A
Asifullah Khan
Researcher at Pakistan Institute of Engineering and Applied Sciences
Publications - 232
Citations - 7325
Asifullah Khan is an academic researcher from Pakistan Institute of Engineering and Applied Sciences. The author has contributed to research in topics: Digital watermarking & Computer science. The author has an hindex of 38, co-authored 192 publications receiving 5109 citations. Previous affiliations of Asifullah Khan include Gwangju Institute of Science and Technology & Ghulam Ishaq Khan Institute of Engineering Sciences and Technology.
Papers
More filters
Journal Article
Image Authenticity and Perceptual Optimization via Genetic Algorithm and a Dependence Neighborhood
TL;DR: Experimental results show that such intelligent selection results in improvement of imperceptibility of the watermarked image, and implicit watermarking of all the coefficients improves security against attacks such as cover-up, vector quantization and transplantation.
Proceedings ArticleDOI
Improving performance of nearest neighborhood classifier using genetic programming
TL;DR: Genetic Programming is used to improve the performance of nearest neighbor classifier by replacing predefined k nearest neighbors with the number of men and women in the first two quartiles in Euclidean space for voting.
Posted Content
Deep Belief Networks Based Feature Generation and Regression for Predicting Wind Power.
TL;DR: It is experimentally shown that the deep learning and unsupervised pre-training capabilities of DBN based model has comparable and in some cases better results than hybrid and complex learning techniques proposed for wind power prediction.
Proceedings ArticleDOI
Ensemble Based Efficient Churn Prediction Model for Telecom
Adnan Idris,Asifullah Khan +1 more
TL;DR: This study proposes a churn prediction approach that exploits the discriminative feature selection capabilities of minimum redundancy and maximum relevance in the first step, leading to enhanced feature-label association and reduced feature set in this study.
Proceedings ArticleDOI
Intelligent combination of kernels information for improved classification
TL;DR: GP is used to develop an optimal composite classifier (OCC) having better performance than individual SVM classifiers, and the experimental results demonstrate that OCC is more effective, generalized and robust.