성하는 사용자들의 영어작문능력을 개선하는 방안을 제시하고자 한다. 컴퓨터와 IT기술의 발달로 영어작문능력 향상을 위한 컴퓨터보조언어학습이 보편적으로 사용되고 있다. 기존의 프로그램들은 일부 단어의 철자, 접속사의 필요성, 주어-동사의 수일치 등과 같은 몇몇 문법오류사항을 인식하여 표시해주는 기능이 있다. 그러나 사용자가 작성한 영어문장의 적절성에 대한 소수의 오류사항을 알려주고 있지만 영어문장에서 가장 흔하게 사용되고 있는 명사구성립의 적법성에 대한 오류인식은 하지 못하고 있다. 따라서 본 연구는 기존 워드프로세서의 문장오류인식 프로세스에 명사구성립인식 기능을 추가하여 더 나은 오류인식기능을 갖추도록 개선하여 사용자 편의성 및 문장적법성을 향상시키는 방안을 제시한다. 제안 방법은 문장 내에 사용된 명사를 추적하여 해당 명사가 문장요소로 사용되기 위한 최소단위인 명사구성립 여부를 확인하고 그에 따라 오류표기를 하여 사용자가 인식할 수 있도록 해준다. 사용자는 오류사항에 대한 인식을 통해 자신이 작성한 텍스트의 문장 적법성을 확인하고 수정하면서 문장작성 능력 및 적절한 어법의 사용에 대한 이해도가 증가할 것이라 판단된다.

• Smart Structures and Systems
• /
• 제31권4호
• /
• pp.335-349
• /
• 2023

Bridges constantly undergo deterioration and damage, the most common ones being concrete damage and exposed rebar. Periodic inspection of bridges to identify damages can aid in their quick remediation. Likewise, identifying components can provide context for damage assessment and help gauge a bridge's state of interaction with its surroundings. Current inspection techniques rely on manual site visits, which can be time-consuming and costly. More recently, robotic inspection assisted by autonomous data analytics based on Computer Vision (CV) and Artificial Intelligence (AI) has been viewed as a suitable alternative to manual inspection because of its efficiency and accuracy. To aid research in this avenue, this study performs a comparative assessment of different architectures, loss functions, and ensembling strategies for the autonomous segmentation of bridge components and damages. The experiments lead to several interesting discoveries. Nested Reg-UNet architecture is found to outperform five other state-of-the-art architectures in both damage and component segmentation tasks. The architecture is built by combining a Nested UNet style dense configuration with a pretrained RegNet encoder. In terms of the mean Intersection over Union (mIoU) metric, the Nested Reg-UNet architecture provides an improvement of 2.86% on the damage segmentation task and 1.66% on the component segmentation task compared to the state-of-the-art UNet architecture. Furthermore, it is demonstrated that incorporating the Lovasz-Softmax loss function to counter class imbalance can boost performance by 3.44% in the component segmentation task over the most employed alternative, weighted Cross Entropy (wCE). Finally, weighted softmax ensembling is found to be quite effective when used synchronously with the Nested Reg-UNet architecture by providing mIoU improvement of 0.74% in the component segmentation task and 1.14% in the damage segmentation task over a single-architecture baseline. Overall, the best mIoU of 92.50% for the component segmentation task and 84.19% for the damage segmentation task validate the feasibility of these techniques for autonomous bridge component and damage segmentation using RGB images.