Henrik Boström, professor
Dept. of Computer and Systems Sciences
Stockholm University
Forum 100, 164 40 Kista
Sweden
Email: henrik.bostrom@dsv.su.se
Phone: +46 8 16 16 16
Fax: +46 8 703 90 25

My research interests are primarily within the area of machine learning, i.e., artificial systems that learn from experience, with a particular focus on predictive modeling. Research in this area may be found under several different headings, including (predictive) data mining, knowledge discovery, predictive analytics and intelligent data analysis. My focus is on decision tree and rule learning, as well as ensemble methods, i.e., techniques for generating sets of models that collectively form predictions by voting.

I am project leader of High-performance data mining for drug effect detection, a 19 MSEK project funded by the Swedish Foundation for Strategic Research during 2012-2016. See press release (in Swedish).

NOTE: We currently have 1-3 open PhD positions in data mining – see the official announcement (also advertised at www.kdnuggets.com). Closing date is April 30, 2012.

Curriculum Vitae

PhD students:

  • PhD Martin Eineborg, during 1998 – 2002. His PhD thesis was entitled Inductive logic programming for part of speech tagging
  • PhD Tony Lindgren , during 2000 – 2006. His PhD thesis was entitled Methods of solving conflicts among induced rules
  • PhLic Thashmee Karunaratne, since 2004. Her licentiate thesis in 2007 was entitled Graph Propositionalization for Learning from Structured Data
  • PhLic Sampath Deegalla, since 2004. His licentiate thesis in 2009 was entitled Towards Improving Performance of Nearest Neighbor Classification in High Dimensions
  • PhLic Tuve Löfström, since 2007. His licentiate thesis in 2009 was entitled Utilizing Diversity and Performance Measures for Ensemble Creation
  • Catarina Dudas, since 2007. She is working on data mining for the analysis of production systems.
  • Cecilia Sönströd, since 2009. She is working on methods for concept description.

I am at the editorial boards of the following journals:

Machine Learning
Journal of Machine Learning Research
Intelligent Data Analysis

I am or have recently been at the following program committees:

KDD 2011
ICML 2011
AAAI 2011
IDA 2011
DS 2011
KDD 2010
ICML 2010 – area chair for rule and decision tree learning
ECML PKDD 2010
KDD 2009
ICML 2009
ECML PKDD 2009
Fusion 2009
HAIS 2009
ICML 2008
ECML PKDD ’08
DaWaK’08

I am co-founder of Compumine AB, and main developer of Rule Discovery System (RDS)

