• 제목/요약/키워드: Engine Health Management

검색결과 60건 처리시간 0.026초

개인화된 힐링 데이터 접근을 위한 개방형 게이트웨이 프레임워크 설계 (Design of Open Gateway Framework for Personalized Healing Data Access)

  • 전영준;임석진;황희정
    • 한국인터넷방송통신학회논문지
    • /
    • 제15권1호
    • /
    • pp.229-235
    • /
    • 2015
  • ICT 힐링 플랫폼은 생체신호 및 생활습관 등의 정보를 기반으로 한 질환조기 경보를 목표로 하는 개념으로서 만성질환 예방을 목적으로 한다. ICT(Information & Communication Technology) 힐링플랫폼의 목표는 개인이 주도하는 건강관리를 위해 여러 건강 관련 서비스 기관들(병원, 피트니스센터, 건강검진센터, 개인건강장치 등)에 산재되어 있는 개인 건강 정보를 개방화하여 개인 단말장치로 모으고, 분석 플랫폼 및 Open API를 제공하여 다양한 부가 서비스들을 활성화하는데 있다. 본 논문에서 제안하는 개인화된 힐링 데이터 접근을 위한 개방형 게이트웨이 프레임워크인 HPAdapter (Healing Platform Adaptor)는 ICT 힐링플랫폼의 데이터 중계를 위해 EMR(Electronic health record), 한방의학, 라이프로그, 웰니스, 만성질활, 피트니스 등 다양한 개인 건강관련 데이터 공급자와 서비스 공급자 사이를 연결해 개인화된 힐링 데이터를 중계하는 소프트웨어 엔진을 뜻한다. 설계된 HPAdaptor는 데이터 및 서비스 공급자 연동을 통해 힐링 레코드 저장소, 모바일 플랫폼 및 분석 플랫폼 등 데이터를 필요로 하는 서비스 혹은 플랫폼의 중계참조 모델로 활용할 수 있다.

자동 에이전트 기법을 활용한 임상문서저장시스템 (A Clinical Data Repository as an Autonomous Agent)

  • 김화선;캠비즈;조훈
    • 대한전기학회논문지:시스템및제어부문D
    • /
    • 제54권12호
    • /
    • pp.732-736
    • /
    • 2005
  • ln general, hospital information system should provide interoperability hat usually and operate independence of other HIS. This study proposes a new HIS paradigm that can be implemented within standard HL7 Interface engine and clinical data repository (CDR). We have developed an alternative architecture relying on agent solutions with distributed queries to heterogeneous databases. This architecture creates a very fine and flexible repository that can handle queries with the bases of standard HL7 messaging structure. Deploying Agent solutions to manipulate autonomy of storage management and sociality for communication with open world is another issue that keeps this system from reinventing existing wheels in medical informatics. This study the first attempt to construct CDR based private clinic. We used the information stored in the clinical patient record system of the internal medicine private hospital which is used rational database. We were searched increasing the 1,000 data entry from 1,000 to 10,000. By the result, experimental CDR showed highly efficient performance more than 6,000. In the future, the CDR can be further extended for clinical information among private hospitals estranged from EHR (Electronic Health Records).

포스트 코로나 시대 농어촌지하수 관리 방안 (Management Plan for Rural Groundwater Resources in the Era of Post COVID-19)

  • 이병선;서상진;이규상;윤석환;송성호
    • 한국지하수토양환경학회지:지하수토양환경
    • /
    • 제27권4호
    • /
    • pp.1-9
    • /
    • 2022
  • This study was conducted to supplement new-normal strategies on management plans of rural groundwater resources in the era of Post COVID-19. Global outbreak of COVID-19 has damaged across all areas including public policy, economics, industrial services, and others without exception, which has resulted in establishing new-normal strategies in order to restore balance and functions as for these areas. The new-normal ones were represented as enhancing preventative management on infectious diseases, expanding non face-to-face services, enhancing protective trades and food securities, and preparing growth policies on public services using the 4th industrial revolution techniques. In this study, G-WASH_AD (Groundwater supply, sanitation, and hygiene with attraction and digitization) was suggested to be new-normal strategies on rural groundwater resources. The G-WASH_AD was consisted of three detailed action plans: a preventative plan on waterborne-diseases of groundwater (PP), a groundwater-tourism plan with rural heritage (GP), and an application plan of the 4th industrial revolution techniques to groundwater facilities and its data (P4). The PP can contribute to protect human health from waterborne-diseases and minimize hazardous effects on crop cultivation. The GP accompanied with high-quality groundwater resources is able to strengthen rural tourism, to promote marketing activities on local agricultural products, and to increase household incomes of rural communities. The P4 can reinforce fast, comfortable, and scientific management on groundwater facilities and its data, creating a virtuous cycle between innovative management on groundwater and growth of technology related to it. Results of the G-WASH_AD strategies can encourage a green growth engine in field of rural groundwater management keeping up with Post COVID-19.

