The Big Data Approach Using Bio-Inspired Algorithms: Data Imputation

In this chapter, the concept of big data is defined based on the five characteristics namely velocity, volume, value, veracity, and variety. Once defined, the sequential phases of big data are denoted, namely data cleansing, data mining, and visualization. Each phase consists of several sub-phases or steps. These steps are briefly described. In order to manipulate data, a number of methods may be employed. In this chapter, we look at an approach for data imputation or the extrapolation of missing values in data. The concept of genetic algorithms along with its off-shoot, meta-heuristic algorithms, is presented. A specialized type of meta-heuristic algorithm, bio-inspired algorithms, is introduced with several example algorithms. An example, a bio-inspired algorithm, the kestrel, is introduced using the steps outlined for the development of a bio-inspired algorithm (Zang et al. 2010). This kestrel algorithm will be used as an approach for data imputation within the big data phases framework.