Publications

  1. T. Karunaratne, H. Boström and U. Norinder. Comparative analysis of the use of chemoinformatics-based and substructure-based descriptors for quantitative structure-activity relationship (QSAR) modeling. Intelligent Data Analysis, vol. 17, no. 2, 2013 (in press)
  2. H. Boström. Forests of probability estimation trees. International Journal of Pattern Recognition and Artificial Intelligence (in press)
  3. U. Johansson, C. Sönströd, T. Löfström and H. Boström. Obtaining accurate and comprehensible classifiers using oracle coaching. Intelligent Data Analysis, vol. 16, no. 2, 2012 (in press)
  4. H. Boström. Concurrent Learning of Large-Scale Random Forests. In Proceedings of Scandinavian Conference on Artificial Intelligence, pages 20-29, 2011. Available from: http://people.dsv.su.se/˜henke/papers/bostrom11.pdf
  5. U. Johansson, C. Sönströd, U. Norinder and H. Boström H. The Trade-Off between Accuracy and Interpretability for Predictive In Silico Modeling. Future Medicinal Chemistry, vol. 3, no. 6, pages 647-663, 2011.
  6. T. Karunaratne, H. Boström, and U. Norinder. Pre-processing structured data for standard machine learning algorithms by supervised graph propositionalization – a case study with medicinal chemistry datasets. In Proceedings of the Ninth International Conference on Machine Learning and Applications. IEEE Computer Society, 2010.
    Available from: http://people.dsv.su.se/˜henke/papers/karunaratne10.pdf
  7. U. Johansson, C. Sönströd, U. Norinder, H. Boström, and T. Löfström. Using feature selection with bagging and rule extraction in drug discovery. In Advances in Intelligent Decision Technologies, Second KES International Symposium IDT 2010, pages 413–422, 2010.
    Available from: http://people.dsv.su.se/˜henke/papers/johansson10.pdf
  8. C. Sönströd, U. Johansson, H. Boström, and U. Norinder. Pin-pointing concept descriptions. In Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, pages 2956–2963, 2010.
    Available from: http://people.dsv.su.se/˜henke/papers/sonstrod10.pdf
  9. T. Löfström, U. Johansson, and H. Boström. Implicit vs. explicit methods for generating diverse ensembles of artificial neural networks. In WCCI 2010 IEEE World Congress on Computational Intelligence, IJCNN 2010, pages 1287–1292, 2010.
    Available from: http://people.dsv.su.se/˜henke/papers/lofstrom10.pdf
  10. T. Karunaratne and H. Boström. Graph propositionalization for random forests. In Proceedings of the Eighth International Conference on Machine Learning and Applications, pages 196–201. IEEE Computer Society, 2009.
    Available from: http://people.dsv.su.se/˜henke/papers/karunaratne09.pdf
  11. S. Deegalla and H. Boström. Improving fusion of dimensionality reduction methods for nearest neighbor classification. In Proceedings of the Eighth International Conference on Machine Learning and Applications, pages 771–775. IEEE Computer Society, 2009.
    Available from: http://people.dsv.su.se/˜henke/papers/deegalla09b.pdf
  12. S. Deegalla and H. Boström. Fusion of dimensionality reduction methods: A case study in microarray classification. In Proceedings of the 12th International Conference on Information Fusion, pages 460–465, 2009.
    Available from: http://people.dsv.su.se/˜henke/papers/deegalla09a.pdf
  13. H. Boström and U. Norinder. Utilizing Information on Uncertainty for In Silico Modeling using Random Forests, Proc. of the 3rd Skövde Workshop on Information Fusion Topics, pp 59-62, 2009.
  14. C. Dudas and H. Boström. Using uncertain chemical and thermal data to predict product quality in a casting process. In Proceedings of the First ACM SIGKDD Workshop on Knowledge Discovery from Uncertain Data, pages 57–61, 2009. Available from: http://people.dsv.su.se/˜henke/papers/dudas09b.pdf
  15. C. Dudas, A. Ng, and H. Boström. Information extraction from solution set of multi-objective simulation optimisation using data mining. In Proceedings of Industrial Simulation Conference, pages 65–69, 2009.
    Available from: http: //people.dsv.su.se/˜henke/papers/dudas09a.pdf
  16. T. Löfström, U. Johansson, and H. Boström. Ensemble member selection using multi-objective optimization. In Proceedings of the IEEE Symposium on Computational Intelligence and Data Mining, pages 245–251, 2009.
    Available from: http://people.dsv.su.se/˜henke/papers/lofstrom09.pdf
  17. H. Boström. Calibrating random forests. In Proceedings of the Seventh International Conference on Machine Learning and Applications, pages 121–126. IEEE Computer Society, 2008.
    Available from: http://people.dsv.su.se/~henke/papers/bostrom08b.pdf
