An improved firefly heuristics for efficient feature selection and its application in big data

Big Data is exceedingly useful for business applications and is fast rising as a domain of the IT industry. It has created considerable interest in several domains, which includes the manufacturing of health care machine, bank transaction, social media, and so on. Due to the diversity and size of datasets in Big Data, effective representation, access as well as analyses of unstructured as well as semi-structured data are still problematic. It is required to determine the way of searching space of all potential variable sub-sets as well as the assessment of prediction performance of learning machines for guiding searches and also which predictor to utilize. Extensive searches may be carried out if the quantity of parameters is not too much. However the issue is NP-Hard and search rapidly turns operationally intractable. Vast set of search schemes may be utilized, which include best-first, branch-and-bound, simulated annealing, genetic algorithm. In the current paper, a features selection method on the basis of Firefly Algorithm ( FA) is suggested to improve the big data analysis. FA meta-heuristic techniques modelled on the behaviour of the fireflies solve the optimization problems. The suggested technique was tested through a huge twitter data set and effectiveness of the proposed method was proven.