Fuzzy Logic Classifier Research Articles

A Novel Application of Deep Belief Networks in Learning Partial Discharge Patterns for Classifying Corona, Surface, and Internal Discharges

This paper introduces a new application of deep belief network (DBN) as an emerging artificial neural network for recognizing and classifying different partial discharge (PD) patterns. Phase resolved PD (PRPD) technique with different window intervals is used to manipulate three PD types, including corona, surface, and internal discharges measured in a high-voltage lab. Four approaches are proposed for extracting features from the raw measured data. In the first approach, the DBN is used as both a feature extractor and a PD classifier. The other three approaches extract discriminatory features using statistical and vector-norm-based operators to train a DBN classifier. The impact of the various phase windows through the PRPD method on the performance of the trained classifier is evaluated to obtain the best window interval. It is shown that the deep architectures are capable of learning important distinguishable features from PD data without any data preprocessing. This eliminates time-consuming feature extraction processes that produce the handcrafted features. Based on a comparison analysis, when the input data are corrupted by noise levels or no feature extraction technique is used to preprocess the data, the proposed approach outperforms other techniques, such as artificial neural networks, fuzzy logic classifiers, and support vector machines.

Combined Fuzzy-logic and Neural Network Classifiers for Uterine Fibroid in vulnerable women

The diagnosis of uterine myoma often referred to as fibroid is poor mostly as women with the ailment present fewer symptoms at the early stage and get less clinical attention. Most times, the tumour is undiagnosed till it gets to an advanced stage, and may also be as a result of the relatively expensive diagnostic equipment used. Over the years the increase in uteri myoma has called for a model that could rapidly recognise the neoplasm at an early stage. In this study, we design a relatively specific model for the detection of uterine myoma. Matrix Laboratory (MATLAB version 7.5.0, R2007b) was used to implement the combined fuzzy logic classifier called adaptive neuro-fuzzy inference system (ANFIS) model. The dataset that was used in training the ANFIS model consist of 90 cases, which involve 78% (70 cases) of the entire dataset that was used in the training process of the system. The remaining 22% (20 cases) of the data were also used in the testing process of the system, which the system will get adapted to for subsequent recognition of similar cases. The ANFIS program was designed using a bell membership function that utilises a hybrid optimisation method with an error tolerance of 0.05. The training dataset was passed through the ANFIS for 30 epochs. At the end of the simulation, the system had a training error of 0.016169 with the training dataset and an average testing error of 0.010315. The system was able to classify approximately 99% of the test data set accurately. Therefore, we have successfully classified the symptoms of uterine fibroid using combined fuzzy-logic and neural network classifiers for vulnerable women. Keywords : Artificial intelligence, ANFIS classifier, Fuzzy-logic, Fibroid & Uterine myoma.

Fuzzy commonsense reasoning for multimodal sentiment analysis

The majority of user-generated content posted online is in the form of text, images and videos but also physiological signals in games. AffectiveSpace is a vector space of affective commonsense available for English text but not for other languages nor other modalities such as electrocardiogram signals. We overcome this limitation by using deep learning to extract features from each modality and then projecting them to a common AffectiveSpace that has been clustered into different emotions. Because, in the real world, individuals tend to have partial or mixed sentiments about an opinion target, we use a fuzzy logic classifier to predict the degree of a particular emotion in AffectiveSpace. The combined model of deep convolutional neural networks and fuzzy logic is termed Convolutional Fuzzy Sentiment Classifier. Lastly, because the computational complexity of a fuzzy classifier is exponential with respect to the number of features, we project features to a four dimensional emotion space in order to speed up the classification performance.

Automated Visual Inspection for Bottle Caps Using Fuzzy Logic

Automated Visual Inspection System (AVIS) has the capability to investigate large numbers of manufactured goods quickly and accurately. In addition, this system operates with a high level of reliability and consistency in their tasks. This study proposed an AVIS for detecting cap situations by using fuzzy logic classifiers. The objectives of this research are to develop an applicable image processing algorithm, together with a feature extraction technique, and to detect the cap for plastic bottles which is based on the average of distances. Three types of classification were compared for detecting the bottle caps. They are Mamdani, Sugeno, and production rule. The system was evaluated in a real time environment. The results are 97.91%, 97.5%, 96.66% accuracy for Mamdani, Sugeno, and production rule respectively.

