• 제목/요약/키워드: AI diagnosis

검색결과 228건 처리시간 0.024초

대규모 dynamic 전력계통의 고장진단 expert system에 관한 연구 (The study on the fault diagnosis expert system of dynamic system : a servey)

  • 허성광;정학영
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 제어로봇시스템학회 1988년도 한국자동제어학술회의논문집(국내학술편); 한국전력공사연수원, 서울; 21-22 Oct. 1988
    • /
    • pp.579-583
    • /
    • 1988
  • As the power facilities grow up, the optimal operation and the best maintenance of power plant can not be overestimated too much, which can enhance the plant availability and reliability much further. In this respect, fault diagnosis methodologies of dynamic system which is time-varing and strongly nonlinear have been studied. On of them is to use algorithm which is based on time-invariant, linear system, but this is not so nice a method for applying to power Plant. Therefore, the study on other techniques using Artificial Intelligence (AI) is under way. In this paper, the existing ways of fault detection are surveyed and their problems are also discussed.

  • PDF

간모세포종에서 복합치료의 성적 (The Results of Combined Therapeutic Modalities for Hepatoblastoma)

  • 한애리;오정탁;한석주;최승훈;황의호
    • Advances in pediatric surgery
    • /
    • 제7권1호
    • /
    • pp.37-41
    • /
    • 2001
  • In hepatoblastoma, encouraging cure rates have been achieved with recent advances in chemotherapy and surgical techniques, The aim of this study is to evaluate the role of combined therapeutic modalities and surgical resection in hepatoblastoma. Fifteen cases of hepatoblastoma were treated from January 1993 to August 2000. Six patients had resectable tumors at initial diagnosis. All underwent surgical resection and in four patients postoperative adjuvant chemotherapy was needed. Nine out of 15 patients had unresectbale tumors at initial diagnosis, and preoperative chemotherapy was applied. There was one operative mortality and 14 patients showed good prognosis after surgery. Although various treatment modalities should be combined for the unresectable hepatoblastoma. surgical resection remains the major curative procedure.

  • PDF

FCM을 이용한 프로세스 고장진단 (Diagnosis of Process Failure using FCM)

  • 이기상;박태홍;정원석;최낙원
    • 대한전기학회:학술대회논문집
    • /
    • 대한전기학회 1993년도 하계학술대회 논문집 A
    • /
    • pp.430-432
    • /
    • 1993
  • In this paper, an algorithm for the fault diagnosis using simple FCM(Fuzzy Cognitive Map) is proposed FCMs which store uncertain causal knowledges are fuzzy signed graphs with feedback. The algorithm allows searching the origin of fault and the ways of propagating the abnormality throughout the process simply and has following characteristics. First, it can distinguish the cause of soft failure which can degenerate the process as well as hard failure. Second, it is proper for the processes which have difficulties to establish the exact quantative model. Finally, it has short amputation time in comparison with the fault tree or the other AI methods. The applicability of the proposed algorithm for the fault diagonosis to a tank or pipeline system is demonstrated

  • PDF

The Investigation of Employing Supervised Machine Learning Models to Predict Type 2 Diabetes Among Adults

  • Alhmiedat, Tareq;Alotaibi, Mohammed
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제16권9호
    • /
    • pp.2904-2926
    • /
    • 2022
  • Currently, diabetes is the most common chronic disease in the world, affecting 23.7% of the population in the Kingdom of Saudi Arabia. Diabetes may be the cause of lower-limb amputations, kidney failure and blindness among adults. Therefore, diagnosing the disease in its early stages is essential in order to save human lives. With the revolution in technology, Artificial Intelligence (AI) could play a central role in the early prediction of diabetes by employing Machine Learning (ML) technology. In this paper, we developed a diagnosis system using machine learning models for the detection of type 2 diabetes among adults, through the adoption of two different diabetes datasets: one for training and the other for the testing, to analyze and enhance the prediction accuracy. This work offers an enhanced classification accuracy as a result of employing several pre-processing methods before applying the ML models. According to the obtained results, the implemented Random Forest (RF) classifier offers the best classification accuracy with a classification score of 98.95%.

Immunological Mechanisms in Cutaneous Adverse Drug Reactions

  • Ai-Young Lee
    • Biomolecules & Therapeutics
    • /
    • 제32권1호
    • /
    • pp.1-12
    • /
    • 2024
  • Adverse drug reactions (ADRs) are an inherent aspect of drug use. While approximately 80% of ADRs are predictable, immune system-mediated ADRs, often unpredictable, are a noteworthy subset. Skin-related ADRs, in particular, are frequently unpredictable. However, the wide spectrum of skin manifestations poses a formidable diagnostic challenge. Comprehending the pathomechanisms underlying ADRs is essential for accurate diagnosis and effective management. The skin, being an active immune organ, plays a pivotal role in ADRs, although the precise cutaneous immunological mechanisms remain elusive. Fortunately, clinical manifestations of skin-related ADRs, irrespective of their severity, are frequently rooted in immunological processes. A comprehensive grasp of ADR morphology can aid in diagnosis. With the continuous development of new pharmaceuticals, it is noteworthy that certain drugs including immune checkpoint inhibitors have gained notoriety for their association with ADRs. This paper offers an overview of immunological mechanisms involved in cutaneous ADRs with a focus on clinical features and frequently implicated drugs.

한우 농장별 번식기록 분석을 통한 번식률 제고 사례 연구 (Case Report on Improvement of Reproduction Rate in Hanwoo Farms)

  • 김의형;정기용;이승환;유일선;강희설
    • 한국수정란이식학회지
    • /
    • 제29권1호
    • /
    • pp.7-12
    • /
    • 2014
  • 본 연구는 한우 번식 기록이 잘 유지되고 있는 4개 농장의 2007년 1월부터 2010년 10월까지의 번식 자료 수집하여 분석하였다. 수태 당 평균 수정 횟수와 평균 공태일은 A농장 $1.7{\pm}0.1$회와 $77.4{\pm}4.8$일, B농장 $1.5{\pm}0.1$회와 $150.8{\pm}11.2$일, C농장 $1.5{\pm}0.1$회와 $90.4{\pm}4.5$일, D농장 $1.4{\pm}0.1$회와 $71.4{\pm}2.5$일이었다. 호르몬으로 발정을 유도하는 D농장을 제외한 3개 농장 531두의 번식 기록으로 분만 후 첫 수정 시기에 따른 평균 수정 횟수와 평균 공태일을 분석한 결과, 총 5개의 수정 시기에 따른 수정 횟수는 30일 이전 첫 수정이 $2.1{\pm}0.2$회로 31일 이후 첫 수정보다 유의적으로 높았다. 번식 장애우 58두에 2가지 배란 동기화법을 사용하여 수태율을 확인해 본 결과, Ovsynsh 법은 55.2%의 수태율을, CIDR-based TAI 법은 65.5%의 수태율을 나타냈다. 농장의 번식률을 높이기 위해서는 정확한 번식 기록 작성, 발정 관찰, 수정 후 임신 감정, 번식 기관 검진, 번식률을 고려한 첫 수정 시기 수정 등이 필요하다.

In-situ Process Monitoring Data from 30-Paired Oxide-Nitride Dielectric Stack Deposition for 3D-NAND Memory Fabrication

  • Min Ho Kim;Hyun Ken Park;Sang Jeen Hong
    • 반도체디스플레이기술학회지
    • /
    • 제22권4호
    • /
    • pp.53-58
    • /
    • 2023
  • The storage capacity of 3D-NAND flash memory has been enhanced by the multi-layer dielectrics. The deposition process has become more challenging due to the tight process margin and the demand for accurate process control. To reduce product costs and ensure successful processes, process diagnosis techniques incorporating artificial intelligence (AI) have been adopted in semiconductor manufacturing. Recently there is a growing interest in process diagnosis, and numerous studies have been conducted in this field. For higher model accuracy, various process and sensor data are required, such as optical emission spectroscopy (OES), quadrupole mass spectrometer (QMS), and equipment control state. Among them, OES is usually used for plasma diagnostic. However, OES data can be distorted by viewport contamination, leading to misunderstandings in plasma diagnosis. This issue is particularly emphasized in multi-dielectric deposition processes, such as oxide and nitride (ON) stack. Thus, it is crucial to understand the potential misunderstandings related to OES data distortion due to viewport contamination. This paper explores the potential for misunderstanding OES data due to data distortion in the ON stack process. It suggests the possibility of excessively evaluating process drift through comparisons with a QMS. This understanding can be utilized to develop diagnostic models and identify the effects of viewport contamination in ON stack processes.