  18. T. Löfström, U. Johansson, and H. Boström. On the use of accuracy and diversity measures for evaluating and selecting ensembles of classifiers. In Proceedings of the Seventh International Conference on Machine Learning and Applications, pages 127–132. IEEE Computer Society, 2008.
    Available from: http://people.dsv.su.se/~henke/papers/lofstrom08.pdf
  19. C. Sönströd, U. Johansson, U. Norinder, and H. Boström. Comprehensible models for predicting molecular interaction with heart-regulating genes. In Proceedings of Seventh International Conference on Machine Learning and Applications, pages 559–564. IEEE Computer Society, 2008.
    Available from: http://people.dsv.su.se/~henke/papers/sonstrod08.pdf
  20. C. Dudas, A. Ng, and H. Boström. Information extraction in manufacturing using data mining techniques. In Proceedings of Swedish Production Symposium, pages 111–118, 2008.
    Available from: http://people.dsv.su.se/~henke/papers/dudas08.pdf
  21. T. Löfström, U. Johansson, and H. Boström. Ensemble member selection using multi-objective optimization. In Proceedings of the IEEE Symposium on Computational Intelligence and Data Mining, pages 245–251, 2009.
    Available from: http://people.dsv.su.se/~henke/papers/lofstrom09.pdf
  22. H. Boström. Calibrating random forests. In Proceedings of the Seventh International Conference on Machine Learning and Applications, pages 121–126. IEEE Computer Society, 2008.
    Available from: http://people.dsv.su.se/~henke/papers/bostrom08b.pdf
  23. T. Löfström, U. Johansson, and H. Boström. On the use of accuracy and diversity measures for evaluating and selecting ensembles of classifiers. In Proceedings of the Seventh International Conference on Machine Learning and Applications, pages 127–132. IEEE Computer Society, 2008.
    Available from: http://people.dsv.su.se/~henke/papers/lofstrom08.pdf
  24. C. Sönströd, U. Johansson, U. Norinder, and H. Boström. Comprehensible models for predicting molecular interaction with heart-regulating genes. In Proceedings of Seventh International Conference on Machine Learning and Applications, pages 559–564. IEEE Computer Society, 2008.
    Available from: http://people.dsv.su.se/~henke/papers/sonstrod08.pdf
  25. C. Dudas, A. Ng, and H. Boström. Information extraction in manufacturing using data mining techniques. In Proceedings of Swedish Production Symposium, pages 111–118, 2008.
    Available from: http://people.dsv.su.se/~henke/papers/dudas08.pdf
  26. R. Johansson, H. Boström, and A. Karlsson. A study on class-specifically discounted belief for ensemble classifiers. In Proceedings of the IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, pages 614–619, 2008.
    Available from: http://people.dsv.su.se/~henke/papers/johansson08d.pdf
  27. H. Boström, R. Johansson, and A. Karlsson. On evidential combination rules for ensemble classifiers. In Proceedings of the 11th International Conference on Information Fusion, pages 553–560, 2008.
    Available from: http://people.dsv.su.se/~henke/papers/bostrom08.pdf
  28. U. Johansson, T. Löfström, and H. Boström. The problem with ranking ensembles based on training or validation performance. In Proceedings of the International Joint Conference on Neural Networks, pages 3221–3227. IEEE Press, 2008. Available from: http://people.dsv.su.se/~henke/papers/johansson08c.pdf
  29. U. Johansson, H. Boström, and R. König. Extending nearest neighbor classification with spheres of confidence. In Proceedings of the 21st Florida Artificial Intelligence Research Society Conference, pages 282–287. AAAI Press, 2008. Available from: http://people.dsv.su.se/~henke/papers/johansson08b.pdf
  30. U. Johansson, C. Sönströd, T. Löfström, and H. Boström. Chipper – a novel algorithm for concept description. In Proceedings of the Scandinavian Conference on Artificial Intelligence, pages 133–140. IOS Press, 2008.
    Available from: http: //people.dsv.su.se/~henke/papers/johansson08a.pdf
  31. Boström H., United States Patent no. 7,379,941. Method for Efficiently Checking Coverage of Rules Derived from a Logical Theory. Filed on September 13, 2003, issued May 27, 2008.
  32. H. Boström. Estimating class probabilities in random forests. In Proceedings of the Sixth International Conference on Machine Learning and Applications, pages 211–216. IEEE Computer Society, 2007.
    Available from: http://people.dsv.su.se/~henke/papers/bostrom07c.pdf
  33. S. Deegalla and H. Boström. Classification of microarrays with knn: Comparison of dimensionality reduction methods. In Proceedings of the 8th International Conference on Intelligent Data Engineering and Automated Learning, LNCS 4881, pages 800–809. Springer-Verlag, 2007.
    Available from: http://people.dsv.su.se/~henke/papers/deegalla07.pdf
