COMPARING THE PERFORMANCE OF PREDICTIVE MODELS CONSTRUCTED USING THE TECHNIQUES OF FEED-FORWORD AND GENERALIZED REGRESSION NEURAL NETWORKS
Journal Title: International Journal of Software Engineering and Computer Systems - Year 2016, Vol 2, Issue 1
Abstract
Artificial Neural Network (ANNs) is an efficient machine learning method that can be used to fits model from data for prediction purposes. It is capable of modelling the class prediction as a nonlinear combination of the inputs. However, a number of factors may affect the accuracy of the model created using this approach. The choice of network type and how the network is optimally configured plays important role in the performance of a predictive model created using neural network techniques. This paper compares the accuracy of two typical neural network techniques used for creating a predictive model. The techniques are feed-forward neural network and the generalized regression networks. The model created using both techniques are evaluated for correctness. The resulting outputs show that, the Generalized Regression Neural Network (GRNN) consistently produces a more accurate result. Findings further show that, the fitting of the network predictive model using the technique of Feed-forward Neural Network (FNN) records error value of 1.086 higher than the generalized regression network.
Authors and Affiliations
Adeleke Raheem Ajiboye, Ruzaini Abdullah-Arshah, Hongwu Qin,, Jamila Abdul-Hadi
Keywords
Related Articles
- EP ID EP254087
- DOI -
- Views 177
- Downloads 0
METAMODELLING APPROACH AND SOFTWARE TOOLS FOR PHYSICAL MODELLING AND SIMULATION
In computer science, metamodelling approach becomes more and more popular for the purpose of software systems development. In this paper, we discuss applicability of the metamodelling approach for development of software...
MANAGING BUILDING CHECKIST PLANS USING BUSCLIS
This paper presents the software namely Building Submission Checklist System (BUSCLIS). It has been developed to manage the submission of building checklist plans process in the construction industry. BUSCLIS helps to si...
A MODIFIED ROUTE DISCOVERY APPROACH FOR DYNAMIC SOURCE ROUTING (DSR) PROTOCOL IN MOBILE AD-HOC NETWORKS
Mobile Ad-hoc networks (MANETs) involved in many applications, whether commercial or military because of their characteristics that do not depend on the infrastructure as well as the freedom movement of their elements, b...
A REVIEW OF SINGLE AND POPULATION-BASED METAHEURISTIC ALGORITHMS SOLVING MULTI DEPOT VEHICLE ROUTING PROBLEM
Multi-Depot Vehicle Routing Problem (MDVRP) arises with rapid development in the logistics and transportation field in recent years. This field, mainly, faces challenges in arranging their fleet efficiently to distribute...
CHALLENGES OF SOFTWARE QUALITY ASSURANCE AND TESTING
Uncertainty exists in Software Company over the world. Software quality problem is leading issue for the software industry. The issue exists from 40 years or 50 years long. The industry is suffering and closing for this...