  • PDF

Building Living Lab for Acquiring Behavioral Data for Early Screening of Developmental Disorders

  • Kim, Jung-Jun;Kwon, Yong-Seop;Kim, Min-Gyu;Kim, Eun-Soo;Kim, Kyung-Ho;Sohn, Dong-Seop
    • 한국컴퓨터정보학회논문지
    • /
    • 제25권8호
    • /
    • pp.47-54
    • /
    • 2020
  • 발달장애는 영유아 기부터 시작하는 뇌 신경계 발달장애들의 집합으로 언어 및 의사소통, 인지력, 사회성 등의 측면에서 이루어져야 할 발달이 심하게 지체되거나 성취되지 않은 장애를 의미한다. 이러한 발달장애 진단에는 아동의 얼굴 표정과 같은 감정표현의 의미와 맥락 등 비언어적 반응에 대한 관찰로 이루어진다. 이를 사람이 측정기에는 상당히 주관적인 판단이 개입하게 되어 객관적인 기술이 필요하다. 따라서 본 연구에서는 영유아/아동의 언어, 비언어적 행동 반응을 관찰하는 ADOS(Autism Diagnostic Observation Schedule)와 BeDevel(Behavior Development Screening for Toddler) 검사에서 검사자와 피검사자간의 상호작용이 녹화된 영상을 리빙랩 환경에서 획득하여 인공지능 기반의 비정상적/상동적 행동 인지 기술 개발에 필요한 영상 및 음성 데이터 확보를 목표로 한다.

전자정부 웹사이트 평가 결과 데이터 기반 지능형(AI) 정부 웹서비스 관리 방안 연구 (A Study on Government Service Innovation with Intelligent(AI): Based on e-Government Website Assessment Data)

  • 이은숙;차경진
    • 한국IT서비스학회지
    • /
    • 제20권2호
    • /
    • pp.1-11
    • /
    • 2021
  • As a key of access to public participation and information, e-government is taking the active role of public service by relevant laws and policy measures for universal use of e-government websites. To improve the accessibility of web contents, the level of deriving the results for each detailed evaluation item according to the Korean web contents accessibility guideline is carried out, which is an important factor according to the detailed evaluation items for each website property and requires data-based management. In this paper, detailed indicators are analyzed based on the quality control level diagnosis results of existing domestic e-government websites, and the results are classified according to high and low to propose new improvement directions and induce detailed improvement. Depending on the necessity of management according to the detailed indicators for each website attribute, not only results but also level diagnosis to strengthen web service quality suggests directions for future improvement through accurate detailed analysis and research for policy feedback. This study ultimately makes it possible to expect government system management based on predicted data through deduction history management based on evaluation score data on public websites. And it provides several theoretical and practical implications through correlation and synergy. The characteristics of each score for the quality management of public sector websites were identified, and the accuracy of evaluation, the possibility of sophisticated analysis, such as analysis of characteristics of each institution, were expanded. With creating an environment for improving the quality of public websites and it is expected that the possibility of evaluation accuracy and elaborate analysis can be expanded in the e-government performance and the post-introduction stage of government website service.

펄스 신호 및 절연저항 측정 알고리즘을 이용한 전동기 열화 추정 (Estimation of Motor Deterioration using Pulse Signal and Insulation Resistance Measurement Algorithm)

  • 정성인
    • 한국인터넷방송통신학회논문지
    • /
    • 제22권5호
    • /
    • pp.111-116
    • /
    • 2022
  • 전동기 소손의 원인으로는 과부하, 결상, 구속, 층간단락, 권선의 지락, 순간과전압의 유입, 회전자가 고정자에 닿는 경우 등 절연파괴로 이어져 고장 또는 전기 사고로 이어지고 있다. 따라서 기기 고장은 기기의 보수/수리에 필요한 비용에 의한 손실뿐만 아니라, 전동기가 포함된 공정 자체를 멈추기 때문에 공정 정지에 따른 생산성 저하에 의한 막대한 경제적 손실을 초래한다. 전동기의 고장을 진단하기 위한 현재의 기술의 수준은 진동, 열, 전력분석 방식을 이용하고 있지만, 고장에 따른 상당 부분의 시간이 진행되어야 문제점을 분석할 수 있는 한계점을 가지고 있다. 따라서 본 논문에서는 이러한 문제점을 해결하고자 DC AMP 신호를 이용하여 절연저항을 측정하는 장치 및 알고리즘을 산업용 전동기에 적용하여 절연저항 상태값을 추종하여 기존방식에서 해결되지 못한 전동기의 열화 및 고장 진단을 제안한다.