Fuzzy Detection Research Articles

DIRECT MODEL REFERENCE TAKAGI–SUGENO FUZZY CONTROL OF SISO NONLINEAR SYSTEMS DESIGN BY MEMBERSHIP FUNCTION

What is discussed in this article is to find a way for membership functions optimally. In most scholars, these functions are constant and have a limited number. Therefore, in some cases, this limitation reduces control performance improvement. One of the best solutions is finding these functions in a differential form. This article used the Takagi-Sugeno function as a fuzzy detector to identify and control a nonlinear SISO system by direct adaptive reference model control. Using this method with Lyapunov for the stability of the control system makes output fuzzy linguistic variables optimally. Then simultaneously using these values, membership functions can be defined in differential form. Therefore, there is no other limitation in the variance and midpoint.

Actuator fault tolerance based on continuous‐time fuzzy singularly perturbed model

AbstractActuator fault tolerance based on fuzzy singularly perturbed model (FSPM) for nonlinear singularly perturbed systems (NSPSs) is investigated. A continuous‐time FSPM with subtractive faults on control input is presented to describe NSPSs with actuator faults, which is less conservative than slow–fast submodel methods. A hybrid fuzzy controller (HFC) consisting of a fuzzy detector and a fault‐tolerant controller can realize real‐time fault tolerance, such that the target system with actuator faults is stabilized. The theorem to solve controller gains is derived by using Lyapunov, singular perturbation, , and Schur complement theories, which can avoid the problem that the feasible solutions cannot be obtained by solving linear matrix inequalities (LMIs). A nonlinear item was replaced by a linear item, which provides a good idea for solving nonlinear matrix inequalities. The sudden and remittent actuator faults of a motor system are suppressed by using the above approaches.

Sensor fault detection based on fuzzy singularly perturbed model

Fuzzy singularly perturbed modelling and sensor fault detection for nonlinear singularly perturbed systems (NSPSs) are investigated. A continuous-time fuzzy singularly perturbed model with superimposed faults on state variables and external disturbances are established to describe NSPSs with sensor faults. Based on the model, a novelty fuzzy fault detector (FFD) is designed, and the sufficient conditions for performance are derived. The above approaches are applied to a CE150 helicopter with abrupt and intermittent faults on sensors. The innovations of this paper are as follows: (i) The nonlinear and slow–fast time-scales are described by a united continuous-time fuzzy singularly perturbed model, and based-it a FFD is designed, which can avoid the incomplete decoupling problem caused by decomposition methods; (ii) The sensor faults are expressed by the superimposed faults on state variables when the continuous-time fuzzy singularly perturbed model is constructed, which is less conservative than existing methods; (iii) In the FFD design, the first-order derivative model of the estimate function for sensor faults is established, and it is combined with a fuzzy observer, which can improve the detection accuracy of the FFD; (iv) control technology is introduced into the FFD design process to suppress external disturbances.

Psychological health analysis based on fuzzy assisted neural network model for sports person

Stress is indeed a life aspect that influences everyone, even though athletes seem to suffer from it one step ahead of others because of the extent they are expected to balance between coursework, workouts, and competitions, along with everyday life and family stress. Therefore, an efficient psychological health analysis for sportspersons is crucial in sports training. This paper introduces a Fuzzy-assisted Neural Network model for Psychological Health Analysis (FNN-PHA) to assess mental stress by monitoring the Electro Cardio Gram signal (ECG), Electroencephalogram (EEG), and Pulse rate. This paper integrates the fuzzy assisted Petri nets, fuzzy assisted k-complex detector, and fuzzy assisted transient time analyzer to ensure the psychological health analysis neural network model’s adaptive performance. The strength of the proposed fuzzy model demonstrates interpretability against the accuracy of different criteria. The simulation analysis shows that the FNN-PHA model enhances the prediction ratio of 98.7%, emotional stability of 96.7%, personal growth of 95.7%, physical fitness level of 97.8%, and depression ratio of 12.5% when compared to other existing models.

