I am a research associate at the Institute for Mathematical Sciences, Imperial College, London. My research centres on a wide range of theoretical and practical issues in pattern recognition and machine learning.

 Professional Career

I studied physics at the Wroclaw University of Technology, Poland and computer science at the National University of Ireland, Galway and received Master degree in 2001 with the thesis "Automatic recognition of arrhythmia from ECG signal". I have received PhD in 2006 from the Information and Communication Theory Group at Delft University of Technology, under the supervision of prof. R.P.W. Duin. The title of my PhD thesis is "Learning to recognise. Study on one-class classification and active learning". Since 2006 I am a research associate at the Institute for Mathematical Science at Imperial College London. My main research interest involves theoretical and practical aspects of machine learning especially one-class classification, domain-based classification and enhancement of classification models by unlabelled data.

 Other activities

Publications

all publications can be downloaded from PAPERS

Books:

P. Juszczak, Learning to recognise. A study on one-class classiifcation and active learning, PhD thesis, Delft University of Technology, ISBN: 978-90-9020684-4, 2006

Journal publications:

P. Juszczak, D.M.J. Tax, E. Pekalska and R.P.W. Duin, Minimum volume enclosing ellipsoid data description , submitted

P. Juszczak, D.M.J. Tax, E. Pekalska and R.P.W. Duin, Minimum spanning tree data description, 2007. 

P. Juszczak, N.M. Adams, D.J. Hand, C. Whitrow,  D.J. Weston, Off-the-peg or bespoke classifiers for fraud detection?, 2007.

L. van Bommel, S.E. van Wieren, P. Funston, P. Juszczak and P. Riordan, Who is who? Identifing lions individually by their footprints, Oecologia, 2007.

D.J. Hand, C. Whitrow, N.M. Adams, P. Juszczak and D. Weston, Performance criteria for plastic card fraud detection tools, Journal of the Operational Research Society, 2007.

D.M.J. Tax and P. Juszczak, Kernel whitening for one-class classification, International Journal of Pattern Recognition and Artificial Intelligence Vol. 17, No. 3 (2003) 333-347.

Conference papers:

P. Juszczak and N. Adams, Behavioural finance as a multi-instance learning problem, The 14th International Conference on Neural Information Processing (ICONIP), 2007.

P. Juszczak, Query diversification in active learning, The 14th International Conference on Neural Information Processing (ICONIP), 2007.

P. Juszczak, Volume-based model selection for one-class classifiers that consist of a set of spheres, The 14th International Conference on Neural Information Processing (ICONIP), 2007.

 P. Juszczak, D.M.J. Tax, S. Verzakov and R.P.W. Duin, Domain based LDA and QDA, in: Y.Y. Tang, S.P. Wang, G. Lorette, D.S. Yeung, H. Yan (eds.), Proceedings of the 18th Intternational Conference on Pattern Recognition, vol. 2, IEEE Computer Society Press, Los Alamitos, 2006, 788-791.

 D.M.J. Tax, P. Juszczak, E. Pekalska and R.P.W. Duin, Outlier detection using ball descriptions with adjustable metric, in: D.Y. Yeung, J.T. Kwok, A. Fred, F. Roli and D. de Ridder (eds.), Structural, Syntactic, and Statistical Pattern Recognition, Proceedings of SSSPR2006, Lecture Notes in Computer Science, vol. 4109, Springer Verlag, Berlin, 2006, 587-595.

 P. Juszczak and R.P.W. Duin, Learning from a test set, Proceedings 4th International Conference on Computer Recognition Systems, Lecture Notes in Computer Science, Springer Verlag, 203-210, 2005.

 P. Juszczak and R.P.W. Duin, Selective sampling based on the variation in label assignments, in: J. Kittler, M. Petrou, M. Nixon (eds.), Proceedings 17th International Conference on Pattern Recognition, vol. 2, IEEE Computer Society, Los Alamitos, CA, 2004, 375-378.

 P. Juszczak and R.P.W. Duin, Combining one-class classifiers to classify missing data, in: F. Roli, J. Kittler, T, Windeatt (eds.), Multiple Classifier Systems, Proceedings Fifth International Workshop MCS 2004, Lecture Notes in Computer Science, vol. 3077, Springer Verlag, Berlin, 2004, 92-101.

 P. Juszczak and R.P.W. Duin, Uncertainty sampling for one-class classifiers, in: N. Chawla, N. Japkowicz, A. Kolcz (eds.), Proc. of the ICML-2003 Workshop: "Learning with Imbalanced Data Sets II", ICML2003 , Washington D.C., 200 3, 81-88.

 P. Juszczak and R.P.W. Duin,  Selective Sampling Methods in One-Class Classification Problems, i n: O. Kaynak, E. Alpaydin, E. Oja, L. Xu (eds.), Artificial Neural Networks and Neural Information Processing (Proc. Joint Int. Conf. ICANN/ICONIP 2003, Lecture Notes in Computer Science, vol. 2714, Springer Verlag, Berlin, 2003, 140-148.

 D.M.J. Tax and P. Juszczak, Kernel Whitening for One-Class Classification, in: S.-W. Lee, A. Verri (eds.), Pattern Recognition with Support Vector Machines, Proc. of SVM2002, Lecture Notes in Computer Science, vol. 2388, Springer Verlag, Berlin, 2002, 40-52.

 P. Juszczak and R.P.W. Duin, Combining one-class classifiers to handle missing data, in: J.J. van Wijk, J.W.J. Heijnsdijk, K.G. Langendoen, R. Veltkamp (eds.), Proc. ASCI 2004, 10th Annual Conf. of the Advanced S chool for Computing and Imaging, ASCI, Delft, 2004, 75-82.

 P. Juszczak and R.P.W. Duin, How to ask an expert for new samples in the one- class classification problem?, in: S. Vassiliades, L.M.J. Florack, J.W.J. Heijnsdijk, A. van der Steen (eds.), Proc. ASCI 2003, 9th Annual Conf. of the Advanced School for Computing and Imaging, ASCI, Delft, 2003, 225-231.

 P. Juszczak, D.M.J. Tax, and R.P.W. Duin, Feature scaling in support vector data description, in: E.F. Deprettere, A. Belloum, J.W.J. Heijnsdijk, F. van der Stappen (eds.), Proc. ASCI 2002, 8th Annual Conf. of the Advanced School for Computing and Imaging, ASCI, Delft, 2002, 95-102.  

Reports:   

R.P.W. Duin, P. Juszczak, D. de Ridder, P. Paclik, E. Pekalska, and D.M.J. Tax, PRTools, a Matlab toolbox for pattern recognition, http://prtools.org, 2004.

Software:   

PRTOOLS.

DD_TOOLS.