An ecological space based hybrid swarm-evolutionary algorithm for software reliability model parameter estimation

Sangeeta, .; Sharma, Kapil; Bala, Manju

doi:10.1007/s13198-019-00926-2

Cited by 10 publications

(2 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(7) Update the position of followers according to formula (5). (8) Update the position of the sparrow that is aware of danger according to formula (6). (9) iter=iter+1, go to step (2).…”

Section: End N Ymentioning

confidence: 99%

See 1 more Smart Citation

Software Defects Prediction Based on Hybrid Particle Swarm Optimization and Sparrow Search Algorithm

Yang

Wang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Software defects reflect software quality, and software failures can be predicted through software reliability models. Aiming at the problem that the parameters of software reliability model are difficult to estimate, this paper used the hybrid algorithm for model parameter estimation to software defect prediction. As a typical swarm intelligence algorithm, PSO (Particle Swarm Optimization) has fast convergence but low solution accuracy. SSA (Sparrow Search Algorithm) not only has high search accuracy and fast convergence speed, but also has the advantages of good stability and strong robustness. Based on the characteristic that the fitness function proposed in this paper, this paper hybrid PSO and SSA to accelerate the convergence before the individual update of the SSA. At the same time, this paper also constructed a new fitness function based on the maximum likelihood estimation of the parameters, and used it for parameter initialization. Through the analysis of the experimental results of five sets of actual data sets, the optimization performance of the hybrid algorithm (SSA-PSO) was better than that of a single algorithm with higher convergence speed and more stable, accurate results. Moreover, with the support of the new fitness function, it effectively solved the problems of slow convergence speed and low accuracy of solution. The experimental results showed that the hybrid SSA-PSO could obtain the better solution, convergence speed and stability than single SSA and PSO in software defections estimation and prediction.

show abstract

“…(7) Update the position of followers according to formula (5). (8) Update the position of the sparrow that is aware of danger according to formula (6). (9) iter=iter+1, go to step (2).…”

Section: End N Ymentioning

confidence: 99%

“…The swarm intelligence optimization is a new type of biological heuristic calculation method that is inspired by observing various behaviors of social biological groups, such as ants, birds, fish, etc. Based on those swarm intelligence optimization, some new [6][7][8] and hybrid algorithm [9][10] comes out to get a better solution.…”

Section: Introductionmentioning

confidence: 99%