Fuzzy CFAR Detectors for MIMO Radars in Homogeneous and Non-Homogeneous Pareto Clutter

In this paper, we propose to use fuzzy fusion rules to improve the performances of the CA-CFAR and OS-CFAR detectors for non-coherent MIMO radars in homogenous and non-homogenous Pareto background. First, the membership function for each individual detector is computed. At the fusion center, the membership functions are combined using four fuzzy fusion rules, namely; the “MIN”, “MAX”, “algebraic product” and the “algebraic sum” to yield a binary decision after defuzzification. The obtained results show that for a number of nodes equal to four, the performance is the best for a high number of receivers. In homogeneous background, the “algebraic product” fusion rule gives the best result when SCR > 4 dB whereas the “algebraic sum” is the best when SCR < 4 dB for the CA-CFAR. For the OS-CFAR, it is clearly shown that the “algebraic product” is the best. In non-homogenous case, the “algebraic sum” fusion rule gives the best results for the CA-CFAR, and the “algebraic product” for the OS-CFAR.

Fuzzy Fault Detection for Permanent Magnet Synchronous Motor

In the transition to automated and automatic manufacturing an urgent problem is to increase the reliability of mobile robots (MR) and their drives, creation of devices to monitor the technical characteristics of MR, diagnose and predict the remaining resource. Inspite of the high relevance of the diagnosing MR drives problem, there are no generally accepted methodology for diagnosing MR drives, criteria for selecting methods, parameters and volumes of diagnostics at present. An unsolved problem, related to the diagnosis of MR drives and the prediction of their residual life remains, is the development of methods that allow to carry out of automatic complex multiparametric diagnostics and prediction of the residual life using artificial intelligence methods. Effective fault detection and diagnosis can improve the reliability of the MR drive and avoid costly maintenance. In this paper a fault detection scheme for synchronous motors with permanent magnets based on a fuzzy system is proposed. The sequence current components (positive and negative sequence currents) are used as fault indicators and are set as input to the fuzzy fault detector. The expediency of the proposed scheme for determining of various types of faults for a synchronous motor with permanent magnets under various operating conditions is simulated using the SimInTech software.

Fuzzy DNA Strand Displacement: A Strategy to Decrease the Complexity of DNA Network Design

AbstractToehold‐mediated DNA strand displacement endows DNA nanostructures with dynamic response capability. However, the complexity of sequence design dramatically increases as the size of the DNA network increases. We attribute this problem to the mechanism of toehold‐mediated strand displacement, termed exact strand displacement (ESD), in which one input strand corresponds to one specific substrate. In this work, we propose an alternative to toehold‐mediated DNA strand displacement, termed fuzzy strand displacement (FSD), in which one‐to‐many and many‐to‐one relationships are established between the input strand and the substrate, to reduce the complexity. We have constructed four modules, termed converter, reporter, fuzzy detector, and fuzzy trigger, and demonstrated that a sequence pattern recognition network composed of these modules requires less complex sequence design than an equivalent network based on toehold‐mediated DNA strand displacement.

Fuzzy Based Detection of Malicious Activity for Security Assessment of MANET

Wireless MANET is particularly vulnerable due to its fundamental characteristics such as open medium, dynamic topology, distributed cooperation, congestion, energy constrained, variable capacity links and security. Due to security vulnerabilities and dynamic nature of network, wireless mobile ad-hoc networks may be unprotected against packet dropping attacks by any unauthorized node. This paper proposes fuzzy based secure architecture (FBSA) for mobile ad-hoc network in which node classification and detection of malicious activity is done through fuzzy detector. After detection of malicious activity, comparative study is performed on various parameters such as packet delivery ratio, average throughput, total packet forwarding and percentage of detection with variation in node speed.

An adaptive image filter based on the fuzzy transform for impulse noise reduction

Impulse noise, also known as impulsive noise, is one of the most common types of noise occurring in digital images. The median filter and morphological filters are often used to remove impulsive noise, but these filters do not preserve image details. In this paper, we first apply the median filter in order to reduce the amount of impulsive noise in a corrupted image. After an application of the direct fuzzy transform (FT) to the resulting image, we restored the pixel values corresponding to locations flagged by the fuzzy rule-based noise detector by means of the inverse fuzzy transform. Finally, we obtained the output of our proposed image filter by combining the restored pixels with the ones marked as noiseless by the aforementioned noise fuzzy detector. We compared the results of our approach that we called adaptive FT-based image filter (AFT-IF) with the ones obtained by a number of other image filters for impulsive noise reduction.

