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 253 records · Page 14Linked to original sources
PubMed2003

Rough set-based hybrid fuzzy-neural controller design for industrial wastewater treatment.

Recent advances in control engineering suggest that hybrid control strategies, integrating some ideas and paradigms existing in different soft computing techniques, such as fuzzy logic, genetic algorithms, rough set theory, and neural networks, may provide improved control performance in wastewater treatment processes. This paper presents an innovative hybrid control algorithm leading to integrate the distinct aspects of indiscernibility capability of rough set theory and search capability of genetic algorithms with conventional neural-fuzzy controller design. The methodology proposed in this study employs a three-stage analysis that is designed in series for generating a representative state function, searching for a set of multi-objective control strategies, and performing a rough set-based autotuning for the neural-fuzzy logic controller to make it applicable for controlling an industrial wastewater treatment process. Research findings in the case study clearly indicate that the use of rough set theory to aid in the neural-fuzzy logic controller design can produce relatively better plant performance in terms of operating cost, control stability, and response time simultaneously, which is effective at least in the selected industrial wastewater treatment plant. Such a methodology is anticipated to be capable of dealing with many other types of process control problems in waste treatment processes by making only minor modifications.

Artificial Intelligence↗
PubMed2006

A new detection algorithm (NDA) based on fuzzy cellular neural networks for white blood cell detection.

White blood cell detection is one of the most basic and key steps in the automatic recognition system of white blood cells in microscopic blood images. Its accuracy and stability greatly affect the operating speed and recognition accuracy of the whole system. But there are only a few methods available for cell detection or segmentation due to the complexity of the microscopic images. This paper focuses on this issue. Based on the detailed analysis of the existing two methods--threshold segmentation followed by mathematical morphology (TSMM), and the fuzzy logic method--a new detection algorithm (NDA) based on fuzzy cellular neural networks is proposed. NDA combines the advantages of TSMM and the fuzzy logic method, and overcomes their drawbacks. With NDA, we can detect almost all white blood cells, and the contour of each detected cell is nearly complete. Its adaptability is strong and the running speed is expected to be comparatively high due to the easy hardware implementation of FCN. Experimental results show good performance.

Algorithms↗
PubMed2004

Model-based control of mechanical ventilation: design and clinical validation.

BACKGROUND: We developed a model-based control system using end-tidal carbon dioxide fraction (FE'(CO(2))) to adjust a ventilator during clinical anaesthesia. METHODS: We studied 16 ASA I-II patients (mean age 38 (range 20-59) yr; weight 67 (54-87) kg) during i.v. anaesthesia for elective surgery. After periods of normal ventilation the patients were either hyper- or hypoventilated to assess precision and dynamic behaviour of the control system. These data were compared with a previous group where a fuzzy-logic controller had been used. Responses to different clinical events (invalid carbon dioxide measurement, limb tourniquet release, tube cuff leak, exhaustion of carbon dioxide absorbent, simulation of pulmonary embolism) were also noted. RESULTS: The model-based controller correctly maintained the setpoint. No significant difference was found for the static performance between the two controllers. The dynamic response of the model-based controller was more rapid (P<0.05). The mean rise time after a setpoint increase of 1 vol% was 313 (sd 90) s and 142 (17) s for fuzzy-logic and model-based control, respectively, and after a 1 vol% decrease was 355 (127) s and 177 (36) s, respectively. The new model-based controller had a consistent response to clinical artefacts. CONCLUSION: A model-based FE'(CO(2)) controller can be used in a clinical setting. It reacts appropriately to artefacts, and has a better dynamic response to setpoint changes than a previously described fuzzy-logic controller.

Adolescent↗
PubMed1993

Finite state model of locomotion for functional electrical stimulation systems.

