Evolutionary Computing Techniques for Software Effort Estimation

Sehra, Sumeet Kaur; Brar, Yadwinder Singh; Kaur, Navdeep

doi:10.5121/ijcsit.2017.9211

Cited by 3 publications

(2 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Almost three decades ago, when COCOMO [11] was introduced by Boehm, several academics presented a variety of cost-estimating models to address a variety of optimizing problems. The extensive spread may be noticed, in the field of optimizing the basic COCOMO Model [12], [13], [4], [14], [15], [16], [17], [18], [19], [20], [21], [5], [22], [23], [24], [25], [26], [27], [28], [29], [30], [31], [32], [33], [34], [35], [36], [37], [38].…”

Section: Related Workmentioning

confidence: 99%

Improving Software Effort Estimation Models Using Grey Wolf Optimization Algorithm

Alsheikh,

Munassar

2023

IEEE Access

View full text Add to dashboard Cite

One of the phases in the Software Development Life Cycle is planning the software project. Estimating the software effort is another task in this project planning phase. Software effort estimation is the method of determining how many workers are required to create a software project. To increase the precision of software effort estimation, many researchers have focused on this field and used both algorithmic and non-algorithmic techniques. The most widely used method is the Constructive Cost Model (COCOMO). However, the COCOMO model has a limitation, which is related to the precision of the software effort estimation. Meta-heuristic algorithms are preferred with parameter optimization because they can provide solutions that are nearly optimal at a reasonable cost. This study aims to enhance the precision of effort estimation by modifying the three COCOMO-based models' coefficients and assess the efficiency of Grey Wolf Optimization (GWO) in finding the optimal value of effort estimation through applying four other algorithms, including Zebra Optimization(ZOA), Moth-Flame Optimization(MFO), Prairie Dog Optimization(PDO), and White Shark Optimization(WSO) with NASA18 dataset. These models include the basic COCOMO model, and another two models were also suggested in the published research as a modification of the basic COCOMO model. To assess the performance of the proposed models, the six most used software effort estimation metrics are used. The results demonstrated that the GWO outperformed other algorithms based on high accuracy and significant error minimization, involving ZOA, MFO, PDO, WSO, and other existing models.

show abstract

Section: Related Workmentioning

confidence: 99%

Improving Software Effort Estimation Models Using Grey Wolf Optimization Algorithm

Alsheikh,

Munassar

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…This output then becomes an excitatory (positive) or inhibitory (negative) input to other neurons in the network. The process continues until one or more outputs are generated [10].…”

Section: Deep Neural Networkmentioning

confidence: 99%

Fault Data Detection in Software Using a Novel FGRNN Algorithm

Rastogi¹,

Rastogi²,

Darbari³

2019

IJCET

View full text Add to dashboard Cite

The use and dependence on software in various fields has been the reason why researchers for past decades have spent their efforts on finding better methods to predict software quality and reliability. Soft computing methods have been used to bring efficient improvement in prediction of software reliability. This study proposed a novel method called Fuzzy Greedy Recurrent Neural Network (FGRNN) to assess software reliability by detecting the faults in the software. A deep learning model based on the Recurrent Neural Network (RNN) has been used to predict the number of faults in software. The proposed model consists of four modules. The first module, attribute selection pre-processing, selects the relevant attributes and improves generalization that improves the prediction on unknown data. Second module called, Fuzzy conversion using membership function, smoothly collects the linear sub-models, joined together to provide results. Next, Greedy selection deals with the attribute subset selection problem. Finally, RNN technique is used to predict software failure using previously recorded failure data. To attest the performance of the software, the popular NASA Metric Data Program datasets are used. Experimental results show that the proposed FGRNN model has better performance in reliability prediction compared with existing other parameter based and NN based models.

show abstract