• 제목/요약/키워드: customized training

검색결과 197건 처리시간 0.021초

Deep learning system for distinguishing between nasopalatine duct cysts and radicular cysts arising in the midline region of the anterior maxilla on panoramic radiographs

  • Yoshitaka Kise;Chiaki Kuwada;Mizuho Mori;Motoki Fukuda;Yoshiko Ariji;Eiichiro Ariji
    • Imaging Science in Dentistry
    • /
    • 제54권1호
    • /
    • pp.33-41
    • /
    • 2024
  • Purpose: The aims of this study were to create a deep learning model to distinguish between nasopalatine duct cysts (NDCs), radicular cysts, and no-lesions (normal) in the midline region of the anterior maxilla on panoramic radiographs and to compare its performance with that of dental residents. Materials and Methods: One hundred patients with a confirmed diagnosis of NDC (53 men, 47 women; average age, 44.6±16.5 years), 100 with radicular cysts (49 men, 51 women; average age, 47.5±16.4 years), and 100 with normal groups (56 men, 44 women; average age, 34.4±14.6 years) were enrolled in this study. Cases were randomly assigned to the training datasets (80%) and the test dataset (20%). Then, 20% of the training data were randomly assigned as validation data. A learning model was created using a customized DetectNet built in Digits version 5.0 (NVIDIA, Santa Clara, USA). The performance of the deep learning system was assessed and compared with that of two dental residents. Results: The performance of the deep learning system was superior to that of the dental residents except for the recall of radicular cysts. The areas under the curve (AUCs) for NDCs and radicular cysts in the deep learning system were significantly higher than those of the dental residents. The results for the dental residents revealed a significant difference in AUC between NDCs and normal groups. Conclusion: This study showed superior performance in detecting NDCs and radicular cysts and in distinguishing between these lesions and normal groups.

생성형 AI에 관한 인식 및 집단간 차이 분석 (Analysis of Perceptions and Differences between Groups regarding Generative AI)

  • 노규성
    • 디지털융복합연구
    • /
    • 제22권1호
    • /
    • pp.15-21
    • /
    • 2024
  • 본 연구는 생성형 AI의 활용 및 사용자 그룹 간 차이에 대한 인식을 분석하고자 하는 목적으로 가지고 있다. 본 연구는 생성형 AI 사용자 그룹 간 차이에 대한 인식을 조사하여 각 사용자층에 대한 AI 활용 역량 증진을 위한 시사점을 도출하였다. 검증 결과, 연령별 집단 간에는 유의적인 차이가 없으며, 전문적 배경에 의한 집단 간에는 생성형 AI 활용 분야와 생성형 AI의 윤리적 관점에서 유의미한 차이를 보였다. 이로 인해 본 연구는 전문 분야에 따라 다른 AI 솔루션 제공 및 맞춤형 교육 훈련 필요성, 윤리적 고려에 대한 특별한 교육과 문화 형성 등에 대한 대안을 제시하였다. 또한 텍스트 마이닝 기법을 통해 연령대별, 전문 분야별로 다른 방식의 AI 활용 및 활용 역량 개발 교육 등을 제안하였다는 점에서 학술적 기여를 했다고 사료된다.

북한이탈의사 교육: 서울의료원에서의 경험을 중심으로 (Medical Education for North Korean Defector Physicians: Experience at the Seoul Medical Center)

  • 최재필
    • 의학교육논단
    • /
    • 제14권2호
    • /
    • pp.95-101
    • /
    • 2012
  • As North Korea passed from the Devotion (Jeongseong) movement to the black market (Jangmadang) system, the medical service system in that country was effectively destroyed. North Korean physicians who have successfully defected to South Korea (North Korean defector physicians, NKDPs) have experienced socio-economic hardships on their way to becoming incorporated into the South Korean medical system due to different medico- social cultures, different (English-based) medical terminology, and the clinical knowledge gap between North and South Korea. Since 2009, we have operated programs at the Seoul Medical Center to help NKDPs prepare for the South Korean medical licensing examination. These programs consist of clinical education at the medical center, personal mentoring, arrangement of educational programs at the medical college, mock tests at the consortium, and administrative aid. Looking forward, we hope to achieve the following: 1) More systematic support plans are needed involving medical education experts, field physicians, and experts on reunification. 2) An evaluation of defector physicians' current medical knowledge may provide information about the areas where supplementary education is most needed and the standards for certificating licenses. 3) In the short term, a customized glossary should be developed to assist defector physicians prepare for the examination. 4) To secure internships and residencies is the most important issue for further sustained training of NKDP physicians to become good clinicians after certification. Hopefully, this short report on the current ongoing educational course will lead to more extensive discussion.

활동 분석을 통한 에이전트 SPC의 요구사항 규명 및 시스템 구현 (Requirements Derivation and Implementation of Agent-based SPC System by Task Analysis)

  • 유기훈;이재훈;김기태;장중순
    • 한국신뢰성학회지:신뢰성응용연구
    • /
    • 제10권1호
    • /
    • pp.39-56
    • /
    • 2010
  • Statistical process control (SPC) is a powerful technique for monitoring, managing, analysing and improving the process performance. However, its has limitations such as lack of engineering, statistical skill and training, and lesser importance of activity. To solve the problems, this study proposes an intelligent SPC system using specified agents which are derived through analysis and evaluation of the SPC activities. The activities investigated by the relevant researches are categorized as collection, process analysis, diagnosis, detection, cause analysis and rule generation. Also, the evaluation criteria are established as feasibility of automation, frequency, level and time. The requirements of the agent functions are derived by the evaluation, and the types of customized agents are as data collection, store, analysis, diagnosis, monitoring, alarm and reporting. A prototype SPC system represents that the functions of the proposed agents are successfully validated.

NFC기반 피트니스센터 맞춤 트레이닝 시스템 설계 (Design of Custom Training System for Fitness Club Based on NFC)

  • 이현석;박석천
    • 인터넷정보학회논문지
    • /
    • 제18권4호
    • /
    • pp.1-6
    • /
    • 2017
  • 가트너(Gartner)에 따르면 2020년 글로벌 헬스케어 산업 규모는 전체 IoT 시장의 15%인 2천 850억불을 형성할 것으로 전망하고 있다. 이처럼 헬스케어 시장의 관심은 최근 크게 증가하고 있으며, 많은 사람들이 건강한 몸을 만들고자 피트니스센터를 찾고 있다. 하지만 자신에게 맞는 운동이 무엇인지 제대로 알지 못하여 잘못된 운동 방법으로 운동을 하여 자신의 건강을 역으로 악화 시키는 경우도 있다. 또한, 자신에게 맞는 운동을 추천 받아도 자신이 이용하는 피트니스센터에서 사용하는 운동기구와 다르거나 어떻게 사용해야 하는지 모르는 경우도 있어 문제가 되고 있다. 본 논문은 앞서 제시한 문제를 개선하고자 사용자들이 많이 이용하는 피트니스센터에 적합한 NFC 기반의 피트니스 센터 맞춤 트레이닝 시스템을 설계 하였다.

맞춤형 방문건강관리사업 내 방문간호사의 직무분석 (Job Analysis of the Nurses Who Work in Customized Visiting Health Care Services using DACUM Technique)

  • 남혜경;조경숙
    • 근관절건강학회지
    • /
    • 제22권3호
    • /
    • pp.205-218
    • /
    • 2015
  • Purpose: This study was performed to analyze the visiting nurses' job using Developing a curriculum (DACUM). Methods: The DACUM committee with 6 visiting nurses participated in the workshop. In this workshop, the visiting nurses role was defined and their duties and tasks were identified. After content validation via the experts, the pilot test was conducted to 78 nurses. Results: A total of 13 duties and 82 tasks were identified on the DACUM chart which represented the importance, difficulty, and frequency of tasks with alphabet A, B, and C as its higher degree. Regarding duties, 'visiting nursing for high risk group' is the highest, while the lowest was 'public welfare events'. Regarding to tasks, 'discovering a new patient' was the highest, while 'selecting patients and offering medical supplies (nutritional supplement, patch)' was the lowest one. Conclusion: The results showed that visiting nurses working in the visiting health care service center were doing more various duties and tasks than those working according to 'Act on Long-term Care Insurance for the Aged'. The results can be used to develop training programs for visiting nurses and evaluation-scale of their job performance.

모바일 웹 캡처 메모 시스템의 학습 완성도에 대한 연구 (Mobile Web Capture notes system Research on learning maturity)

  • 이연란;임영환
    • 만화애니메이션 연구
    • /
    • 통권32호
    • /
    • pp.363-381
    • /
    • 2013
  • 본 논문은 모바일 웹 상에서 오프라인의 학습 내용을 복습 할 때 학습 동영상에 필요한 재학습 영역을 프레임 단위로 중요 영역만 캡처한다. 캡처된 프레임은 영상 중에서 진행된 학습 시간과 이미지의 형태로 저장하고 또한 설명에 대한 메모 기능을 함께 저장한다. 캡처 영역은 학습자에 필요한 영역만 재학습하는 학습자 중심의 맞춤형 시스템을 적용할 수 있다. 캡처 프로그램의 구성은 학습 순서에 상관없이 선택한 순서에 따라 프레임 단위 캡처로 사용자 중심의 스토리텔링형 학습을 적용할 수 있다. 캡처 시스템 효과는 전체 학습에 비해 학습 시간을 절약하고 학습자 중심의 프레임 재구성으로 맞춤형 학습에 따른 학습 효용성 향상에 긍정적인 역할을 한다.