Shape, Color and Texture Based CBIR System Using Fuzzy Logic Classifier

Shape, Color and Texture Based CBIR System Using Fuzzy Logic Classifier

РАЗРАБОТКА БАЗЫ НЕЧЕТКИХ ПРОДУКЦИОННЫХ ПРАВИЛ НЕЧЕТКОЙ ЛОГИЧЕСКОЙ СИСТЕМЫ КЛАССИФИКАЦИИ ВОЗДУШНЫХ ОБЪЕКТОВ В ПРОЦЕССЕ КОНТРОЛЯ ВОЗДУШНОГО ПРОСТРАНСТВА И ОБОБЩЕННОГО АЛГОРИТМА ИХ РЕАЛИЗАЦИИ

Контроль воздушного пространства требует создания системы классификации воздушных объектов. Данная задача решается в нечеткой постановке. Для этого разработана база нечетких продукционных правил и обобщенный алгоритм их реализации. Утверждается, что традиционные подходы к разработке баз правил не достаточно эффективны для рассматриваемой предметной области. Цель статьи – разработка базы нечетких продукционных правил нечеткой логической системы классификации воздушных объектов. Проанализированы подходы к разработке базы нечетких продукционных правил нечетких логических систем классификации. Для классификации воздушного объекта устанавливается его принадлежность к наперед заданному классу. Наперед заданные классы формально задаются в виде множества. Элементами множества являются классы, определяемые автоматически или задаваемые автоматизировано. Определены основные признаки для классификации воздушных объектов. Значения признаков определяются по результатам обобщения трассовой информации или устанавливаются по умолчанию. Значения признаков представляют собой лингвистические переменные. В общем случае они являются нечеткими числами, описывающими термы соответствующих лингвистических переменных. Структурно нечеткие продукционные правила соответствуют правилам нечеткой логической модели Сугэно 0-го порядка. Разработан пример использования нечеткого логического вывода Сугэно 0-го порядка на базе разработанных правил. Разработанная база нечетких продукционных правил и обобщенный алгоритм их реализации являются основой метода верификации программного обеспечения нечеткой логической системы классификации воздушных объектов в процессе контроля воздушного пространства.

Usage of co-event pattern mining with optimal fuzzy rule-based classifier for effective web page retrieval

With the coming of the World Wide Web and the rise of web-based business applications and informal organizations, associations over the web create a lot of information on a daily basis. It is becoming more complex and critical task to retrieve exact information from web expected by its users. In the recent times, the Web has extended its noteworthiness to the point of transforming into the point of convergence of our propelled lives. The search engine as an apparatus to explore the web must get the coveted outcomes for any given query. The greater part of the search engines can't totally fulfill user’s necessities and the outcomes are regularly inaccurate and irrelevant. knowledge of ontology and history is not much personalization in the existing techniques. To conquer these issues, data mining systems must be connected to the web and one advanced powerful concept is web-page recommendation which is becoming more powerful now a day. In this paper, the design of a fuzzy logic classifier algorithm is defined as a search problem in the solution space where every node represents a rule set, membership function, and the particular framework behaviour. Therefore, the hybrid optimization algorithm is applied to search for an optimal location of this solution space which hopefully represents the near optimal rule set and membership function. In this article, we reviewed various techniques proposed by different researchers for web page personalization and proposed a novel approach for finding optimal solutions to search the relevant information..

Multiclass adaptive neuro-fuzzy classifier and feature selection techniques for photovoltaic array fault detection and classification

Abstract In this paper, a Multiclass Adaptive Neuro-Fuzzy Classifier (MC-NFC) for fault detection and classification in photovoltaic (PV) array has been developed. Firstly, to show the generalization capability in the automatic faults classification of a PV array (PVA), Fuzzy Logic (FL) classifiers have been built based on experimental datasets. Subsequently, a novel classification system based on Adaptive Neuro-fuzzy Inference System (ANFIS) has been proposed to improve the generalization performance of the FL classifiers. The experiments have been conducted on the basis of collected data from a PVA to classify five kinds of faults. Results showed the advantages of using the fuzzy approach with reduced features over using the entire original chosen features. Then, the designed MC-NFC has been compared with an Artificial Neural Networks (ANN) classifier. Results demonstrated the superiority of the MC-NFC over the ANN-classifier and suggest that further improvements in terms of classification accuracy can be achieved by the proposed classification algorithm; furthermore faults can be also considered for discrimination.

A Quality Control Method of Ground-Based Weather Radar Data Based on Statistics

The detection of meteorological targets using ground-based weather radars usually suffers from ground clutter and beam blockage. These nonmeteorological or weakened signals should be identified so quality control should be implemented before weather radar data can be used. Conventional quality control methods aim at differentiating between echo structures of ground clutter and meteorological targets, and use terrain information to calculate beam blockage regions based upon standard atmospheric refraction. However, it is difficult to achieve the goal for long-term large data sets by conventional methods due to the complexity and diversity of weather radar echoes. In this paper, regions of ground clutter and beam blockage are first identified through the statistics on spatial distribution of reflectivity and fuzzy logic classification, and then they are used as masks to remove data from the scan. The new method is applied to data of the Nanjing weather radar in China. By the aid of a proposed evaluation scheme and the visual recognition, quality control results of the new method are compared with those of the conventional methods. It is found that the new method can provide better identification of ground clutter or beam blockage and thus better quality control results. The new scheme has a good prospect in operational service for its principle advantages, easy applicable conditions, and better performance compared with conventional methods.

Detection of Failure in Asynchronous Motor Using Soft Computing Method

This paper investigates the stator short winding failure of asynchronous motor also their effects on motor current spectrums. A fuzzy logic approach i.e., model based technique possibly will help to detect the asynchronous motor failure. Actually, fuzzy logic similar to humanoid intelligent methods besides expected linguistic empowering inferences through vague statistics. The dynamic model is technologically advanced for asynchronous motor by means of fuzzy logic classifier towards investigate the stator inter turn failure in addition open phase failure. A hardware implementation was carried out with LabVIEW for the online-monitoring of faults.

English

English

Decision support system for triage management: A hybrid approach using rule-based reasoning and fuzzy logic

ObjectivesFast and accurate patient triage for the response process is a critical first step in emergency situations. This process is often performed using a paper-based mode, which intensifies workload and difficulty, wastes time, and is at risk of human errors. This study aims to design and evaluate a decision support system (DSS) to determine the triage level. MethodsA combination of the Rule-Based Reasoning (RBR) and Fuzzy Logic Classifier (FLC) approaches were used to predict the triage level of patients according to the triage specialist’s opinions and Emergency Severity Index (ESI) guidelines. RBR was applied for modeling the first to fourth decision points of the ESI algorithm. The data relating to vital signs were used as input variables and modeled using fuzzy logic. Narrative knowledge was converted to If-Then rules using XML. The extracted rules were then used to create the rule-based engine and predict the triage levels. ResultsFourteen RBR and 27 fuzzy rules were extracted and used in the rule-based engine. The performance of the system was evaluated using three methods with real triage data. The accuracy of the clinical decision support systems (CDSSs; in the test data) was 99.44%. The evaluation of the error rate revealed that, when using the traditional method, 13.4% of the patients were miss-triaged, which is statically significant. The completeness of the documentation also improved from 76.72% to 98.5%. ConclusionsDesigned system was effective in determining the triage level of patients and it proved helpful for nurses as they made decisions, generated nursing diagnoses based on triage guidelines. The hybrid approach can reduce triage misdiagnosis in a highly accurate manner and improve the triage outcomes.