  34. H. Boström. Feature vs. classifier fusion for predictive data mining – a case study in pesticide classification. In Proceedings of the 10th International Conference on Information Fusion, pages 121–126, 2007.
    Available from: http://people.dsv.su.se/~henke/papers/bostrom07b.pdf
  35. H. Boström. Maximizing the area under the roc curve with decision lists and rule sets. In Proceedings of the SIAM International Conference on Data Mining, pages 27–34, 2007.
    Available from: http://people.dsv.su.se/~henke/papers/bostrom07a.pdf
  36. T. Karunaratne and H. Boström. Using background knowledge for graph based learning: a case study in chemoinformatics. In Proceedings of the 16th International Conference on Inductive Logic Programming, pages 116–118, 2006. Available from: http://people.dsv.su.se/~henke/papers/karunaratne06c.pdf
  37. T. Karunaratne and H. Boström. Learning to classify structured data by graph propositionalization. In Proceedings of the Second IASTED International Conference on Computational Intelligence, pages 393–398, 2006.
    Available from: http://people.dsv.su.se/~henke/papers/karunaratne06b.pdf
  38. S. Deegalla and H. Boström. Reducing high-dimensional data by principal component analysis vs. random projection for nearest neighbor classification. In Proceedings of the Fifth International Conference on Machine Learning and Applications, pages 245–250, 2006.
    Available from: http://people.dsv.su.se/~henke/papers/deegalla06.pdf
  39. T. Karunaratne and H. Boström. Learning from structured data by finger printing. In Proceedings of the Ninth Scandinavian Conference on Artificial Intelligence, pages 120–126. IOS Press, 2006.
    Available from: http://people.dsv.su.se/~henke/papers/karunaratne06a.pdf
  40. U. Norinder, P. Liden, and H. Boström. Discrimination between modes of toxic action of phenols using rule based methods. Molecular Diversity, 10(2):207–212, 2006. H. Boström. Maximizing the area under the roc curve using incremental reduced error pruning. In Proceedings of the ICML 2005 Workshop on ROC Analysis in Machine Learning, 2005.
    Available from: http://people.dsv.su.se/~henke/papers/bostrom05.pdf
  41. H. Boström. Pruning and exclusion criteria for unordered incremental reduced error pruning. In Proceedings of the Workshop on Advances in Rule Learning at 15th European Conference on Machine Learning, pages 17–29, 2004.
    Available from: http://people.dsv.su.se/~henke/papers/bostrom04.pdf
  42. T. Lindgren and H. Boström. Resolving rule conflicts with double induction. Intelligent Data Analysis, 8(5):457–468, 2004.
    Available from: http://people.dsv.su.se/~henke/papers/lindgren04.pdf
  43. W. Rao, H. Boström, and S. Xie. Rule induction for structural damage identification. In Proceedings of International Conference on Machine Learning and Cybernetics, pages 2865–2869, 2004.
  44. M. Jacobsson, P. Liden, E. Stjernschantz, H. Boström, and U. Norinder. Improving structure-based virtual screening by multivariate analysis of scoring data. Medicinal Chemistry, 46(26):5781–5789, 2003.
  45. T. Lindgren and H. Boström. Resolving rule conflicts with double induction. In Proceedings of the 5th International Symposium on Intelligent Data Analysis, pages 60–67. Springer, 2003.
    Available from: http://people.dsv.su.se/~henke/papers/lindgren03.pdf
  46. T. Lindgren and H. Boström. Classification with intersecting rules. In Proceedings of the 13th International Conference on Algorithmic Learning Theory, pages 395–402. Springer, 2002.
    Available from: http://people.dsv.su.se/~henke/papers/lindgren02.pdf
  47. P. Liden, L. Asker, and H. Boström. Rule induction for classification of gene expression array data. In Proceedings of Principles of Data Mining and Knowledge Discovery: 6th European Conference, LNAI vol. 2431, pages 338–347. Springer, 2002.
    Available from: http://people.dsv.su.se/~henke/papers/liden02.pdf
  48. M. Eineborg and H. Boström. Classifying uncovered examples by rule stretching. In Proceedings of the Eleventh International Conference on Inductive Logic Programming, volume 2157 of LNAI, pages 41–50. Springer, 2001.
    Available from: http://people.dsv.su.se/~henke/papers/eineborg01.pdf
  49. A. Hulth, J. Karlgren, A. Jonsson, H. Boström, and L. Asker. Automatic keyword extraction using domain knowledge. In Proceedings of Second International Conference on Computational Linguistics and Intelligent Text Processing, LNCS 2004, pages 472–482. Springer, 2001.
    Available from: http://people.dsv.su.se/~henke/papers/hulth01.pdf