근로자들의 직무스트레스 수준과 관련 요인 - 한국형 직무스트레스 측정도구 단축형을 이용하여 - (Workers' Job Stress Status and Related Factors - Using Korean Occupational Stress Questionnaire Short Form -)

  • 조동란
    • 한국직업건강간호학회지
    • /
    • 제15권1호
    • /
    • pp.58-71
    • /
    • 2006
  • Purpose: This study was performed to identify workers' Job stress status and to analyse the influencing factors. Method: Data were collected from 456 workers with Korean Occupational Stress Questionnaire Short Form(KOSQ SF) and analysed using descriptive statistics, t-test, ANOVA. Results: Total job stress status of men was slightly lower than Korean workers' standard. In case of women, the score of total job stress was lower than Korean workers' standard. The most significant influencing factors to stressors were insufficient sleeping time and self cognitive bad health condition. Among seven domains of job stressors, job demand was affected by 8 characteristics. Conclusion: This study indicated that workers' job stress level were various by their characteristics except workplace size. The development of stress management programs by types of industry is required. On the base of the model program, planning of customized program for every company or employee is required. High job demand, insufficient job control, insufficient sleeping time, bad health condition are the key factors of workers' job stress in this study. The change of workers' health behavior with supportive environment is essential to stress management program. More researches for adding physical environment domain to KOSQ SF are expected.

  • PDF

Self-adaptive sampling for sequential surrogate modeling of time-consuming finite element analysis

  • Jin, Seung-Seop;Jung, Hyung-Jo
    • Smart Structures and Systems
    • /
    • 제17권4호
    • /
    • pp.611-629
    • /
    • 2016
  • This study presents a new approach of surrogate modeling for time-consuming finite element analysis. A surrogate model is widely used to reduce the computational cost under an iterative computational analysis. Although a variety of the methods have been widely investigated, there are still difficulties in surrogate modeling from a practical point of view: (1) How to derive optimal design of experiments (i.e., the number of training samples and their locations); and (2) diagnostics of the surrogate model. To overcome these difficulties, we propose a sequential surrogate modeling based on Gaussian process model (GPM) with self-adaptive sampling. The proposed approach not only enables further sampling to make GPM more accurate, but also evaluates the model adequacy within a sequential framework. The applicability of the proposed approach is first demonstrated by using mathematical test functions. Then, it is applied as a substitute of the iterative finite element analysis to Monte Carlo simulation for a response uncertainty analysis under correlated input uncertainties. In all numerical studies, it is successful to build GPM automatically with the minimal user intervention. The proposed approach can be customized for the various response surfaces and help a less experienced user save his/her efforts.

산업안전규제 순응 스트레스, 인적오류, 직무만족도간의 연관성 분석 (Correlation Analysis of Stress to Industrial Safety Regulatory Compliance, Human Error and Job Satisfaction)

  • 박용훈;백종배
    • 한국안전학회지
    • /
    • 제29권3호
    • /
    • pp.91-97
    • /
    • 2014
  • This study aims to suggest a measure to reduce industrial accident and secure adaptation to the industrial safety regulation policies by empirically establishing the effects of stress from adaptation to the industrial safety regulation on the human error, one of direct causes of industrial accident to the target groups of the industrial safety regulation policies. This study as for content range examines the stress from adaptation to the industrial safety regulation, job satisfaction, human error, and as for spatial range, this study performed an empirical research on the workers of 24 companies located within Chungcheong region centers district among 153 companies nationwide that uses 7 chemicals by introducing PSM (process safety management) system of the Ministry of Employment & Labor as of January 2012. Based on these results and suggestions there are five(5) necessities to reduce industrial safety regulations adaptation stress and human error generation, first(1st) is the necessity of understanding influential factors to stress, second(2nd) is the necessity to customized vocational training, third(3rd) is improving enhance system of job satisfaction, forth(4th) is preparing stress-reduction program, and fifth(5th) is introducing on-site restrictive action of advanced country as politics items.