We report the development of fuzzy hardware system for appraising the results of orthodontic treatment. The method of inference is illustrated in Figure 1, and 2. The terms of the antecedent are the are- and post-treatment appraisals. These were treated as fuzzy variables, their membership functions were defined and linked with the conjunction "and". The membership functions of the consequent for the four logical outcomes were defined as the singleton values 10, 6.6, 3.3, and 0. The hardware consists of MFC blocks, and fuzzy logic complement circuits, pin matrix, centroid, and mean value circuits (Figure 3). This computer is the first model designed for appraisal of orthodontic results and improvements are planned for the future. It has demonstrated, however, the utility of fuzzy inference for evaluating orthodontic treatment, which often involves subjective judgements.
This an expert system for thyroid function test using fuzzy theory. The investigations about a given patients start from the laboratory tests (TSH, FreeT4, FreeT3). The final result of investigations consists of the assesment of the thyroid function in terms of three aspects (hormone level, non thyroid illness, inappropriateness), each of which is assigned a linguistlic value describing its impairment degree.
The main aim of Therapeutic Drug Monitoring is to maximize efficacy of drug therapy while minimizing toxic effects. It is often difficult to design dosage regimens, because drug or patient information are very complex and contain defectiveness or fuzziness. So, we applied fuzzy logic to the decision making in drug therapy, and evaluated it's usefulness.
During a surgical operation, anesthesiologists evaluate the patient's vital signs at every moment. The control of blood pressure is the most important task for them in order to keep the patient's normal physiological conditions against surgical stimuli. In this system, we adopt two variables for the input informations, the value of blood pressure at the observation time and the value before 30 seconds, and also one variable for the output, the inhalational concentration of general anesthetics. The rule for the relationship between two input variables and one output is constructed upon clinical experiences. After converting the input data to the fuzzy information with the membership function, the inhalational concentration is determined by using a fuzzy inference. For the clinical demand, two types of rules, the "rapid rule" and the "slow rule" are prepared for responding to the abrupt and gradual changes of blood pressure, respectively. From the results of animal experiments and some clinical trials, it was suggested that this control system was a useful supporting system for anesthesiologists.
Solution of composite fuzzy relational equation has been viewed as a construction tool for building a fuzzy model. However, this method poses the problem related to the low solvability of the equation. This study describes the three attempts to resolve the low solvability in the solution of composite fuzzy equation. One relates to teh alpha-cut level in the liguistic truth values in the fuzzy relation. Second relates to the evolutionary methods to confirm the observed input data with the fuzzy relational equation had no solutions. Third relates to the distinction of no solutions in the fuzzy relational equations and confirms the consistency of the fuzzy relation which the expert has developed.
Although the achievement of satisfactory results with our newly devised diagnostic system using a fuzzy inference has been already reported, these results were based on subjective evaluation of the findings by only one physician. In order to determine the usefulness of this diagnostic system for general use, ultrasonic images from 50 cases of histologically confirmed thyroid nodules, consisting of 22 cases of papillary carcinoma and 28 of benign nodules, were evaluated by nine examiners; six physicians and three medical technicians with varying degrees of experience. Then their subjective diagnostic results were compared with those of our diagnostic system with a fuzzy inference. The distribution of the degrees of variation in the evaluation of the seven items measured using a fuzzy scale differed among the examiners for the items of shape, margin, boundary and internal echoes, but was relatively similar for the items of hyperechoic spots, cysts and echo level. The sensitivity of cancer diagnoses made with our diagnostic system with a fuzzy inference with input data from eight of the examiners was greater than that of their subjective diagnoses. The diagnostic results for the remaining examiner were the same. The mean diagnostic sensitivity using our system was 84.9%, while that of the diagnoses without the system was 71.7% (P<0.05). There was no statistically significant difference in the mean diagnostic accuracy due to the results of the specificity. We believe that this diagnostic system should be useful for any physician, but especially for novice physicians.
Optokinetic nystagmus (OKN) test is popularly performed to diagnose the disequilibrium-disorders on clinical examination. Only the experts of this diseases can, however, diagnose the test result exactly, which is expressed by patterns of nystagmus requiring the pattern recognition. We constructed the computer assisted instruction system of pattern recognition using the numerical information consisting of 6 variables from the 29 normal and 22 abnormal patterns of the OKN diagnosed by one expert. The theoretical bases were Fuzzy theory especially fuzzy reasoning; if-then rule and max-min method. The high consistent rate (96%) of diagnosis was obtained between the result of the expert and of our system with this data. A lower rate (83.7%) of consistency was calculated with another 251 numerical data of OKN using this rule of fuzzy reasoning. The degree of normality and abnormality were, however, retained in this rule of reasoning. It was concluded that the fuzzy theory was useful to construct the computer assisted instruction system but the subsequent analysis was required to obtain the higher rate of consistency.
