• 한국인터넷방송통신학회논문지
• /
• 제9권2호
• /
• pp.1-6
• /
• 2009

많은 양의 데이터로부터 유용성있는 정보의 추출, 진단 및 예후에 대한 결정, 질병 치료의 응용 등은 바이오 인포머틱스(Bioinformatics)분야에서 매우 중요한 문제들이다. 본 논문에서는 암진단시스템에 적용하기위해 support vector machine을 위한 weogjted lernel fuction과 빠른 수렴성과 좋은 분류성능을 갖는 학습방법을 제안하였다. 제안된 kernel function에서 기본적인 kernel fuction의 weights는 암진단 학습단계에서 결정되고 분류단계에서 파리미터로 사용된다. 대장암 데이터와 같은 임상 데이터에 대한 실험결과에서 제안된 방법은 기존의 다른 kernel fuction들 보다 더 우수하고 안정적인 분류성능을 보여주었다.

• 한국컴퓨터정보학회논문지
• /
• 제20권5호
• /
• pp.161-169
• /
• 2015

본 논문에서는 초등 영재들의 IT 융합 학습을 위한 스마트 기기 기반의 로봇 프로그래밍 교육 프로그램을 제안하고, 스마트 기기 기반의 로봇 프로그래밍 교육 이후 초등 영재 수준에 따른 IT 융합 학습에 대한 만족도와 기대-가치 인식 차이를 분석하였다. 초등 영재들의 IT 융합 학습을 위한 스마트 기기 기반의 로봇 프로그래밍 교육 프로그램은 WTEC에서 제안한 인간 융합 과정을 기초로 설계하였으며, 초등 영재들이 실질적인 IT 융합 과정을 경험할 수 있도록 하기 위해서 창의성 단계, 통합 단계, 혁신 단계, 산출 단계로 구성하였다. 본 연구를 통해서 개발된 스마트 기기 기반의 로봇 프로그래밍 교육 프로그램은 초등 영재 126명을 대상으로 적용하였으며 그 결과를 분석하였다. 스마트 기기 기반의 로봇 프로그래밍 교육에 대한 만족도를 분석한 결과, 초등 심화 집단과 초등 기초 집단 모두 높은 수업 만족도를 보이는 것으로 나타났으나, 초등 심화 집단의 수업 만족도가 상대적으로 높은 것으로 나타났다. 또한, 초등 심화 집단이 초등 기초 집단에 비해 IT 융합 학습에 대한 기대-가치 인식이 높은 것으로 나타났다. 본 논문의 2장에서는 IT 융합 학습과 로봇 활용 교육을 분석한 관련 연구를 제시하였으며, 3장에서는 실제 스마트기기 기반의 로봇 프로그래밍 교육 프로그램 설계 및 연구 과정을 기술하였고, 4장에서는 실험 수업 결과를 분석한 연구결과를 제시하였다.

• 한국간호교육학회지
• /
• 제24권2호
• /
• pp.168-180
• /
• 2018

Purpose: The purpose of this study was to explore preceptees' experience among nursing students in the Clinical Nursing Practice program as integral practice. Specific aims were to identify problems students face as preceptees at a clinical practice and how they interact with preceptors and others. Methods: Grounded theory methodology was utilized. Data were collected from interactive field notes and transcribed notes with individual in-depth interview from 12 senior nursing students who had experiences as a preceptee in the Clinical Nursing Practice. Results: Through constant comparative analysis, a core category emerged as "Being refined while taking a firm stand with lack." The process of "Being refined while taking a firm stand with lack" consisted of four phases: sailing phase, adaptation phase, achievement phase and wistful returning phase. Conclusion: The findings of the study indicate that there is a need for nursing students to understand the limitations and strengths to learning experiences in preceptorship. In addition, the Clinical Nursing Practice as an integral practice program is needed to improve nursing capacity and for proper adaptation to real clinical environment among graduating students.

