Software Cost Estimation by Optimizing COCOMO Model Using Hybrid BATGSA Algorithm

Abstract

This paper estimates the effort for software by optimizing the COnstructive COst MOdel (COCOMO) model parameters using hybrid BATGSA (Bat inspired Gravitational Search Algorithm) algorithm. The performance of the COCOMO model completely depends upon its parameters which can be optimized by using meta-heuristic algorithms. This paper uses hybrid BATGSA algorithm which hybrids the improved bat algorithm with the gravitation search algorithm (GSA) to optimize the COCOMO model. The bat algorithm demonstrates the hunting and routing behavior of the bat which is improved by using a random walk in the exploration phase. The exploration phase is further improved by using GSA as gravitation force affects the velocity of the bat. The algorithm has been analyzed on four NASA datasets downloaded from promise repository. The comparison of the algorithm has been made with existing three states of art techniques i.e. COCOMO model, BAT algorithm, Improved BAT(IBAT) algorithm by using normalized error as a parameter. The reduction in error ranges from 2% to 10% on different dataset as compared other state of art algorithms proves the significance of proposed algorithm.

Metaheuristic Algorithms in Optimizing Deep Neural Network Model for Software Effort Estimation

“…The main drawback of existing literature [21][22][23][24][25][26][27][28][29][30][31][32][33][34][35] is that it is very difficult to figure out which meta-heuristic algorithm provides better accuracy in estimating software effort. The main reasons behind unpredictability in the performances of the meta-heuristic algorithms are as follows.…”

“…2) The results obtained from GWO and SB algorithms are compared with five other meta-heuristic algorithms used in the literature for software effort estimation. We selected five widely used nature-inspired algorithms (BAT [29,45], Cuckoo Optimization (CO) [35,53,54], Genetic Algorithm (GA) [22,30,33] and Ant Colony Optimization (ACO) [24,32], Particle Swarm Optimization (PSO) [27,34,46]) for comparison. In this work, for comparison analysis nature-inspired meta-heuristics algorithms are selected based on inspiration from: (i) Natural biological system (GA, SB), (ii) Theory of evolution (PSO), (iii) Insects activities (ACO), (iv) Group behavior of animals, and birds (GWO, CO, BAT).To validate the performances of these seven algorithms, a set of nine benchmark functions having wide dimensions is applied.…”

“…WCO integrates Whale Optimization Algorithm (WOA) and the Crow Search Algorithm (CSA) to find the optimal regression coefficients for a regression model. BATGSA hybrid algorithm based on BAT and Gravitational Search Algorithm (GSA) is presented in [29] to obtain better software estimation. BAT algorithm determines the routing and hunting behavior of bat in the exploration phase which is further improved by using gravitational force effect of the GSA to speed up the searching speed of the BAT.…”

“…Xin-She Yang proposes the Bat algorithm (BA) [29,45], influenced by the echolocation behavior of micro bats. This kind of behavior guides and helps bats in their conduct of flying and hunting.…”

Designing a Tool to Estimate Software Projects Based on The Swarm Intelligence

“…The hybrid method gave better results than the previous methods. Although the hybrid method was improved the work, the mean absolute error values were also high, meaning that there was a difference between estimated effort and actual effort [12]. Researcher Bhaskar Marapelli introduced a working method for software estimating, proposing linear regression techniques for machine learning and closest K neighbors to predict program effort estimation using the COCOMO81, COCOMONasa and COCOMONasa2 data sets.…”