SEARCH · Search PubMed

Results for “Fuzzy Logic”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 559 records · Page 31Linked to original sources

PubMed1996

Perceptual recognition of facial affect: cross-cultural comparisons.

Previous research has shown that the perception of affect in faces is well described by the fuzzy logical model of perception (FLMP). In this study, we asked whether the processes involved in recognition depended on the race/culture of the face and/or of the perceiver. A computer-generated face was used to manipulate two features of facial affect: brow deflection and mouth deflection. An expanded-factorial design was used, with four levels of brow deflection crossed with four levels of mouth deflection, as well as their corresponding half-face conditions. Participants identified these faces as either happy or angry. Japanese and U.S. students were tested on faces from these two countries that were texture-mapped onto the animated face. The FLMP gave the best description of performance for both groups and for both types of faces. These findings challenge previous claims of holistic perception, categorical perception, and additive feature integration.

Adult↗

PubMed1993

Long-term training, transfer, and retention in learning to lipread.

A long-term training paradigm in lipreading was used to test the fuzzy logical model of perception (FLMP). This model has been used successfully to describe the joint contribution of audible and visible speech in bimodal speech perception. Tests of the model were extended in the present experiment to include the prediction of confusion matrices, as well as performance at several different levels of skill. The predictions of the FLMP were contrasted with the predictions of a prelabeling integration model (PRLM). Subjects were taught to lipread 22 initial consonants in three different vowel contexts. Training involved a variety of discrimination and identification lessons with the consonant-vowel syllables. Repeated testing was given on syllables, words, and sentences. The test items were presented visually, auditorily, and bimodally, at normal rate or three times normal rate. The subjects improved in their lipreading ability across all three types of test items. Replicating previous results, the present study illustrates that substantial gains in lipreading performance are possible. Relative to the PRLM, the FLMP gave a better description of the confusion matrices at both the beginning and the end of practice. One new finding from the present study is that the FLMP can account for the gains in bimodal speech perception as subjects improve their lipreading and listening abilities.

Adolescent↗

PubMed1996

An intelligent system with EMG-based joint angle estimation for telemanipulation.

Bio-control of telemanipulators is being researched as an alternate control strategy. This study investigates the use of surface EMG from the biceps to predict joint angle during flexion of the arm that can be used to control an anthropomorphic telemanipulator. An intelligent system based on neural networks and fuzzy logic has been developed to use the processed surface EMG signal and predict the joint angle. The system has been tested on various angles of flexion-extension of the arm and at several speeds of flexion-extension. Preliminary results show the RMS error between the predicted angle and the actual angle to be less than 3% during training and less than 15% during testing. The technique of direct bio-control using EMG has the potential as an interface for telemanipulation applications.

Artificial Intelligence↗

PubMed2000

Dynamic optimization of hybridoma growth in a fed-batch bioreactor.

This study addressed the problem of maximizing cell mass and monoclonal antibody production from a fed-batch hybridoma cell culture. We hypothesized that inaccuracies in the process model limited the mathematical optimization. On the basis of shaker flask data, we established a simple phenomenological model with cell mass and lactate production as the controlled variables. We then formulated an optimal control algorithm, which calculated the process-model mismatch at each sampling time, updated the model parameters, and re-optimized the substrate concentrations dynamically throughout the time course of the batch. Manipulated variables were feed rates of glucose and glutamine. Dynamic parameter adjustment was done using a fuzzy logic technique, while a heuristic random optimizer (HRO) optimized the feed rates. The parameters selected for updating were specific growth rate and the yield coefficient of lactate from glucose. These were chosen by a sensitivity analysis. The cell mass produced using dynamic optimization was compared to the cell mass produced for an unoptimized case, and for a one-time optimization at the beginning of the batch. Substantial improvements in reactor productivity resulted from dynamic re-optimization and parameter adjustment. We demonstrated first that a single offline optimization of substrate concentration at the start of the batch significantly increased the yield of cell mass by 27% over an unoptimized fermentation. Periodic optimization online increased yield of cell mass per batch by 44% over the single offline optimization. Concomitantly, the yield of monoclonal antibody increased by 31% over the off-line optimization case. For batch and fed-batch processes, this appears to be a suitable arrangement to account for inaccuracies in process models. This suggests that implementation of advanced yet inexpensive techniques can improve performance of fed-batch reactors employed in hybridoma cell culture.

