Pravin Chandra

A non-sigmoidal activation function for feedforward artificial neural networks

2015

For a single hidden layer feedforward artificial neural network to possess the universal approximation property, it is sufficient that the hidden layer nodes activation functions are continuous non-polynomial function. It is not required that the …

A new weight initialization method for sigmoidal FFANN

2018 · Journal of Intelligent & Fuzzy Systems

Weight initialization is the most important component which affects the performance of artificial neural network during training the network using Back-propagation algorithm. The initial starting weights have significant effect on the training. If the weights …

A Comparative Study of Clustering Algorithms

2019 · International Conference on Computing for Sustainable Global Development

In present era, data analysis plays vital role in various domains. Data clustering is a data analysis technique used for grouping of data objects based on unsupervised learning. Many clustering algorithms have been proposed in …

Linear regression with factor analysis in fault prediction of software

2020 · Journal of Interdisciplinary Mathematics

In software fault prediction, before beginning with the real software testing process, faultprone software modules are identified with the help of various properties related to the software project. This leads to the achievement of minimal …