A finite state model of locomotion was developed to simplify a controller design for motor activities of handicapped humans. This paper presents a model developed for real time control of locomotion with functional electrical stimulation (FES) assistive systems. Hierarchical control of locomotion was adopted with three levels: voluntary, coordination and actuator level. This paper deals only with coordination level of control. In our previous studies we demonstrated that a skill-based expert system can be used for coordination level of control in multi-joint FES systems. Basic elements in this skill-based expert system are production rules. Production rules have the form of If-Then conditional expressions. A technique of automatic determination of these conditional expressions is presented in this paper. This technique for automatic synthesis of production rules uses fuzzy logic and artificial neural networks (ANN). The special class of fuzzy logic elements used in this research is called preferential neurons. The preferential neurons were used to estimate the relevance of each of the sensory inputs to the recognition of patterns defined as finite states. The combination of preferential neurons forms a preferential neural network. The preferential neural network belongs to a class of ANNs. The preferential neural network determined the set of finite states convenient for a skill-based expert system for different modalities of locomotion.

Ankle Joint↗
PubMed2002

Neural network identification of high-risk suicide patients.

BACKGROUND: A history of medically serious suicide attempts (MSSA) has been considered a major risk factor for suicide. Backpropagation (BP) neural networks (NN) successfully detected patient files of patients who had committed MSSA but failed to identify MSSA patients when trained with data collected during face-to-face interviews. PRIMARY OBJECTIVES: To develop an expert support system for the detection of suicide risk in patients with major psychiatric disorders using fuzzy adaptive learning control networks (FALCON) and BP enhanced with fuzzy logic neural networks. METHODS AND PROCEDURES: We used four types of input sets: (a) the most significant variables as defined by Garson's calculation of trained BP; (b) variables identified by logistic regression; (c) variables considered significant by experienced clinicians; or (d) the variables considered definitive by the computer programmer. In addition, the complete set of 59 input variables was used. The target variable was the existence of prior MSSA. EXPERIMENTAL INTERVENTIONS: Four training trials were performed with each input set (75% of the data was used for training and 25% for testing). Data was collected from 197 (50 MSSA, 147 non-MSSA) patients hospitalized at Sha'ar Menashe Mental Health Centre. MAIN OUTCOMES AND RESULTS: BP enhanced with fuzzy logic achieved the most accurate results with the three variables chosen by the programmer (mean +/- SD; sensitivity=97% +/- 3.4%, specificity=69.2% +/- 6.9%), and FALCON trained with 15 variables chosen by an expert clinician obtained the highest sensitivity and specificity (mean +/- SD; sensitivity=94% +/- 6.9%, specificity=69% +/- 6.9%). CONCLUSIONS: A combined system of BP enhanced with fuzzy logic and FALCON may improve the detection rate of MSSA patients during patient interviews. A prospective validation study testing a combined system across 1, 2 and 5-year spans may provide a reliable instrument to aid in the detection of suicide prone psychiatric patients.

Adult↗
PubMed2003

Fuzzy epidemics.

The purpose of this paper is to provide a review of the current state of fuzzy logic theory in epidemiology, which is a recent area of research. We present four applications of fuzzy logic theory in epidemic problems, using linguistic fuzzy models, possibility measure, probability of fuzzy events and fuzzy decision making techniques. The results demonstrate that the applications of fuzzy sets in epidemiology is a very promising area of research. The final discussion sets the future stage of fuzzy sets application in epidemiology.

Acquired Immunodeficiency Syndrome↗
PubMed2001

Learning from noisy information in FasArt and FasBack neuro-fuzzy systems.

Neuro-fuzzy systems have been in the focus of recent research as a solution to jointly exploit the main features of fuzzy logic systems and neural networks. Within the application literature, neuro-fuzzy systems can be found as methods for function identification. This approach is supported by theorems that guarantee the possibility of representing arbitrary functions by fuzzy systems. However, due to the fact that real data are often noisy, generation of accurate identifiers is presented as an important problem. Within the Adaptive Resonance Theory (ART), PROBART architecture has been proposed as a solution to this problem. After a detailed comparison of these architectures based on their design principles, the FasArt and FasBack models are proposed. They are neuro-fuzzy identifiers that offer a dual interpretation, as fuzzy logic systems or neural networks. FasArt and FasBack can be trained on noisy data without need of change in their structure or data preprocessing. In the simulation work, a comparative study is carried out on the performances of Fuzzy ARTMAP, PROBART, FasArt and FasBack, focusing on prediction error and network complexity. Results show that FasArt and FasBack clearly enhance the performance of other models in this important problem.

