Παρακαλώ χρησιμοποιήστε αυτό το αναγνωριστικό για να παραπέμψετε ή να δημιουργήσετε σύνδεσμο προς αυτό το τεκμήριο:
https://hdl.handle.net/20.500.14279/4251
Τίτλος: | On the problem of attribute selection for software cost estimation: Input backward elimination using artificial neural networks | Συγγραφείς: | Papatheocharous, Efi Andreou, Andreas S. |
metadata.dc.contributor.other: | Ανδρέου, Ανδρέας Σ. | Major Field of Science: | Engineering and Technology | Field Category: | Electrical Engineering - Electronic Engineering - Information Engineering | Λέξεις-κλειδιά: | Artificial neural network;Software project;Artificial neural network models;Attribute selection;Backward elimination;Complex software;Connection weights;Cost drivers;Garson's algorithm;Input dimensions;Network weights;Nonlinear interactions;Prediction performance;Saliency measure;Software cost estimations;Software development effort;Software systems;Algorithms;Costs;Estimation;Project management;Software design;Neural networks | Ημερομηνία Έκδοσης: | Οκτ-2010 | Πηγή: | 6th IFIP WG 12.5 International Conference, Larnaca, Cyprus, 6-7 October, 2010. | Conference: | International Conference on Artificial Intelligence Applications and Innovations | Περίληψη: | Many parameters affect the cost evolution of software projects. In the area of software cost estimation and project management the main challenge is to understand and quantify the effect of these parameters, or 'cost drivers', on the effort expended to develop software systems. This paper aims at investigating the effect of cost attributes on software development effort using empirical databases of completed projects and building Artificial Neural Network (ANN) models to predict effort. Prediction performance of various ANN models with different combinations of inputs is assessed in an attempt to reduce the models' input dimensions. The latter is performed by using one of the most popular saliency measures of network weights, namely Garson's Algorithm. The proposed methodology provides an insight on the interpretation of ANN which may be used for capturing nonlinear interactions between variables in complex software engineering environments. | URI: | https://hdl.handle.net/20.500.14279/4251 | ISSN: | 1868-4238 | DOI: | 10.1007/978-3-642-16239-8_38 | Rights: | IFIP International Federation for Information Processing | Type: | Conference Papers | Affiliation: | University of Cyprus Cyprus University of Technology |
Publication Type: | Peer Reviewed |
Εμφανίζεται στις συλλογές: | Δημοσιεύσεις σε συνέδρια /Conference papers or poster or presentation |
CORE Recommender
SCOPUSTM
Citations
4
checked on 8 Νοε 2023
Page view(s)
374
Last Week
1
1
Last month
5
5
checked on 31 Αυγ 2024
Google ScholarTM
Check
Altmetric
Όλα τα τεκμήρια του δικτυακού τόπου προστατεύονται από πνευματικά δικαιώματα