• 제목/요약/키워드: Logic, Medical

검색결과 115건 처리시간 0.027초

피라미드 영상과 퍼지 이론을 이용한 흉부 혈관 성분의 검출에 관한 연구 (A Study on Algorithm of Pulmonary Blood Vessel Search Using Pyramid Images and Fuzzy Theory)

  • 황준현;임정기;한만청;민병구
    • 대한의용생체공학회:학술대회논문집
    • /
    • 대한의용생체공학회 1990년도 추계학술대회
    • /
    • pp.11-14
    • /
    • 1990
  • The detection of pulmonary blood vessels is very difficult owing to their complex tree structures and different widths. In this paper, We propose a new detection algorithm. The motivation of this algorithm is that Han is the best detector. So, this algorithm is developed to imitate the human searching process. To realize it, the algorithm consist of two components. One is Pyramid Images whose one pixel is median value of four pixels of the previous low level. Searching gradually from high level to low level, We concentrate on global and main information of structure at the first. Then based on it, We search the detailed data in low level. The other is fuzzy logic which makes it easy to convert searching process expressed as human language into numeric multi_value. This algorithm showes speedy and robust results. But the more study on both human searching process and the detection of small part is needed.

  • PDF

System Generator를 이용한 카오스 신호 발생기의 FPGA 구현 (FPGA Implementation of Chaotic Signal Generator Using System generator)

  • 허용원;하정우;장은영;변건식
    • 한국정보통신학회:학술대회논문집
    • /
    • 한국해양정보통신학회 2007년도 추계종합학술대회
    • /
    • pp.336-339
    • /
    • 2007
  • 카오스 신호는 공학, 의학 그리고 생물학과 같은 모든 분야에서 많이 이용되고 있으며 최근 카오스 신호를 이용한 디지털 통신시스템에 대한 연구도 활발히 이루어지고 있다. 본 논문은 카오스 신호를 디지털 통신시스템에 적용할 목적으로 System Generator를 이용하여 비선형 방정식으로 구성된 6개의 카오스 신호 발생기를 설계하고 FPGA로 하드웨어를 구현하였다. 이 결과로부터 Hardware co-simulation으로 본 설계를 검증하기 위해 비트 스트림을 FPGA 보드로 로드하였다. 또한 6개의 카오스 발생기의 성능을 평가하기 위해 타이밍 해석을 통한 최대 동작 주파수와 사용한 로직의 resource량을 조사하여 비교하였다.

  • PDF

맥파검출용 트랜스듀서의 개발 (Development of P-5 Transducer or Detection of the Pulse Wave)

  • 한성현;권오상;박승환;홍승홍
    • 대한의용생체공학회:학술대회논문집
    • /
    • 대한의용생체공학회 1997년도 추계학술대회
    • /
    • pp.395-398
    • /
    • 1997
  • Human pulse represents the physical characteristics of heart and cardiovascular system. Therefore, malfunctions and errors of heart and cardiovascular system can be determined by using an automatic diagnosis system that can detect the pulse signal. Not only will the computerised system preclude the possibilities of observational errors by giving an accurate measurement with great stability, but minimize the possibilities of misinterpretation by using an automated diagnostic logic. A new combinational fiber-optic sensor, which has a detecting part and a transmitting part was used to acquire radial pulse signal noninvasively. The development of P-5 transducer makes it possible to obtain more effective detection and obvious display of pulse signals in the aspect of reliability. Using P-5 transducer in the field of plethysomography and MAC- JIN, one of our diagnoses in Korean traditional medicine, it is expected that we can ontain quantitative and valuable information or the diagnosis of human pulses.

