Entity

Time filter

Source Type

India

Rajakumar B.R.,Aloy Labs
International Journal of Computational Science and Engineering | Year: 2013

In this paper, a systematic comparative analysis is presented on various static and adaptive mutation techniques to understand their nature on genetic algorithm. Three most popular random mutation techniques such as uniform mutation, Gaussian mutation and boundary mutation, two recently introduced individual adaptive mutation techniques, a self-adaptive mutation technique and a deterministic mutation technique are taken to carry out the analysis. A common experimental bench of benchmark test functions is used to test the techniques and the results are analysed. The analysis intends to identify a best mutation technique for every benchmark problem and to understand the dependency behaviour of mutation techniques with other genetic algorithm parameters such as population sizes, crossover rates and number of generations. Based on the analytical results, interesting findings are obtained that would improve the performance of genetic algorithm. Copyright © 2013 Inderscience Enterprises Ltd. Source


Dennis B.,Aloy Labs | Muthukrishnan S.,Aloy Labs
Applied Soft Computing Journal | Year: 2014

A Genetic Fuzzy System (GFS) is basically a fuzzy system augmented by a learning process based on a genetic algorithm (GA). Fuzzy systems have demonstrated their ability to solve different kinds of problems in various application domains. Currently, there is an increasing interest to augment fuzzy systems with learning and adaptation capabilities. Two of the most successful approaches to hybridize fuzzy systems with learning and adaptation methods have been made in the realm of soft computing. The GA can be merged with Fuzzy system for different purposes like rule selection, membership function optimization, rule generation, co-efficient optimization, for data classification. Here we propose an Adaptive Genetic Fuzzy System (AGFS) for optimizing rules and membership functions for medical data classification process. The primary intension of the research is 1) Generating rules from data as well as for the optimized rules selection, adapting of genetic algorithm is done and to explain the exploration problem in genetic algorithm, introduction of new operator, called systematic addition is done, 2) Proposing a simple technique for scheming of membership function and Discretization, and 3) Designing a fitness function by allowing the frequency of occurrence of the rules in the training data. Finally, to establish the efficiency of the proposed classifier the presentation of the anticipated genetic-fuzzy classifier is evaluated with quantitative, qualitative and comparative analysis. From the outcome, AGFS obtained better accuracy when compared to the existing systems. © 2014 Elsevier B.V. All rights reserved. Source


Binu D.,Aloy Labs | Selvi M.,Aloy Labs
Journal of Medical Imaging and Health Informatics | Year: 2015

Optimization algorithms are applied on Fuzzy system for various purposes like membership function optimization, co-efficient optimization, rule generation, rule selection, etc. Here we amalgamate Bat algorithm with fuzzy classifier to generate optimized rules and membership functions effectively. The key contributions in our classifier are (i) generating and selecting optimized rules using bat algorithm, (ii) simplifying the design and discretizing process in membership function, (iii) formulating a fitness function based on frequency of occurrence of the rules in the learning data. The proposed Bat algorithm based fuzzy classifier is subjected to quantitative and qualitative analysis for performance comparisons. Experimental results demonstrate that BFC has achieved 75.21% accuracy when Lung cancer data is used. Moreover, BFC has accomplished 76.67% accuracy for Indian Liver data. Copyright © 2015 American Scientific Publishers. Source


Binu D.,Aloy Labs
Expert Systems with Applications | Year: 2015

Clustering finds various applications in the field of medical and telecommunication for unsupervised learning which is much required in expert system and its application. Various algorithms have been developed to clustering for the past fifty years after the introduction of k-means clustering. Recently, optimization algorithms are applied for clustering to find optimal clusters with the help of different objective functions. Accordingly, in this research, clustering is performed using three newly designed objective functions along with four existing objective functions with the help of optimization algorithms like, genetic algorithm, cuckoo search and particle swarm optimization algorithm. Here, three different objective functions are designed including the cumulative summation of fuzzy membership and distance value with normal data space, kernel space as well as multiple kernel space. In addition to the existing seven objective functions, totally, 21 different clustering algorithms are discussed and the performance is validated with 16 different datasets which are synthetic, small and large scale real data. The comparison is made with five different evaluation metrics to validate the effectiveness and efficiency. From the research outcome, the suggestion is presented to select a suitable algorithm among 21 algorithms for a particular data and results proved that the effectiveness of cluster analysis is mainly dependent on objective function and the efficiency of cluster analysis is based on search algorithm. © 2015 Elsevier Ltd All rights reserved. Source


Binu D.,Aloy Labs | George A.,Aloy Labs
Proceedings of the 2013 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2013 | Year: 2013

In recent times, clustering has been well known for various researchers due to various applications in most of the fields like, telecommunication, networking, biomedical domain and so on. So, various attempts have been already made by the researchers to develop a better algorithm for clustering. One of the procedures well known among the researchers is optimization that has been effectively utilized for clustering. In most of the clustering, the objective function is to minimize the intra cluster distance among the data points. Here, we have made significant trial in developing optimization based clustering algorithm utilizing kernel-based FCM and PSO algorithm. The objective function for minimization is taken from kernel-based FCM and the same objective is solved using PSO algorithm. The algorithm developed based on these scenarios are named as, KF-PSO. At first, the input data is given to PSO algorithm and the final best cluster centers are chosen from PSO algorithm useful for grouping based on the objective of the kernel clustering. Finally, the experimentation have been performed in various datasets and from the results, we have showed that the proposed hybrid algorithm achieved 98% and 90.5 % accuracy in iris and wine dataset. © 2013 IEEE. Source

Discover hidden collaborations