TsFSIM: a three-step fast selection algorithm for influence maximisation in social network

Qiu, Liqing; Sai, Shiqi; Tian, Xiangbo

doi:10.1080/09540091.2021.1904206

Cited by 7 publications

(1 citation statement)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Estimates of effort below real values often lead to project cancellations or failures due to spent budgets. Additionally, this is a problem for both software companies that have already invested resources in projects and for clients who will not get the desired products or have to invest more (Goyal & Parashar, 2018;Jiang et al, 2021;Jiao et al, 2021;Qiu et al, 2021;Subasri et al, 2020). On the other hand, the estimated effort is higher than realistic conduct to uncompetitive project design bids, so software teams often fail to get and start a project.…”

Section: Introductionmentioning

confidence: 99%

COSMIC FP method in software development estimation using artificial neural networks based on orthogonal arrays

Ranković

Ivanović

et al. 2021

Connection Science

View full text Add to dashboard Cite

This paper proposes a new, improved COmmon Software Measurement International Consortium function point (COSMIC FP) method that uses Artificial Neural Network (ANN) architectures based on Taguchi's Orthogonal Array to estimate software development effort. The minimum magnitude relative error (MRE) to evaluate these architectures considering the cost effect function, the type of data used in the training, testing, and validation of the proposed models, was used. Applying the fuzzification and clustering method to obtain seven different datasets, we would like to achieve excellent reliability and accuracy of the obtained results. Besides examining the influence of four input values, we aim to reduce the risks of potential errors, increase the coverage of a wide range of different projects and increase the efficiency and success of completing many various software projects. The main contributions of our work are as follows: the influence of four input values of the COSMIC FP method on the change of mean (MRE), development of two simple ANN architectures, the attainment of a small number of performed iterations in software effort estimation (less than 7), reduced software effort estimation time, the use of different values of the International Software Benchmarking Standards Group and other datasets used in the experiment.

show abstract