Dr Muhammad Atif Tahir

SUMMARY OF RESEARCH PROJECTS

1.  Vidi-Video (Improving the Accessibility of Media):This project aims to integrate and develop state of the art components from machine learning, audio event detection, video processing, interaction and visualization into a fully implemented audio-visual search engine combining large number of categories, and exploiting the interclass similarities as well as using the information from different sources: metadata, keyword annotations, audio visual data, speech, and explicit knowledge. One of the key industrial partners in this project is the Netherlands Institute for Sound & Vision which archives 700,000 hours of television, radio, music and film. In this project, we improve the accessibility of media using advanced machine learning and large-scale visual category recognition methods involving very large data sets. 
2. Multi-label Classification and its application in Music and Media: Multi-label classification is a challenging research problem in which each instance may belong to more than one class. Despite some research effort, many scientific challenges posed by e.g. highly imbalanced training sets and correlation among labels remain to be addressed. The aim of this project is to address these issues with applications in music, media, bioinformatics and text categorization.
3. Making Early Prediction of the Accuracy of Machine Learning Applications: The aim of this project is to investigate techniques for making early predictions of the error rate achievable after further interactions e.g. in financial markets, CD-Print and Egg inspection problems. We have shown that how decomposing the error in different components such as bias and variance can lead to useful predictors of achievable accuracy. This approach combines several classification algorithms including Bayesian network, Support Vector Machine etc.
4. Face Recognition in Uncontrolled Environment: The aim is to recognise faces under uncontrolled lighting conditions and blur either due to misfocus and or motion. We are currently investigating advanced image processing and machine learning to solve this proble Dynamically Reconfigurable Quality Control for Manufacturing and Production Processes Using Learning Machine Vision (DynaVis) : The main goal of this project is the development of machine learning methods for machine vision systems in production and manufacturing to achieve dynamically reconfigurable systems. Several machine learning methods are developed during this project and are now successfully used by two industrial partners.
5. Prostate Cancer Classification using Multispectral Images and Tabu Search: The aim of this project is to classify 4 major groups: Stroma, Benign Prostatic Hyperplasia, Prostatic Intraepithelial Neoplasia and Prostatic Carcinoma. Several methods based on Tabu Search are then proposed to solve this problem.An FPGA based coprocessor for the classification of tissue patterns in prostatic cancer:  The aim of this project is to use FPGA to speed up the diagnosis and classification of prostate cancer.
6. QoS Driven Multicast Routing Algorithms: The aim of this project is to develop novel multicast tree methods that simultaneously optimize bandwidth cost, number of Steiner nodes, end-to-end delay and delay variations

Journal Papers :

1. M. A. Tahir, J. Kittler, and A. Bouridane, “Multilabel classification using Heterogeneous Ensemble of Multi-label Classifiers”,  Pattern Recognition Letters (Accepted conditioned on minor revisions)
2. F. Yan, J. Kittler, K. Mikolajczyk and M. A. Tahir, Non-Sparse Multiple Kernel Fisher Discriminant Analysis, Journal of Machine Learning Research (Accepted conditioned on minor revisions) 
3. M. A. Tahir, and J. E. Smith, "Creating Diverse Nearest Neighbour Ensembles using Simultaneous Metaheuristic Feature Selection." Pattern Recognition Letters, 2010
4. E. Lughofer , J. E. Smith, M. A. Tahir, P. Caleb-Solly, C. Eitzinger, D. Sannen and M. Nuttin, “ Human–Machine Interaction Issues in Quality Control Based on On-Line Image Classification”, IEEE Transactions on Systems, Man and Cybernetics, Part A, 2009
5. C. Eitzinger, W. Heidl, E. Lughofer, S. Raiser, J. E. Smith, M. A. Tahir, D. Sannen and H. Van Brussel “Assessment of the Influence of Adaptive Components in Trainable Surface Inspection Systems": Machine Vision and Applications, Special Issue on ’Integrated Imaging and Vision Techniques for Industrial Inspection’, 2009
6. M. A. Tahir, A. Bouridane, and F. Kurugollu, “Simultaneous Feature Selection and Feature Weighting using Hybrid Tabu Search/K-Nearest Neighbour Classifier”, Pattern Recognition Letters, 28, 2007
7. M. A. Tahirand A. Bouridane, “A Novel Round Robin Tabu Search Algorithm for Prostate Cancer Classification and Diagnosis using Multispectral Imagery”, IEEE Transactions on Information Technology in Biomedicine, 10(4), October 2006 
8. M. A. Tahir, A Bouridane and F. Kurugollu, “An FPGA based coprocessor for GLCM Haralick Texture Features and their Application in Prostate Cancer Classification, Anlaog Integrated Circuits and Signal Processing, 43, 205-215, 2005.
9. M. A. Tahir, A. Bouridane, F. Kurugollu, and A. Amira, “A Novel Prostate Cancer Classification Technique using Intermediate Memory Tabu Search”, EURASIPJournal on Applied Signal Processing, Special Issue: Advances in Intelligent Vision Systems: Methods and Applications, 14, 2241-2249 , 2005
10. H. Youssef, A. Almulhem, Sadiq M. Sait, M. A. Tahir, “QoS-Driven Multicast Tree Generation using Tabu Search” , Computer Communications, 25, 1140-1149, July 2002. 

