Fuzzy Diagnosis Research Articles

Clinical decision support system using hierarchical fuzzy diagnosis model for migraine and tension-type headache based on International Classification of Headache Disorders, 3rd edition.

To determine whether the diagnostic ability of the newly designed hierarchical fuzzy diagnosis method is consistent with that of headache experts for probable migraine (PM) and probable tension-type headache (PTTH). Clinical decision support systems (CDSS) are computer systems designed to help doctors to make clinician decisions by information technology, and have proven to be effective in improving headache diagnosis by making medical knowledge readily available to users in some studies. However, one serious drawback is that the CDSS lacks the ability to deal with some fuzzy boundaries of the headache features utilized in diagnostic criteria, which might be caused by patients' recall bias and subjective bias. A hybrid mechanism of rule-based reasoning and hierarchical fuzzy diagnosis method based on International Classification of Headache Disorders, 3rd edition (ICHD-3) was designed and then validated by a retrospective study with 325 consecutive patients and a prospective study with 380 patients who were clinically diagnosed with migraine and TTH at the headache clinic of Chinese PLA General Hospital. The results of the diagnostic test in the retrospective study indicated that the fuzzy-based CDSS can be used in the diagnosis of migraine without aura (MO) (sensitivity 97.71%, specificity 100%), TTH (sensitivity 98.57%, specificity 100%), PM (sensitivity 91.25%, specificity 98.75%) and PTTH (sensitivity 90.91%, specificity 99.63%). While in the prospective study, the diagnostic performances were MO (sensitivity 91.62%, specificity 96.52%), TTH (sensitivity 92.17%, specificity 95.47%), PM (sensitivity 85.48%, specificity 98.11%) and PTTH (sensitivity 87.50%, specificity 98.60%). Cohen's kappa values for the consistency test were 0.984 ± 0.018 (MO), 0.991 ± 0.018 (TTH), 0.916 ± 0.051 (PM), 0.932 ± 0.059 (PTTH) in the retrospective study and 0.884 ± 0.047 (MO), 0.870 ± 0.055 (TTH), 0.853 ± 0.073 (PM), 0.827 ± 0.118 (PTTH) in the prospective study, which indicated good consistency with the fuzzy-based CDSS and the gold standard (p < 0.001). We developed a fuzzy-based CDSS performs much more similarly to expert diagnosis and performs better than the routine CDSS method in the diagnosis of migraine and TTH, and it could promote the application of artificial intelligence in the area of headache diagnosis.

Heart Rate and Body Temperature Tracking Application Based on Fuzzy Logic

Temperature and heart rate are indicators of health. It is necessary to monitor heart rate and body temperature to prevent the spread of a virus or disease. In most cases, heart rate and body temperature are monitored independently, and the patient cannot view a record of previous examinations. This study uses fuzzy logic to develop an application for monitoring heart rate and body temperature. It can monitor heart rate and body temperature in real-time, store a history of previous examinations, and use fuzzy logic to diagnose body conditions based on heart rate and body temperature data. Based on test results, the sensor reading error rate for heart rate is minimal at 0.68 and for body temperature at 0.18. The accuracy of fuzzy diagnosis of the patient's body condition is one hundred percent. The performance indicator for the application is excellent, the completion rate is 100 percent, and the time-based efficiency is 93%. The results of the user satisfaction test indicate that most users are pleased with the application's usability. The average value for measuring user satisfaction is 80%, with the highest result of the five measurement criteria being 89.6% for the ease-of-use criterion.

Machine Learning-Based Label-Free SERS Profiling of Exosomes for Accurate Fuzzy Diagnosis of Cancer and Dynamic Monitoring of Drug Therapeutic Processes.

Exosomes are a class of extracellular vesicles secreted by cells, which can be used as promising noninvasive biomarkers for the early diagnosis and treatment of diseases, especially cancer. However, due to the heterogeneity of exosomes, it remains a grand challenge to distinguish accurately and reliably exosomes from clinical samples. Herein, we achieve accurate fuzzy discrimination of exosomes from human serum samples for accurate diagnosis of breast cancer and cervical cancer through machine learning-based label-free surface-enhanced Raman spectroscopy (SERS), by using "hot spot" rich 3D plasmonic AuNPs nanomembranes as substrates. Due to the existence of some weak distinguishable SERS fingerprint signals and the high sensitivity of the method, the machine learning-based SERS analysis can precisely identify three (normal and cancerous) cell lines, two of which are different types of cancer cells, without specific labeling of biomarkers. The prediction accuracy based on the machine learning algorithm was up to 91.1% for the discrimination of different cell lines (H8, HeLa, and MCF-7 cell)-derived exosomes. Our model trained with SERS spectra of cell-derived exosomes could reach 93.3% prediction accuracy for clinical samples. Furthermore, the action mechanism of the chemotherapeutic process of MCF-7 cells can be revealed by dynamic monitoring of SERS profiling of the exosomes secreted. The method would be useful for noninvasive and accurate diagnosis and postoperative assessment of cancer or other diseases in the future.

