Novel Software Cost Estimation Model Based on the Hybrid of Artificial Neural Network and Firefly Algorithm
By: Wani, Zahid Husain.
Contributor(s): Quadri, S. M. K.
Publisher: New delhi STM Journals 2018Edition: Vol 5 (1),Jan- Apr.Description: 38-45p.Subject(s): Computer EngineeringOnline resources: Click Here In: Journal of artificial intelligence research and advances (JoAIRA)Summary: Software cost estimation is the prediction of software development effort and software development time required to develop a software project. Software cost estimation is a basic and important task for both successful execution of software development life cycle and its management interms of its cost & time. Accurate software cost estimation is considered to be a difficult task as the information about the software project to be developed at the time of its inception and conclusion remains vague, thus prompts the researchers from both academics and industry to explore in the same. In this paper, we present a novel hybrid model of multi-layer artificial neural network and firefly algorithm for the purpose getting accurate estimation of software development costs. Artificial Neural Networks because of their capabilities in self-learning, modeling complex nonlinear relationships, fastness and fault tolerance against noise are considered to be a very powerful in giving solution to prediction problems. In our proposed study, we are using Multilayer Layer Artificial Neural Network as our core architecture for developing the accurate estimates of software development costs and Firefly algorithm as its training algorithm because of its multimodal optimization capability. The proposed model has been evaluated using two basic evaluating criterias namely Magnitude of Relative Error and Median of Magnitude of Relative Error as a measure of performance index to simply weigh the obtained quality of estimation.Item type | Current location | Call number | Status | Date due | Barcode | Item holds |
---|---|---|---|---|---|---|
Articles Abstract Database | School of Engineering & Technology Archieval Section | Not for loan | 2021-2021449 |
Software cost estimation is the prediction of software development effort and software development time required to develop a software project. Software cost estimation is a basic and important task for both successful execution of software development life cycle and its management interms of its cost & time. Accurate software cost estimation is considered to be a difficult task as the information about the software project to be developed at the time of its inception and conclusion remains vague, thus prompts the researchers from both academics and industry to explore in the same. In this paper, we present a novel hybrid model of multi-layer artificial neural network and firefly algorithm for the purpose getting accurate estimation of software development costs. Artificial Neural Networks because of their capabilities in self-learning, modeling complex nonlinear relationships, fastness and fault tolerance against noise are considered to be a very powerful in giving solution to prediction problems. In our proposed study, we are using Multilayer Layer Artificial Neural Network as our core architecture for developing the accurate estimates of software development costs and Firefly algorithm as its training algorithm because of its multimodal optimization capability. The proposed model has been evaluated using two basic evaluating criterias namely Magnitude of Relative Error and Median of Magnitude of Relative Error as a measure of performance index to simply weigh the obtained quality of estimation.
There are no comments for this item.