A Decision Support System for Improving Resiliency of Cooperative Adaptive Cruise Control Systems

Advanced driver assistance systems (ADASs) enhance transportation safety and mobility, and reduce impacts on the environment and economical costs, through decreasing driver errors. One of the main features of ADASs is cruise control system that maintains the driver's desired speed without intervention from the driver. Adaptive cruise control (ACC) systems adjust the vehicle's speed to maintain a safe following distance to the vehicle in front. Adding vehicle-to-vehicle and vehicle-to-infrastructure communications (V2X) to ACC systems, result in cooperative adaptive cruise control (CACC) systems, where each vehicle has trajectory data of all other vehicles in the same lane. Although CACC systems offer advantages over ACC systems in increasing throughput and average speed, they are more vulnerable to cyber-security attacks. This is due to V2X communications that increase the attack surface from one vehicle to multiple vehicles. In this paper, we inject common types of attack on the application layer of connected vehicles to show their vulnerability in comparison to autonomous vehicles. We also proposed a decision support system that eliminates risk of inaccurate information. The microscopic work simulates a CACC system with a bi-objective PID controller and a fuzzy detector. A case study is illustrated in detail to verify the system functionality.

Distributed fuzzy maximum‐censored mean level detector‐constant false alarm rate detector based on voting fuzzy fusion rule

In this study, a new distributed fuzzy maximum-censored mean level detector (MX-CMLD) constant false alarm rate (CFAR) detection based on fuzzy space and voting fuzzy fusion rule is presented. In the distributed fuzzy MX-CMLD CFAR detector, each sensor computes the value of the membership function to the false alarm space from the samples of the reference cells and transmits it to the fusion centre. The values are combined according to the voting fuzzy fusion rule and the credibility measure of each sensor to produce a global membership function to the false alarm space in the fusion centre. The simulation results show that the detection performance of the distributed fuzzy MX-CMLD CFAR detector is better than the other fuzzy distributed detectors in homogeneous and non-homogeneous background. Furthermore, the simulation results indicate that the fuzzy algebraic product operator rule gives better performance than the binary AND and the binary OR fusion rules.

Removal of High-Density Salt-and-Pepper Noise in Images With an Iterative Adaptive Fuzzy Filter Using Alpha-Trimmed Mean

Suppression of impulse noise in images is an important problem in image processing. In this paper, we propose a novel adaptive iterative fuzzy filter for denoising images corrupted by impulse noise. It operates in two stages-detection of noisy pixels with an adaptive fuzzy detector followed by denoising using a weighted mean filter on the “good” pixels in the filter window. Experimental results demonstrate the algorithm to be superior to state-of-the-art filters. The filter is also shown to be robust to very high levels of noise, retrieving meaningful detail at noise levels as high as 97%.

Morphological analysis of 3D SPECT images via nilpotent t-norms in diagnosis of Alzheimer's disease

We propose a fuzzy image processing approach serving as a potential diagnostic tool for Alzheimer's disease. We have set up a sequence of several image-processing methods based on morphological fuzzy edge detection followed by a region-growing segmentation. We applied these operations to two sets of three-dimensional SPECT images of human brains: one set of images was composed of patients with Alzheimer's disease and the second was represented by control brains from non-demented patients. Then we undertook an analysis of nilpotent t-norms forming the edge detectors and the parameter of Gaussian filter, and in the end we carried out an evaluation of segments that was computed after the final watershed segmentation. This article provides a detailed description of these methods as well as the analysis of evaluated data using Student's two-sample t-test. Traditional gradient magnitude edge detectors are included and compared with fuzzy detectors. Our goal was to demonstrate the usefulness of the Łukasiewicz BL-algebra in feature extraction of 3D biomedical images by using enhanced methods of image morphology.

AN ARTIFICIAL IMMUNE SYSTEM FOR CLASSIFYING AERODYNAMIC INSTABILITIES OF CENTRIFUGAL COMPRESSORS

Anomaly detection prevents rotating machinery from unforeseeable faults. Using such detection methods, we consider the problem of identifying aerodynamic instabilities in centrifugal compressors by analyzing just the compressor's sound signal. Therefore, an artificial immune system (AIS)-based classification is applied. The deployed v-detectors work according to the negative selection principle and were optimized in position and shape by using a novel procedure of detector generation. This allows reducing the number of detectors while maintaining classification success. Ideas such as multiple layer AIS and fuzzy detector edges enhance the tuning of the classification response. Numerical results demonstrate the design, show the validity for the presented application and give an example for adopting soft computing methods for condition monitoring.

Two-step fuzzy logic-based method for impulse noise detection in colour images

We present a novel fuzzy noise detector based on a fuzzy metric specifically designed to detect impulses. The fuzzy detector is inspired on the recent rank-ordered differences ( ROD) statistic. We propose a noise detection process performed in two steps followed by noise filtering using the vector median filter. Experimental results show that the method is among the best-performing methods for impulse noise reduction and computational analysis indicates that the method is pretty efficient.

