Pintu Chandra Shill

Optimization of interval type-2 fuzzy logic controller using quantum genetic algorithms

A Type-2 Fuzzy logic controller adapted with quantum genetic algorithm, referred to as type-2 quantum fuzzy logic controller (T2QFLC), is presented in this article for robot manipulators with unstructured dynamical uncertainties. Quantum genetic algorithm is employed to tune type-2 fuzzy sets and rule sets simultaneously for effective design of interval type-2 FLCs. Traditional fuzzy logic controllers (FLCs), often termed as type-1 FLCs using type-1 fuzzy sets, have difficulty in modeling and minimizing the effect of uncertainties present in many real time applications. Therefore, manually designed type-2 FLCs have been utilized in many control process due to their ability to model uncertainty and it relies on heuristic knowledge of experienced operators. The type-2 FLC can be considered as a collection of different embedded type-1 FLCs. However, manually designing the rule set and interval type-2 fuzzy set for an interval type-2 FLC to give a good response is a difficult task. The purpose of our study is to make the design process automatic. The type-2 FLCs exhibit better performance for compensating the large amount of uncertainties with severe nonlinearities. Furthermore, the adaptive type-2 FLC is validated through a set of numerical experiments and compared with QGA evolved type-1 FLCs, traditional and neural type-1 FLCs.

Genetic algorithm based fully automated and adaptive fuzzy logic controller

In this paper, an integration of fuzzy logic controller (FLC) and genetic algorithm (GA) is developed with a view to make the design process fully automatic, without requiring any human expert knowledge. Here, GA is used in two stages simultaneously: the first stage involves selection and definition of fuzzy rules, while the second stage performs an optimal selection of membership function types associated to the fuzzy rules. It is argued that the performance of an FLC greatly depends on the fuzzy rules as well as the types of membership functions associated to the fuzzy sets. Thus, the aforementioned two-stage GA is a viable solution for designing an efficient FLC system. In order to evaluate performance, the proposed approach is applied to a well-known benchmarking controller design task, “backing up a truck reversing system”. The simulation result exhibits superior performance and thereby validates the proposed integrated GA and FLC system.

Bangla handwritten numeral recognition using convolutional neural network

Recognition of handwritten numerals has gained much interest in recent years due to its various application potentials. Although Bangla is a major language in Indian subcontinent and is the first language of Bangladesh study regarding Bangla handwritten numeral recognition (BHNR) is very few with respect to other major languages such Roman. The existing BHNR methods uses distinct feature extraction techniques and various classification tools in their recognition schemes. Recently, convolutional neural network (CNN) is found efficient for image classification with its distinct features. It also automatically provides some degree of translation invariance. In this paper, a CNN based BHNR is investigated. The proposed BHNR-CNN normalizes the written numeral images and then employ CNN to classify individual numerals. It does not employ any feature extraction method like other related works. 17000 hand written numerals with different shapes, sizes and variations are used in this study. The proposed method is shown satisfactory recognition accuracy and outperformed other prominent exiting methods.

Genetic algorithm based fuzzy decision support system for the diagnosis of heart disease

Decision in medical diagnosis is mostly taken by experts experiences. In many cases, not all the experts experiences contribute towards effective diagnosis of a disease. Researchers have taken multiple approaches like attribute reduction, rule extraction, fuzzy model optimization, etc. But noisy data in datasets, irrelevant attributes, and lack of effective fuzzy rules are major hindrances to provide best decision. In this study, we propose genetic algorithm based fuzzy decision support system for predicting the risk level of heart disease. Our proposed fuzzy decision support system (FDSS) works as follows: i) Preprocess the dataset, ii) Effective attributes are selected based on different methods, iii) Weighted fuzzy rules are generated on the basis of selected attributes using GA, iv) Build the FDSS from the generated fuzzy knowledge base, v) Predict the heart disease. The experiments carried out with real-life data set show the effectiveness of this proposed innovative approach.

Optimization of Fuzzy Logic Controllers with Rule Base Size Reduction using Genetic Algorithms

In this paper, we present the automatic design methods with rule base size reduction for fuzzy logic controllers (FLCs). The adaptive schema is divided into two phases: the first phase is concerned with the adaptive learning method for optimizing the MFs parameters based on the binary coded genetic algorithms. The second phase is about the learning and reducing: automatically generate the fuzzy rules and at the same time apply the genetic reduction technique to determine the minimum number of fuzzy rules required in building the fuzzy models. In the rule base, the redundant rules are removed by setting their all consequents weight factor to zero and merging the conflicting rules during the learning process. The real and binary coded coupled genetic algorithms are applied for generating the optimal controllers that reduce the rule base size and optimal selection of fuzzy sets. Optimizing the MFs of FLCs with learning and reducing the number of fuzzy control rules concurrently represents a way to improve the computational efficiency and interpretability of FLCs to minimize the errors. The control algorithm is successfully tested for intelligent control of two degrees of freedom inverted pendulum. Finally, the simulation studies exhibits competing results with high accuracy that demonstrate the effective use of the proposed algorithm.

