S
Sundaram Suresh
Researcher at Nanyang Technological University
Publications - 218
Citations - 6190
Sundaram Suresh is an academic researcher from Nanyang Technological University. The author has contributed to research in topics: Artificial neural network & Radial basis function network. The author has an hindex of 37, co-authored 216 publications receiving 5583 citations. Previous affiliations of Sundaram Suresh include National Institute of Technology, Tiruchirappalli & Indian Institutes of Technology.
Papers
More filters
Journal ArticleDOI
Reversible Watermarking Algorithm Using Sorting and Prediction
TL;DR: This paper presents a reversible or lossless watermarking algorithm for images without using a location map in most cases that employs prediction errors to embed data into an image.
Journal ArticleDOI
Self regulating particle swarm optimization algorithm
TL;DR: A statistical analysis on performance evaluation of the different algorithms on CEC2005 problems indicates that SRPSO is better than other algorithms with a 95% confidence level.
Journal ArticleDOI
No-reference image quality assessment using modified extreme learning machine classifier
TL;DR: The experimental results prove that the estimated visual quality of the proposed RCGA-ELM emulates the mean opinion score very well and indicate that the proposed schemes significantly improve the performance of ELM classifier under imbalance condition for image quality assessment.
Journal ArticleDOI
Performance enhancement of extreme learning machine for multi-category sparse data classification problems
TL;DR: A new, real-coded genetic algorithm approach called 'RCGA-ELM' to select the optimal number of hidden neurons, input weights and bias values which results in better performance and two new genetic operators called 'network based operator' and 'weight based operator" are proposed to find a compact network with higher generalization performance.
Journal ArticleDOI
Risk-sensitive loss functions for sparse multi-category classification problems
TL;DR: The proposed risk-sensitive loss functions minimize both the approximation and estimation error and indicate the superior performance of the neural classifier using the proposed loss functions both in terms of the overall and per class classification accuracy.