A fuzzy neural network-based automatic fault diagnosis method for permanent magnet synchronous generators.

In recent years, automatic fault diagnosis for various machines has been a hot topic in the industry. This paper focuses on permanent magnet synchronous generators and combines fuzzy decision theory with deep learning for this purpose. Thus, a fuzzy neural network-based automatic fault diagnosis method for permanent magnet synchronous generators is proposed in this paper. The particle swarm algorithm optimizes the smoothing factor of the network for the effect of probabilistic neural network classification, as affected by the complexity of the structure and parameters. And on this basis, the fuzzy C means algorithm is used to obtain the clustering centers of the fault data, and the network model is reconstructed by selecting the samples closest to the clustering centers as the neurons in the probabilistic neural network. The mathematical analysis and derivation of the T-S (Tkagi-Sugneo) fuzzy neural network-based diagnosis strategy are carried out; the T-S fuzzy neural network-based generator fault diagnosis system is designed. The model is implemented on the MATLAB/Simulink platform for simulation and verification, the experiments show that the T-S fuzzy diagnosis strategy is significantly improved, and the design purpose is achieved. The fuzzy neural network has a parallel structure and can perform parallel data processing. This parallel mechanism can solve the problem of large-scale real-time computation in control systems, and the redundancy in parallel computation can make the control system highly fault-tolerant and robust. The fault diagnosis model based on an improved probabilistic neural network is applied to the fault data to verify the effectiveness and accuracy of the model.

A deep fuzzy model for diagnosis of COVID-19 from CT images

From early 2020, a novel coronavirus disease pneumonia has shown a global “pandemic” trend at an extremely fast speed. Due to the magnitude of its harm, it has become a major global public health event. In the face of dramatic increase in the number of patients with COVID-19, the need for quick diagnosis of suspected cases has become particularly critical. Therefore, this paper constructs a fuzzy classifier, which aims to detect infected subjects by observing and analyzing the CT images of suspected patients. Firstly, a deep learning algorithm is used to extract the low-level features of CT images in the COVID-CT dataset. Subsequently, we analyze the extracted feature information with attribute reduction algorithm to obtain features with high recognition. Then, some key features are selected as the input for the fuzzy diagnosis model to the training model. Finally, several images in the dataset are used as the test set to test the trained fuzzy classifier. The obtained accuracy rate is 94.2%, and the F1-score is 93.8%. Experimental results show that, compared with the deep learning diagnosis methods widely used in medical image analysis, the proposed fuzzy model improves the accuracy and efficiency of diagnosis, which consequently helps to curb the spread of COVID-19.

Fuzzy diagnostics for gearbox failures based on induction motor current and wavelet entropy

In this work, a strategy is proposed for the automatic diagnosis of failures in gearboxes using current signals from an induction motor. The stator currents were represented by the extended Park vector approach technique and decomposed by the wavelet packet transform. The calculation of the wavelet packet entropy promoted the distinction between broken tooth failures and the levels of severity of surface wear. The entropies of two wavelet details were used as inputs for a fuzzy inference for automatic classification of the gearbox condition. The experimental results presented a high rate of correctness in the fuzzy diagnosis, confirming the efficiency of the strategy for high rotation (60 Hz) and low rotation (20 Hz). The strategy presents simplicities related to the practical implementation and reduction of the amount of data analyzed.

An intelligent diagnosis model of accidents in nuclear power plant

This essay focus on the situation when the operator of the main control room can not handle the accident in time or make wrong judgment under accident condition in nuclear power plant, which may lead to the occurrence of major accidents or even more accidents concurrently. An intelligent fuzzy diagnosis model based on Grey Relational degree is constructed in this paper, by establishing accident-state correlation matrix and accident-state probability matrix, defining the vector of information weights for accident characteristic vector and monitoring result vector with linear transform, using Grey Relation to measure the relevance degree between monitoring result vector and accident characteristic vector, Searching for suspected accidents approaching to real solutions in iterative recursive algorithms, realizing automatic fuzzy diagnosis of multiple accidents. The results of simulation experiments of LOCA accidents indicate that the model and algorithm can diagnose various common accidents accurately and rapidly in complex nuclear power systems, providing strategy for operator’s diagnosis decision.

