Search PubMed⌕ Search

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.

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

At least 577 records · Page 32Linked to original sources
PubMed1995

Analytic importance of the coding features for the discrimination of vowels in the cochlear implant signal.

The present study considers the analytic importance of the excitation pulse features delivered by a Nucleus cochlear implant using the F0F1F2 strategy. Four cochlear implant patients and 10 speakers uttering two 48-item lists constructed from four basic French vowels participated in this study. Patterns were presented to the patients and played at the input of an acquisition system in order to record the pulse features. Confusion matrices obtained with the patients and with automatic recognition procedures were then compared in order to find out the best-matching models simulating the patients' performances, out of 255 possibilities. The automatic recognition was carried out according to fuzzy logic based on the elementary features of the pulses coding the vowels. Results show that the essential features strongly depended on the subject.

Adult↗
PubMed1995

Independence of lexical context and phonological information in speech perception.

M. A. Pitt (1995a) studied the joint influence of phonological information and lexical context in W. F. Ganong's (1980) task. Pitt improved on earlier studies by collecting enough observations to make possible the quantitative analyses of an individual's data. The present article shows that the results of such analyses demonstrate that the integration of phonological information and lexical context is very well accounted for by the fuzzy logical model of perception (FLMP). Although Pitt concluded that the results of his research argued against the FLMP in favor of an interactive feedback system, his conclusion was based on an analysis of transformed results. It is argued that this use of a response transformation led to incorrect conclusions and that ultimately, models must be tested directly against observed behavior.

Humans↗
PubMed1994

A dermatologic decision support system that processes lexical knowledge from standard textbooks.

We present a decision support system that processes lexical fuzzy knowledge from standard pathology textbooks. The user can choose among four methods: full text and hypertext approaches (classic lexical retrieval methods) and two possibilistic, knowledge-based approaches (the fuzzy logic computation and an adapted evidence combination scheme based upon the theory of belief functions). All these methods, including their algorithms, are presented in this paper. The effectiveness of these approaches is demonstrated by examples from dermatopathology. At the top of the lists of differential diagnoses generated by the system the degree of conformity between the approaches is high.

Algorithms↗
PubMed1994

A device for urologic post-surgical monitoring.

This article reports on the preliminary development of an instrument that is intended to monitor catheterized, post-TURP patients specifically to assist care-providers in the reduction of clot retention. The primary objective of the instrument is to detect conditions that indicate an alarm condition for which the probability of clot retention is considered to be high. In response to an alarm, intervention by means of increased irrigation flow rate or other action is expected. The density of outflow consisting of the mixture of irrigation fluid, urine, and blood from the prostate, is monitored optically. Multiple transducer sites along the catheter improve the monitoring by minimizing the effects of bubbles and particulates in the stream. Development of algorithms for processing the data have concentrated on the use of fuzzy logic in keeping with the linguistic descriptors used by medical experts. This allows the formulation of decision rules that mimic the knowledge base and syntax used by care providers who judge the conditions of the outflow and make decisions about the patient's condition and the optimum flow rate for irrigation fluid. A laboratory prototype has been completed and tested in vitro; a second-generation prototype has been designed in preparation for a clinical study.

Blood Coagulation↗
PubMed1994

Nonlinear approaches for separation of slow and fast phase nystagmus signals.

Central nervous system (CNS) disorders and vestibulo-ocular reflex (VOR) degradation contribute to the loss of orientation and balance, typically causing the illusion of motion. VOR degradation may be caused by illnesses or common prescription medications, and this degradation may have serious repercussions in affecting one's ability to walk, maintain balance, or track moving objects. The two current VOR analysis techniques are applied to nystagmus signals (recordings of eye position during standardized tests) to isolate the two neuronal pathways used. These techniques are only partially successful because the VOR signal is passed through several filtering layers, to isolate the nystagmus signal, leaving it severely altered. In this paper, several alternate approaches are introduced: nonlinear robust ordering procedures, mathematical morphology, and wavelet filtering techniques are demonstrated. All approaches were as successful as the current techniques in isolating data from one neuronal pathway. Techniques for each of the three were also developed which would identify data from the second neuronal pathway as well. The nonlinear approach, which works using raw position data, bypasses layers of filtering. A robust technique is used to identify the points at which the data changes from that due to one neuronal pathway to the other, and the end result is obtained by concatenating the respective segments. The other two approaches work with velocity data obtained by differentiation, and because they are applied to non-original data, their results may be open to the possibility of error. Additionally, the two most recent approaches in the literature (using order statistic filters and fuzzy logic) have been implemented for a comparison of results.

