Ensembling Artificial Bee Colony With Analogy-Based Estimation to Improve Software Development Effort Prediction

Shah, Muhammad Arif; Jawawi, Dayang Norhayati Abang; Isa, Mohd Adham; Younas, Muhammad; Abdelmaboud, Abdelzahir; Sholichin, Fauzi

doi:10.1109/access.2020.2980236

Cited by 30 publications

(13 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The outputs of EEABE and other models such as GABE, MICBR, PABE, BABE, and WGre‐ABE are provided in Table 6. GABE represents feature weighting ABE that assigns ideal feature weights via GAs; MICBR denotes CBR with mutual information; PABE denotes a polynomial ABE that using combined PSO and SA; BABE represents a model that ensemble Artificial Bee Colony with ABE; WGre‐ABE denotes a combined method integrating ABE and PSO 14,37,42,50,51 . The outputs reveal that the EEABE model is better than other models except for BABE, both in the MMRE, PRED(0.25) performance measures.…”

Section: Resultsmentioning

confidence: 99%

“…Furthermore, the ensemble with KNN imputation can be considered as an alternative to address the problem of lost data in the ABE process. Arif Shah et al 37 presented an artificial bee colony guided analogy‐based estimation (BABE) model that ensemble artificial bee colony (ABC) with ABE for estimation. ABC can generate multiple weights, which the most precise weight should be used in the similarity function of ABE.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

An evolutionary ensemble analogy‐based software effort estimation

Shahpar

Bardsiri

2021

Softw Pract Exp

View full text Add to dashboard Cite

Analogy-based estimation (ABE) is the most commonly applied method for estimating using software. Although there are several analogy-based estimation techniques, there is no consistent conclusion of which technique is the best in all circumstances. Therefore, this article presents an evolutionary ensemble ABE (EEABE) for software cost estimation. Ensemble effort estimation (EEE) models forecast software development endeavors through using multiple estimation methods. In this article, EEABE combines GA as an evolutionary algorithm with six ABE models. The proposed method has been evaluated on four well-known datasets comprising Maxwell, Albrecht, Kemerer, and Desharnais, by the k-fold cross-validation technique and based on the performance criteria of MRE, MMRE, MDMRE, BMMRE, and PRED(0.25).The simulation results demonstrate that the use of EEABE increases the accuracy of estimation and reduces the cost. Besides, EEABE is a flexible and adaptable model with any type of dataset and software development project, and it has been optimized with the possibility of using various ABE techniques.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

An evolutionary ensemble analogy‐based software effort estimation

Shahpar

Bardsiri

2021

Softw Pract Exp

View full text Add to dashboard Cite

show abstract

“…Authors in Ref. 17 have created ensemble of Analogy and Artificial Bee colony for software development effort estimation. Ensemble are evaluated in Ref.…”

Section: Related Workmentioning

confidence: 99%

An efficient ANFIS-EEBAT approach to estimate effort of Scrum projects

Arora

Verma

Kavita

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Software effort estimation is a significant part of software development and project management. The accuracy of effort estimation and scheduling results determines whether a project succeeds or fails. Many studies have focused on improving the accuracy of predicted results, yet accurate estimation of effort has proven to be a challenging task for researchers and practitioners, particularly when it comes to projects that use agile approaches. This work investigates the application of the adaptive neuro-fuzzy inference system (ANFIS) along with the novel Energy-Efficient BAT (EEBAT) technique for effort prediction in the Scrum environment. The proposed ANFIS-EEBAT approach is evaluated using real agile datasets. It provides the best results in all the evaluation criteria used. The proposed approach is also statistically validated using nonparametric tests, and it is found that ANFIS-EEBAT worked best as compared to various state-of-the-art meta-heuristic and machine learning (ML) algorithms such as fireworks, ant lion optimizer (ALO), bat, particle swarm optimization (PSO), and genetic algorithm (GA).

show abstract

“…The suggested approach operates in a two-stage setting that includes testing and training. However, missing data imputation techniques should be combined with the model used in this work to improve further [15].…”

mentioning

confidence: 99%

The Proposed Critical Factors to Improve the Performance of Scrum Teams

Alzubaidi¹,

Salama²,

Qureshi³

2022

IJCSMC

View full text Add to dashboard Cite

Scrum is one of the most popular and widely practiced agile software development methodologies. Scrum team consists of a Scrum Master, Product Owner, and developers. While using Scrum, several factors have been reported in the existing studies to improve or lower the performance of a Scrum team such as managing the priority of the product backlog items, role of an efficient product owner, cost and time to perform integration tests, accurate estimation of story points and code quality. This paper aims to determine critical factors those impact the most over the performance of the Scrum teams using a survey and systematic literature review. Furtherly, a model is proposed presenting the impact of critical factors to enhance the performance of Scrum teams to increase efficiency and work perfection, organizing and managing product backlogs, clarity in goals, execution of sprints in an estimated duration and increase productivity of product owner. The identified critical factors are validated using a survey and the results are found encouraging.

show abstract

Ensembling Artificial Bee Colony With Analogy-Based Estimation to Improve Software Development Effort Prediction

Cited by 30 publications

References 61 publications

An evolutionary ensemble analogy‐based software effort estimation

An evolutionary ensemble analogy‐based software effort estimation

An efficient ANFIS-EEBAT approach to estimate effort of Scrum projects

The Proposed Critical Factors to Improve the Performance of Scrum Teams

Contact Info

Product

Resources

About