Fault Diagnosis and Identification of Power Capacitor Based on Edge Cloud Computing and Deep Learning

Nowadays, power electronic technology is widely affecting people’s daily work and life. However, there are still many problems in the current power supply research. When the fault information of power transformer is not complete or there is some ambiguity or even the information is lost, it will largely lead to the conclusion and correct conclusion of fault diagnosis. In this case, the fuzzy theory is applied to the fault diagnosis of shunt capacitor, and the fuzzy fault diagnosis system of shunt capacitor is studied. At the same time, a map-based fault diagnosis system is proposed. In this paper, the cloud computing technology is introduced into the deep learning and compared with SVM and DBN algorithm. The research results of this paper show that the accuracy of fuzzy diagnosis results is 94%, 84%, 90%, 80%, 83%, and 70%, respectively, which shows that the model diagnosis reliability is relatively high. Among the three algorithms, MR-DBN overall detection rate is higher and the time-consuming is lower than the other two methods. The diagnostic accuracy and misjudgment rate of DBN are as follows: 96.33% and 3.90%. The diagnosis accuracy and misjudgment rate of SVM are as follows: 96.40% and 3.83%. The diagnostic accuracy and misjudgment rate of MR-DBN are, respectively, 99.52% and 0.57%. Compared with the other two methods, MR-DBN has the highest diagnostic accuracy and the lowest error rate, which to a large extent indicates that MR-DBN algorithm has higher diagnostic accuracy and has greater advantages and reliability in power supply diagnosis and identification. It not only improves the accuracy of power capacitor fault diagnosis and identification but also provides a new method for the application of power capacitor fault research and development.

Comparative study of interval Type-2 and general Type-2 fuzzy systems in medical diagnosis

Nowadays, computer science has the ability of assisting experts in different application areas. Recently there has been increasing attention in the health area, and there exist different approaches based on artificial intelligence that have been proposed in the diagnosis of several kinds of diseases. In particular, fuzzy systems have been successfully used as Diagnosis Systems, in this way helping doctors to realize a faster and more accurate diagnosis. However, with the emergence of Type-2 Fuzzy Systems, there have been important improvements in handling the uncertainty with respect to traditional Fuzzy Systems (now called Type-1 Fuzzy Systems) in different kinds of problems. In the present paper, a new approach to Fuzzy Diagnosis based on Type-2 Fuzzy Systems is proposed and compared with respect to Type-1 Fuzzy Systems on a set of diagnosis problems, in order to evaluate the relevance of the uncertainty handling in this kind of problems. On the other hand, the paper is also aiming at observing the accuracy behavior in Fuzzy Diagnosis Systems by changing the uncertainty level in the models. Finally, a comparison of Interval Type-2 Fuzzy Systems with respect to General Type-2 Fuzzy Systems for a set of diagnosis problems is presented.

MULTIPLE FAULT ANALYSIS USING A FUZZY LOGIC TECHNIQUE FOR AN INVERTER CONTROL DRIVE

This study evaluates electrical faults on an inverter control drive using simulations in MATLAB Simulink and recommends a fuzzy logic technique for analyzing electrical faults of such drives. Fault analysis of a drive is based on voltage, speed, current, and torque. This article presents soft computing methods for voltage fluctuations and fault detection in an inverter switch to an inverter control drive with the support of a MATLAB Simulink model. Accordingly, failure analysis techniques based on fuzzy logic are explained. The fuzzy system allows altered voltage and open-switch fault detection. Soft computing techniques offer excellent analysis of a faulty structure, even if precise models are not available. This study presents a fuzzy logic-based fault diagnosis scheme for detecting and identifying faults. The simulation outcomes reveal excellent performance of the method, proving its applicability for fault detection in squirrel-cage induction motors. All simulated results, voltage fluctuations, torques, currents, ripples, and harmonics in healthy and defective situations are analyzed.