Optimization of fuzzy logic controllers with rule base size reduction using genetic algorithms

In this paper, we present the automatic design methods with rule base size reduction for fuzzy logic controllers (FLCs). The adaptive schema is divided into two phases: the first phase is concerned with the adaptive learning method for optimizing the MFs parameters based on the binary coded genetic algorithms. The second phase is about the learning and reducing: automatically generate the fuzzy rules and at the same time apply the genetic reduction technique to determine the minimum number of fuzzy rules required in building the fuzzy models. In the rule base, the redundant rules are removed by setting their all consequents weight factor to zero and merging the conflicting rules during the learning process. The real and binary coded coupled genetic algorithms are applied for generating the optimal controllers that reduce the rule base size and optimal selection of fuzzy sets. Optimizing the MFs of FLCs with learning and reducing the number of fuzzy control rules concurrently represents a way to improve the computational efficiency and interpretability of FLCs to minimize the errors. The control algorithm is successfully tested for intelligent control of two degrees of freedom inverted pendulum. Finally, the simulation studies exhibits competing results with high accuracy that demonstrate the effective use of the proposed algorithm.

Design of a self-tuning hierarchical fuzzy logic controller for nonlinear swing up and stabilizing control of inverted pendulum

Fuzzy logic controllers suffer from rule explosion problem as the number of rules increases exponentially with the number of input variables. Although several methods have been proposed for eliminating the combinatorial rule explosion problem, none of them is fully satisfactory. In this paper, we describe a new adaptive method for the design of cascaded layer based hierarchical fuzzy system with high input dimensions. This new adaptive hierarchical architecture could be applied to dimensionality reduction in fuzzy modeling. An evolutionary algorithm based off-line leaning algorithm is employed to generate the fuzzy rules and their corresponding membership functions. The evolutionary learning paradigm is a powerful tool to tune the fuzzy logic controllers since it requires no prior knowledge about the systems behavior in order to formulate a set of functional control rules through adaptive learning. The resulting hierarchical fuzzy system has not only an equivalent approximation capability, but less number of fuzzy rules compared with the conventional fuzzy logic system. Simulation studies exhibit competing results with high accuracy that illustrating the effectiveness of the approach.

New Automatic Fuzzy Relational Clustering Algorithms Using Multi-Objective NSGA-II

Abstract Most of the fuzzy clustering methods use only centroid information and cannot differentiate the geometric structures of clusters due to the cohesion and separation measures of the fuzzy partition. Moreover, conventional clustering methods confine the search space of automatic fuzzy clustering as it shows a tendency to fall into local minima as well as the number of clusters is required to be provided as prior knowledge. In this paper, combining fuzzy relational clustering (FRC) with multi-objective genetic algorithm NSGA-II, we propose two new fuzzy relational clustering methods, referred to as FRC NSGA and IFRC NSGA. In IFRC NSGA, NSGA-II is used to adjust the parameters of FRC algorithm dynamically such as the appropriate number of clusters and the initial membership values. Thus this proposed model handles the intricacy of automatic clustering a dataset, at the same time, avoids the problem of falling into local minima quickly. For both of the proposed models, NSGA-II is used to optimize two cluster validity indices named, separation, and cohesion, simultaneously, whereas, FRC is used to handle the overlapping properties of clusters. In this case, fuzzy membership degrees are used to compute the overlap-separation. To eliminate the impediment of automatic fuzzy clustering, it is necessary to optimize one or more criteria. Therefore, we consider NSGA-II as an optimization algorithm to optimize more than single criterion. The experimental results have exhibited that the intended methods provide competitive results in the compound, overlapped, high-dimensional gene expression and non-gene expression datasets. The proposed methods are able to determine well-separated, hyperspherical, noncompact and overlapping clusters compared to other existing methods.

Adaptive weighted fuzzy rule-based system for the risk level assessment of heart disease

Expert’s knowledge base systems are not effective as a decision-making aid for physicians in providing accurate diagnosis and treatment of heart diseases due to vagueness in information and impreciseness and uncertainty in decision making. For this reason, automatic diagnostic fuzzy systems are very time demanding to improve the diagnostic accuracy. In this paper, we have developed an automatic fuzzy diagnostic system based on genetic algorithm (GA) and a modified dynamic multi-swarm particle swarm optimization (MDMS-PSO) for prognosticating the risk level of heart disease. Our proposed fuzzy diagnostic system (FS) works as follows: i) Preprocess the data sets ii) Effective attributes are selected through statistical methods such as Correlation coefficient, R-Squared and Weighted Least Squared (WLS) method, iii) Weighted fuzzy rules are formed on the basis of selected attributes using GA, iv) MDMS-PSO is employed for the optimization of membership functions (MFs) of FS, v) Build the ensemble FS from the generated fuzzy knowledge base by fusing the different local FSs. Finally, to ascertain the efficiency of the adaptive FS, the applicability of the FS is appraised with quantitative, qualitative and comparative analysis on the publicly available different real-life data sets. From the empirical analysis, we see that this hybrid model can manage the knowledge vagueness and decision-making uncertainty precisely and it has yielded better accuracy on the different publicly available heart disease data sets than other existing methods so that it justifies its adaptability with different data sets.

Generating Weighted Fuzzy Rules for Estimating Null Values Using an Evolutionary Algorithm

In this paper we have been trying to estimate null values from relational database systems. At present some methods exist to estimate null values from relational database systems. The estimated accuracy of the existing methods are not good enough. We use advance technique for estimating null values in relational database systems. In our paper we present the technique to generate weighted fuzzy rules from relational database systems for estimating null values using evolutionary algorithms. The parameters (operators) of the evolutionary algorithms are adapted via fuzzy systems. We have fuzzified the attribute values using membership functions shape, type and parameter values. The results of the evolutionary algorithms are the weights of the attributes. The different weight of attribute generates a set of fuzzy rules. From this we have obtained a set of rules. Our proposed techniques have a higher average estimated accuracy rate and able to estimate the null values in relational database systems