Home

Publications - Jana Novovičová


Books and chapters (6)
1. Petr Somol, Jana Novovičová, Pavel Pudil: Moderní metody výběru příznaků ve statistickém rozpoznávání. Umělá inteligence 6, 424-468. Academia, Praha 2013.   Download
2. Petr Somol, Jana Novovičová, Pavel Pudil: Efficient Feature Subset Selection and Subset Size Optimization. Pattern Recognition, Recent Advances, 75-98. In-Teh, Vukovar, Croatia 2010.   Download
3. * Pavel Pudil, Jana Novovičová, Petr Somol: Recent feature selection methods in statistical pattern recognition. Pattern Recognition and String Matching, 1-51. Kluwer, Dordrecht 2003.
4. * Jana Novovičová: Pravděpodobnost a matematická statistika. ČVUT, Praha 1999.
5. * Pavel Pudil, Jana Novovičová: Novel methods for feature subset selection with respect to problem knowledge. Feature Extraction, Construction and Selection: A Data Mining Perspective, 101-116. Kluwer Academic, Boston 1998.
6. * Jana Novovičová, Pavel Pudil: Feature selection and classification by modified model with latent structure. Dealing with Complexity. A Neural Networks Approach, 126-138. Springer, London 1997.

Journal articles (31)
1. Petr Somol, Jiří Grim, Jana Novovičová, P. Pudil: Improving feature selection process resistance to failures caused by curse-of-dimensionality effects. Kybernetika 47:3 (2011), 401-425. Ústav teorie informace a automatizace AV ČR, v. v. i..   Download
2. Petr Somol, Jana Novovičová: Evaluating Stability and Comparing Output of Feature Selectors that Optimize Feature Subset Cardinality. IEEE Transactions on Pattern Analysis and Machine Intelligence 32:11 (2010), 1921-1939. IEEE Computer Society.   Download
3. * Petr Somol, Jana Novovičová: Evaluating the Stability of Feature Selectors that Optimize Feature Subset Cardinality. Lecture Notes in Computer Science 5342 (2008), 956-966.   Download
4. * Petr Somol, Jana Novovičová, Pavel Pudil: Notes on the evolution of feature selection methodology. Kybernetika 43:5 (2007), 713-730. Ústav teorie informace a automatizace AV ČR, v. v. i..
5. * Jana Novovičová, Petr Somol, Michal Haindl, Pavel Pudil: Conditional Mutual Information Based Feature Selection for Classification Task. Lecture Notes in Computer Science 45:4756 (2007), 417-426.
6. * P. Paclík, Jana Novovičová, R.P.W. Duin: Building Road-Sign Classifiers Using a Trainable Similarity Measure. IEEE Transactions on Intelligent Transportation Systems 7:3 (2006), 309-321.   Download
7. * Jana Novovičová, Petr Somol, Pavel Pudil: Oscillating feature subset search algorithm for text categorization. Lecture Notes in Computer Science 44:4225 (2006), 578-587.
8. * Petr Somol, Jana Novovičová, Pavel Pudil: Flexible-hybrid sequential floating search in statistical feature selection. Lecture Notes in Computer Science 44:4109 (2006), 623-639.   Download
9. * Jana Novovičová: Text document classification. ERCIM News, 53-54. European Research Consortium for Informatics and Mathematics.
10. * M. Svítek, Jana Novovičová: Performance parameters definition and processing. Neural Network World 15:6 (2005), 1-11. Ústav informatiky AV ČR, v. v. i..
11. * Jana Novovičová, Antonín Malík: Text document classification based on mixture models. Kybernetika 40:3 (2004), 293-304. Ústav teorie informace a automatizace AV ČR, v. v. i..
12. * Miroslav Kárný, Ivan Nagy, Jana Novovičová: Mixed-data multi-modelling for fault detection and isolation. International Journal of Adaptive Control and Signal Processing 16:1 (2002), 61-83. Wiley.   Download
13. * Pavel Pudil, Jana Novovičová, Petr Somol: Feature selection toolbox software package. Pattern Recognition Letters 23:4 (2002), 487-492. Elsevier.