Fuzzy screen detector to improve performance of vision-based pointing device

An advanced screen detector is proposed as a tool for selecting the reference object used in movement estimation of a hand-held pointing device. The system applies the fuzzy rules to the selected pairs of line segments of input images in order to find the peripheral framework of the screen. The proposed technique is applicable to various pointing devices detecting the monitor display.

Fuzzy‐based multiuser detector for impulsive CDMA channel

AbstractA new fuzzy multiuser detector for non‐Gaussian synchronous direct sequence code division multiple access (DS‐CDMA) is proposed for jointly mitigating the effects of impulsive noise and multiple access interference (MAI). The proposed scheme combines a linear decorrelator and antenna array with a nonlinear preprocessor based on fuzzy logic and rank ordering. The fuzzy rule is incorporated to combat impulsive noise by eliminating outliers from the received signal. The performance of the proposed scheme is assessed by Monte Carlo simulations and the obtained results demonstrate that the proposed fuzzy detector outperforms other reported schemes in terms of bit error rate (BER) and channel capacity. Copyright © 2007 John Wiley &amp; Sons, Ltd.

Ontological fuzzy agent for electrocardiogram application

The electrocardiogram (ECG) signal is adopted extensively as a low-cost diagnostic procedure to provide information concerning the healthy status of the heart. However, the QRS complex must be calculated accurately before proceeding with the heart rate variability (HRV). In particular, the R peak needs to be detected reliably. This study presents an adaptive fuzzy detector to detect the R peak correctly. Additionally, an ontological fuzzy agent is presented to process the collection of ECG signals. The required knowledge is stored in the ontology, which comprises some personal ontologies and predefined by domain experts. The ontological fuzzy agent retrieves the ECG signals with R peaks marked for HRV analysis and ECG further applications. It contains a personal fuzzy filter, an HRV analysis mechanism, and a fuzzy normed inference engine. Moreover, the ECG fuzzy signal space and some important properties are presented to define the working environment of the agent. An experimental platform has been constructed to test the performance of the agent. The results indicate that the proposed method can work effectively.

Development and comparison of four sleep spindle detection methods

The objective of the present work was to develop and compare methods for automatic detection of bilateral sleep spindles. All-night sleep electroencephalographic (EEG) recordings of 12 healthy subjects with a median age of 40 years were studied. The data contained 6043 visually scored bilateral spindles occurring in frontopolar or central brain location. In the present work a new sigma index for spindle detection was developed, based on the fast Fourier transform (FFT) spectrum, aiming at approximating our previous fuzzy spindle detector. The sigma index was complemented with spindle amplitude analysis, based on finite impulse response (FIR) filtering, to form of a combination detector of bilateral spindles. In this combination detector, the spindle amplitude distribution of each recording was estimated and used to tune two different amplitude thresholds. This combination detector was compared to bilaterally extracted sigma indexes and fuzzy detections, which aim to be independent of absolute spindle amplitudes. As a fourth method a fixed spindle amplitude detector was included. The combination detector provided the best overall performance; in S2 sleep a 70% true positive rate was reached with a specificity of 98.6%, and a false-positive rate of 32%. The bilateral sigma indexes provided the second best results, followed by fuzzy detector, while the fixed amplitude detector provided the poorest results so that in S2 sleep a 70% true positive rate was reached with a specificity of 97.7% and false-positive rate of 46%. The spindle amplitude distributions automatically determined for each recording by the combination detector were compared to amplitudes of visually scored spindles and they proved to correspond well. Inter-hemispheric amplitude variation of visually scored bilateral spindles is also presented. Flexibility is beneficial in the detection of bilateral spindles. The present work advances automated spindle detection and increases the knowledge of bilateral sleep spindle characteristics.

A Study on Gender and Age Differences in Sleep Spindles

In the present work, gender differences in sleep spindle topography were examined in 40 subjects. Their median age was 32 years (range 22–49 years). Spindles were detected from 3,306,060 s of visually scored stage 2 sleep EEG by a previously validated automatic fuzzy detector at 1-second intervals. A total of 271,168 spindles were found from the six EEG channels analyzed. Females showed a significantly higher percentage of spindles in the left frontal channel than males (Fp1-A2; p = 0.026). To confirm that this difference was gender and not age related, the subjects were divided into two age groups. No significant differences in spindle activity of the frontal channels were found between the groups. However, the interindividual spindle variability seemed to be at least as large as that stemming from gender.