  • PDF

Statistical RBF Network with Applications to an Expert System for Characterizing Diabetes Mellitus

  • Om, Kyong-Sik;Kim, Hee-Chan;Min, Byoung-Goo;Shin, Chan-So;Lee, Hong-Kyu
    • Journal of Electrical Engineering and information Science
    • /
    • 제3권3호
    • /
    • pp.355-365
    • /
    • 1998
  • The purposes of this study are to propose a network for the characterizing of the input data and to show how to design predictive neural net재가 expert system which doesn't need previous knowledge base. We derived this network from the radial basis function networks(RBFN), and named it as a statistical EBFN. The proposed network can replace the statistical methods for analyzing dynamic relations between target disease and other parameters in medical studies. We compared statistical RBFN with the probabilistic neural network(PNN) and fuzzy logic(FL). And we testified our method in the diabetes prediction and compared our method with the well-known multilayer perceptron(MLP) neural network one, and showed good performance of our network. At last, we developed the diabetes prediction expert system based on the proposed statistical RBFN without previous knowledge base. Not only the applicability of the characterizing of parameters related to diabetes and construction of the diabetes prediction expert system but also wide applicabilities has the proposed statistical RBFN to other similar problems.

  • PDF

Genetically Optimized Fuzzy Polynomial Neural Network and Its Application to Multi-variable Software Process

  • Lee In-Tae;Oh Sung-Kwun;Kim Hyun-Ki;Pedrycz Witold
    • International Journal of Fuzzy Logic and Intelligent Systems
    • /
    • 제6권1호
    • /
    • pp.33-38
    • /
    • 2006
  • In this paper, we propose a new architecture of Fuzzy Polynomial Neural Networks(FPNN) by means of genetically optimized Fuzzy Polynomial Neuron(FPN) and discuss its comprehensive design methodology involving mechanisms of genetic optimization, especially Genetic Algorithms(GAs). The conventional FPNN developed so far are based on mechanisms of self-organization and evolutionary optimization. The design of the network exploits the extended Group Method of Data Handling(GMDH) with some essential parameters of the network being provided by the designer and kept fixed throughout the overall development process. This restriction may hamper a possibility of producing an optimal architecture of the model. The proposed FPNN gives rise to a structurally optimized network and comes with a substantial level of flexibility in comparison to the one we encounter in conventional FPNNs. It is shown that the proposed advanced genetic algorithms based Fuzzy Polynomial Neural Networks is more useful and effective than the existing models for nonlinear process. We experimented with Medical Imaging System(MIS) dataset to evaluate the performance of the proposed model.

In vitro Estimation of Cardiac Output for the TAH using an Adaptive Fuzzy Identifier

  • Choi, W.W.;Jo, Y.H.;Ahn, J.M.;Park, S.K.;Choi, J.S.;Om, K.S.;Lee, J.J.;Choi, J.H.;Kim, H.C.;Min, B.G.
    • 대한의용생체공학회:학술대회논문집
    • /
    • 대한의용생체공학회 1996년도 추계학술대회
    • /
    • pp.263-267
    • /
    • 1996
  • An estimation algorithm based on training of fuzzy logic system using back-propagation is proposed, in this paper, for determining cardiac output in the TAH. The proposed estimation utilizes only a motor current waveform generated from the moving actuator of the electromechanical TAH without using any extra transducers as an information source for estimation. In in vitro tests, the resultant estimation performance was acceptable to alppy the proposed algorithm to animal experiments and further clinical applications.

  • PDF

사물인터넷 기술을 이용한 가스상 물질 측정용 스마트센서 개발과 향후과제 (Development of an IoT Smart Sensor for Detecting Gaseous Materials)