14. * Pavel Pudil, Jana Novovičová, Petr Somol: Znalostní přístup k výběru nejinformativnějších proměnných pro rozhodovací problémy klasifikačního typu. Acta Oeconomica Pragensia 8:2 (2000), 11-24.
15. * Pavel Paclík, Jana Novovičová, Pavel Pudil, Petr Somol: Road sing classification using Laplace kernel classifier. Pattern Recognition Letters 21, 1165-1173. Elsevier.
16. * Petr Somol, Pavel Pudil, Jana Novovičová, Pavel Paclík: Adaptive floating search methods in feature selection. Pattern Recognition Letters 20, 1157-1163. Elsevier.   Download
17. * Pavel Pudil, Jana Novovičová, Petr Somol, Radislav Vrňata: Conceptual base of feature selection consulting system. Kybernetika 34:4 (1998), 451-460. Ústav teorie informace a automatizace AV ČR, v. v. i..
18. * Pavel Pudil, Jana Novovičová: Novel methods for subset selection with respect to problem knowledge. IEEE Intelligent Systems 13:2 (1998), 66-74.
19. * Jana Novovičová, Pavel Pudil, J. Kittler: Divergence based feature selection for multimodal class densities. IEEE Transactions on Pattern Analysis and Machine Intelligence 18:1 (1996), 218-223. IEEE Computer Society.
20. * Pavel Pudil, Jana Novovičová, N. Choakjarernwanit, J. Kittler: Feature selection based on the approximation of class densities by finite mixtures of special type. Pattern Recognition 28:9 (1995), 1389-1398. Elsevier.
21. * Pavel Pudil, Jana Novovičová, J. Kittler: Floating search methods in feature selection. Pattern Recognition Letters 15, 1119-1125. Elsevier.   Download
22. * Pavel Pudil, Jana Novovičová, J. Kittler: The Max-Min approach to feature selection: its foundations and practical potential. Indian Journal of Pure and Applied Mathematics 25, 71-84.
23. * Pavel Pudil, Jana Novovičová, J. Kittler: Simultaneous learning of decision rules and important attributes for classification problems in image analysis. Image and Vision Computing 12:3 (1994), 193-198. Elsevier.
24. * Pavel Pudil, Jana Novovičová, N. Choakjarernwanit, J. Kittler: An analysis of the Max-Min approach to feature selection and ordering. Pattern Recognition Letters 14:11 (1993), 841-847. Elsevier.
25. * Pavel Pudil, Jana Novovičová, Svatopluk Bláha: Statistical Approach to Pattern Recognition: Theory and Practical Solution by Means of PREDITAS System. Kybernetika 27:6 (1991), příloha 57-78.
26. * Pavel Pudil, Jana Novovičová, Svatopluk Bláha: Statistical Approach to Pattern Recognition: Theory and Practical Solution by Means of PREDITAS System. Kybernetika 27:5 (1991), 41-56.
27. * Pavel Pudil, Jana Novovičová, Svatopluk Bláha: Statistical Approach to Pattern Recognition: Theory and Practical Solution by Means of PREDITAS System. Kybernetika 27:2 (1991), 25-40/příl..
28. * Pavel Pudil, Jana Novovičová, Svatopluk Bláha: Statistical Approach to Pattern Recognition: Theory and Practical Solution by Means of PREDITAS System. Kybernetika 27:1 (1991), 1-24/příl..
29. * Jana Novovičová: Mr-Estimators and Gnostical Estimators of Location. Problems of Control and Information Theory 19:2 (1990), 129-140.
30. * Jana Novovičová: M-estimators and Gnostical Estimators for Identification of a Regression Model. Automatica 26:3 (1990), 607-610.
31. * Jana Novovičová: M-Estimators and Gnostical Estimators of Location. Problems of Control and Information Theory 18:6 (1989), 397-407.

