The Cuckoo Search Guided By Correlation And Classi Cation Accuracy

Table 12: Factor and their level for maximizing throughput and system utilization through genetic algorithm

For binary attributes support is an important measure used in validating association rules generated as well as in defining other interestingness measures. In Boolean transactions item can be either present or absent, hence support count is defined as \\

(2011) presented research of a clustering issue for office workplaces using a fuzzy bat algorithm. Khan and Sahari (2012a) as well presented a comparison study of bat algorithm with PSO, GA, along with other algorithms in the perspective for e-learning, and thus recommended that bat algorithm has clearly some advantages over other algorithms. Then, they (Khan and Sahari, 2012b) also suggested a study of clustering problems using bat algorithm and its expansion like a bi-sonar optimization variant with positive results. On the other side, Mishra et al. (2012) applied bat algorithm to categorize microarray data, while Natarajan et al. (2012) presented a comparison study of cuckoo search and also bat algorithm for Bloom filter optimization. Damodaram and Valarmathi (2012) studied phishing website detection applying modified bat algorithm and also attained very good outcome.

Utilizing different techniques for data mining is extremely important for what may work for ne may not work for the other. With the

[Key words] prediction, multicollinearity, high dimension, principle component analysis, robust regression, ridge regression, linear regression

The problem of variable selection is always the center of statistical research. Some classical methods like best subset selection, forward selection and backward elimination are proposed to handing massive data set. These methods are basically based on the idea of grid search. For example, the best subset selection searches the optimal model by all possible combination of the predictors. The forward selection find the best model by adding one predictor at each time, while the backward elimination finds the best model by removing one predictor at each time. Although these methods are powerful and accurate, they also cost a lot. For instance, suppose our model has 10 predictors, if we run the best subset selection to get the optimal model, we need to compare 1024 combinations of the predictors. It is unrealistic to perform such method in our real life because it time consuming. As a result, more efficient methods to solve the problem of variable selection are urgently desired.

The top node in the graph includes all existing match field values with no rules and is successively grouping rules to describe the dependencies . The investigation of rules semantics and the generation of groups with dependencies is a nontrivial task owing to the computational challenges [4] . To tackle this issue, we have applied Formal concept Analysis (FCA) [7], which relies on results from algebra and lattice theory [10]. In order to adapt the FCA method to our case, the rules were considered as objects and the match field values as attributes. The clusters of FCA helps to find the rule sets that are intentionally described by the respective sets of common match fields.

• Characterization: is a summary of common features of items in a target class, and yields what is known as characteristic rules. The information pertinent to a user-specified class are usually retrieved by a database request and run through a summarization segment to mine the soul of the data at diverse levels of mining. For example, one may want to illustrate the OurVideoStore clienteles who frequently lease more than 30 movies a year. With conception chain of command on the traits describing the objective class, the trait based induction technique can be used, for example, to carry out data summarization.

Data mining, association rule, fuzzy logic, neural network, particle swarm optimization, artificial bee colony algorithm and harmony search algorithm

The best value of the problem is taken by taking care of all the solutions and comparing the results. Different parameters has to be initialised before the start of the problem. The maximum number of generations (maxgen), maximum population size in each population (sizepop), mac function and fly range (FR) are those parameters. In ACFOA the initial parameters are maxgen (maximum generations), sizepop (population size) and FR (fly range)

Formal Concept Analysis (FCA), also known as Galois lattice mining, is a branch of lattice theory that allows identification of meaningful groupings of objects that have common attributes (Wille, 2009; Ganter & Wille, 2012). It is a data analysis method which enables the discovery of hidden knowledge in the data in the form of concepts. Godin, Gecsei, and Pichet (1989) have demonstrated the effectiveness of using FCA for indexing and retrieval as an alternative to hierarchical classification and boolean query based systems.

The vast majority of the optimization problems emerging in real-world applications incorporate vast numbers of variables and constraints, which

Abstract— Classification problems often have a large number of features in the data sets, but only some of them are useful for classification. Data Mining Performance gets reduced by Irrelevant and redundant features. Feature selection aims to choose a small number of relevant features to achieve similar or even better classification performance than using all features. It has two main objectives are maximizing the classification performance and minimizing the number of features. Moreover, the existing feature selection algorithms treat the task as a single objective problem. Selecting attribute is done by the combination of attribute evaluator and search method using WEKA Machine Learning Tool. We compare SVM classification algorithm to automatically classify the data using selected features with different standard dataset.

Abstract— Process of selecting relevant features from available dataset is known as features selection. Feature selection is use to remove or reduce redundant and irrelevant features. Various feature selection algorithms such as CFS (correlation feature selection), FCBF (Fast Correlation Based Filter) and CMIM (Conditional Mutual Information Maximization) are used to remove redundant and irrelevant features. To determine efficiency and effectiveness is the aim of feature selection algorithm. Time factor is denoted by efficiency and quality factor is denoted by effectiveness of subset of features. Problem of feature selection algorithm is accuracy is not guaranteed, computational complexity is large, ineffective at removing redundant features. To overcome these problems Fast Clustering based feature selection algorithm (FAST) is used. Removal of irrelevant features, construction of MST (Minimum Spanning Tree) from relative one and partition of MST and selecting representative features using kruskal’s method are the three steps used by FAST algorithm.

First we will define a cost function related to the NS. Then we will describe the important variables. After defining the cost function, the relevance of the cost function will be explained.