Artifacts↗
PubMedDate not supplied

The Section on Medical Expert and Knowledge-Based Systems at the Department of Medical Computer Sciences of the University of Vienna Medical School.

The Section on Medical Expert and Knowledge-Based Systems at the Department of Medical Computer Sciences pursues methodological research in and practical development of knowledge-based computer systems to assist in the decision-making processes for all areas of medical application. Vagueness of medical terms, uncertainty in the co-occurrence of medical entities, and incompleteness in medical theories are well-known characteristics of medical knowledge and ought to be considered in practically-used medical knowledge-based systems. We found that fuzzy set theory and fuzzy logic are powerful theories that model the above-mentioned characteristics. Fuzzy set theory and fuzzy logic were applied in the following systems: CADIAG-II and MedFrame/CADIAG-IV, FuzzyARDS, and FuzzyKBWean. CADIAG-II and MedFrame/CADIAG-IV are framework programs for consultation systems to aid in the differential diagnostic process in internal medicine. FuzzyARDS is an intelligent on-line monitoring program of data from patients with acute respiratory distress syndrome (ARDS) at an intensive care unit (ICU). It employs fuzzy trend detection and fuzzy automata. FuzzyKBWean is an open-loop fuzzy control program for optimization and quality control of the ventilation and weaning process of patients after cardiac surgery at the ICU. The above-mentioned computer systems have reached the state of extensive clinical integration and testing at the Vienna General Hospital. The obtained results show the applicability and usefulness of these systems.

Artificial Intelligence↗
PubMed2000

[Fuzzy space based segmentation algorithm on periosteum medical image processing].

Object description in medical image often has the property of fuzziness, and with the development of computing, fuzzy logical theories are progressively used in medical image processing. Color medical images differ in spacial presentation and fuzzy description from grey-scale images and must be analyzed by special methods. In this paper, a new method of bone cell segmentation based on fuzzy logical theories is presented. With the utilization of fuzzy set theories in the steps of color enhancing, feature extraction and automatical segmentation, bone cells are detected from the background. The method has the advantages of high accuracy and flexibility to many situations. Experiments of bone cell images have proved that it is a fast and effective method.

Algorithms↗
PubMedDate not supplied

The intelligent systems in biomedicine laboratory in the Department of Automatic Control and Systems Engineering at the University of Sheffield, UK.

The group has been engaged in research into modelling and control in biomedicine for many years. Initially, this used quantitative approaches but increasingly this has moved towards qualitative techniques, in particular that of fuzzy logic. The current emphasis is on hybrid models (quantitative/qualitative) and hybrid intelligent algorithms (fuzzy logic, neural networks, evolutionary computing) applied into anaesthesia.

Algorithms↗
PubMed2001

Volume delineation by fusion of fuzzy sets obtained from multiplanar tomographic images.

Techniques of three-dimensional (3-D) volume delineation from tomographic medical imaging are usually based on 2-D contour definition. For a given structure, several different contours can be obtained depending on the segmentation method used or the user's choice. The goal of this work is to develop a new method that reduces the inaccuracies generally observed. A minimum volume that is certain to be included in the volume concerned (membership degree mu = 1), and a maximum volume outside which no part of the volume is expected to be found (membership degree mu = 0), are defined semi-automatically. The intermediate fuzziness region (0 < mu < 1) is processed using the theory of possibility. The resulting fuzzy volume is obtained after data fusion from multiplanar slices. The influence of the contrast-to-noise ratio was tested on simulated images. The influence of slice thickness as well as the accuracy of the method were studied on phantoms. The absolute volume error was less than 2% for phantom volumes of 2-8 cm3, whereas the values obtained with conventional methods were much larger than the actual volumes. Clinical experiments were conducted, and the fuzzy logic method gave a volume lower than that obtained with the conventional method. Our fuzzy logic method allows volumes to be determined with better accuracy and reproducibility.

Artificial Intelligence↗
PubMed1999

HyFIS: adaptive neuro-fuzzy inference systems and their application to nonlinear dynamical systems.