Humans↗
PubMed1993

Cognitive style and perception: the relationship between category width and speech perception, categorization, and discrimination.

Category width, as defined by Pettigrew's (1958) Category Width Scale, is a cognitive variable that purportedly reveals individual differences in categorization strategy. Subjects differ in terms of broadness and narrowness of judgments of category width--to what extent they will accept exemplars as good instances of a category. We tested the hypothesis that category width would be related to how subjects behave in different speech perception tasks. Differences found between extremely broad and narrow categorizers on such tasks would be helpful in understanding the nature of the perceptual and cognitive processes underlying the category width distinction. No effects attributable to category width were found when results were analyzed in terms of subjects' (a) discrimination and feature evaluation of auditory and visual information in speech events, (b) integration of these sources of information, (c) the process of decision, and (d) subjective preference for a two-choice versus a nine-choice response method. The results from both male and female and broad and narrow categorizers supported the predictions made by a fuzzy logical model of perception (FLMP). In the FLMP, people have access to continuous information about each feature of a stimulus, they make independent evaluations of each feature based on this information, the various features are integrated, and a decision is made based on the relative support for the viable alternatives. Given the common processes involved in speech and other pattern perceptual-recognition tasks, we conclude that fundamental processes involved in pattern recognition are unlikely to vary with personality measures, such as category width.

Acoustic Stimulation↗
PubMed1997

Fault diagnosis in an expert system for health services management in the tropics.

An integrated large-scale expert system called Health-2000, for the management of health services in regions where tropical diseases are endemic, has been designed. This system combines knowledge and databases, the contents of which are operated upon by an inference engine, to produce usable information. The system allows a host of applications, ranging from medical diagnosis to fault detection and preventive maintenance of biomedical equipment. The theoretical background and approach used in the development of the fault diagnosis and equipment maintenance sub-system of Health-2000 is presented. Model-based knowledge acquisition, and an extension of the Failure Modes, Effects and Criticality Analysis are two methodologies applied to build its knowledge bases. The inference engine which supports backward and forward chaining, operates on numerical and non-numerical facts, and uses fuzzy logic to handle vague and uncertain knowledge. Fault isolation proceeds in a top-down fashion, from equipment sub-system, to modules and components.

Developing Countries↗
PubMed1998

Automatic classifiers for the interpretation of electrocardiograms.

The morphological diagnosis of ECGs is a pattern recognition procedure. The way the clinician does this is not clearly elucidated. Nevertheless, several models aimed at achieving identical results by automatic means are empleyed. While in the doctor's case this is not exactly so, the computer task for ECG interpretation comprises two distinct and sequential phases: feature extraction and classification. A set of signal measurements containing information for the characterization of the waveform is first obtained. These waveform descriptors are then used to allocate the ECG to one or more diagnostic classes in the classification phase. The classifier can embody rules-of-thumb used by the clinician to decide between conflicting ECG diagnosis and formal or fuzzy logic as a reasoning tool (heuristic classifiers). On the other hand, it can use complex and even abstract signal features as waveform descriptors and different discriminant function models for class allocation (statistical classifiers). More recently, artificial neural network techniques have also been used for signal classification. The authors review feature selection techniques and classification strategies, problems and methods of performance evaluation and results obtained by different classification approaches. A brief discussion of the relative merits of the two main types of ECG classifiers, logical and statistical, is included.

Diagnosis, Computer-Assisted↗
PubMedDate not supplied

Principles underlying real-time nystagmus analysis of horizontal and vertical eye movements recorded with electro-, infra-red-, or video-oculographic techniques.

New methods for separating fast and slow phases of human nystagmus in real time are presented that are adaptive to the time-dependent noise properties of the input eye movement signal and therefore applicable to different recording techniques and directions. The methods employ a statistical filter technique to track slow-phase eye movements, uninfluenced by fast phases and blink artifacts, and fuzzy-logic techniques to identify fast-phase eye movements. Because these two techniques are decoupled from one another, highly accurate phase separation and slow-phase velocity profiles are achieved. In addition, the tracking of the variance of slow-phase and fast-phase eye movement recording permits a quality control of the analysis for different recording techniques and a variety of ocular nystagmus responses. Because blinks impose different eye velocity profiles on the recordings, depending on the type of recording technique and direction (horizontal, vertical), blink detection and its effect on fast-phase amplitude must be individually adjusted to each recording technique. Results are illustrated in the context of simultaneously recorded video-oculographic, infra-red, and electro-oculographic recordings of vestibulo-ocular reflex and optokinetic reflex responses causing horizontal or vertical eye movements.

