Neuro Fuzzy Inference System Classifier Research Articles

Adaptive neuro-fuzzy inference system classifier with interpretability for cancer diagnostic

Clinical outcome analysis using patient medical data facilitates clinical decision-making and increases prognostic accuracy. Recently, deep learning (DL) with learning big data features has shown expert-level accuracy in predicting clinical outcomes. Many of these sophisticated machine learning models, however, lack interpretability, creating significant trust-related healthcare issues. This necessarily requires the need for interpretable AI systems capable of explaining their decisions. In this respect, the paper proposes an interpretable classifier of the adaptive neuro-fuzzy inference method (iANFIS), which combines the fuzzy inference system with critical rule selection by attention mechanism. The rule-based processing of ANFIS helps the user to understand the behavior of the proposed model. The essential activated rule and the most important input features that predict the outcome are identified by the attention-based rule selector. We conduct two experiments with two cancer diagnostic datasets for verifying the performance of the proposed iANFIS. By using recursive rule elimination (RRE) to prune fuzzy rules, the model’s complexity is significantly reduced while preserving system efficiency that makes it more interpretable.

Fault diagnosis in industrial rotating equipment based on permutation entropy, signal processing and multi-output neuro-fuzzy classifier

Rotating equipment is considered as a key component in several industrial sectors. In fact, the continuous operation of many industrial machines such as sub-sea pumps and gas turbines relies on the correct performance of their rotating equipment. In order to reduce the probability of malfunctions in this equipment, condition monitoring, and fault diagnosis systems are essential. In this work, a novel approach is proposed to perform fault diagnosis in rotating equipment based on permutation entropy, signal processing, and artificial intelligence. To that aim, vibration signals are employed for an indication of bearing performance. In order to facilitate fault diagnosis, fault detection and isolation are performed in two separate steps. As first, once a vibration signal is received, the faulty state of the bearing is determined by permutation entropy. In case a faulty state is detected, the fault type is determined using an approach based on signal processing and artificial intelligence. Wavelet packet transform and envelope analysis of the vibration signals are utilized to extract the frequency components of the fault. The proposed approach allows for the automatic selection of a frequency band that includes the characteristic resonance frequency of the fault, which is subject to change in different operational conditions. The method works by extracting the proper features of the signals that are used to decide about the faulty bearing’s condition by a multi-output adaptive neuro-fuzzy inference system classifier. The effectiveness of the approach is assessed by the Case Western Reserve University dataset: the analysis demonstrates the proposed method’s capabilities in accurately diagnosing faults in rotating equipment as compared to existing approaches.

RETRACTED ARTICLE: Detection and classification of mechanical faults of three phase induction motor via pixels analysis of thermal image and adaptive neuro-fuzzy inference system

The fault diagnosis in motor is substantial as it results in breakdown of production line and the faults may damage motor and results in economic losses. Bearing failure, rotor eccentricity, shaft misalignment and load related faults are the most frequent failures under mechanical fault category. This paper addresses three such faults that may increase the stator temperature namely air gap eccentricity, shaft misalignment and cooling system failure. The thermography technique has been used widely for fault detection in induction motor. In three phase induction motor the thermal images are analyzed for healthy condition and the above mentioned faults conditions. This paper presents thermal pixels counting algorithm to calculate the diagnosis indicators and adaptive neuro-fuzzy inference system classifier is used to classify the faults based on the diagnosis indicator data base. Laboratory based experimental investigation are carried out to verify the accuracy of the proposed method. This method provides accurate diagnosis indicator that will be used as a bench mark value for preparing the maintenance schedule under non-destructive mode.

Computer aided detection and diagnosis methodology for brain stroke using adaptive neuro fuzzy inference system classifier

AbstractA stroke or “brain attack” occurs when the blood flow to an area of the brain is interrupted. In this article, ischemic stroke is detected and diagnosed using the following stages: noise reduction, enhancement, skull removal, feature extraction and k‐means clustering. The impulse noises in brain magnetic resonance imaging (MRI) image are reduced using directional filtering algorithm. The noise reduced brain image is further enhanced using oriented local histogram equalization technique. The skull is removed from the enhanced brain image. Features are extracted and stroke region is segmented using k‐means clustering and adaptive neuro fuzzy inference system (ANFIS) classifier. The main objective of this article is to develop a methodology for the detection of stroke using MRI brain images.

An accurate classifier based on adaptive neuro-fuzzy and features selection techniques for fault classification in analog circuits

This paper presents a new approach for faults classification in analog integrated circuits using a multiclass adaptive neuro fuzzy inference system classifier. This is carried out to assist analog circuit's faults diagnosis suffering from inaccurate faults classification on one hand, and to lessen computational burden on the other hand. This has been achieved from features number reduction. These features serving as input feature vector are extracted from the selected circuits (CUT) frequency and transient responses under both fault free and faulty conditions. The considered faults are resistors and capacitors values variations of about 50% low and high from their nominal ones. The method accuracy has been validated with three experiment circuits, the Sallen Key band-pass, the four opamp biquad high-pass and the leapfrog filters. The obtained results reveal a high level of efficiency with an accuracy average reach to 99.76%. Hence, the proposed method has shown a good performance in term of fault classification accuracy when compared with those of both the Artificial Neural Networks (ANN) approach and the fractional Fourier transform (FRFT) method based on a statistical property.