• Educational Technology International
• /
• 제7권2호
• /
• pp.93-106
• /
• 2006

The knowledge-based society increasingly demands professionals possessing essential knowledge, and the ability to use this knowledge effectively in their work settings. In response to the requirement for these professionals, PBL is a promising educational method. This paper suggests an educational development program for faculty to implement problem-based learning(PBL). To implement PBL at the higher educational level, there is a need for a systemic approach. First, a well-designed educational plan for PBL is necessary. Before implementing PBL, both the instructor and the students should be prepared. Faculty members should be well informed on the characteristics of PBL, effective tutoring or facilitation skills, and how to design problems reflecting features of their own academic subject areas. Students also have to know the characteristics of PBL. Both of these groups need to be trained through workshops rather than through lectures. Second, a phase of design and implementation of PBL is necessary. PBL methods may seem to be intuitive and even unstructured because a problem is, in nature, unstructured and authentic. However, a closer look at PBL reveals that it is complex, carefully designed, and highly structured activity. Therefore, if it is poorly and incompletely designed, PBL can be a frustrating and exhausting experience for students and faculty members. Well-designed PBL can be an exhilarating and rewarding experience for both of them. Third, a phase of sharing PBL experiences is important: faculty members who have implemented PBL are required to share their experiences to help others enhance tutoring skills, and acquire practical information of students, contents, and what happened during PBL, and to develop PBL model in a specific domain. Based on the developed PBL model in a specific domain, PBL can be expanded and stabilized at the university level.

• Korean Journal of Radiology
• /
• 제25권4호
• /
• pp.384-394
• /
• 2024

Objective: To evaluate the image quality of novel dark-blood computed tomography angiography (CTA) imaging combined with deep learning reconstruction (DLR) compared to delayed-phase CTA images with hybrid iterative reconstruction (HIR), to visualize the cervical artery wall in patients with Takayasu arteritis (TAK). Materials and Methods: This prospective study continuously recruited 53 patients with TAK (mean age: 33.8 ± 10.2 years; 49 females) between January and July 2022 who underwent head-neck CTA scans. The arterial- and delayed-phase images were reconstructed using HIR and DLR. Subtracted images of the arterial-phase from the delayed-phase were then added to the original delayed-phase using a denoising filter to generate the final-dark-blood images. Qualitative image quality scores and quantitative parameters were obtained and compared among the three groups of images: Delayed-HIR, Dark-blood-HIR, and Dark-blood-DLR. Results: Compared to Delayed-HIR, Dark-blood-HIR images demonstrated higher qualitative scores in terms of vascular wall visualization and diagnostic confidence index (all P < 0.001). These qualitative scores further improved after applying DLR (Dark-blood-DLR compared to Dark-blood-HIR, all P < 0.001). Dark-blood DLR also showed higher scores for overall image noise than Dark-blood-HIR (P < 0.001). In the quantitative analysis, the contrast-to-noise ratio (CNR) values between the vessel wall and lumen for the bilateral common carotid arteries and brachiocephalic trunk were significantly higher on Dark-blood-HIR images than on Delayed-HIR images (all P < 0.05). The CNR values were significantly higher for Dark-blood-DLR than for Dark-blood-HIR in all cervical arteries (all P < 0.001). Conclusion: Compared with Delayed-HIR CTA, the dark-blood method combined with DLR improved CTA image quality and enhanced visualization of the cervical artery wall in patients with TAK.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제6권2호
• /
• pp.105-109
• /
• 2006

In this paper, we constructed a two-phase spam-mail filtering system based on the lexical and conceptual information. There are two kinds of information that can distinguish the spam mail from the ham (non-spam) mail. The definite information is the mail sender's information, URL, a certain spam keyword list, and the less definite information is the word list and concept codes extracted from the mail body. We first classified the spam mail by using the definite information, and then used the less definite information. We used the lexical information and concept codes contained in the email body for SVM learning in the 2nd phase. According to our results the ham misclassification rate was reduced if more lexical information was used as features, and the spam misclassification rate was reduced when the concept codes were included in features as well.

