Article Preview
TopI. Introduction
Computational Intelligence (CI) is the fastest growing and promising area of study that have drawn more attention from the researchers over the years (Zadeh, L. A., et al., 2014). CI, also termed as Soft Computing in Lotfi Zadeh’s terminology (Zadeh, L. A., 1996) is concerned with achieving of pattern recognition in data and structures in data (Wang, Y., 2017; Wang, Y., et al., 2016). CI is the only destination for many design and engineering researchers those who are working on modeling and analyzing complex systems (Pedrycz, W., Et al., 2014).CI embraces Nature-Inspired Metaheuristics (NIMs) like Bio-Inspired Computing (BIC), Swarm Intelligence (SI),Evolutionary Computations (EC), Metaphor-based Metaheuristics (MbM) and other Computational methodologies in solving NP-hard optimization problems (Bouarara, H. A., et al., 2015;Gheraibia, Y., et al., 2015;Kaynak, O., et al., 2012;Nouaouria, N., et al., 2014; Schor, D., & Kinsner, W., 2011; Zadeh, L. A., 1973).Numerous successful applications of CI have been found in many design and engineering domains like data mining and knowledge discovery, pattern recognition, clinical decision making system, control system design, Market analysis and forecasting, etc. (Azar, A. T., & Vaidyanathan, S. (Eds.), 2015).
Nature is the key source of rich models for solving computational problems. The algorithms which are designed by mimicking various phenomena existed in the nature for solving complex problems are called NIMs (Nanda, S. J., & Panda, G., 2014). NIMs, a sub-field of CI, are popular, economical approaches for solving various problems, including tough optimization problems and NP-hard problems (Fister Jr, I., et al., 2013). There are several population based meta-heuristic optimization algorithms, for instance Particle Swarm Optimization (PSO) (Eberhart, R., & Kennedy, J., 1995),Whale Optimization Algorithm (WOA) (Mirjalili, S., & Lewis, A., 2016), Grey Wolf Optimization Algorithm (GWO) (Mirjalili, S., Et al., 2014), Tornadogenesis Optimization Algorithm (TOA) (Saidala, R. K., & Devarakonda, N., 2017d), Salp Swarm Algorithm (SSA) (Mirjalili, S., Et al., 2017),New Class Topper Optimization Algorithm (Class TOA) (Das, P., Et al., 2018), etc. were developed and successfully applied to optimization problems. Population based NIMs have several unique features over other algorithms. These include collaborative learning, high exploration ability, decentralized control, and inspiration from the dynamic social behavior. Thus, many global optimization problems which can be observed frequently in many real-life applications like engineering, decision making, machine learning, statistics, optimal control, etc. (James, J. Q., & Li, V. O., 2015;Li, X., Et al., 2014; Mirjalili, S., 2015; Saidala, R. K., & Devarakonda, N., 2017b) are solved with low solution cost. Over the recent years NIMs were successfully dealing with various clustering problems. So, recently the research community has kept their special interests on developing new NIMs and applying them to various data cluster problems (Nanda, S. J., & Panda, G.,2014;Saidala, R. K., & Devarakonda, N., 2017a; Saidala, R. K., & Devarakonda, N., 2018a).
Table 1. Notations of Unimodal benchmark functions
| Function Description | Range | fmin |
 |  | 0 |
 |  | 0 |
 |  | 0 |
 |  | 0 |
 |  | 0 |
 |  | 0 |
 |  | 0 |