  • 김욱;김영교;유연선;정기효;최원준;이완형;강성규;함승헌
    • 한국산업보건학회지
    • /
    • 제32권1호
    • /
    • pp.78-88
    • /
    • 2022
  • Objectives: To develop the smart sensor to protect worker's health from chemical exposure by adopting ICT (Information and Communications Technology) technologies. Methods: To develope real-time chemical exposure monitoring system, IoT (Internet of Things) sensor technology and regulations were reviewed. We developed and produced smart sensor. A smart sensor is a system consisting of a sensor unit, a communication unit, and a platform. To verify the performance of smart sensors, each sensor has been certified by the Korea Laboratory Accreditation Scheme (KOLAS). Results: Chemicals (TVOC; Total Volatile Organic Compounds, Cl2: Chlorine, HF: Hydrogen fluoride and HCN: Hydrogen cyanide) were selected according to a priority logic (KOSHA Alert, acute poisoning statistics, literature review). Notifications were set according to OEL (occupational exposure limit). Sensors were selected based on OEL and the capabilities of the sensors. Communication is designed to use LTE (Long Term Evolution) and Wi-Fi at the same time for convenience. Electronic platform were applied to build this monitoring system. Conclusions: Real-time monitoring system for OEL of hazardous chemicals in workplace was developed. Smart sensor can detect chemicals to complement monitoring of traditional workplace environmental monitoring such as short term and peak exposure. Further research is needed to expand the scope of application, improve reliability, and systematically application.

방사선 의료영상 잡음제거를 위한 퍼지논리 활용 다해상도 기반 유도필터 (A Multi Resolution Based Guided Filter Using Fuzzy Logic for X-Ray Medical Images)

  • 고승현;수레쉬 라에 판트;이준환
    • 한국지능시스템학회논문지
    • /
    • 제24권4호
    • /
    • pp.372-378
    • /
    • 2014
  • 방사선 의료영상의 잡음은 화질을 떨어트리며, 진단의 정확성을 낮추는 원인이 된다. 특별히 환자보호를 목적으로 방사선 피폭량을 줄인 저선량 의료영상은 잡음 수준이 높아 잡음 제거 기술이 더욱 중요하다. 본 논문에서는 다양한 해상도에서 경계선 특징을 보존하며 잡음을 효과적으로 제거하는 잡음제거 방법을 제안한다. 제안된 방법에서는 영상을 여러 개의 해상도의 피라미드 영상으로 분해하고, 각각의 분해된 영상으로 부터 퍼지 규칙기반 경계선 검출기를 통하여 안정된 경계 신뢰도 맵을 얻는다. 이들 다해상도 영상의 경계 신뢰도 맵은 유도 필터의 파라메터를 적응적으로 결정하며, 이를 이용하여 해당 영상의 경계를 보전하며 잡음을 제거한다. 이렇게 잡음이 제거된 다해상도 영상은 보간법을 통하여 확장되고 합성되어 결과영상을 얻는다. 제안된 방법은 미디언 필터, 양방향 필터, 유도 필터 등과 비교하여 경계선을 잘 보존하며, 잡음제거 능력이 우수함을 실험을 통해 확인하였다.

CPL을 이용한 저전력 격자 웨이브 디지털 필터의 설계 (Low-power Lattice Wave Digital Filter Design Using CPL)

  • 김대연;이영중;정진균;정항근
    • 전자공학회논문지D
    • /
    • 제35D권10호
    • /
    • pp.39-50
    • /
    • 1998
  • 넓은 통과대역과 좁은 천이대역폭을 갖는 디지털 필터는 이동통신 장비의 CODEC이나 의료장비등에 사용된다. 이러한 주파수 특성을 갖는 디지털 필터는 다른 주파수 특성의 디지털 필터에 비해 계수 및 내부신호의 양자화 영향을 크게 받기 때문에 긴 워드 길이가 요구되며 이로 인해 칩의 면적 및 소모 전력이 증가한다. 본 논문에서는 이러한 주파수 특성을 갖는 디지털 필터의 저전력 구현을 위하여 CPL (Complementary Pass-Transistor Logic), 격자 웨이브 디지털 필터와 수정된 DIFIR (Decomposed & Interpolated FIR) 알고리듬을 이용한 설계 방법을 제시한다. CPL에서의 단락전류 성분을 줄이기 위하여 PMOS 몸체효과, PMOS latch 및 weak PMOS를 이용하는 3가지 방법에 대해 시뮬레이션을 통하여 비교한 결과 전파지연, 에너지 소모 및 잡음여유 면에서 PMOS latch를 사용하는 방법이 가장 유리하였다. 통찰력을 가지고 CPL 회로를 최적화하기 위해 CPL 기본구조에 대해 시뮬레이션 결과로부터 전파지연과 에너지 소모에 대한 경험식을 유도하여 트랜지스터의 크기를 정하는데 적용하였다. 또한 필터계수를 CSD (Canonic Signed Digit)로 변환하고 계수 양자화 프로그램을 이용하여 필터계수의 non-zero 비트수를 최소화시켜 곱셈기를 효율적으로 구현하였다. 알고리듬 측면에서 하드웨어 비용을 최소화하기 위해 수정된 DIFIR 알고리듬을 사용하였다. 시뮬레이션 결과 제안된 방법의 전력 소모가 기존 방법보다 38% 정도 감소되었다.

