A novel hybrid approach for feature selection in software product lines
- PDF / 2,227,715 Bytes
- 24 Pages / 439.37 x 666.142 pts Page_size
- 79 Downloads / 176 Views
A novel hybrid approach for feature selection in software product lines Hitesh Yadav 1 & Rita Chhikara 1 & A. Charan Kumari 2 Received: 15 April 2020 / Revised: 22 August 2020 / Accepted: 17 September 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
Software Product Line (SPL) customizes software by combining various existing features of the software with multiple variants. The main challenge is selecting valid features considering the constraints of the feature model. To solve this challenge, a hybrid approach is proposed to optimize the feature selection problem in software product lines. The Hybrid approach ‘Hyper-PSOBBO’ is a combination of Particle Swarm Optimization (PSO), Biogeography-Based Optimization (BBO) and hyper-heuristic algorithms. The proposed algorithm has been compared with Bird Swarm Algorithm (BSA), PSO, BBO, Firefly, Genetic Algorithm (GA) and Hyper-heuristic. All these algorithms are performed in a set of 10 feature models that vary from a small set of 100 to a high-quality data set of 5000. The detailed empirical analysis in terms of performance has been carried out on these feature models. The results of the study indicate that the performance of the proposed method is higher to other state-of-the-art algorithms. Keywords Particle swarm optimization . Hyper-heuristic . Biogeography-based optimization . Firefly . Genetic algorithm (GA) . Bird swarm optimization (BSA) . Software product lines (SPL) . Feature model (FM)
* Hitesh Yadav [email protected]; [email protected] Rita Chhikara [email protected] A. Charan Kumari [email protected]
1
The NorthCap University, Gurugram, Haryana, India
2
Dayalbagh Educational Institute, Gurugram, Haryana, India
Multimedia Tools and Applications
1 Introduction Software Product Line (SPL) [6] represents common systems with multiple variants. SPL is the basic requirement of an organization. To organize SPL, feature model [16, 30] is used. If a feature model has ‘n’ features, then SPL can be produced exponentially by selecting and unselecting features. Therefore, feature selection optimization in SPL is an NP-hard problem. Literature shows that multiple types of metaheuristic algorithms can be applied to solve NPhard problems such as Bird Swarm Algorithm, Particle Swarm Optimization, Firefly, DE, BBO, GA [2] etc. In past years, various hybridization methods have been proposed such as PSO & BBO [1], PSO & Firefly [11], PSO with GA [25], PSO with DE [21] etc. One of the popular algorithm i.e. BBO which is used by many real problems such as aircraft sensor [27], satellite image recognition [22] and power problem [24], robot manipulator [26], UCAV path planning [33], covariance matrix based migration [3], orthogonal crossover [10]. As per our knowledge, not much work has been done on discrete problems like feature selection in SPL with BBO, PSO and hyper-heuristic. The overview of the algorithms are as follows:
1.1 Particle swarm optimization (PSO) Eberhart and Kennedy formed the PSO in 1995 [9
Data Loading...