This paper proposes an adaptive neuro-fuzzy system, HyFIS (Hybrid neural Fuzzy Inference System), for building and optimising fuzzy models. The proposed model introduces the learning power of neural networks to fuzzy logic systems and provides linguistic meaning to the connectionist architectures. Heuristic fuzzy logic rules and input-output fuzzy membership functions can be optimally tuned from training examples by a hybrid learning scheme comprised of two phases: rule generation phase from data; and rule tuning phase using error backpropagation learning scheme for a neural fuzzy system. To illustrate the performance and applicability of the proposed neuro-fuzzy hybrid model, extensive simulation studies of nonlinear complex dynamic systems are carried out. The proposed method can be applied to an on-line incremental adaptive learning for the prediction and control of nonlinear dynamical systems. Two benchmark case studies are used to demonstrate that the proposed HyFIS system is a superior neuro-fuzzy modelling technique.

Journal Article↗
PubMed2003

Tools for intelligent control: fuzzy controllers, neural networks and genetic algorithms.

The goal of this expository paper is to bring forth the basic current elements of soft computing (fuzzy logic, neural networks, genetic algorithms and genetic programming) and the current applications in intelligent control. Fuzzy sets and fuzzy logic and their applications to control systems have been documented. Other elements of soft computing, such as neural networks and genetic algorithms, are also treated for the novice reader. Each topic will have a number of relevant references of as many key contributors as possible.

Algorithms↗
PubMed2004

Single-trial lambda wave identification using a fuzzy inference system and predictive statistical diagnosis.

The aim of the study was to automate the identification of a saccade-related visual evoked potential (EP) called the lambda wave. The lambda waves were extracted from single trials of electroencephalogram (EEG) waveforms using independent component analysis (ICA). A trial was a set of EEG waveforms recorded from 64 scalp electrode locations while a saccade was performed. Forty saccade-related EEG trials (recorded from four normal subjects) were used in the study. The number of waveforms per trial was reduced from 64 to 22 by pre-processing. The application of ICA to the resulting waveforms produced 880 components (i.e. 4 subjects x 10 trials per subject x 22 components per trial). The components were divided into 373 lambda and 507 nonlambda waves by visual inspection and then they were represented by one spatial and two temporal features. The classification performance of a Bayesian approach called predictive statistical diagnosis (PSD) was compared with that of a fuzzy logic approach called a fuzzy inference system (FIS). The outputs from the two classification approaches were then combined and the resulting discrimination accuracy was evaluated. For each approach, half the data from the lambda and nonlambda wave categories were used to determine the operating parameters of the classification schemes while the rest (i.e. the validation set) were used to evaluate their classification accuracies. The sensitivity and specificity values when the classification approaches were applied to the lambda wave validation data set were as follows: for the PSD 92.51% and 91.73% respectively, for the FIS 95.72% and 89.76% respectively, and for the combined FIS and PSD approach 97.33% and 97.24% respectively (classification threshold was 0.5). The devised signal processing techniques together with the classification approaches provided for an effective extraction and classification of the single-trial lambda waves. However, as only four subjects were included, it will be valuable to further evaluate the methods on a larger group of subjects.

Adult↗
PubMed1996

Children's processing of prosodic cues for phrasal interpretation.

Using synthetic speech, word duration and fundamental frequency (F0) contours were parametrically manipulated to examine processes of phrasal interpretation by adult and child (5 and 7 years old) listeners. From an adult male voice, versions of the phrase "pink and green and white" were resynthesized to produce stimuli suggesting two possible interpretations: [(pink and green) and white] and [pink and (green and white)]. For each stimulus, listeners pointed to a picture to indicate which interpretation was intended. All subjects used duration and (to a lesser extent) intonation as perceptually salient cues for phrasal interpretation. The manner in which subjects processed this information was evaluated by comparing subjects' performance with the predictions of three different information processing models: a nonindependent cue-evaluation model, and two independent cue-evaluation models (an additive model, and the multiplicative, fuzzy logical model). Performance was best described by the fuzzy logical model, which assumes independent cue evaluation and generates a classification function characterized by cue trading relations. The results suggest that, similar to adults, children as young as 5 years of age rely on acoustic-prosodic information for syntactic phrase interpretation, and they process this information in an adultlike manner.

