An Efficient Approach for Software Maintenance Effort Estimation Using Particle Swarm Optimization Technique
Chamkaur Singh1, Neeraj Sharma2, Narender Kumar3

1Chamkaur Singh, Research Scholar, I.K. Gujral Punjab Technical University, Jalandhar (Punjab), India.
2Dr. Neeraj Sharma, Professor, Gian Jyoti Group of Institutions, Mohali (Punjab), India.
3Dr. Narender Kumar, Assistant Professor, HNB Garhwal University, Srinagar Garhwal (Uttarakhand), India.
Manuscript received on 25 March 2019 | Revised Manuscript received on 02 April 2019 | Manuscript Published on 12 April 2019 | PP: 1-6 | Volume-7 Issue-6C April 2019 | Retrieval Number: F90190476C19/2019©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: The main objective of software engineering community is to develop useful models that are able to calculate the accurate estimating software effort. COCOMO (Constructive Cost Model) is consider as mostly used algorithmic maintenance cost modeling technique among other software maintenance cost estimation techniques. It is mostly used technique due to its simplicity for estimating the effort in person-months for a project at different stages. In this paper we have proposed a new approach that is able to give better results. In proposed approach we have used Tomcat server dataset whose features are extracted using Principle component analysis approach which is further optimized using Particle Swarm Optimization. In previous work most of researchers have used Genetic algorithm but it is a time consuming part. So, in this paper we have used Particle swarm optimization that gives improved results. At the end we have used Linear discriminant analysis for classification that classifies the priority levels and tell how much your system is having the estimations for the cost based on Source lines of the codes or functional points or the efforts required. The proposed approach is tested in terms of functional point, set effort person per month and SLOC that gives best results.
Keywords: COCOMO, Functional Point, Set Effort Per Month, SLOC, Software Engineering, PCA, LDA, PSO.
Scope of the Article: Systems and Software Engineering