Book Chapters:

1. M. A. Tahir, A. Bouridane and M. A. Roula, “Prostate Cancer Classification using Multispectral Imagery and Meta Heuristics”, Computational Intelligence in Medical Imaging, Taylor & Francis, 2009.
2. M. A. Tahir and J. Smith,  “Feature Selection using Intensified Tabu Search for Supervised Classification”, Local Search Techniques; Focus on Tabu Search, I-Tech Publishing, Vienna, Austria, 2009.
3. M. A. Tahir, and J. Smith, “ Feature Selection for Heterogeneous Ensembles of Nearest Neighbour Classifiersusing Hybrid Tabu Search”, Advances in Metaheuristics for Hard Optimization, Springer Verlag, 2008.

International Conference/Workshop Refereed Papers:

1. M. A. Tahir, C. Chan, J. Kittler and A. Bouridane, “Face Recognition using Multi-Scale Local Phase Quantisation and Linear Regression Classifier”, IEEE International Conference on Image Processing, Brussels, Belgium, 2011
2. M. A. Tahir, ,F. Yan, M. Barnard, M. Awais, K. Mikolajczyk, J. Kittler, “The University of Surrey Visual Concept Detection System at ImageCLEF 2010: Working Notes”, International Conference on Pattern Recognition (ICPR2010), Istanbul, Turkey
3. C. Chan, J. Kittler and M. A. Tahir, “Kernel Fusion of Multiple Histogram Descriptors for Robust Face Recognition”, In Proceedings of Joint IAPR International Workshop on Structural, Syntactic, and Statistical Pattern Recognition, 2010
4. M. A. Tahir , J. Kittler, K. Mikolajczyk, and F. Yan. “Improving Multilabel classification using Ensemble of Multi-label classifiers”, In Proceedings of the 9^th International Workshop on Multiple Classifier Systems, Cairo, Egypt, 2010
5. F . Yan, K. Mikolajczyk, J. Kittler, and M. A. Tahir. “Combining Multiple Kernels by Augmenting the Kernel Matrix”, In Proceedings of the 9^th International Workshop on Multiple Classifier Systems, Cairo, Egypt, 2010
6. F. Yan, K. Mikolajczyk, J. Kittler, and M. A. Tahir, “Non-Sparse Multiple Kernel Learning for Linear Discriminant Analysis ”, In Proceedings of the International Conference on Data Mining (ICDM 09), Florida, USA.
7. M. A. Tahir , J. Kittler, K. Mikolajczyk, F. Yan, K. Sande, and T. Gevers    “Visual Category Recognition Using Spectral Regression and Kernel Discriminant Analysis ”. In Proceedings of the Subspace 2009 in conjunction with 12^th IEEE International Conference on Computer Vision,  Kyoto, Japan, 2009
8. M. A. Tahir , J. Kittler, K. Mikolajczyk, and F. Yan, “Concept learning for Image and Video Retrieval: The inverse random under sampling approach”. In Proceedings of the 17^th European Conference on Signal Processing (EUSIPCO 2009), Glasgow, United Kingdom, 2009. 
9. M. A. Tahir , J. Kittler, F. Yan, and K. Mikolajczyk. “Kernel discriminant analysis using triangular kernel for semantic scene classification”. In Proceedings of the 7^th IEEE International Workshop on Content-Based Multimedia Indexing, Crete, Greece, 2009.
10. 23.     F. Yan, K. Mikolajczyk, J. Kittler, and M. A. Tahir. “A comparison of 1-norm and 2-norm multiple kernel SVMs in image and video classification”. In Proceedings of the 7^th IEEE International Workshop on Content-Based Multimedia Indexing, Crete, Greece, 2009.
11. M. A. Tahir , J. Kittler, K. Mikolajczyk, and F. Yan. “A multiple expert approach to the class imbalance problem using inverse random under sampling”. In Proceedings of the 8^th International Workshop on Multiple Classifier Systems, Reykjavik, Iceland, 2009.
12. E Lughofer, J. E. Smith, M. A. Tahir, P. Caleb-Solly, C. Eitzinge, D. Sannen, H. V. Brussel. “On Human-Machine Interaction during Online Image Classifier Training”, In Proc. of the International Conference on Computational Intelligence for Modelling, Control and Automation (CIMCA), Vienna, 2008
13. M. A. Tahir, J. Smith and C. Praminda, “A Novel Feature Selection based Semi-Supervised method for Image Classification”, Proceedings of the 6^th International Conference on Computer Vision Systems, Greece, 2008. 