Adult↗
PubMed2002

Modeling for neuromonitoring depth of anesthesia.

This article reviews the various modeling techniques for neuromonitoring depth of anesthesia (DOA). Traditional techniques such as parametric, predictive, optimal, and adaptive modeling, proportional, integral, derivative (PID) modeling, together with modern techniques such as bispectral-based, artificial neural-network-based, fuzzy logic, and neuro-fuzzy modeling, bring us to the current state of the art in DOA neuromonitoring. This article reviews historical information about each of the modern techniques and provides an example demonstrating its implementation; reviews drug pharmacokinetic/pharmacodynamic (PK/PD) and drug interaction PK/PD modeling techniques for a balanced total intravenous anesthesia (TIVA) administration; and discusses the existing technical problems and clinical challenges, suggesting new techniques necessary for the future development of a DOA monitoring and control system.

Anesthesia↗
PubMed2003

Database mining with adaptive fuzzy partition: application to the prediction of pesticide toxicity on rats.

A data set of 235 pesticide compounds, divided into three classes according to their toxicity toward rats, was analyzed by a fuzzy logic procedure called adaptive fuzzy partition (AFP). This method allows the establishment of molecular descriptor/chemical activity relationships by dynamically dividing the descriptor space into a set of fuzzily partitioned subspaces. A set of 153 molecular descriptors was analyzed, including topological, physicochemical, quantum mechanical, constitutional, and electronic parameters, and the most relevant descriptors were selected with the help of a procedure combining genetic algorithm concepts and a stepwise method. The ability of this AFP model to classify the three toxicity classes was validated after dividing the data set compounds into training and test sets, including 165 and 70 molecules, respectively. The experimental class was correctly predicted for 76% of the test-set compounds. Furthermore, the most toxic class, particularly important for real applications of the toxicity models, was correctly predicted in 86% of cases. Finally, a comparison between the results obtained by AFP and those obtained by other classic classification techniques showed that AFP improved the predictive power of the proposed models.

Algorithms↗
PubMed2001

Prevention of haemodialysis-induced hypotension by biofeedback control of ultrafiltration and infusion.

BACKGROUND: Haemodialysis-induced hypotension is still a severe complication in spite of all the progress in haemodialysis treatment. Because of its multifactorial causes, haemodialysis-induced hypotension cannot be reliably prevented by conventional ultrafiltration and sodium profiling in open-loop systems, as they are unable to adapt themselves to actual decreases in blood pressure. METHODS: A blood-pressure-guided closed-loop system, for prevention of haemodialysis-induced hypotension by biofeedback-driven computer control of both ultrafiltration and saline infusion was clinically tested in 237 treatments of seven patients prone to hypotension. As medical knowledge on multifactorial causes of hypotension is characterized by a lack in deterministic knowledge, fuzzy logic and linguistic variables were used to involve clinical experience on hypotension phenomena in terms of fuzzy knowledge. Biofeedback control is based on frequent measurements of blood pressure at 5 min intervals. Blood pressure behaviour is described by linguistic variables and fuzzy sets. Adaptive rule bases were used for the simultaneous fuzzy control of both the ultrafiltration and infusion of hypertonic saline (20% NaCl). Proper adaptation of control features to patient's conditions was provided by the critical borderline pressure, which was set by the physician individually at the beginning of each treatment. During the initial and medium phases of the sessions, ultrafiltration rates up to 150% of the average rates were applied as long as decreases in blood pressure could be compensated by saline infusion. The surplus of ultrafiltrate volume was used for blood pressure stabilization in the final phase in most instances by low ultrafiltration rates. RESULTS: The advantages of biofeedback-controlled haemodialysis were demonstrated by both decreasing the frequency of hypotonic episodes and by increasing or maintaining constant levels of systolic blood pressure during the final phase in 88% of treatments. As saline infusion was applied mainly in the initial and medium phases, blood sodium levels were not significantly higher at the end of the sessions, and interdialytic weight gain was not elevated. CONCLUSION: The application of fuzzy logic in the blood-pressure-guided biofeedback control of ultrafiltration and sodium infusion during haemodialysis is able to minimize haemodialysis-induced hypotension.

Biofeedback, Psychology↗