Prediction of Software Cost Estimation Using Spiking Neural Networks

2018 ◽  
pp. 101-112 ◽  
Author(s):  
V. Venkataiah ◽  
Ramakanta Mohanty ◽  
M. Nagaratna
Keyword(s):  
Neural Networks ◽  
Cost Estimation ◽  
Spiking Neural Networks ◽  
Software Cost Estimation ◽  
Software Cost

Kernel Fuzzy Clustering with Output Layer Self-Connection Recurrent Neural Networks for Software Cost Estimation

2019 ◽  
Vol 29 (06) ◽  
pp. 2050091
Author(s):  
V. Resmi ◽  
S. Vijayalakshmi
Keyword(s):  
Neural Networks ◽  
Fuzzy Clustering ◽  
Recurrent Neural Networks ◽  
Cost Estimation ◽  
Clustering Algorithm ◽  
Estimation Problem ◽  
Software Cost Estimation ◽  
Software Cost ◽  
Output Layer ◽  
Fuzzy C Means Clustering

In the current world, the software cost estimation problem has been resolved using various newly developed methods. Significantly, the software cost estimation problems can be dealt with effectively with the recently grown recurrent neural network (RNN) than the other newly developed methods. In this paper, an improved approach is proposed to software cost estimation using Output layer self-connection recurrent neural networks (OLSRNN) with kernel fuzzy c-means clustering (KFCM). The proposed OLSRNN method follows the basics of traditional RNN models for integrating self-connections to the output layer; thereby, the output temporal dependencies are better captured. Also, the performance of neural networks is improved using the kernel fuzzy clustering algorithm to enhance software estimation results. Ultimately, five publicly available software cost estimation datasets are adapted to verify the efficacy of the proposed KFCM-OLSRNN method using the validation metrics such as MdMRE, PRED (0.25) and MMRE. The experimental results proved the efficiency of the proposed method for solving the software cost estimation problem.

Sign in / Sign up

Export Citation Format

Share Document