!!Saso Dzeroski - Publications
\\
__OVERAL NUMBERS OF CITATIONS AND PUBLICATIONS__\\
\\
As of June 19, 2016\\
No. of citations: 12592 (Google Scholar), Most cited computer scientist in Slovenia \\
H-index: 53 (Google Scholar)\\
\\
Professor Džeroski has published 10 books, 40 book chapters, 140 scientific articles in journals (112 in journals with impact factor), and 278 conference papers. The last two  books (edited volumes)  he has published are the research monograph »Inductive Databases and Constraint Based Data Mining« (2010) and the conference proceedings »Discovery Science« (2014).\\
\\
__HIGHLY CITED PUBLICATIONS__ (Citations as of June 19, 2016)\\
\\
N. Lavrač, and S. Džeroski.(1994) Inductive Logic Programming: Techniques and Applications. Ellis Horwood, Chichester. (No. of citations from Google Scholar: 1160)\\
\\
L. de Raedt and S. Džeroski. (1994). First order jk-clausal theories are PAC-learnable. Artificial Intelligence, 70: 375–392. IF(publication year/p.y.)=1.915. (No. of citations from Google Scholar: 197)\\
\\
S. Džeroski, and L. Todorovski. (1995). Discovering dynamics: From inductive logic programming to machine discovery. Journal of Intelligent Information Systems, 4: 89–108. IF(current)= 0.866. (No. of citations from Google Scholar: 116)\\
\\
S. Džeroski, L. de Raedt, and K. Driessens. (2001). Relational reinforcement learning. Machine Learning, 43: 7–52. IF(p.y.)=1.476. (No. of citations from Google Scholar: 401)\\
\\
S. Džeroski and B. Ženko. (2004). Is combining classifiers with stacking better than selecting the best one? Machine Learning, 54: 255-273. IF(p.y.)=3.258. (No. of citations from Google Scholar: 455)\\
\\
RECENT PUBLICATIONS (Citations as of June 19, 2016)\\
\\
C. Vens, J. Struyf, L. Schietgat, S. Džeroski, H. Blockeel. (2008). Decision trees for hierarchical multi-label classification. Machine Learning, 73(2): 185-214. IF(p.y.)=2.326. (No. of citations from Google Scholar: 310)\\
\\
W. Bridewell, P. Langley, L. Todorovski, S. Džeroski. (2008). Inductive process modeling. Machine Learning, 71(1): 1-32. IF(p.y.)=2.326. (No. of citations from Google Scholar: 64)\\
\\
G. Madjarov, D. Kocev, D. Gjorgjevikj, S. Džeroski. (2012). An extensive experimental comparison of methods for multi-label learning. Pattern Recognition, 45(9): 3084-3104. IF(p.y.)=2.292. (No. of citations from Google Scholar: 215)\\
\\
P. Radivojac, ..., S. Džeroski, et al. [[a total of 102 authors]] (2013). A large-scale evaluation of computational protein function prediction. Nature Methods, 10:221-227. IF(p.y.)=25.953. (No. of citations from Google Scholar: 258)\\
\\
D. Kocev, C. Vens, J. Struyf, S. Džeroski. (2013). Tree ensembles for predicting structured outputs. Pattern Recognition, 46(3): 817-833. IF(p.y.)=2.584. (No. of citations from Google Scholar: 56)