RETRACTED ARTICLE: Recognition of autism in children via electroencephalogram behaviour using particle swarm optimization based ANFIS classifier

Autism spectrum disorders (ASD) are pervasive neuro developmental conditions portrayed by disabilities in social intercommunication, besides stereotyped conduct. Since Electroencephalogram (EEG) recording together with analysis stands one among the basic devices in diagnosing along with recognizing the issue in neurophysiology, utilized the signals of EEG aimed at diagnosing persons with ASD. These signals have heaps of data which mirror the conduct of brain functions which thusly catches the marker for autism, help to early analyze and speed the treatment. To beat such disadvantage, this given work proposes an Adaptive Neuro-Fuzzy Inference System classifier joined with Particle Swarm Optimization that is named as PSO-ANFIS for classifying the diagnosing signals of EEG. To start with, utilizing Savitzky Golay (S-G) filter pre-processed the input signal, after that by variational mode decomposition (VMD) disintegrated the signal. Presently, features are extracted; additionally, these are trained and also characterized utilizing PSO-ANFIS, which classifies whether the signal seems normal or else autism signal. The proposed strategy classified the abnormal besides normal signal, all the more precisely, when contrasted with the current ones are established through the experiment.

Multiple Criteria Decision Analysis Based Overlapped Latent Fingerprint Recognition System Using fuzzy Sets

Latent fingerprints have attracted considerable attention from researchers in the fields of forensics and law enforcement applications. Public demand for these applications may be the driving force behind further progress in biometrics research. Although great effort has been taken to devise algorithms for overlapped latent fingerprint classification system, there are still many challenging problems involved in fingerprint classification systems. Most of the fingerprint-based applications will prolong with fingerprint recognition because of its proven performance, the existence of large databases and the availability of the fingerprint devices with minimum cost. There are various issues that need to be addressed to develop fingerprint classification system. In this connection, there are some designing challenges such as nonlinear distortion, low-quality image, segmentation, sensor noise, skin conditions, overlapping, inter-class similarity, intra-class variations and template ageing. In crime scenes, the latent images can be overlapped with some background images or more number of fingerprint images from same person or different person. An overlapped fingerprint image should be processed for fingerprint classification. This proposed recognition system suggests multiple criteria decision analysis technique to assess the overlapped latent fingerprints. The proposed multiple criteria such as first-order, second-order and third-order features are used to classify the overlapped latent fingerprints. The proposed system designs the novel classification system for overlapped latent fingerprint images using ANFIS classifier. Extensive experiments are performed on the simultaneous latent fingerprint databases, and National Institute of Standards and Technology-Special Database 27, Fingerprint Verification Competition 2006 Database1-A and Database2-A databases. The planned work enables accurate and fast data retrieval by using one-to-N fingerprint classification for overlapped latent images. The experimental results are highly promising, and they outperform the existing systems in classifying overlapped images. The performance of adaptive neuro fuzzy inference system classifier is evaluated by applying the k-fold cross-validation technique. The outcome of the work shows that the overlapped fingerprint is classified in a successful manner, and the results are compared with Bayes, SVM and MLP classifiers. The obtained results show that the proposed system achieves a better classification rate of 90.66% with 5 s, 86.66% with 12 s compared to the existing system.

Classification of masses in digital mammograms using Biogeography-based optimization technique

Breast cancer is a leading cause of death in women in both developed and developing countries. Design and development of computer-based systems can assist radiologists in the effective treatment of breast cancer. For the design of an efficient classification system, efficient feature selection techniques must be used to reduce complexity of feature space in digital mammogram classification. The proposed methodology aims to explore use of Biogeography-based optimization to select a subset of features. Adaptive neuro-fuzzy inference system and artificial neural network are employed to evaluate fitness of the selected features. The features selected are used to train and test adaptive neuro-fuzzy inference system and artificial neural network classifiers. The experiment employed over 651 mammograms. The classification results shows that Biogeography-based optimization with adaptive neuro-fuzzy inference system is superior to Biogeography-based optimization with artificial neural network. Adaptive neuro-fuzzy inference system classifier achieve an accuracy of 98.92% with sensitivity of 99.10%, specificity of 98.72% and area under curve AZ = 0.999 ± 0.000. Outcomes achieved with the proposed Biogeography-based optimization with adaptive neuro-fuzzy inference system are far better as compared to some recent work.