Ultrasonogram of prostatic cancer is heterogeneous and the clinical diagnosis by ultrasonography might be variable depending on the physicians. Japanese Urological Association and Pathological Society published "the general rule for clinical and pathological studies on prostatic cancer, 1985", in which six items of echogram should be checked by binary judgement. We used three of them ((1) asymmetry in shape, (2) margins of the capsule, (3) internal echogenicity) and added three items ((4) F-line, (5) image of peripheral zone, (6) distance between the rectal wall and the bottom of capsule). Fuzzy scales and fuzzy inference were used. Membership functions were prepared to each item. The final desicion was made by the center of the gravity of the max-sets of membership functions for output. The results were fitted of some items can not be contributed enough, but the often particular informations can produce sharp effect. So, we are making an attempt to get the inferactive effects among the particular items.
We designed the machine to make a diagnosis of the thyroid gland cancer by using Ultrasonic images with Dr. Katagiri. Now today, We preset the improved machine. The meaning of mprovement is three points. One is to be able to change the number of items easily. Twe is to be able to change the membership functions easily. Tree is to be able to choice the decision patterns. Four is to apply another fields widely.
This paper represents some design features of an intelligent support system for artificial heart control. The proposed system is characterized by incorporation of fuzzy logic circulatory model, HUMAN. This system is designed to provide control strategy minimizes abnormality of recipient's state measured based on the normal state generated by the model HUMAN. Advantages of the incorporation of fuzzy logic into the on-line model HUMAN are discussed.
The capability of the human brain to solve hard problems is one of the main manifestations of intelligent behaviour. Experts in a domain are better than novices in performing problem solving tasks. This is due to their greater experience in solving problems that provides them with better problem solving strategies. Such strategies are knowledge about how to use the knowledge they have in their domain, i.e. metaknowledge. In Artificial Intelligence it is possible to represent such metaknowledge by means of declarative control strategies. Diagnostic reasoning heavily involves metaknowledge to focus attention on the most plausible hypotheses in a given situation and to control the inference process. In this presentation I will develop these concepts in the context of a medical expert system and I will also point out the key role that uncertainty plays in the problem solving strategies.
Medical data provides us the valuable information that is useful for medical diagnosis. Medical information is based on the results of blood tests, physical examinations, interviews and medical images such as X-ray images and ultrasonic images. It is often unclear, however, which facets or items of medical information are most valuable, how much weight should be given to each item, and how diagnostic logic can be used with these items. Moreover, in the process of scaling the degree of these items, fuzzy characteristics are encountered. For example, in considering the item of "Shape" in images, it can often be difficult to judge the degree of disorder clearly. The criteria for evaluation of each item differ from doctor to doctor; i. e., judgement becomes subjective. Fuzziness also exists in the diagnostic logic because its framework cannot be clearly defined. One medical doctor will select some items from medical information for use in diagnosis, while another will choose others. Moreover, the weights of these items do not always remain constant. To construct a diagnostic system using images, we applied a fuzzy scale, by which the degree of variation in items is evaluated, and applied fuzzy inference using membership functions of the weights of the items to the diagnostic system. In this paper, a fuzzy inference and defuzzination system for the medical diagnosis are discussed. We propose a few methods of defuzzination having two dimensional evluation which are different from the type of central points of gravity on thye fuzzy subsets for all rules.
The safety policy of the European Space Agency (ESA) gives precedence to the protection of human life and is applicable to all ESA space flight projects. The ESA safety program is based on the performance of safety analysis comprising hazard analysis and risk assessment. One of the hazardous conditions to be studied for future manned space missions is the exposure of astronauts to gamma radiation. The space radiation environment consists of mainly galactic cosmic rays, trapped particles and solar cosmic rays. The interaction of radiation with the space Vehicle and the astronaut space suit produces direct effects such as ionization and secondary effects i.e. mainly bremsstrahlung. Such a generated photon flux can constitute a significant radiological hazard and can be more penetraing than the electrons that produce it. In hazard analysis all radiation exposure scenarios leading to sever detrimental health effects of the astronauts are identified. In risk assessment the scenarios are evaluated on a probabilistic basis, by taking into consideration all possible uncertainties. There are uncertainties in the radiation environment, the bremsstrahlung generation, the exposure situations of astronauts to radiation and the dose response relationship. In particular in the low dose region there is large uncertainty. Effects of the microgravity environment on orbit increase this uncertainty even further as e.g. biomedical effects can be synergetic and non additive. As there are no relevant statistical data systematic use of subjective expert judgement has to be made. The elicitation and use of expert judgement data as well as the representation of non-statistical uncertainty involves "fuzzy logic". Fuzzy logic is an extension of binary logic and allows the use of qualitative formulations. For example the "degree of information dependence" that determines the coupling of uncertainties in the risk calculations ranges between "no dependence" and "complete dependence". Several radiation hazard and risk reduction alternatives exist. These are passive protection by shielding, in orbit radiation monitoring and warning, mission profile planning and chemotherapeutical protection. Risk reuslts with a proper representation of uncertainties are finally used to determine the optimum radiation hazard and risk reduction approach.