Reservoir lithology classification based on seismic inversion results by Hidden Markov Models: Applying prior geological information

Abstract Hidden Markov Models (HMMs) have been applied to predict reservoir lithologies using seismic inversion results as inputs. This approach takes into account the conditional probabilities between different lithologies, i.e. the vertical transitions in sedimentary sequences. These properties are used as prior geological information. In order to relate the seismic inversion results to the true well-log data, HMMs need to be trained based on the Expectation-Maximization theory. Application of the resulting model on a synthetic example from the Book Cliffs (Utah, USA) showed that most lithologies are classified correctly, even for some thin layers. A comparison with point-wise methods in which data samples are treated independently from each other, such as k-means and fuzzy logic classifiers, leads to the conclusion that the spatial correlation in HMMs allows better lithological predictions because the prior information accounts for the geological depositional processes. A real case study with data from the Vienna Basin (Austria) is performed, in which lithologies in a 3D cube are obtained based on properties from seismic inversions, via trained HMMs. While the vertical sequences are shown to be reasonably well predicted, the horizontal continuities are not. This indicates that the future research should focus on the lateral geological relationships.

Self-organising fuzzy logic classifier

In this paper, we present a self-organising nonparametric fuzzy rule-based classifier. The proposed approach identifies prototypes from the observed data through an offline training process and uses them to build a 0-order AnYa type fuzzy rule-based system for classification. Once primed offline, it is able to continuously learn from the streaming data afterwards to follow the changing data pattern by updating the system structure and meta-parameters recursively. The meta-parameters of the proposed approach are derived from data directly. By changing the level of granularity, the proposed approach can make a trade-off between performance and computational efficiency, and, thus, the classifier is able to address a wide variety of problems with specific needs. The classifier also supports different types of distance measures. Numerical examples based on benchmark datasets demonstrate the high performance of the proposed approach and its ability of handling high-dimensional, complex, large-scale problems.

Multi‐layer photovoltaic fault detection algorithm

This study proposes a fault detection algorithm based on the analysis of the theoretical curves which describe the behaviour of an existing grid-connected photovoltaic (GCPV) system. For a given set of working conditions, a number of attributes such as voltage ratio (VR) and power ratio (PR) are simulated using virtual instrumentation LabVIEW software. Furthermore, a third-order polynomial function is used to generate two detection limits (high and low limits) for the VR and PR ratios. The high and low detection limits are compared with real-time long-term data measurements from a 1.1 kWp GCPV system installed at the University of Huddersfield, United Kingdom. Furthermore, samples that lie out of the detecting limits are processed by a fuzzy logic classification system which consists of two inputs (VR and PR) and one output membership function. The obtained results show that the fault detection algorithm accurately detects different faults occurring in the PV system. The maximum detection accuracy (DA) of the proposed algorithm before considering the fuzzy logic system is equal to 95.27%; however, the fault DA is increased up to a minimum value of 98.8% after considering the fuzzy logic system.

WIRELESS BODY AREA NETWORK (WBAN) FOR HEALTH MONITORING SYSTEM USING GENETIC ALGORITHM AND FUZZY LOGIC

WBAN (Wireless Body Area Network) is one of the mostly used real time networks can be explained by certain limitations and constraints. The difficulties of the network occur because of the environmental constraints, device restrictions and architectural constraints. These problems also lift up various issues associated to network life, reliability and security. It is an automatic system utilized for the supervision of patients in circle condition. In the research, we have designed a network area with length and width of size 1000×1000 and 50 numbers of sensor nodes and the procedure is being iterated for almost six times. The research is being simulated in MATLAB environment. Parameters, namely, energy Consumption and Throughput have been used for checking the performance of the research. Optimization algorithm that is Genetic Algorithm is utilized for improving the performance of the parameters. The extraneous data is being removed by using Fuzzy logic classifier.