A Diagnostic System for Detection of Atrial and Ventricular Arrhythmia Episodes from Electrocardiogram

Cardiac arrhythmias, with each passing day, are becoming highly prevalent in modern society. The ever increasing number of patients added to the sheer amount of data that is recorded from a patient during monitoring limits the ability of a medical practitioner to diagnose these problems quickly. Therefore, an intelligent system is required which can produce a reliable diagnosis in a short period of time. In this paper, a new intelligent diagnostic system for detection of atrial arrhythmia (atrial flutter and atrial fibrillation) and ventricular arrhythmia (premature ventricular contractions, ventricular bigeminy, ventricular escape rhythm, ventricular tachycardia and ventricular fibrillation) episodes from Electrocardiogram (ECG) is proposed. This system is based on the non-linear analysis of the variational modes of ECG. Variational mode decomposition is used for decomposition of ECG signal into several modes. Then, the non-linear features namely, the distribution entropy and the sample entropy are evaluated from the modes of ECG. The performance of variational mode distribution entropy (VMDE) and variational mode sample entropy (VMSE) features is assessed using support vector machine (SVM) and adaptive neuro-fuzzy inference system classifiers. Experimental results reveal that, the combination of VMDE and VMSE features, and the radial basis function kernel based multi-class SVM classifier are suitable for detection of arrhythmia episodes from ECG with an average accuracy value of 95.60%.

Comparative Analyses of Classifiers for Diagnosis of Skin Cancer using Dermoscopic Images

In recent years one of the emerging deadliest diseases is Skin cancer. Skin cancers are of different types. But melanoma, basal cell carcinoma and squamous cell carcinoma these types are most commonly found in humans. The death rate due to skin lesions can be reduced if detected early. An efficient image analysis module has been developed with efficient algorithm to detect the skin lesions. In the analysis system classification plays an important role in identification of defect. In the proposed system different types of classifiers such as Support Vector Machine, ensemble classifier, probabilistic neural network and adaptive neuro-fuzzy inference system classifiers are used in the classification process and their performance is compared and the classifier with best performance is used in identifying the skin lesions. Keywords: Classification, Ensemble, Image Segmentation, Neural Network, Neuro-Fuzzy, Skin Cancer

Computer Aided Detection of Cervical Cancer Using Pap Smear Images Based on Adaptive Neuro Fuzzy Inference System Classifier

Computer Aided Detection of Cervical Cancer Using Pap Smear Images Based on Adaptive Neuro Fuzzy Inference System Classifier

Dynamic cattle behavioural classification using supervised ensemble classifiers

In this paper various supervised machine learning techniques were applied to classify cattle behaviour patterns recorded using collar systems with 3-axis accelerometer and magnetometer, fitted to individual dairy cows to infer their physical behaviours. Cattle collar data was collected at the Tasmanian Institute of Agriculture (TIA) Dairy Research Facility in Tasmania. In the first stage of analysis a novel hybrid unsupervised clustering framework, comprised of probabilistic principal component analysis, Fuzzy C Means, and Self Organizing Map network algorithms was developed and used to study the natural structure of the sensor data. Findings from this unsupervised clustering were used to guide the next stage of supervised machine learning. Five major behaviour classes, namely, Grazing, Ruminating, Resting, Walking, and other behaviour were identified for the classification trials. An ensemble of classifiers approach was used to learn models of cow behaviour using sensor data and ground truth behaviour observations acquired from the field. Ensemble classification using bagging, Random Subspace and AdaBoost methods along with conventional supervised classification methods, namely, Binary Tree, Linear Discriminant Analysis classifier, Naive Bayes classifier, k-Nearest Neighbour classifier, and Adaptive Neuro Fuzzy Inference System classifier were compared. The highest average correct classification accuracy of 96% was achieved using the bagging ensemble classification with Tree learner, which had 97% sensitivity, 89% specificity, 89% F1 score and 9% false discovery rate. This study has shown that cattle behaviours can be classified with a high accuracy using supervised machine learning technique. As dairy and beef systems become more intensive, the ability to identify the changes in the behaviours of individual livestock becomes increasingly difficult. Accurate behavioural monitoring through sensors provides a significant potential in providing a mechanism for the early detection and quantitative assessment of animal health issues such a lameness, informing key management events such as the identification of oestrus, or informing changes in supplementary feeding requirements.

An expert system approach based on principal component analysis and adaptive neuro-fuzzy inference system to diagnosis of diabetes disease

Diabetes occurs when a body is unable to produce or respond properly to insulin which is needed to regulate glucose (sugar). Besides contributing to heart disease, diabetes also increases the risks of developing kidney disease, blindness, nerve damage, and blood vessel damage. In this paper, we have detected on diabetes disease, which is a very common and important disease using principal component analysis (PCA) and adaptive neuro-fuzzy inference system (ANFIS). The aim of this study is to improve the diagnostic accuracy of diabetes disease combining PCA and ANFIS. The proposed system has two stages. In the first stage, dimension of diabetes disease dataset that has 8 features is reduced to 4 features using principal component analysis. In the second stage, diagnosis of diabetes disease is conducted via adaptive neuro-fuzzy inference system classifier. We took the diabetes disease dataset used in our study from the UCI (from Department of Information and Computer Science, University of California) Machine Learning Database. The obtained classification accuracy of our system was 89.47% and it was very promising with regard to the other classification applications in literature for this problem.