14. D. Sannen, M. Nuttin, J. Smith, C. Praminda, M. A. Tahir, E. Christian, and E. Lughofer, “An On-Line Interactive Self-Adaptive Image Classification Framework”, Proceedings of 6^th International Conference on Computer Vision Systems, Greece, 2008. 
15. J. E. Smith and M. A. Tahir, “Stop Wasting Time: On Predicting the Success or Failure of Learning for Industrial Applications”, Proceedings of the 8^th International Conference on Data Engineering and Automated Learning (IDEAL’07), Birmingham, UK, 2007. 
16. M. A. Tahir, and J. Smith, “Improving Nearest Neighbor Classifier using Tabu Search and Ensemble Distance Metrics”, IEEE International Conference on Data Mining (ICDM), Hong Kong, 2006.
17. M. A. Tahir, and A. Bouridane, “An FPGA based coprocessor for cancer classification using nearest neighbour classifier”, Proceedings of the 31^st IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Toulouse, France, 2006.
18. M. A. Tahir, A. Bouridane, F. Kurugollu, and A. Amira, “Accelerating the Computation of GLCM and Haralick Texture Features on Reconfigurable Hardware”, Proceedings of the IEEE International Conference on Image Processing (ICIP), Singapore, Vol. 5, 2857-2860, October 2004.
19. M. A. Tahir, A. Bouridane, F. Kurugollu, and A. Amira, “Feature Selection using Tabu Search for Improving the Classification Rate of Prostate Needle Biopsies”, Proceedings of the 17^th  International Conference on Pattern Recognition (ICPR), Cambridge, UK, Vol. 2, pp. 335-338, August 2004.
20. M. A. Tahir, A. Bouridane, and F. Kurugollu. “Simultaneous Feature Selection and Weighting for Nearest Neighbor Using Tabu Search”, 5^th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL’04) , Lecture Notes in Computer Science, LNCS 3177, pp 390-395, Springer Verlag, August 2004. 
21. M. A. Tahir, A. Bouridane, and F. Kurugollu. “An FPGA based Coprocessor for the Classification of Tissue Patterns in Prostatic Cancer”, 14^th International Conference on Field Programmable Logic and its Applications (FPL) , Lecture Notes in Computer Science, LNCS 3203, pp 771-780, Springer Verlag, August /September 2004.
22. M. A. Tahir, A. Bouridane, F. Kurugollu, and A. Amira, “An FPGA based coprocessor for calculating grey level co-occurrence matrix’’, Proceedings of the 46^th IEEE International Midwest Symposium on Circuits and Systems (MWCAS), Cairo, Egypt, 2003. 
23. M. A. Tahir, M. A. Roula, A. Bouridane, F. Kurugollu, and A. Amira, “An FPGA based co-processor for GLCM texture features measurement”, Proceedings of the 10^th IEEE International Conference on Electronics, Circuits and Systems (ICECS), Sharjah, UAE, vol 3, 1006-1009, 2003.
24. M. A Tahir , Habib Youssef, A. Almulhem, and Sadiq M. Sait, “Fuzzy based MultiObjective Multicast Routing using Tabu Search”, Proceedings of the International Conference on Internet Computing (IC2002), Las Vegas, Nevada, USA, 2002. 
25. H. Youssef, A. Almulhem, S. M. Sait, M. A. Tahir, “QoS-Driven Multicast Tree Generation using Tabu Search”, Proceedings of the 2001 International Symposium on Performance Evaluation of Computer and Telecommunication Systems (SPECTS), Orlando, Florida, USA,  2001.                                                                                                  
26. M. A. Tahir, A. Bouridane, F. Kurugollu, and A. Amira, “Improving Prostate Cancer Diagnosis Using Tabu Search”, IEE Proceedings of the Irish Signals and Systems Conference (ISSC), Belfast, UK, 2004.
27. M. A Tahir, H. Youssef, A. Almulhem, S. M. Sait “Multicast Tree Generation using Tabu Search”, Proceedings of the Sixth Saudi Engineering Conference, KFUPM, Dhahran, Saudi Arabia, 2002.

Currently, I am teaching following two modules

• EN0407: Web Technologies
• EN0365: Ethical Hacking for Network Security