Conference papers (34)
1. Petr Somol, Jana Novovičová, Pavel Pudil: Improving Sequential Feature Selection Methods Performance by Means of Hybridization. Proc. 6th IASTED Int. Conf. on Advances in Computer Science and Engineering. ACTA Press, Calgary 2010.   Download
2. Petr Somol, Jana Novovičová, Pavel Pudil: On the Over-Fitting Problem of Complex Feature Selection Methods. Proc. 5th International Computer Engineering Conference - A better Information Society Through the e@, 12-17. Cairo University, Káhira 2009.   Download
3. Jana Novovičová, Petr Somol, Pavel Pudil: A New Measure of Feature Selection Algorithms’ Stability. ICDMW '09: Proceedings of the 2009 IEEE International Conference on Data Mining Workshops, 382-387. IEEE Computer Society, Washington, DC, USA 2009.
4. * P. Paclík, C. Lai, Jana Novovičová, R.P.W. Duin: Variance estimation for two-class and multi-class ROC analysis using operating point averaging. Proceedings on the 19th International Conference on Pattern Recognition, 1-4. IEEE, Tampa 2008.   Download
5. * Jiří Grim, Jana Novovičová, Petr Somol: Structural Poisson Mixtures for Classification of Documents. Proceedings of the 19th International Conference on Pattern Recognition, 1324-1327. IEEE Press, Los Alamitos 2008.   Download
6. * Petr Somol, Jana Novovičová, Jiří Grim, Pavel Pudil: Dynamic Oscillating Search Algorithm for Feature Selection. ICPR 2008 Proceedings (Int. Conf. on Pattern Recognition), 2308-2311. IEEE Computer Society, Tampa, Florida 2008.   Download
7. * Petr Somol, Jana Novovičová, Pavel Pudil: Are Better Feature Selection Methods Actually Better? Discussion, Reasoning and Examples. Proceedings of the International Joint Conference on Biomedical Engineering Systems and Technologies - BIOSTEC 2008, 246-253. INSTICC Press, Madeira 2008.   Download
8. * P. Paclík, Jana Novovičová, R.P.W. Duin: A trainable similarity measure for image classification. Proceedings of the 18th Conference on Pattern Recognition. ICPR 2006, 391-394. IEEE, Los Alamitos 2006.
9. * Jana Novovičová, Antonín Malík: Information-theoretic feature selection algorithms for text classification. Proceedings of the International Joint Conference on Neural Networks, 3272-3277. IEEE Computational Intelligence Society, Los Alamitos 2005.
10. * Jana Novovičová, Antonín Malík, Pavel Pudil: Feature selection using improved mutual information for text classification. Structural, Syntactic, and Statistical Pattern Recognition. Joint IAPR International Workshops SSPR 2004 and SPR 2004. Proceedings, 1010-1017. Springer, Berlin 2004.
11. * Jana Novovičová, Antonín Malík: Application of multinomial mixture model to text classification. Lecture Notes in Computer Science. 2652. Pattern Recognition and Image Analysis, 646-653. Springer, Berlin 2003.
12. * Jana Novovičová, Antonín Malík: Application of finite mixtures to text document classification. Znalosti 2003. Sborník příspěvků 2. ročníku konference, 23-32. VŠB, Ostrava 2003.
13. * P. Paclík, Jana Novovičová: Number of components and initialization in Gaussian mixture model for pattern recognition. Artificial Neural Nets and Genetic Algorithms. Proceedings, 406-409. Springer, Wien 2001.
14. * P. Paclík, Jana Novovičová: Road sign classification without color information. Proceedings of the 6th Annual Conference of the Advanced School for Computing and Imaging (ASCI), 84-90. Technische Universiteit, Delft 2000.
15. * Pavel Paclík, Jana Novovičová, Pavel Pudil, Petr Somol: Road sign classification using the Laplace kernel classifier. Proceedings of the 11th Scandinavian Conference on Image Analysis, 275-282. Pattern Recognition Society Denmark, Lyngby 1999.
16. * Pavel Pudil, Jana Novovičová, Petr Somol: Knowledge based feature selection in statistical pattern recognition. International Symposium on Pattern Recognition. "In Memoriam Pierre Devijver", 129-134. Royal Military Academy, Brussels 1999.
17. * Pavel Pudil, Jana Novovičová, Petr Somol, Radislav Vrňata: Feature selection expert - user oriented approach. Methodology and concept of the system. Lecture Notes in Computer Science. 1451. Advances in Pattern Recognition. Proceedings, 573-582. Springer, Berlin 1998.
