• Bulletin of the Korean Chemical Society
• /
• 제31권8호
• /
• pp.2163-2169
• /
• 2010

G-protein coupled receptors (GPCRs) are involved in a wide variety of physiological processes and are known to be targets for nearly 50% of drugs. The various functions of GPCRs are affected by their cognate ligands which are mainly classified as agonists and antagonists. The purpose of this study is to develop a Bayesian classification model, that can predict a compound as either human GPCR agonist or antagonist. Total 6627 compounds experimentally determined as either GPCR agonists or antagonists covering all the classes of GPCRs were gathered to comprise the dataset. This model distinguishes GPCR agonists from GPCR antagonists by using chemical fingerprint, FCFP_6. The model revealed distinctive structural characteristics between agonistic and antagonistic compounds: in general, 1) GPCR agonists were flexible and had aliphatic amines, and 2) GPCR antagonists had planar groups and aromatic amines. This model showed very good discriminative ability in general, with pretty good discriminant statistics for the training set (accuracy: 90.1%) and a good predictive ability for the test set (accuracy: 89.2%). Also, receiver operating characteristic (ROC) plot showed the area under the curve (AUC) to be 0.957, and Matthew's Correlation Coefficient (MCC) value was 0.803. The quality of our model suggests that it could aid to classify the compounds as either GPCR agonists or antagonists, especially in the early stages of the drug discovery process.

• PNF and Movement
• /
• 제12권2호
• /
• pp.107-113
• /
• 2014

Purpose: The objective of this study was to identify functional problems, including walking ability, of patients with strokes using the International Classification of Functioning, Disability, and Health (ICF) and to present a method that could solve functional problems, thereby determining the applicability of the ICF to increase the quality of evaluation and intervention in clinical fields in the future. Methods: Information on stroke patients who were admitted and treated in a hospital was collected. The authors conducted evaluations, interventions, and measurements of the results of the ICF tool in order to improve gait abilities of patients. The subjects were trained using proprioceptive neuromuscular facilitation (PNF) one hour a day and five times a week for four weeks. The result measurement variables were a six-minute gait test, 10 m velocity test, gait instability test, and measurements using the ICF sheet. Results: In the six-minute gait test, gait distance increased by 48 m, from 102 m to 150 m. The gait velocity test result showed an improvement from 0.36m/s to 0.44m/s. The subjects performed a gait instabilitytestwithacupfilledwith50mmwater. In the gait instability test, the amount of water was 38 mm before the intervention; however, it was 50 mm after the intervention. The gait velocity with a cup filled with water improved from 0.25m/s to 0.31m/s. Conclusion: An evaluation and intervention were designed with the ICF tool for stroke patients. Gait abilities improved when the PNF technique was used. The IFC method can be used for evaluation and intervention, and it could help improve gait abilities of stroke patients.

• 융합신호처리학회논문지
• /
• 제22권3호
• /
• pp.110-115
• /
• 2021

4차 산업혁명 시대가 도래하면서 인공지능에 대한 교육이 활발하게 진행되고 있다. 그러나 기존의 강의식 교육은 지식의 전달을 목적으로 두고 있어 인공지능 분야에서 요구하는 능동적인 문제해결 능력과 인공지능 활용능력을 기르는 데 어려움을 겪는다. 본 논문에서는 이를 해결하기 위해 학습자가 제시된 문제를 해결하는 과정에서 학습이 이루어지는 문제 중심학습 기반 교육 방안을 제안한다. 학습자들에게 제공되는 문제는 완성된 하나의 프로젝트이다. 이 프로젝트는 3가지 종류로 구성된다. 분류 모델, 분류 모델의 학습 데이터, 분류된 결과에 따라 실행될 블록 코드. 해당 프로젝트는 동작은 하지만 각각의 구성요소들이 낮은 동작 수준을 보이도록 설계되어 있다. 이를 해결하기 위해 학습자들은 테스팅을 통해 프로젝트의 문제점을 찾고 토론을 통해 해결책을 찾아 좀 더 높은 동작 수준으로 개선하는 과정을 거치며 컴퓨팅 사고력 향상을 기대할 수 있다.

• 대한이식학회지
• /
• 제31권4호
• /
• pp.170-176
• /
• 2017

We need to establish an informative guideline to increase inter-institutional and inter-observer reproducibility of renal transplant diagnosis, and to improve the diagnostic ability of pathologists in Korea. A first nation-wide survey for renal transplant pathology was conducted by Renal Pathology Study Group of the Korean Society of Pathologists in 2016, to provide the continued excellence in the transplantation pathology laboratory, and to improve the diagnostic ability for the best treatment of transplant patients. This survey revealed the significant variations in scale, work load and biopsy indications for the renal transplant pathology in various institutions in Korea. The Banff classification were used by all institutions for the diagnosis of renal transplant pathology, but different formats were used: most institutions (70%) used the "2013 Banff classification" while the others were using "2007 Banff classification" (20%) or even older formats. In daily diagnostic practice of the renal allografts, difficulties that pathologists encounter were quite diverse due to different environments they work in. Most respondents agreed that standardized diagnostic practice guidelines, regular education on renal transplant pathology and convenient ways of consultation are further needed. We are currently working toward the enhancement of the expertise of renal pathologists and to increase inter-institutional and inter-observer reproducibility by 1) development of a set of virtual slides of renal allograft biopsies for the training, 2) validation and gathering expert's consensus on the core variables of rejection diagnosis by using virtual slides, and 3) continued education by the developed virtual slide atlas.