Antibodies, Monoclonal↗

PubMed2000

The development of algorithms in electrical impedance computerized tomography.

Electrical Impedance Computerized Tomography (EICT) is an imaging method to reconstruct the impedance distribution inside of domain through the boundary injected current and display the impedance contrast ratio as an image. This paper concentrates on developing two algorithms to enhance the quality of the conductivity image. The two algorithms are "Fine-Mesh Conversion Method" and "Sub-Domain EICT Method". "Fine-Mesh Conversion Method" is a numerical calibration process to find a coarse mesh impedance network that behaves like a fine mesh network in terms of giving similar voltages under the same current excitations. "Sub-Domain EICT" solves a higher resolution EICT with the cost of a lower resolution EICT by combining "Fine-Mesh Conversion Method", and a Fuzzy Logic Inference Systems (FLIS) classifier.

Algorithms↗

PubMedDate not supplied

Development of software in the study of carotid artery in the neck.

The aim of this work was to develop and employ software for the study of the common carotid artery and its branches in the neck. We first constructed geometric models of anatomic components, for the building of knowledge bases to be used in automatic feature extraction techniques from images. Then, we developed a software system characterised by three-dimensional visualisation, image processing functions, knowledge base and a programming language to describe classification processing by means of fuzzy logic. The software system was used to perform automatic reconstruction of three-dimensional models of carotid arteries from contiguous CT scans of the neck. These findings suggest that such software systems represent a useful help in the study of image based diagnosis of carotid arteries.

Carotid Artery, Common↗

PubMedDate not supplied

[Computer simulation of different types of evolutionary process].

The computer model of two alternative variants of biological evolution is proposed. The first variant supposes random while the second--directed change of individual features, thus corresponding to the Darwinian and non-Darwinian evolution. The evolution of fish communities in fresh waters serves as a particular example. The model is executed using object-oriented method of programming and mathematical apparatus of fuzzy logics. The investigation of the model showed that process of Darwinian evolution is connected with significantly greater species diversity and variability of evolutionary process trajectories than non-Darwinian one. On the other hand, non-Darwinian type of evolution provides fast achievement of high individual fitness, especially under conditions of constant environment. Non-Darwinian type evolution failed in big evolutionary alteration (for example, transition to predation); while the Darwinian evolution under the same conditions can produce such alterations though it took more time and many extinct species. Phylogenetic tree of Darwinian evolution is always more complex than of non-Darwinian one under the same conditions.

Animals↗

PubMed2003

[Application of a mathematical algorithm for the detection of electroneuromyographic results in the pathogenesis study of facial dyskinesia].

To carry out a differential diagnosis of two facial dyskinesia (FD) models--facial hemispasm (FH) and facial paraspasm (FP), a combined program of electroneuromyographic (ENMG) examination has been created, using statistical analyses, including that for objects identification based on hybrid neural network with the application of adaptive fuzzy logic method and standard statistics programs (Wilcoxon, Student statistics). In FH, a lesion of peripheral facial neuromotor apparatus with augmentation of functions of inter-neurons in segmental and upper segmental stem levels predominated. In FP, primary afferent strengthening in mimic muscles was accompanied by increased motor neurons activity and reciprocal augmentation of inter-neurons, inhibiting motor portion of V pair. Mathematical algorithm for ENMG results recognition worked out in the study provides a precise differentiation of two FD models and opens possibilities for differential diagnosis of other facial motor disorders.

Algorithms↗

PubMedDate not supplied

Multi-valued logic in breast cancer detection.

The aim of this paper is to determine the type of the breast cancer disease. The two classes of separation are malignant respectively benign. A multi-valued logic system (fuzzy system) was develop and applied in this classification. The system uses nine attributes as inputs that were scaled with an integer value in the range between 1 and 10. The attributes represent: 1. Clump Thickness, 2. Uniformity of Cell Size, 3. Uniformity of Cell Shape, 4. Marginal Adhesion, 5. Single Epithelial Cell Size, 6. Bare Nuclei, 7. Bland Chromatin, 8. Normal Nucleoli, 9. Mitoses. After training the system managed to get a good detection with an error less than 5%.

Algorithms↗

PubMed2004

Artificial neural network in pharmacoeconomics.