Photovoltaic fault detection algorithm based on theoretical curves modelling and fuzzy classification system

This work proposes a fault detection algorithm based on the analysis of the theoretical curves which describe the behavior of an existing PV system. For a given set of working conditions, solar irradiance and PV modules' temperature, a number of attributes such as voltage ratio (VR) and power ratio (PR) are simulated using virtual instrumentation (VI) LabVIEW software. Furthermore, a third order polynomial function is used to generate two detection limits for the VR and PR ratios obtained using VI LabVIEW simulation tool.The high and low detection limits are compared with measured data taken from 1.1 kWp PV system installed at the University of Huddersfield, United Kingdom. Samples lie out of the detection limits are processed by a fuzzy logic classification system which consists of two inputs and one output membership function.In this paper, PV faults corresponds to a short circuited PV module. The obtained results show that the fault detection algorithm can accurately detect different faults occurring in the PV system, where the maximum detection accuracy of before considering the fuzzy logic system is equal to 95.27%. However, the fault detection accuracy is increased up to a minimum value of 98.8% after considering the fuzzy system.

A Support Vector Machine Hydrometeor Classification Algorithm for Dual-Polarization Radar

An algorithm based on a support vector machine (SVM) is proposed for hydrometeor classification. The training phase is driven by the output of a fuzzy logic hydrometeor classification algorithm, i.e., the most popular approach for hydrometer classification algorithms used for ground-based weather radar. The performance of SVM is evaluated by resorting to a weather scenario, generated by a weather model; the corresponding radar measurements are obtained by simulation and by comparing results of SVM classification with those obtained by a fuzzy logic classifier. Results based on the weather model and simulations show a higher accuracy of the SVM classification. Objective comparison of the two classifiers applied to real radar data shows that SVM classification maps are spatially more homogenous (textural indices, energy, and homogeneity increases by 21% and 12% respectively) and do not present non-classified data. The improvements found by SVM classifier, even though it is applied pixel-by-pixel, can be attributed to its ability to learn from the entire hyperspace of radar measurements and to the accurate training. The reliability of results and higher computing performance make SVM attractive for some challenging tasks such as its implementation in Decision Support Systems for helping pilots to make optimal decisions about changes inthe flight route caused by unexpected adverse weather.

A hierarchical fuzzy logic systems frame work for data security

Data security and privacy plays a key role in carrying out day to day and long term business operations successfully. Organizations need to protect their data in the areas of data security and privacy. Therefore data security and privacy is a significant activity for large organizations. One novel method used to achieve data security is to use fuzzy logic based data classification to determine the required data security levels based on various government and business policies. Classifying data provides organizations the facilities to categorise organisational data based on organisational policies. Organisational data needs to be evaluated. Fuzzy logic based categorisation is explored in this paper. The method employed is based on Mohammadian et al. (Int J Electron Financ 3(4):374–386, 2009). This paper considers the application of a hierarchical fuzzy logic (HFL) classification method for categorizing organisational data based on governmental and business data policies. This paper demonstrates the use of a HFL to improve data classification. HFL reduces the size of the required fuzzy knowledge base system of the HFL data classification. This paper demonstrates how a HFL system can be employed to improve data security, privacy and user access control to determine data and user access control based on data sensitivity government and organizational data security requirements and user level security measures.

Diagnostic method for photovoltaic systems based on six layer detection algorithm

This work proposes a fault detection algorithm based on the analysis of the theoretical curves which describe the behaviour of an existing grid-connected photovoltaic (GCPV) plant. For a given set of working conditions, solar irradiance and PV modules’ temperature, a number of attributes such as voltage ratio (VR) and power ratio (PR) are simulated using virtual instrumentation (VI) LabVIEW software. Furthermore, a third order polynomial function is used to generate two detection limits (high and low limit) for the VR and PR ratios obtained using LabVIEW simulation tool.The high and low detection limits are compared with real-time long-term data measurements from a 1.1kWp and 0.52kWp GCPV systems installed at the University of Huddersfield, United Kingdom. Furthermore, samples that lies out of the detecting limits are processed by a fuzzy logic classification system which consists of two inputs (VR and PR) and one output membership function.The obtained results show that the fault detection algorithm can accurately detect different faults occurring in the PV system. The maximum detection accuracy of the algorithm before considering the fuzzy logic system is equal to 95.27%, however, the fault detection accuracy is increased up to a minimum value of 98.8% after considering the fuzzy logic system.