Role of Soft Computing Techniques in Software Effort Estimation: An Analytical Study

Kumar, P. Suresh; Behera, Himansu Sekhar

doi:10.1007/978-981-13-9042-5_70

Cited by 10 publications

(3 citation statements)

References 96 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SEE plays a crucial role in supporting efficient software development and maintenance for software developers, while also empowering clients to negotiate contracts, plan project completion timelines, and establish release dates for prototypes, among other aspects. Despite the existence of numerous approaches to software effort estimation, the development of accurate and consistent estimation techniques remains challenging for researchers [13], [1].…”

Section: A Software Development Effort Estimation Problemmentioning

confidence: 99%

“…Software engineering encompasses a systematic, methodical, and quantitative approach to the creation, operation, and maintenance of software systems. In order to ensure the effective and timely production of software products, software engineering management adopts specific actions such as planning, monitoring, measuring, and reporting [1], [2]. Conversely, software development effort estimation (SEE) represents a formidable challenge that holds significant importance in the software development process.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Parameter Identification of a Multilayer Perceptron Neural Network using an Optimized Salp Swarm Algorithm

Al-Laham¹,

Abdullah²,

Al-Ma’aitah³

et al. 2023

IJACSA

View full text Add to dashboard Cite

Effort estimation in software development (SEE) is a crucial concern within the software engineering domain, as it directly impacts cost estimation, scheduling, staffing, planning, and resource allocation accuracy. In this scientific article, the authors aim to tackle this issue by integrating machine learning (ML) techniques with metaheuristic algorithms in order to raise prediction accuracy. For this purpose, they employ a multilayer perceptron neural network (MLP) to perform the estimation for SEE. Unfortunately, the MLP network has numerous drawbacks as well, including weight dependency, rapid convergence, and accuracy limits. To address these issues, the SSA Algorithm is employed to optimize the MLP weights and biases. Simultaneously, the SSA algorithm has shortcomings in some aspects of the search mechanisms as well, such as rapid convergence and being susceptible to the local optimal trap. As a result, the genetic algorithm (GA) is utilized to address these shortcomings through fine-tuning its parameters. The main objective is to develop a robust and reliable prediction model that can handle a wide range of SEE problems. The developed techniques are tested on twelve benchmark SEE datasets to evaluate their performance. Furthermore, a comparative analysis with state-ofthe-art methods is conducted to further validate the effectiveness of the developed techniques. The findings demonstrate that the developed techniques surpass all other methods in all benchmark problems, affirming their superiority.

show abstract

Section: A Software Development Effort Estimation Problemmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Parameter Identification of a Multilayer Perceptron Neural Network using an Optimized Salp Swarm Algorithm

Al-Laham¹,

Abdullah²,

Al-Ma’aitah³

et al. 2023

IJACSA

View full text Add to dashboard Cite

show abstract

“…The soft computing approaches nowadays are gaining popularity in building the effort estimation model even if the effort drivers are uncertain and incomplete (Suresh Kumar and Behera, 2020). Depending on the study and its goals, various Machine Learning (ML) methods and implementations are used in different research fields.…”

Section: Introductionmentioning

confidence: 99%

Software Development Effort Estimation Using Relational Database and Optimized Learning Mechanism

Nagarajappa,

Suresh

2023

Journal of Computer Science

View full text Add to dashboard Cite

Accurately estimating the cost of software development is crucial for effective project planning and resource allocation. However, traditional cost estimation methods rely heavily on expert judgment and historical data, which can be time consuming and prone to errors. This study suggests a learning-based cost estimation model that leverages relational databases to improve accuracy. The proposed approach estimates project cost based on the effort required to complete software development, which is a key driver of the project cost. The proposed model is designed to address the challenges posed by the variability in open-source development, including variable team sizes, working hours, and expertise. The study collects and pre-processes data from open-source platforms and selects cost drivers and metrics based on logical rules and SQL queries. Moreover, we propose an optimized Artificial Neural Network (ANN) with augmented topology to automate the selection of neuron units, layers, and adjustment of learnable parameters according to the input variables. The proposed model is evaluated on a 100 open-source software repositories dataset and demonstrates its effectiveness in accurately estimating development cost. The system is implemented using Python and evaluated using performance parameters such as MSE, RMSE, MAE, and MMRE. Results indicate that our proposed model offers a more accurate and efficient approach to software cost estimation, especially for freelancers and outsourcing firms. The proposed model has the potential to save time and resources and improve the reliability and accuracy of software cost estimation.

show abstract

Influence of input values on the prediction model error using artificial neural network based on Taguchi's orthogonal array

Ranković

Ivanović

et al. 2022

Concurrency and Computation

View full text Add to dashboard Cite

Rapid and accurate assessment of software project development using artificial intelligence tools can be essential for success in the software industry. This article has two objectives: to reduce the magnitude relative error (MRE) value in estimating the effort and cost of software development using the proposed artificial neural network architecture based on the Taguchi method and examine the influence of input variables on the change in relative error value. Clustering and fuzzification methods further mitigate the heterogeneous structure of the different project values of the datasets used.Taguchi method contributes to the reduction of the number of iterations by 99%, which achieves a significant reduction in estimation and value of MRE. By monitoring additional criteria, such as prediction, correlation, and comparing two activation functions, such as sigmoid and radial basis function, the proposed model's correctness, reliability, and stability are confirmed. Significantly better results are expected using the sigmoid activation function and a decrease in the value of the mean (MRE).

show abstract

Role of Soft Computing Techniques in Software Effort Estimation: An Analytical Study

Cited by 10 publications

References 96 publications

Parameter Identification of a Multilayer Perceptron Neural Network using an Optimized Salp Swarm Algorithm

Parameter Identification of a Multilayer Perceptron Neural Network using an Optimized Salp Swarm Algorithm

Software Development Effort Estimation Using Relational Database and Optimized Learning Mechanism

Influence of input values on the prediction model error using artificial neural network based on Taguchi's orthogonal array

Contact Info

Product

Resources

About