Pharmacoeconomics research identifies, measures, and compares the costs (resources consumed) and consequences of medical products and services, where at least one of the compared alternatives is pharmacotherapy. Pharmacoeconomics has been designed to enable the decision maker to identify the preferred choice among existing alternatives. The decisions are often important for the patients' lives on the one hand, and for payers on the other (where the payer is understood as the institution responsible for financial resources allocation). One of the most commonly used types of pharmacoeconomic analysis is cost-effectiveness analysis. Two different alternatives can be compared using cost-effectiveness analysis if only their medical and clinical consequences could be measured in similar units (clinical or physical parameters). The aim of the project is to use an artificial neural network (ANN) for medical effect prediction, which could help in the extrapolation of pharmacoeconomic analysis' results. To depict neural data analysis tools, a database containing 100 non-small cell lung cancer (NSCLC) patients in non-operative IIIB and IV stage has been used. Each patient was described using 30 factors (i.e. sex, age, anticancer drugs dosage) and, as an output value, the expected survival time was established. The role of the ANN system was to predict the patient's survival time based on the above mentioned information. Binary values were tested as outcomes. Positive values (coded as 1) meant that patient survival time would be equal to or longer than 35 weeks. Negative values (coded as 0) meant that the patient survival time would be shorter than 35 weeks. Binary values were obtained using a threshold, which based on the mean survival time of patients derived from literature. Back-propagation as well as fuzzy-logic neural networks were applied. A 10-fold cross validation method was used to obtain the appropriate models. Final results were compared with the generic, logistic regression-based model. The best prediction score of the ANN model was 82%; higher than logistic regression prediction rate.

Antineoplastic Agents↗

PubMed1992

Database technology for medical records.

Paper truncation may be the first goal that comes to mind when people think of computerized medical records, but this is probably the least realistic goal at present. Structuring a medical records system to improve record quality and to open the door to data analysis are two more realistic goals. Of the many significant barriers to computerized medical records, the most serious is the lack of agreement in the medical community regarding what should go into a medical record. Even small steps in that area should bring major improvements in available medical records software. Choosing a database for medical records requires familiarity with database principles and a detailed understanding of data needs. The safe choice is an SQL-based relational database, but a smaller system will suffice if present and future medical records challenges are small enough. The rate of change in the computer world is increasing all the time. Emerging and maturing technologies that can have a significant impact on medical records software include data entry tools such as the mouse, pen, and voice; better data retrieval tools such as GUIs and 4GLs; and software tools that use rules, pattern-matching, hypermedia links, and fuzzy logic to create systems that seem to think like humans. While computerized medical records systems are not yet comparable with medical office management systems, they should be someday. In the meantime, smart physicians will begin exploring possibilities on their own in order to reap some benefits at an early stage and to be better prepared when the tide finally turns.

Databases, Factual↗

PubMed2005

Knowledge logistics as an intelligent service for healthcare.

OBJECTIVES: The technology of grid services is developing fast. This paper presents an approach to the implementation of an intelligent grid service that configures a hospital taking advantage of the knowledge logistics idea. METHODS: The presented approach is based on synergistic integration of knowledge acquired from distributed sources in order to obtain new or complement insufficient knowledge. Presented approach uses ontologies and the formalism of object-oriented constraint networks for knowledge representation and applies ILOG to constraint-based problem solving. RESULTS: The application of the approach is illustrated via a decision support system for a fictitious case study of a hospital configuration in the Binni region. The system showed the ability to produce interrelated solutions for subtasks of the hospital configuration task based on the built ontology and input parameters. Besides, such preferences as cost or time minimization are also considered by the implemented fuzzy logic module that finds a feasible solution. CONCLUSIONS: KL would benefit from the grid, and particularly from the concept of a semantic grid. The scalable architecture of the approach enables its extension with regard to knowledge/information sources number and, thereby, with regard to factors taken into account during complex problem solving. Utilizing ontologies allows integration of the approach into existing processes and facilitates knowledge sharing with similar systems. Application of constraint networks allows rapid problem manipulation and usage of such existing efficient technologies as ILOG.

Artificial Intelligence↗

PubMed2006

Automatic matching of spine images to assess changes in scoliosis.