• International Journal of Computer Science & Network Security
• /
• 제24권5호
• /
• pp.53-63
• /
• 2024

Alzheimer's disease is a brain disorder that worsens over time and affects millions of people around the world. It leads to a gradual deterioration in memory, thinking ability, and behavioral and social skills until the person loses his ability to adapt to society. Technological progress in medical imaging and the use of artificial intelligence, has provided the possibility of detecting Alzheimer's disease through medical images such as magnetic resonance imaging (MRI). However, Deep learning algorithms, especially convolutional neural networks (CNNs), have shown great success in analyzing medical images for disease diagnosis and classification. Where CNNs can recognize patterns and objects from images, which makes them ideally suited for this study. In this paper, we proposed to compare the performances of Alzheimer's disease detection by using two deep learning methods: You Only Look Once (YOLO), a CNN-enabled object recognition algorithm, and Visual Geometry Group (VGG16) which is a type of deep convolutional neural network primarily used for image classification. We will compare our results using these modern models Instead of using CNN only like the previous research. In addition, the results showed different levels of accuracy for the various versions of YOLO and the VGG16 model. YOLO v5 reached 56.4% accuracy at 50 epochs and 61.5% accuracy at 100 epochs. YOLO v8, which is for classification, reached 84% accuracy overall at 100 epochs. YOLO v9, which is for object detection overall accuracy of 84.6%. The VGG16 model reached 99% accuracy for training after 25 epochs but only 78% accuracy for testing. Hence, the best model overall is YOLO v9, with the highest overall accuracy of 86.1%.

• 대한토목학회논문집
• /
• 제26권5D호
• /
• pp.885-894
• /
• 2006

본 논문의 의도는 하이퍼스펙트럴 영상의 다량의 밴드를 사용하면서도 효율적인 분류기법의 개발에 초점을 두고 있다. 본 연구에서는 하이퍼스펙트럴 영상의 분류에 있어 이론적으로 밴드수가 많아질수록 분류정확도가 높을 것이라 예상되는, 다변량 통계분석기법중의 하나인 정준상관분석을 적용한 분류기법을 제안한다. 그리고 기존의 대표적인 전통적 분류기법인 최대 우도분류 방법과 비교한다. 사용되는 하이퍼스펙트럴 영상은 2001년 9월 2일 취득된 EO1-Hyperion 영상이다. 실험을 위한 밴드수는 LANDSAT TM 영상에서 열밴드를 제외한 나머지 데이터의 파장대와 일치하는 부분을 감안하여 30개 밴드로 선정하였다. 지상실제데이터로서 비교기본도를 채택하였다. 이 비교기본도와 시각적으로 윤곽을 비교하고, 중첩분석하여 정확도를 평가하였다. 최대우도분류의 경우 수역 분류를 제외하고는 전혀 분류기법으로서의 역할을 하지 못하는 것으로 판단되며, 수역의 경우도 큰 호수 외에 작은 호수나 골프장내 연못, 부분적으로 물이 존재하는 작은 영역 등은 전혀 분류하지 못하고 있는 것으로 나타났다. 그러나 정준상관분류결과는 비교기본도와 형태적으로 시각적 비교를 해볼 때 골프장잔디를 거의 명확히 분류해 내고 있으며, 도시역에 대해서도 고속도로의 선형 등을 상당히 잘 분류해내고 있음을 알 수 있다. 또한 수역의 경우도 골프장 연못이나 대학교내 연못, 기타지역의 연못, 웅덩이 등 까지도 잘 분류해내고 있음을 확인할 수 있다. 결과적으로 정준상관분석 알고리즘의 개념상 트레이닝 영역 선정시 시행착오를 겪지 않고도 정확한 분류를 할 수 있었다. 또한 분류항목 중에서 잔디와 그 외 식물을 구분해 내는 능력과 수역을 추출해 내는 능력이 최대우도분류기법에 비해 우수하였다. 이상의 결과로 판단해 볼 때 하이퍼스펙트럴영상에 적용되는 정준상관분류기법은 농작물 작황 예측과 지표수 탐사에 매우 유용하리라 판단되며, 나아가서는 분광적 고해상도 영상인 하이퍼스펙트럴 데이터를 이용한 GIS 데이터베이스 구축에 중요한 역할을 할 수 있을 것으로 기대된다.