18. * Jana Novovičová: Approximation of Bayes classifier using t-mixtures. Preprints of the 3rd European IEEE Workshop on Computer-Intensive Methods in Control and Data Processing, 247-252. ÚTIA AV ČR, Praha 1998.
19. * Jiří Grim, Jana Novovičová, Pavel Pudil, Petr Somol, F. J. Ferri: Initializing normal mixtures of densities. Proceedings of the 14th International Conference on Pattern Recognition, 886-890. IEEE, Los Alamitos 1998.
20. * Pavel Pudil, Jana Novovičová, Petr Somol, Radislav Vrňata: User oriented approach to feature selection in statistical pattern recognition. Multidisciplinární přístupy k podpoře rozhodování v ekonomii a managementu. Workshop '97 grantu VS 96063, 15-26. Fakulta managementu JU, Jindřichův Hradec 1997.
21. * Pavel Pudil, Jana Novovičová, Petr Somol, Radislav Vrňata: Conceptual base of feature selection consulting system. Proceedings of the 1st IAPR TC1 Workshop on Statistical Techniques in Pattern Recognition, 125-134. ÚTIA AV ČR, Praha 1997.
22. * Jana Novovičová, Pavel Pudil, Petr Somol: Feature selection in statistical pattern recognition via modified model with latent structure. Computer-Intensive Methods in Control and Signal Processing. Preprints of the 2nd European IEEE Workshop CMP'96, 217-222. ÚTIA AV ČR, Praha 1996.
23. * F. J. Ferri, J. Albert, I. Gracia, F. Pla, Pavel Pudil, Jana Novovičová: Hierarchical feature selection: A decision tree based approach. Intelligent Feature Selection: Statistical and Neural Approaches, 7-8. University of Sussex, Brighton 1996.
24. * Pavel Pudil, Jana Novovičová, F. J. Ferri: New tools for knowledge guided approach to feature selection in statistical pattern recognition. Intelligent Feature Selection: Statistical and Neural Approaches, 1-4. University of Sussex, Brighton 1996.
25. * Pavel Pudil, Jana Novovičová, F. J. Ferri, J. Kittler: Advances in the statistical methodology for the selection of image descriptors for visual pattern representation and classification. Lecture Notes in Computer Science. 970. Computer Analysis of Images and Patterns, 832-837. Springer, Berlin 1995.
26. * Jana Novovičová, Pavel Pudil, J. Kittler: Feature selection based on divergence for empirical class densities. Proceedings of the 9th Scandinavian Conference on Image Analysis, 989-996. SSAB, Uppsala 1995.
27. * Pavel Pudil, F. J. Ferri, Jana Novovičová, J. Kittler: Floating Search methods for feature selection with nonmonotonic criterion functions. International Conference on Pattern Recognition. Proceedings, 279-283. IEEE Computer Society Press, Los Alamitos 1994.
28. * Pavel Pudil, Jana Novovičová, F. J. Ferri: Methods of dimensionality reduction in statistical pattern recognition. Computer-Intensive Methods in Control and Signal Processing, 185-198. ÚTIA AV ČR, Praha 1994.
29. * F. J. Ferri, Pavel Pudil, Jana Novovičová: Methods for selecting features from high dimensional pattern spaces. Computer-Intensive Methods in Control and Signal Processing, 273-278. ÚTIA AV ČR, Praha 1994.
30. * Pavel Pudil, Jana Novovičová, J. Kittler: Automatic Machine Learning of Decision Rule for Classification Problems in Image Analysis. Proceedings of the 4th British Machine Vision Conference, 15-24. BMVA Press, Sheffield 1993.
31. * Pavel Pudil, Jana Novovičová, J. Kittler: Computationally Efficient Quasioptimal Algorithms for Feature Selection. Czech Pattern Recognition Workshop '93, 12-17. Czechoslovak Pattern Recognition Society, Praha 1993.
32. * Pavel Pudil, Jana Novovičová, Svatopluk Bláha, J. Kittler: Multistage Pattern Recognition with Reject Option. Proceedings of the 11th International Conference on Pattern Recognition, 92-95. IEEE Computer Society Press, Los Alamitos 1992.
