[Magyar változat]

Krisztian Buza, assistant professor

Department of Computer Science and Information Theory
Faculty of Electrical Engineering and Informatics
Budapest University of Technology and Economics

E-Mail: buza (at) cs (dot) bme (dot) hu
Telephone: + 36 20 912 7426

Secretary telephone: + 36 1 463 2585

Office: I. E. 217. 3., 1117 Budapest, Magyar tudósok körútja 2., Hungary

Book Book Chapter Textbook [in Hungarian]
K. Buza (2011): Fusion Methods for Time Series Classification, Peter Lang Verlag, ISBN: 978-3631630853
You can purchase it at amazon.de or download from the University of Hildesheim.
S. Blohm, K. Buza, P. Cimiano, L. Schmidt-Thieme (2011): Relation Extraction for the Semantic Web with Taxonomic Sequential Patterns, in V. Sugumaran and J.A. Gulla: Applied Semantic Web Technologies, CRC Press, Taylor&Francis Group.
You can purchase it at amazon.com.
Ferenc Bodon, Krisztian Buza (2013):
Adatbányászat [Data Mining]
Electronic textbook
Selected publications

See also: Hungarian National Publication Database (MTMT)

Krisztian Buza, Gabor Nagy, Alexandros Nanopoulos (2014):
Storage-Optimizing Clustering Algorithms for High-Dimensional Tick Data [paper]
Expert Systems with Applications, Vol. 41, pp. 4148-4157.

Nenad Tomasev, Krisztian Buza, Kristóf Marussy, Piroska B. Kis (to appear): Hubness-aware Classification, Instance Selection and Feature Construction: Survey and Extensions to Time-Series [paper]
In: U. Stanczyk, L. Jain (eds.), Feature selection for data and pattern recognition (tentative title), Springer-Verlag

Krisztian Buza, Gabor I. Nagy, Alexandros Nanopoulos (2014):
Trend analysis and anomaly detection in time series of language usage [poster]
VI. Dubrovnik Conference on Cognitive Science (DUCOG)

Krisztian Buza, Gabor I. Nagy, Alexandros Nanopoulos (2014):
Three Open Questions related to the Tick Data Decomposition Problem [abstract]
Summit240 Conference, abstract

Kristóf Marussy, Krisztian Buza (2013):
SUCCESS: A New Approach for Semi-Supervised Classification of Time-Series [paper]
ICAISC, LNCS Vol. 7894, pages 437-447, Springer.
The original publication is available at www.springerlink.com.

Krisztian Buza, Julia Koller (2013):
Speeding up the classification of biomedical signals via instance selection [abstract] [poster]
5th Dubrovnik Conference on Cognitive Science, Learning & Perception, Volume 5, Supplement 1

Krisztian Buza, Ilona Galambos (2013): [paper]
An Application of Link Prediction in Bipartite Graphs: Personalized Blog Feedback Prediction, 8th Japanese-Hungarian Symposium on Discrete Mathematics and Its Applications

Gabor I. Nagy, Krisztian Buza (2012):
Efficient Storage of Tick Data That Supports Search and Analysis, [paper] [presentation slides]
12th Industrial Conference on Data Mining, Berlin, LNCS Vol. 7377, pages 38-51, Springer.
Nominated for the Best Paper Award
The original publication is available at www.springerlink.com.

K. Buza, A. Nanopoulos, T. Horváth, L. Schmidt-Thieme (2012):
GRAMOFON: General Model-selection Framework based on Networks, [paper at Elsevier]
Neurocomputing, Volume 75, Issue 1, pages 163-170, Elsevier

Gabor I. Nagy, Krisztian Buza (2012):
Clustering Algorithms for Storage of Tick Data, [abstract]
The 36th Annual Conference of the German Classification Society on Data Analysis, Machine Learning and Knowledge Discovery August 1-3, 2012, Hildesheim, Germany

Krisztian Buza (2012):
Feedback Predicition for Blogs, [abstract] [Data used for the experiments in the paper] [presentation slides] [paper]
The 36th Annual Conference of the German Classification Society on Data Analysis, Machine Learning and Knowledge Discovery August 1-3, 2012, Hildesheim, Germany

Gabor I. Nagy, Krisztian Buza (2012):
Partitional Clustering of Tick Data to Reduce Storage Space.
IEEE 16th International Conference on Intelligent Engineering Systems

K. Buza, A. Buza, P.B. Kis (2011):
A Distributed Genetic Algorithm for Graph-Based Clustering, [paper] [presentation slides]
Man-Machine Interactions 2, Advances in Intelligent and Soft Computing, Volume 103/2011, pages 323-331, Springer
The original publication is available at www.springerlink.com.

T. Horváth, A. Eckhardt, K. Buza, P. Vojtás, L. Schmidt-Thieme (2011):
Value-transformation for Monotone Prediction by Approximating Fuzzy Membership Functions, [paper] [poster]
12th IEEE International Symposium on Computational Intelligence and Informatics

K. Buza, A. Nanopoulos, L. Schmidt-Thieme (2011):
INSIGHT: Efficient and Effective Instance Selection for Time-Series Classification, [paper]
Proceedings of the 15th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), LNCS Vol. 6635, pages 149-160, Springer. The original publication is available at www.springerlink.com.

K. Buza, A. Nanopoulos, L. Schmidt-Thieme (2010):
Time-Series Classification based on Individualised Error Prediction, [paper]
13th IEEE International Conference on Computational Science and Engineering (CSE-2010). Best Paper Award

You can find most of my older publications on my old web page.

Biography
Krisztian Buza (born 1984) obtained his Diploma in Computer Science (Informatics Engineer) in 2007 from the Faculty of Electrical Engineering and Informatics of the Budapest University of Technology and Economics. Between 2007 and 2011 he was a research assistant and PhD student at the University of Hildesheim, where he obtained his PhD in 2011. Since 2011 he gives the Data Mining Algorithms course at the Budapest University of Technology and Economics. In the last five years, he co-authored more than 20 publications and participated in several research projects in cooperation with industrial partners such as Rolls Royce, Morgan Stanley and Capgemini. His work on time series classification was honored by the Best Paper Award of IEEE's renowned conference on Computational Science and Engineering (2010) and his joint work with Gabor Nagy was nominated for the Best Paper Award of the 12th Industrial Conference on Data Mining (Berlin, 2012). His main research interests are data mining and machine learning with special focus on hybrid models, time-series classification and their applications.

If you are interested in more details, you can read my CV.
Teaching
  • Data Mining Algoritms Lecture
  • Data Mining Techniques
  • Data Mining Laboratory (BSc) slides [in Hungarian]
  • Applied functional and logic programming [Logic programming part, in Hungarian]
  • Project Topics for Students (MSc and BSc thesis, etc.) [in Hungarian]