• 대한간호학회지
• /
• 제30권2호
• /
• pp.514-526
• /
• 2000

The active treatment phase in preparation for bone marrow transplantation(BMT) of che- motherapy regimen and total body irradiation (TBI) containing regimen requires considerable teaching. There have been researches that are related to treatment onto BMT patients and to psychological change during BMT process. However, it was hard to find researches focused on learning needs of patients undergoing BMT. The purpose of this study was to provide the basic data for effective educational program about BMT by investigating the learning needs in patients undergoing BMT. The subjects consisted of 90 BMT patients have been admitted to the department of BMT at three university hospitals. Data were obtained from October 1998 to March 1999 and analyzed by SAS program for unpaired t-test, ANOVA, Duncan test. The results were as follows : 1. Learning needs related to demographic characteristics was identified as below. That of male was higher than that of female. That of under age 29, unmarried, religious and university graduated group was higher than that of opposite group but it didn't show significant difference. Learning needs of group of patients who were employed was significantly higher then that of unemployed patients. 2. According to types of diagnosis, learning needs of myelodysplastic syndrome(MDS) patients was the higher than that of others, but admission frequency was the least. Learning needs of unrelated matched BMT(UBMT) patients was higher than that of autologous BMT patients. However, it didn't show significant difference. With regard to learning needs according to process of BMT, learning needs of Pre- BMT period or Post-BMT period was significantly higher than that of BMT day. 3. Learning needs related to BMT was relatively high (total mean: 3.11 of 4.0). The order of the mean score of leaning needs was shown as follows : Restricted activities after discharge, Relapse symptom, Complications of BMT, Kinds of available drugs at home. Therefore the learning needs that is related to life after discharge and to relapse and complications after BMT was high. 4. Learning needs related to radiation therapy was high (total mean: 3.35 of 4.0). The learning needs in radiation therapy items was the Skin care of radiation therapy and Purpose of radiation therapy. 5. Learning needs related to graft versus host disease(GVHD) therapy was high (total mean: 3.55 of 4.0). The highest learning needs in GVHD therapy items was the Preventive method GVHD. less admission frequency and UBMT patients. It is necessary that education for BMT patients should be focused on life after discharge and on relapse and complications after BMT. Especially education for allogeneic BMT patients should be emphasized on GVHD. For all of these, it is necessary to develop systematic and concrete educational program.

• 공학교육연구
• /
• 제19권1호
• /
• pp.37-46
• /
• 2016

The purposes of the study were to examine engineering students' concerns and problems while they were choosing a project topic in interdisciplinary collaboration and to suggest ways to support them in an early stage of collaboration phase. To answer the research questions, we conducted a case study with engineering participants in GCTI 2015, an interdisciplinary collaborative and creative group project. Multiple data sources including focus group interviews, online survey and researchers' observation notes were used to triangulate research findings. We found four main concerns of engineering students. These concerns include (1) lack of self-efficacy, (2) limited resources, (3) lack of shared, meaningful, and common goals, and (4) lack of content knowledge. Based on these concerns we proposed four supports in an early stage of the collaborative project. These supports includes (1) implementing an orientation program, (2) providing opportunities for social interactions, (3) providing expert feedback, and (4) providing consultation for team building.

• ETRI Journal
• /
• 제46권2호
• /
• pp.165-174
• /
• 2024

We propose a method to suppress the speckle noise and blur effects of the light field extracted from a hologram using a deep-learning technique. The light field can be extracted by bandpass filtering in the hologram's frequency domain. The extracted light field has reduced spatial resolution owing to the limited passband size of the bandpass filter and the blurring that occurs when the object is far from the hologram plane and also contains speckle noise caused by the random phase distribution of the three-dimensional object surface. These limitations degrade the reconstruction quality of the hologram resynthesized using the extracted light field. In the proposed method, a deep-learning model based on a generative adversarial network is designed to suppress speckle noise and blurring, resulting in improved quality of the light field extracted from the hologram. The model is trained using pairs of original two-dimensional images and their corresponding light-field data extracted from the complex field generated by the images. Validation of the proposed method is performed using light-field data extracted from holograms of objects with single and multiple depths and mesh-based computer-generated holograms.

• Nuclear Engineering and Technology
• /
• 제52권2호
• /
• pp.287-295
• /
• 2020

Group method of data handling (GMDH) is considered one of the earliest deep learning methods. Deep learning gained additional interest in today's applications due to its capability to handle complex and high dimensional problems. In this study, multi-layer GMDH networks are used to perform uncertainty quantification (UQ) and sensitivity analysis (SA) of nuclear reactor simulations. GMDH is utilized as a surrogate/metamodel to replace high fidelity computer models with cheap-to-evaluate surrogate models, which facilitate UQ and SA tasks (e.g. variance decomposition, uncertainty propagation, etc.). GMDH performance is validated through two UQ applications in reactor simulations: (1) low dimensional input space (two-phase flow in a reactor channel), and (2) high dimensional space (8-group homogenized cross-sections). In both applications, GMDH networks show very good performance with small mean absolute and squared errors as well as high accuracy in capturing the target variance. GMDH is utilized afterward to perform UQ tasks such as variance decomposition through Sobol indices, and GMDH-based uncertainty propagation with large number of samples. GMDH performance is also compared to other surrogates including Gaussian processes and polynomial chaos expansions. The comparison shows that GMDH has competitive performance with the other methods for the low dimensional problem, and reliable performance for the high dimensional problem.