This paper presents an image matching approach that can be used to measure changes in scoliotic curves. The proposed approach uses a novel fuzzy logic controller to estimate all open parameters. Using fluoroscopy images of a spine phantom, it was found that, with minimal user interaction, the matching of spine images could be achieved with high accuracy (the average errors were around 0.03 mm) and high computational efficiency (requiring less than 1 minute for matching each vertebra).

Automation↗

PubMedDate not supplied

[Hypotension induced by sodium nitroprusside administered via an automatic-adaptive dose regulating system. Experimental development].

Sodium nitroprusside (NPS) is a potent vasodilator which is frequently administered for the control of arterial blood pressure and peripheral resistances. Manual regulation of the dose is difficult and requires a permanent surveillance of patients under treatment. Several attempts have been made to develop an automatized system able to safely control the dose of the drug in clinical practice. However, since now the results have not been completely satisfactory. The aim of our study was to develop of a new automatic-adaptative system able to continuously control the dose of NPS. The system consists of a high precision infusion pump controlled by a microprocessor. Arterial blood pressure is continuously monitorized and according to its values NPS is automatically regulated to maintain blood pressure within a preselected range. A control "fuzzy logic" algorithm was used. We have assessed the efficacy, adaptability, and safeness of the system. The system was tested in 15 mongrel dogs. The protocol was divided into two parts. During the first part a 25% to 30% reduction in blood pressure from baseline values lasting for a period of 4 hours was attempted. The second part was devoted to test the adaptability of the control unit during induced unstable hemodynamic situations. Group I dogs were subjected to volume overload. Group II were treated with noradrenaline to increase blood pressure, and group III underwent a venous bleeding to produce arterial hypotension. Control of arterial blood pressure was achieved after a minimum of 5 min and a maximum of 19 min (mean values = 13.3 min).(ABSTRACT TRUNCATED AT 250 WORDS)

Animals↗

PubMed1982

[The fuzzy set theory as a biomedical diagnostic aid (author's transl)].

In this paper, the theory of fuzzy sets and fuzzy logic is approached as a diagnostic aid for practitioners and biologists. A few theoretical considerations are followed by two practical applications. The first is a modification of the WHO-Fredrickson classification of hyperlipoproteinemias, with the introduction of secondary or minor types corresponding to everyday medical practice. The other is an attempt at classifying the four most prevalent anemias encountered in internal medicine. Recent studies have shown that the various parameters should be grouped on a hierarchical basis.

Anemia↗

PubMedDate not supplied

[Polyclinic-based automated system for mass prophylactic examinations of adolescents].

Some problems of computer-based automating processes of adolescent health screening in an outpatient clinic are discussed. The block diagram of investigations is presented, and results of utilizing the system in a district outpatient clinic are analysed. Operation of the system in an interactive mode is described by using algorithms of fuzzy logic.

Adolescent↗

PubMed1984

[Computer-assisted diagnosis and its application in pancreatic diseases].

The medical expert system CADIAC-2 based on fuzzy logic supports diagnostic decisions in the field of internal medicine. A medical knowledge base contains nosological descriptions of diseases. Given patient data, diagnostic decisions are made on the basis of the medical knowledge stored. Reasonings for the established diagnoses or diagnostic hypotheses are presented as well as plans for further examinations on the patient. Unexplained symptoms, signs or test results are also indicated. The usefulness of CADIAC-2 is demonstrated in a case study involving 38 patients with various pancreating diseases.

Diagnosis, Computer-Assisted↗

PubMed1984

Children's perception of visual and auditory speech.

Preschool children's evaluation and integration of visual and auditory information in speech perception was compared with that of adults. Subjects identified speech events, which consisted of synthetic speech syllables ranging from /ba/ to /da/ combined with a videotaped /ba/, /da/, or no articulation. Both variables influenced the identification judgments for both groups of subjects. The results were used to test current views of the development of perceptual categorization and speech perception. Tests of quantitative models indicated that both preschool children and adults had available continuous and independent sources of information. The results were well described by a fuzzy logical model of perception, which assumes that the perceiver integrates continuous and independent sources of information and determines the relative goodness of match to prototype definitions in memory. The only developmental difference was less of an influence of the visual source of information for children relative to adults. 1 explanation is that the children simply attended less to the visual source. A second experiment eliminated the attentional explanation by showing identical results when the children were also required to indicate whether or not the speaker's mouth was moving.

Adolescent↗