An Adaptive Neural Network for the Cost Estimation of E-Learning Projects in the United Kingdom

An Adaptive Neural Network for the Cost Estimation of E-Learning Projects in the United Kingdom

Raul Valverde (Consejo Nacional de Acreditación en Informática y. Computación, A.C., Mexico City, Mexico)
Copyright: © 2017 |Pages: 18
DOI: 10.4018/IJDSST.2017070104
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

This research aims to address the problems of estimating e-Learning development costs particularly within the United Kingdom. Hundreds of managers with no prior experience of managing e-Learning development often find themselves needing to produce cost estimations for e-Learning development. The lack of prior experience in e-Learning development means that these managers will not be able to apply structured expert judgement to their cost estimations and the risk of inaccurate estimations will be high, with all the subsequent problems this will bring with it. Although an e-learning project cost model that serves this purpose has been developed in the past by the author, the previous e-learning model was based on multi regression analysis that has the great limitation of losing its relevancy as the industry changes, the new proposed model uses an adaptive neural network model that copes with changes as it can be trained easily with new data and this allows the management to keep more accurate cost estimates that reflect market changes.
Article Preview

2. Neural Networks

Winston (2010), gives a simple layman, yet effective and elegant definition describing that Artificial Intelligence, machine learning (Simon, 2013) and cognitive science (Miller, 2003) paradigms encompassing Artificial Neural Networks (ANN) could loosely be defined as “representations that support the making of models, that facilitate understanding targeted at thinking, perception and action.” Similarly, ANN first envisioned and conceptualized by McCulloch and Pitts (1943), could be described as a set of mathematical rules, able to respectively mimic both complex and rudimentary neural structures found in biological organisms, modelled as representations of synapses fired during thought and reflex processes.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 10: 4 Issues (2018): 1 Released, 3 Forthcoming
Volume 9: 4 Issues (2017)
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing