Feature selection and instance selection using cuttlefish optimisation algorithm through tabu search

Abstract

Over the recent decades, the amount of data generated has been growing exponentially, the existing machine learning algorithms are not feasible for processing of such huge amount of data. To solve such kind of issues, we have two commonly adopted schemes, one is scaling up the data mining algorithms and other one is data reduction. Scaling up the data mining algorithms is not a best way, but data reduction is fairly possible. In this paper, cuttlefish optimisation algorithm along with tabu search approach is used for data reduction. Dataset can be reduced mainly in two ways, one is the selecting optimal subset of features from the original dataset, in other words eliminating those features which are contributing lesser information another method is selecting optimal subset of instances from the original data set, in other words eliminating those instances which are contributing lesser information. Cuttlefish optimisation algorithm with tabu search finds both optimal subset of features and instances. Optimal subset of feature and instance obtained from the cuttlefish algorithm with tabu search provides a similar detection rate, accuracy rate, lesser false positive rate and the lesser computational time for training the classifier that we obtained from the original data set.

Generalization ability of Extreme Learning Machine using different Sample Selection Methods

“…A fuzzy rough instance selection approach was presented in [5]. In [8] sample entropy based dataset reduction method was proposed for ELM. A number of other methods are suggested in literature like instance selection for one class problem [16] and selection of instances in Meta Learning to estimate the performance of classifier [9].…”

“…From the literatures, one can see that much of the research works from the KDD domain, focus on either by scaling up machine learning algorithms or scaling down the data [3]. Instance selection is one of the data reduction techniques [4] and having many advantages such as it helps to increase capabilities and generalization performance of the classification model [5], reduces the space complexity [6], decreases the computational time and speeds up the knowledge extraction process [3,7,8]. In a classification process, Machine learning deals with algorithms that allow machines to generate trained models after learning from data.…”