• 한국도서관정보학회지
• /
• 제31권1호
• /
• pp.87-114
• /
• 2000

The purpose of this study is offering appropriate system and training program to helf the system designer and the trainer in addition to analyze information use behavior about the web search tools and evaluate the estimated system by user groups. The results of the study are as follows $\circledS1$ It is desirable to consider age than other demographic variables in the case of web search tool. $\circledS2$ It is desirable to design Directory Search Tool in the case of web search tool which serves the student user group. $\circledS3$ An Intelligent Search Tool is more appropriate for the students who are using keyword search tool than any other tools. $\circledS4$ A discussion about standard classification of the web information should be accomplished soon because users feel confused in using web search tools due t o absence of standard mode of classification about classified item. $\circledS5$ Librarians need the cognition about data on internet s a source of information and need positive service and user training program about these information because student users hardly get help from librarians or library orientation for learning method to use web search tool. $\circledS6$ Internet use experience and years of computer use had effect on their use ability when using web search tool, whereas computer use experience, library use experience and Online Public Access Catalogs (OPAC) use experience had no effect on it. Especially, OPAC use experience had no effect on use ability of web search tool of student user group because student user groups had no information about internet and web search tool and they did not recognized the difference about search method between web search tool and OPAC. $\circledS7$In the case of web search tool, it si important to index the increasing web resource automatically by a searching robot. But in the case of student users, web search tool is much more needed to index by index expert due to the absence of ability about selecting and combining keyword.

• 대한물리의학회지
• /
• 제12권1호
• /
• pp.121-129
• /
• 2017

PURPOSE: This study was conducted to determine the effect of dual-task training (based on the International Classification of Functioning, Disability, and Health; ICF) on walking ability and self-efficacy in individuals with chronic stroke. METHODS: 22 chronic stroke patients participated in this study. Participants were randomly allocated into either the single-task group (n=11) or the dual-task group (n=11). Both groups had physical training three a week for 4 weeks, and at a three-week follow-up. Outcome measures included the 10m walking test (10MWT), figure of 8 walk test (F8WT), dynamic gait index (DGI), and Self-efficacy scale. All data were analyzed using SPSS 18.0 for Windows. Between-group and within-group comparison were analyzed by using the Mann-Whitney U test and Wilcoxon singed-rank test respectively. RESULTS: In the dual-task group, the 10MWT, time and steps of F8WT, DGI, and self-efficacy showed significant differences between pre- and post-test (p<.05). The Changes between the pre- and post-test values of 10MWT (p<.05), DGI (p<.05), and self-efficacy scale (p<.05) showed significant differences between the dual-task group and single-task group. CONCLUSION: Participants reported improved walking ability and self-efficacy, suggesting that dual-task training holds promise in the rehabilitation of walking in chronic stroke patients. This study showed that ICF-based on a dual-task protocol contiributes to motor learning after chronic stroke.

• 대한가정학회지
• /
• 제11권3호
• /
• pp.314-328
• /
• 1973

Highly developed and Complicated modern society demands earlier development of a human intelligence. Thus the trend of ecucations nowadays has been rapid increase of efford in the field of child education. As a result experiments to find out the ways of developing child intelligence have been repeatedly carried out and various theories concerning them have been expressed. The aim of this study is to review such theories and researches. Generally, the ways how to develop child intelligence are divided into tow parts. One is by means of operating mental abilities of a child and the other is providing abundant environment to a child for the facilitation of such mental operation. A. Mental Operation The intelligence of a child is more likely to be developed by thorough and precise training of following four mental abilities. 1. Ability of classification 2. Ability of analogy 3. Ability of variation 4. Ability of inference B. Environment Child intelligence is also more likely to be developed by providing him next four environments. 1. When the parents maintaina moderate expectation and have know-ledge of the child's mental development. 2. When the parents follow the standard linguistic form and provide the child with ample opportunities for the verval expression. 3. When the parents provide tools and materials and opportunities for the cultural experiences. 4. When the parents furnish immediate rewards to the child's intellectual achievements and help him form a positive self-concept with regard to the intellectual abilities.

• 대한안전경영과학회지
• /
• 제16권1호
• /
• pp.129-138
• /
• 2014

As S. Korea is becoming an "aged society", workers in the country would be exposed to higher risk of workplace injuries due to their reducing work abilities as they are getting old. To identify the relationship between the work ability and the incident rate of workplace injuries, the work ability index (WAI) scores were surveyed from 409 workers occupied in different manufacturing industries reside on north GyoengBuk area. The workplace injury statistics in the year of 2010 for the corresponding industries were analyzed and summarized with the WAI scores by age groups, years of service, and sizes of business. The results showed the WAI scores of the workers occupied in the higher risk of workplace injury was lower than that of the workers of the lower risk. It means the lower the WAI score, the higher the chance of being injured during the task. It is concluded that appropriate correlation exists between the WAI scores of workers and the incident rate of workplace injury. It is recommended to administrate individual work abilities of aged workers in order to keep low rate of workplace injuries in upcoming aged and highly aged society.