Note: This page will be discontinued. Please visit my new webpage HERE and update your bookmarks.

Machine Learning Research

Currently, we are working on multiple instance learning and feature selection.

We have developed pyLemmings: A software suite for Multiple Instance Learning and investigated Self-taught learning of the protein universe.

Below are some of our projects.

Biometrics

Fingerprint Identification

As part of my BS (Computer & Information Sciences) thesis, I developed a minutiae based fingerprint identification and classification system. We have developed our own fingerprints database.

• Fayyaz A. Afsar, Automatic Fingerprint Identification and Verification, BS (Computer and Information Sciences) thesis, Pakistan Institute of Engineering and Applied Sciences, Islamabad, Pakistan, 2005. (Download)
• Fingerprint Identification and Verification using Minutiae Matching, Fayyaz A. Afsar, M. Arif and M. Hussain, in proc. National Conference on Emerging Technologies, Karachi, Pakistan, 2004. (Download)
• Fingerprint Based Person Identification and Verification for Commercial Applications, Fayyaz A. Afsar, M. Arif, M. Hussain, in proc. IEEE International Multitopic Conference (INMIC) 2004, Lahore, Pakistan, 2004. (Online)

Speaker Recognition

I supervised an undergraduate student project aimed at telephonic, cellular phone and non-telephonic speaker recognition. We developed a speaker database for this purpose containing more than 60 speakers.

• Wavelet Transform Based Automatic Speaker Recognition, S. Malik and Fayyaz A. Afsar, in proc. International Multitopic Conference (INMIC), Islamabad, Pakistan, December 2010. (Online)
• Thesis by S. Malik: Download here.

Signature Recognition

I supervised an undergraduate student project aimed at person identification using online signatures. For this purpose, we developed a database of online signatures and their skilled forgeries for more 100 individuals.

• Thesis by M. Nauman Sajid: Download here.
• Wavelet Transform Based Global Features for Online Signature Recognition, Fayyaz A. Afsar, U. Farrukh and M. Arif, in proc. IEEE International Multitopic Conference (INMIC) 2005, Karachi, Pakistan, 2005 (Online).

Palm and Hand based Identification

As a student project I supervised, we developed a hand and palm based person identification system. We developed our own database of hand images for this purpose.

• Person Identification based on Palm & Hand Geometry, Qaiser N. Ashraf and Fayyaz A. Afsar, presented at Doctoral Symposium on Computer Science, Lahore, Pakistan, August 9-10, 2008. (Download)
• Thesis by Qaiser N. Ashraf: Download here.

Evolutionary algorithms

MOX

MOX is a novel computational intelligence approach to numerical optimization for finding the global optima of a multidimensional function based upon biological inspirations drawn from the highly selective behavior of female mosquitoes in choosing a habitat to lay their eggs and the inhibition of those eggs to hatch into the next stage. Comparison of convergence results of MOX for different benchmarks with existing methods in the literature clearly indicates the efficacy of the proposed scheme in maintaining a high success rate while reducing the number of function evaluations (NFE) required to reach a goal value for an optimization problem.

• MOX: A Novel Global Optimization Algorithm Inspired from Oviposition Site Selection and Egg Hatching Inhibition in Mosquitoes, Fayyaz A. Afsar and M. Arif in Journal of Applied Soft Computing, vol. 11, no. 8, pp. 4614-4625, 2011 (Paper), (Download draft), (Matlab Code)

GA based Robotic path planning

We developed a novel genetic algorithm based robotic path planning algorithm based on morphological processing.

• Genetic Algorithm Based Path Planning and Optimization for Autonomous Mobile Robots with Morphological Preprocessing, Fayyaz A. Afsar, M. Arif, and M. Hussain, in proc. IEEE International Multitopic Conference (INMIC) 2006, Karachi, Pakistan, 2006. (Online)