A Study on the DB-IR Integration: Per-Document Basis Online Index Maintenance

  • Jin, Du-Seok;Jung, Hoe-Kyung
    • Journal of information and communication convergence engineering
    • /
    • 제7권3호
    • /
    • pp.275-280
    • /
    • 2009
  • While database(DB) and information retrieval(IR) have been developed independently, there have been emerging requirements that both data management and efficient text retrieval should be supported simultaneously in an information system such as health care, customer support, XML data management, and digital libraries. The great divide between DB and IR has caused different manners in index maintenance for newly arriving documents. While DB has extended its SQL layer to cope with text fields due to lack of intact mechanism to build IR-like index, IR usually treats a block of new documents as a logical unit of index maintenance since it has no concept of integrity constraint. However, In the DB-IR integrations, a transaction on adding or updating a document should include maintenance of the posting lists accompanied by the document. Although DB-IR integration has been budded in the research filed, the issue will remain difficult and rewarding areas for a while. One of the primary reasons is lack of efficient online transactional index maintenance. In this paper, performance of a few strategies for per-document basis transactional index maintenance - direct index update, pulsing auxiliary index and posting segmentation index - will be evaluated. The result shows that the pulsing auxiliary strategy and posting segmentation indexing scheme, can be a challenging candidates for text field indexing in DB-IR integration.

국내 의료기기관리제도의 현황분석에 따른 정책적 제도개선 방안에 관한 연구 (A study on the system improvement policy according to the status analysis of medical device control system in Korea)

  • 이경만;백낙기;서종현
    • 대한안전경영과학회지
    • /
    • 제12권3호
    • /
    • pp.37-52
    • /
    • 2010
  • This study is aimed at proposing the national policy for medical device control system in Korea as deeply analysed the present status of the system. On 1979, Korean government had started to inspect 24 kinds of the medical devices such as X-ray diagnostic equipments, medical sterilizer and etc. mostly imported from advanced countries which USA, Germany and Japan for the first time according to the Pharmaceutical Affairs Law. However medical devices were becoming consideration as an important partner of diagnosis, curing and alleviation of diseases by medical doctors and also much important keeping the health at home. Furthermore medical devices industry can be designated as a national growth engine industry. So it is necessary not only to harmonize to international standards but also the harmonization of the system including pre-market application and post-market surveillance, is strongly needed by the Korea Food and Drugs Administration(KFDA).

잔여 유효 수명 예측 모형과 최소 수리 블록 교체 모형에 기반한 비용 최적 예방 정비 방법 (Cost-optimal Preventive Maintenance based on Remaining Useful Life Prediction and Minimum-repair Block Replacement Models)

  • 주영석;신승준
    • 산업경영시스템학회지
    • /
    • 제45권3호
    • /
    • pp.18-30
    • /
    • 2022
  • Predicting remaining useful life (RUL) becomes significant to implement prognostics and health management of industrial systems. The relevant studies have contributed to creating RUL prediction models and validating their acceptable performance; however, they are confined to drive reasonable preventive maintenance strategies derived from and connected with such predictive models. This paper proposes a data-driven preventive maintenance method that predicts RUL of industrial systems and determines the optimal replacement time intervals to lead to cost minimization in preventive maintenance. The proposed method comprises: (1) generating RUL prediction models through learning historical process data by using machine learning techniques including random forest and extreme gradient boosting, and (2) applying the system failure time derived from the RUL prediction models to the Weibull distribution-based minimum-repair block replacement model for finding the cost-optimal block replacement time. The paper includes a case study to demonstrate the feasibility of the proposed method using an open dataset, wherein sensor data are generated and recorded from turbofan engine systems.

Beacon기술을 이용한 MICE시스템 설계 및 구현 (Implementation of total management system for exhibitions and Convention using beacon)

  • 김영익;김미정;김휴찬
    • 예술인문사회 융합 멀티미디어 논문지
    • /
    • 제6권2호
    • /
    • pp.35-44
    • /
    • 2016
  • 최근 마이스산업이 신성장동력산업으로 떠오르고 있다. 국내의 대부분 MICE행사는 소규모/저비용으로 진행되고 있다. 행사주최자 입장에서는 반복, 소모적으로 발생하는 브로슈어, 홍보물제작 등의 인쇄물 비용의 절감과 행사진행에 필요한 단순 안내진행요원들의 경비 절감을 원하고 있다. 기존 모바일웹은 행사 참가자가 필요한 정보를 바로 얻지 못하고 스스로 정보를 찾고 검색해야 되는 단점이 있다. 따라서 행사기간에 단기적으로 사용할 수 있는 저비용, 고효율의 행사정보 제공 솔루션의 개발이 필요하다. 본 연구에서는 비콘 기술을 이용한 전시/컨벤션 행사용 통합관리시스템을 구현하였다. 비콘 기술을 적용하여 행사현장 안내시스템을 통한 행사지원 관리의 효율성을 제공하고, 콘텐츠관리시스템(CMS)을 이용한 디지털브로슈어 관리기능을 통한 정보검색 용이성과 비용절감 효과를 높일 수 있다. 소규모 전시/컨벤션 행사에 주최 측의 직접 홈페이지 구축과 현장관리시스템 운영을 통해 효율적인 행사관리를 할 수 있다.