Algorithms↗
PubMedDate not supplied

A fuzzy-based histogram analysis technique for skin lesion discrimination in dermatology clinical images.

A fuzzy logic-based color histogram analysis technique is presented for discriminating benign skin lesions from malignant melanomas in dermatology clinical images. The approach utilizes a fuzzy set for benign skin lesion color, and alpha-cut and support set cardinality for quantifying a fuzzy ratio skin lesion color feature. Skin lesion discrimination results are reported for the fuzzy ratio and fusion with a previously determined percent melanoma color feature over a data set of 258 clinical images. For the fusion technique, alpha-cuts for the fuzzy ratio can be chosen to recognize over 93.30% of melanomas with approximately 15.67% false positive lesions.

Algorithms↗
PubMed2006

Adaptive neuro-fuzzy modeling of poorly soluble drug formulations.

PURPOSE: The purpose of this study was to evaluate the efficiency of a neuro-fuzzy logic-based methodology to model poorly soluble drug formulations and predict the development of the particle size that has been proven to be an important factor for long-term stability. METHODS: An adaptive neuro-fuzzy inference system was used to model the natural structures within the data and construct a set of fuzzy rules that can subsequently used as a predictive tool. The model was implemented in Matlab 6.5 and trained using 75% of an experimental data set. Subsequently, the model was evaluated and tested using the remaining 25%, and the predicted values of the particle size were compared to the ones from the experimental data. The produced adaptive neuro-fuzzy inference system-based model consisted of four inputs, i.e., acetone, propylene glycol, POE-5 phytosterol (BPS-5), and hydroxypropylmethylcellulose 90SH-50, with four membership functions each. Moreover, 256 fuzzy rules were employed in the model structure. RESULTS: Model training resulted in a root mean square error of 4.5 x 10(-3), whereas model testing proved its highly predictive efficiency, achieving a correlation coefficient of 0.99 between the actual and the predicted values of the particle size (mean diameter). CONCLUSIONS: Neuro-fuzzy modeling has been proven to be a realistic and promising tool for predicting the particle size of drug formulations with an easy and fast way, after proper training and testing.

Acetone↗
PubMed2004

Approaching the Ocean Color problem using fuzzy rules.

In this paper, we propose a fuzzy logic-based approach which exploits remotely sensed multispectral measurements of the reflected sunlight to estimate the concentration of optically active constituents of the sea water. The relation between the concentrations of interest and the subsurface reflectances is modeled by a set of fuzzy rules extracted automatically from the data through a two-step procedure. First, a compact initial rule base is generated by projecting onto the input variables the clusters produced by a fuzzy clustering algorithm. Then, a genetic algorithm is applied to optimize the rules. Appropriate constraints maintain the semantic properties of the initial model during the genetic evolution. Results of the application of the fuzzy model obtained from data simulated with an ocean color model over the channels of the Medium Resolution Imaging Spectrometer are shown and discussed.

Algorithms↗
PubMed2004

Different methodologies to quantify uncertainties of air emissions.

Characterization of the uncertainty associated with air emission estimates is of critical importance especially in the compilation of air emission inventories. In this paper, two different theories are discussed and applied to evaluate air emissions uncertainty. In addition to numerical analysis, which is also recommended in the framework of the United Nation Convention on Climate Change guidelines with reference to Monte Carlo and Bootstrap simulation models, fuzzy analysis is also proposed. The methodologies are discussed and applied to an Italian example case study. Air concentration values are measured from two electric power plants: a coal plant, consisting of two boilers and a fuel oil plant, of four boilers; the pollutants considered are sulphur dioxide (SO(2)), nitrogen oxides (NO(X)), carbon monoxide (CO) and particulate matter (PM). Monte Carlo, Bootstrap and fuzzy methods have been applied to estimate uncertainty of these data. Regarding Monte Carlo, the most accurate results apply to Gaussian distributions; a good approximation is also observed for other distributions with almost regular features either positive asymmetrical or negative asymmetrical. Bootstrap, on the other hand, gives a good uncertainty estimation for irregular and asymmetrical distributions. The logic of fuzzy analysis, where data are represented as vague and indefinite in opposition to the traditional conception of neatness, certain classification and exactness of the data, follows a different description. In addition to randomness (stochastic variability) only, fuzzy theory deals with imprecision (vagueness) of data. Fuzzy variance of the data set was calculated; the results cannot be directly compared with empirical data but the overall performance of the theory is analysed. Fuzzy theory may appear more suitable for qualitative reasoning than for a quantitative estimation of uncertainty, but it suits well when little information and few measurements are available and when distributions of data are not properly known.