33. * Pavel Pudil, Jana Novovičová, Svatopluk Bláha: Experimental Study of the Relationship of the Error Probability to Certain Separability Measures in Normal Classification. Proceedings DIANA III Conference on Discriminant Analysis, Cluster Analysis, Factor Analysis, and Related Topics of Multivariate Statistics and Data Analysis, 221-232. MÚ ČSAV, Praha 1990.
34. * Svatopluk Bláha, Jana Novovičová: Use of Robust Estimates of Covariance Matrices. COSMEX '89. International Conference on Stochastic, 8-9. Technical University, Wroclaw 1989.

Other publications (19)
1. Petr Somol, Jana Novovičová, Pavel Pudil, J. Kittler: Feature Selection - A Very Compact Survey Over the Diversity of Existing Approaches. Research Report 2285. ÚTIA AV ČR, v.v.i, Praha 2010.
2. * Petr Somol, Jana Novovičová: Evaluating Stability of Single and Multiple Feature Selectors that Optimize Feature Subset Cardinality. Research Report 2251. ÚTIA AV ČR, Praha 2009.
3. * Petr Somol, Jana Novovičová: Does It Make Sense to Develop New Feature Selection Methods?. Research Report 2193. ÚTIA AV ČR, Praha 2007.
4. * Petr Somol, Jana Novovičová, Pavel Pudil: Advances in Feature Selection Methodology: an Overview of Recent ÚTIA Results. Interní publikace - DAR - ÚTIA 2006/21. ÚTIA AV ČR, Praha 2006.
5. * Jana Novovičová, Antonín Malík: Text Document Classification Using Finite Mixtures. Research Report 2063. ÚTIA AV ČR, Praha 2002.   Download
7. * Miroslav Kárný, Ivan Nagy, Jana Novovičová: Quasi-Bayes Approach to Multi-Model Fault Detection and Isolation. Research Report 1974. ÚTIA AV ČR, Praha 1999.
8. * Ivan Nagy, Miroslav Kárný, Jana Novovičová, Markéta Valečková: Mixture-model Identification in Traffic Control Problems. Research Report 1973. ÚTIA AV ČR, Praha 1999.
9. * Jana Novovičová: [Recenze]. IAPR Newsletter 18:3 (1996), 5.
10. * Jana Novovičová, Pavel Pudil, J. Kittler: Feature Selection for Discrimination Based on Finite Mixtures Approximation of Class Densities. Research Report 1/93. University of Surrey, Surrey 1993.
11. * Pavel Pudil, Jana Novovičová: On the Amplifying Dependence Effect in Feature Selection. Research Report 4/92. University of Surrey, Surrey 1992.
12. * Pavel Pudil, Jana Novovičová, N. Choakjarernwanit, J. Kittler: A Comparative Evaluation of Floating Search Methods for Feature Selection. Research Report VSSP-TR-5/92. University of Surrey, Guildford 1992.
13. * Pavel Pudil, Jana Novovičová, N. Choakjarernwanit, J. Kittler: Selection of Features Optimizing a Finite Mixture Approximation of Nonparametric Densities. Research Report VSSP-TR-3/92. University of Surrey, Guildford 1992.
14. * Svatopluk Bláha, Jana Novovičová, Pavel Pudil: Solution of pattern recognition problem by means of the PREDITAS program system. Part IV. Realization. ÚTIA ČSAV, Praha 1990.
15. * František Matúš, Jana Novovičová: Odhady motivované relativistickou mechanikou. ÚTIA ČSAV, Praha 1989.
16. * Jana Novovičová: [Recenze]. Kybernetika 25:4 (1989), 321-322.
19. * Jana Novovičová: Asymptotic behaviour of Mr-estimators of location. ÚTIA ČSAV, Praha 1989.

Miscellaneous (1)
1. * Pavel Pudil, Jana Novovičová, Jiří Grim: Proceedings of the 1st IAPR TC1 Workshop on Statistical Techniques in Pattern Recognition. ÚTIA AV ČR, Praha 1997.