  • PDF

한의학적(韓醫學的) 대상관(對象觀)의 특징과 성격 (The Characteristic and Implication of the View of Object in Oriental Medicine)

  • 이충열
    • 대한한의학회지
    • /
    • 제16권1호통권29호
    • /
    • pp.505-530
    • /
    • 1995
  • Recently some people in learned circles of oriental medicine raised a Question about a terminological problem, i.e., 'oriental medical'. This question was thought as an attempt to find out the identity of oriental medicine which exists among the various current medical knowledge systems. In spite of same object, human body, there are diverse medical knowledge systems which has different concepts and theories. This come from the difference of a view of object which defines the experiences of that. The knowledge system of oriental medicine was established by the view of object in oriental medicine which depended on the way of thinking as Yin and Yang. The view of object in oriental medicine has come out in the special cultural soil, namely, the oriental world. Because of this the view of object in oriental medicine cannot be seperated from the oriental world view. What distintive feature does the oriental world view have? It can be summarized as the holistic, dynamical and organic ideas of the world. The term 'oriental medical' is being used to emphasize the characteristic and the peculiarity of the oriental medicine among the various medical knowledge systems. Can the current so called scientific method accept this peculiar and special method of oriental medicine? The efforts of philosophers who had been stimulated by the awful scientific achivements and had tried to find out the unified method penetrating through all the empirical science by mobilizing the logic and mathematics has became out of date for the raise of a question about the inductive method. On the contrary, the theses of theory-laden observation was accepted widely and the relativism was accepted as a new established theory. But the relativism has its own problem. The relativism was founded upon the concept, the incommensurability, which Khun and Feyerabend had proposed. This concept was criticized strongly by some of philosophers because of its own self-refuting. The view of object in oriental medicine has a relative characteristic in the aspect of its urge that in accordance with the perspective a different medical knowledge system can be possible. But our possible choice is the moderate conceptual relativism. Therefore if the view of object in oriental medicine includes the relative aspect, there is the 'conceptual relativity' between the knowledge system of oriental medicine and the western medicine. This preview an important aspect for the standardization and modernizing research of oriental medicine by lending the knowledge of the western medicine. And when we choose the moderate conceptual relativism, it means that we do not support the extreme relativism, that is, 'anything goes'. The concept of truth and rationality cannot be abandoned, and it plays the role of the norm on the knowledge system of oriental medicine and other knowledge systems of medicine in a limited meaning. And the view of object in oriental medicine has an organic view about the human body and the characteristic which wants to interpret the phenomena of human body by using the holistic method. But the availability of this method will be evaluated by the achievements of oriental medicine. Finally what relationship does the theory of oriental medicine have with the world the theory is applied to? It is recognized that the theory of oriental medicine has the instrumental characteristic. But it can be thought the instrumentalism is different from the oriental medical standpoint in the aspect that the instrumentalism seperates the theoretical existence from the observational existence sharply. Because in the oriental thinking way there is no seperation between the mind of observer and the object and no conflict between the idealism and the realism like the western world. For this problem there must be a further study.

  • PDF