Air Pollutants↗
PubMed1997

Fuzzy systems approach to diagnosis in the postpartum cow.

A computer-based fuzzy systems approach to diagnosis was compared with a standard rule-based approach for ability to diagnose 1 or more of 14 diseases in postpartum cows. A comparison between the 2 systems, using the same 12 input variables (clinical signs and laboratory measurements), resulted in 93% diagnostic agreement. Much of the study compared a fuzzy diagnostic system that had 12 input variables with a standard system that had 17 input variables. The results indicated that the fuzzy diagnostic system was more efficient to design (fewer rules), that the fuzzy system often provided a more accurate diagnosis, and that selection of input variables is critically important to diagnostic accuracy for any computer-based diagnostic system. The apparent advantages of fuzzy logic-based decision systems over standard rule-based methods of modeling the medical diagnostic process warrant continued study to determine limitations and other possible applications.

Animals↗
PubMed2004

Computerized coding of injury narrative data from the National Health Interview Survey.

OBJECTIVE: To investigate the accuracy of a computerized method for classifying injury narratives into external-cause-of-injury and poisoning (E-code) categories. METHODS: This study used injury narratives and corresponding E-codes assigned by experts from the 1997 and 1998 US National Health Interview Survey (NHIS). A Fuzzy Bayesian model was used to assign injury descriptions to 13 E-code categories. Sensitivity, specificity and positive predictive value were measured by comparing the computer generated codes with E-code categories assigned by experts. RESULTS: The computer program correctly classified 4695 (82.7%) of the 5677 injury narratives when multiple words were included as keywords in the model. The use of multiple-word predictors compared with using single words alone improved both the sensitivity and specificity of the computer generated codes. The program is capable of identifying and filtering out cases that would benefit most from manual coding. For example, the program could be used to code the narrative if the maximum probability of a category given the keywords in the narrative was at least 0.9. If the maximum probability was lower than 0.9 (which will be the case for approximately 33% of the narratives) the case would be filtered out for manual review. CONCLUSIONS: A computer program based on Fuzzy Bayes logic is capable of accurately categorizing cause-of-injury codes from injury narratives. The capacity to filter out certain cases for manual coding improves the utility of this process.

Forms and Records Control↗
PubMedDate not supplied

Fuzzy oxygen control system for the indirect calorimeter of premature infants.

The indirect calorimetric system of measuring O2 consumption and CO2 production has been developed for energy expenditure estimation of premature infants. This apparatus requires an input room air mixing with pure oxygen to obtain a stable gas with definite oxygen concentration flowing into the hood for neonatal breath or supplemental oxygen treatments. In this paper, we propose an oxygen control system based on fuzzy control logic to automatically adjust the mixing ratio of room air to pure oxygen gas from the hospital's supply system, designed for premature infants. It is designed to reduce the risks of oxygenic toxicity and retinopathy of prematurity by lowering the overshoot of oxygen concentration. Its performance was evaluated and optimal membership functions were obtained. As a result, the system is quite robust with little effect caused by disturbance and has little or no overshoot when step changing the level of oxygen concentration in the mixed gas.

Calorimetry, Indirect↗
PubMed1998

Primer design for large scale sequencing.

We have developed PRIDE, a primer design program that automatically designs primers in single contigs or whole sequencing projects to extend the already known sequence and to double strand single-stranded regions. The program is fully integrated into the Staden package (GAP4) and accessible with a graphical user interface. PRIDE uses a fuzzy logic-based system to calculate primer qualities. The computational performance of PRIDE is enhanced by using suffix trees to store the huge amount of data being produced. A test set of 110 sequencing primers and 11 PCR primer pairs has been designed on genomic templates, cDNAs and sequences containing repetitive elements to analyze PRIDE's success rate. The high performance of PRIDE, combined with its minimal requirement of user interaction and its fast algorithm, make this program useful for the large scale design of primers, especially in large sequencing projects.

Algorithms↗