C-MAPSS 데이터를 이용한 항공기 엔진의 신경 회로망 기반 건전성관리 (Neural Network based Aircraft Engine Health Management using C-MAPSS Data)

  • 윤유리;김석구;조성희;최주호
    • 항공우주시스템공학회지
    • /
    • 제13권6호
    • /
    • pp.17-25
    • /
    • 2019
  • 항공기 엔진의 고장예지 및 건전성 관리(PHM)는 고장 또는 수명한계 도달 전에 잔존 유효 수명을 예측하는 것이다. PHM 기술 중 예측모델을 확립하는 방법은 물리 기반과 데이터 기반 방법이 있다. 물리기반 방법은 적은 데이터로 정확한 예측이 가능하지만 확립된 손상 물리 모델이 적어서 적용에 한계가 있다. 본 연구는 따라서 데이터 기반 방법을 적용하였으며, 수명 예측을 위해서 신경회로망 알고리즘 중 Multi-layer Perceptron을 이용하였다. 이를 위해 미국 항공우주국(NASA)에서 개발한 C-MAPSS 코드로 생성된 가상 데이터 세트를 이용하여 신경회로망을 학습하였다. 학습된 신경회로망 모델은 테스트 세트에 적용한 후 잔존 유효 수명의 신뢰구간을 예측하고 실제 값을 통해 정확도를 검증하였다. 또한 본 연구에서 제시된 방법을 기존 문헌의 것과도 비교하였고 그 결과 비교적 양호한 정확도를 확인할 수 있었다.

서울시 소재 대학교 차량 요금정산소 수납원의 블랙카본 노출 평가 (Exposure Assessment of Black Carbon among Tollbooth Worker at a University)

  • 김동원;조혜리;우철운;류승훈;윤충식
    • 한국산업보건학회지
    • /
    • 제29권4호
    • /
    • pp.464-476
    • /
    • 2019
  • Objectives: This study aimed to assess the exposure levels of tollbooth workers to diesel particulate matter using black carbon (BC) and to find the correlations among variables associated with BC using the motor vehicle management act regulated by the Ministry of Land, Infrastructure and Transport. Methods: This study was performed over 14 days at a university in Seoul. BC levels were monitored using an aethalometer and were conducted around the breathing zones of the workers. There were three sampling locations: inside the tollbooth (front gate and rear gate) and an office as a control group. T-test, correlation, and multiple linear regression analysis were performed using SPSS. Results: The geometric mean (GM) of BC30min concentrations in the exposure group was 2.44 ㎍/㎥, approximately 1.4 times higher than the control group (1.75 ㎍/㎥). The GM of BC30min concentrations was 2.75 ㎍/㎥ during the heavy traffic time (9-10 am) and 2.30 ㎍/㎥ during non-heavy traffic times (p<0.001). The multiple linear regression analysis shows that the number of all types of vehicles and PM2.5 concentrations in the atmosphere were factors increasing the GM of BC(ln(BC30min)) concentrations (adjusted R2=0.42, p<0.001). The workers were constantly exposed to low concentrations (GM of BC30min=2.44 ㎍/㎥), but they were exposed to peak concentrations instantly (BC10sec=3545.04 ㎍/㎥). When the GM of BC30min concentrations was momentarily represented as high, it was identified that a vehicle mainly using diesel fuel or an aging vehicle had passed. Conclusions: A ventilation system should be installed in the closed tollbooth or aging vehicles should be controlled so as not to pass tollbooths.

스파크를 이용한 머신러닝의 분산 처리 성능 요인 (Performance Factor of Distributed Processing of Machine Learning using Spark)

  • 류우석
    • 한국전자통신학회논문지
    • /
    • 제16권1호
    • /
    • pp.19-24
    • /
    • 2021
  • 본 논문에서는 아파치 스파크를 이용하여 머신러닝을 분산 처리할 때의 성능 요인을 분석하고 효율적인 분산 처리를 위한 실행 환경을 실험을 통해 제시한다. 먼저, 분산 클러스터 환경에서 머신러닝을 수행할 때 고려해야 하는 성능 요인으로 클러스터의 성능, 데이터의 규모, 스파크 엔진의 속성으로 구분하여 분석한다. 그리고 하둡 클러스터에서 동작하는 스파크 MLlib을 이용하여 회귀분석을 수행할 때 노드의 구성과 스파크 Executor의 설정을 변화하면서 성능을 측정한다. 실험 결과 최적의 Executor 개수는 데이터의 블록의 수에 영향을 받으나 클러스터 규모에 따라 최대값, 최소값은 각각 코어의 수, 워커 노드의 수로 제한됨을 실증하였다.