Design of Portable Fuzzy Diagnosis Instrument for ECG Signal Based on Internet of Things

A method for dynamically collecting and processing ECG signals was designed to obtain classification information of abnormal ECG signals. Firstly, the ECG eigenvectors were acquired by real-time acquisition of ECG signals combined with discrete wavelet transform, and then the ECG fuzzy information entropy was calculated. Finally, the Euclidean distance was used to obtain the semantic distance of ECG signals, and the classification information of abnormal signals was obtained. The device could effectively identify abnormal ECG signals on an embedded platform based on the Internet of Things, and improved the diagnosis accuracy of heart diseases. The fuzzy diagnosis device of ECG signal could accurately classify the abnormal signal and output an online signal classification matrix with a high confidence interval.

Step-by-Step Fuzzy Diagnosis Method for Equipment Based on Symptom Extraction and Trivalent Logic Fuzzy Diagnosis Theory

A step-by-step fuzzy diagnostic method based on frequency-domain symptom extraction and trivalent logic fuzzy diagnosis theory (TLFD), which is established by combining the trivalent logic inference theory with the possibility and fuzzy theories, is proposed herein. The features for diagnosing a number of abnormal states are extracted sequentially from the measured signals using statistical tests in the frequency domain. The symptom parameters (SPs) that can sensitively reflect symptoms of abnormal states are then selected to provide effective information for the discrimination of each state. The membership function of each state is then generated based on the possibility theory using the probability functions of the SPs. The step-by-step fuzzy diagnoses are performed based on the TLFD. This method can be used extensively to diagnose anomalies in various equipment. In this study, the diagnosis of structure faults of a rotating machine is cited as an example to demonstrate the effectiveness and universality of this method.

An intuitionistic fuzzy diagnosis analytics for stroke disease

One of the challenges in diagnosing stroke disease is the lack of useful analysis tool to identify critical stroke data that contains hidden relationships and trends from a vast amount of data. In order to address this problem, we proposed Intuitionistic Fuzzy Based Decision Tree in order to diagnosis the different types of stroke disease. The approach is implemented by mapping observation data into Intuitionistic Fuzzy Set. These results lead to a compound of a membership function, non-membership function, and a hesitation degree for each record. The result of Intuitionistic Fuzzy is calculated using Hamming Distance as main requirement for Intuitionistic Fuzzy Entropy. The Hamming Distance calculate the difference between values on the same variable. Main advantage of this approach is that we can find out variables effected on the stroke disease using information gain derived from Intutionistics Entropy. Furthermore, the Intuitionistic Fuzzy based Decision Tree are able to provide plenty of information to stakeholders regarding the hidden facts of established rules and utilize linguistic terms to accommodate unclearness, ambiguity, and hesitation in human perception. The results of Intuitionistic Fuzzy Entropy determine the root and node in the formation of the decision tree model based on the information gain of variables in the data. In this study, simulation results show that the approach successfully determine 20 variables that directly influence stroke. These variables are used to classify the types of stroke. Furthermore, results show that the approach has resulted in 90.59% in classifying stroke disease. Results of the study also demonstrates that the approach produces the best diagnosis performance compared to the other two models according to the accuracy of classification from the type of stroke disease.

Minimum rational entropy fault tolerant control for non-Gaussian singular stochastic distribution control systems using T-S fuzzy modelling

ABSTRACTIn this paper, a new fault diagnosis (FD) and fault tolerant control (FTC) algorithm for a non-Gaussian nonlinear singular stochastic distribution control (SDC) system is studied. The rational square-root fuzzy logic model is used to approximate the output probability density function of non-Gaussian processes and a Takagi-Sugeno (T-S) fuzzy model is employed to transform the non-Gaussian nonlinear SDC system into a fuzzy SDC system. An adaptive fuzzy fault diagnosis observer is constructed to achieve reconstruction of system state and fault. Based on the estimated fault information, the controller is reconfigured by minimising the performance index with regard to the rational entropy subjected to mean constraint. Minimum rational entropy fault tolerant control is introduced to make the output of the past-fault SDC system still have the minimum uncertainty. Simulation results are provided to demonstrate the validity of the FD and minimum rational entropy FTC algorithm.

Research on interval triangular fuzzy multi-attribute fault diagnosis methods based on the grey relation grade

Considering the fuzzy multi-attribute problems of components' failure information, a fault diagnosis model of a Bayesian network based on the interval triangular fuzzy multi-attribute decision method was built. First, the fault multi-attribute hierarchies were represented as a Bayesian network structure by Bayesian network causal dependencies, which reduced the complexity of the multi-attribute hierarchy. Second, in the condition that weight information is completely unknown, grey correlation optimal models were constructed based on the grey correlation analysis method. Furthermore, faulty components were sorted and the component with the highest value was optimised, and the calculation method of interval triangle fuzzy multi-attribute decision based on the grey correlation was given, which realised the fault diagnosis of the system fuzzy multiple-attribute problem. Finally, the method was applied in an analysis of a case of fault diagnosis on a CNC machine tool servo system with a low voltage alarm, which verified the effectiveness of the method.

Research on interval triangular fuzzy multi-attribute fault diagnosis methods based on the grey relation grade

Research on interval triangular fuzzy multi-attribute fault diagnosis methods based on the grey relation grade

Prognostic Methods on Accelerator’s Anode Voltage Regulator

This study investigated an adaptive control, fault diagnostics and prognostics of the anode voltage regulator system at an ion implantation accelerator. The system was modeled as a 4th order AutoRegressive with eXogenous (ARX) model, controlled by a Fuzzy Logic Controller (FLC). This model was then used as a basis for constructing and updating a fault diagnosis module and a failure prognostics module. To maintain the system’s performance, the controller’s response was continuously re-adjusted through an optimization scheme. A Failure Mode and Effect Analysis (FMEA) was conducted resulting on five failure modes of the regulator system. Fault data were generated in MATLAB simulation to train a random forest fault classification engine. The optimal random forest classifier was 20 decision trees with a fault diagnostics accuracy of 98.06%. A Hidden Markov Model (HMM) was constructed as the system’s fault progression model based on the interaction between environmental conditions and controller actions. The particle filter and Bayesian inference methods were then employed to continuously update the HMM and predict the system’s Remaining Useful Lifetime (RUL). The proposed methodology was able to integrate an adaptive fuzzy logic control, prognosis and failure diagnosis altogether allowing a continual satisfactory performance of the voltage regulator system throughout its lifetime.

Refinement of Fuzzy Diagnosis in Decentralized Two-Level Diagnostic Structure

The novel and practicable on-line fuzzy fault isolation approach is proposed and discussed in this paper. This approach refers to proposition of diagnosing in decentralized two-level diagnostic structure. The idea of the proposed diagnostic structure is described in details as well as depicted in examples. It is particularly foreseen for applications in diagnostics of large scale industrial systems. Diagnosing in decentralized structures involves the problem of diagnosis refinement. Substantial part of the paper is devoted to clarify and solve this problem. Here, the fuzzy approach was proposed motivated by its inherent ability to handle uncertainties. Proposed approach is characterized by: better efficiency by application of parallel diagnosing, simplification of diagnostic process, providing better robustness of diagnoses compared to the centralized diagnosing. An example of industrial application of on-line decentralized diagnostics for steam-water line of power boiler was briefly discussed. Finally, the conclusions regarding main features of the decentralized two-level diagnostic structures were given.

A Fuzzy Reasoning Method in Fault Diagnosis of House Transformer Simulating System

Fuzzy set and reasoning are studied and used in the fault diagnosis of House Transformer Simulating System in this paper. Fuzzy diagnosis matrix and Fault cause fuzzy vector are firstly constructed according to collection of fault symptoms and the cause set. With maximum membership method performed on the fault fuzzy vector, fuzzy fault diagnosis algorithm is implemented. Experiments on real data about House Transformer from a hydro-electric factory are performed and efficiency of the fuzzy fault diagnosis method is guaranteed.

The OWA distance operator and its application in business failure

PurposeThe purpose of this paper is to develop a goodness index based on Hamming distance and ordered weighted averaging distance (OWAD), which is useful to make decisions. These alternative measures enrich the results of diagnostic fuzzy models and facilitate the experts’ task in decision-making. An application to a set of firms to verify the results is also presented.Design/methodology/approachThe paper follows the basis of OWA operators to design a methodology to reduce the map of causes of business failure into monitoring key areas.FindingsThe present paper introduces two alternative measures to test the proposal of grouping. In the empirical application, the superiority of the minimum T-norm over other decision rules is verified. The ordered weighted averaging distance (OWAD) goodness index predicts a better adjustment over the index built using OWA and Hamming distance measures.Practical implicationsA useful mechanism to reduce the map of causes or diseases detected in key areas is added through this analysis. At the same time, these key areas can be disaggregated once some alert indicator is identified; this allows knowing the causes that require special attention. This application of OWA can encourage the development of suitable computer systems for monitoring the firm’s problems, alerting regarding failures and easing decision-making.Originality/valueA comparison of grouping causes into key areas through a goodness index based on Hamming distance and OWAD is proposed. These contributions enrich the Vigier and Terceño (2008) model and could be applied to any model of fuzzy diagnosis to test the results.