  50. M. Huss, H. Boström, L. Asker, and J. Cöster. Learning to recognize brain specific proteins based on low-level features from on-line prediction servers. In Proceedings of BIOKDD-2001: Workshop on Data Mining in Bioinformatics, pages 45–49, 2001.
    Available from: http://people.dsv.su.se/~henke/papers/huss01.pdf
  51. J. J. Rodriguez, C. J. Alonso, and H. Boström. Boosting interval based literals. Intelligent Data Analysis, 5(3):245–262, 2001.
    Available from: http://people.dsv.su.se/~henke/papers/rodriguez01.pdf
  52. H. Boström. Induction of recursive transfer rules. In J. Cussens and S. Dzeroski, editors, Learning Language in Logic, LNAI 1925, pages 237–246. Springer- Verlag, 2001.
    Available from: http://people.dsv.su.se/~henke/papers/bostrom01.pdf
  53. J. J. Rodriguez, C. J. Alonso, and H. Boström. Learning first order logic time series classifiers: Rules and boosting. In Principles of Data Mining and Knowledge Discovery: 4th European Conference, LNAI vol. 1910, pages 299–308. Springer, 2000.
    Available from: http://people.dsv.su.se/~henke/papers/rodriguez00b.pdf
  54. J. J. Rodriguez, C. J. Alonso, and H. Boström. Learning first order logic time series classifiers. In Inductive Logic Programming: 10th International Conference. Work-in-Progress Reports, pages 260–275, 2000.
    Available from: http://people.dsv.su.se/~henke/papers/rodriguez00a.pdf
  55. H. Boström and P. Idestam-Almquist. Induction of logic programs by example-guided unfolding. Journal of Logic Programming, 40(2-3):159–183, 1999. Available from: http://people.dsv.su.se/~henke/papers/bostrom99b.pdf
  56. H. Boström and L. Asker. Combining divide-and-conquer and separate-andconquer for efficient and effective rule induction. In Proceedings of the Ninth International Workshop on Inductive Logic Programming, LNAI Series 1634, pages 33–42. Springer, 1999.
    Available from: http://people.dsv.su.se/~henke/papers/bostrom99a.pdf
  57. H. Boström. Predicate invention and learning from positive examples only. In Proceedings of the Tenth European Conference on Machine Learning, pages 226–237. Springer, 1998.
    Available from: http://people.dsv.su.se/~henke/papers/bostrom98.pdf
  58. Z. Alexin, T. Gyimothy, and H. Boström. Imput: An interactive learning tool based on program specialization. Intelligent Data Analysis, 1(4):219–244, 1997. H. Boström. Theory-guided induction of logic programs by inference of regular languages. In Proceedings of the 13th International Conference on Machine Learning, pages 46–53. Morgan Kaufmann, 1996.
    Available from: http://people.dsv.su.se/~henke/papers/bostrom96.ps
  59. Z. Alexin, T. Gyimothy, and H. Boström. Integrating algorithmic debugging and unfolding transformation in an interactive learner. In Proceedings of the 12th European Conference on Artificial Intelligence, pages 403–407. John Wiley and Sons, 1996. H. Boström. Covering vs. divide-and-conquer for top-down induction of logic programs. In Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, pages 1194–1200. Morgan Kaufmann, 1995. Available from: http://people.dsv.su.se/~henke/papers/bostrom95b.ps
  60. H. Boström. Specialization of recursive predicates. In Proceedings of the Eighth European Conference on Machine Learning, pages 92–106. Springer, 1995. Available from: http://people.dsv.su.se/~henke/papers/bostrom95a.ps
  61. H. Ade and H. Boström. Jigsaw: puzzling together ruth and spectre (extended abstract). In Proceedings of the Eighth European Conference on Machine Learning, pages 263–266. Springer, 1995.
  62. L. Asker and H. Boström. The denox system: Machine learning for process control. In Proceedings of the IJCAI-95 Workshop on Machine Learning in Engineering, 1995.
  63. L. Asker and H. Boström. Building the denox system: Experience from a realworld application of machine learning. In Proceedings of the Workshop on Applying Machine Learning in Practice at the International Conference on Machine Learning, 1995.
  64. H. Boström and P. Idestam-Almquist. Specialization of logic programs by pruning sld-trees. In Proceedings of the 4th International Workshop on Inductive Logic Programming, volume 237 of Gesellschaft fur Mathematik und Datenverarbeitung MBH, pages 31–48, 1994.
    Available from: http://people.dsv.su.se/~henke/papers/bostrom94.ps
  65. H. Boström. Explanation-based transformation of logic programs. Ph.D. thesis, Dept. of Computer and Systems Sciences, Stockholm University, 1993.
  66. H. Boström. Explanation-based generalization of multiple training examples. In Proceedings of the Third International Workshop on Knowledge Compilation and Speedup Learning, pages 14–20, 1993.
  67. L. Asker, H. Boström, and C. Samuelsson. Dynamic explanation-based generalization. In Proceedings of the Third International Workshop on Knowledge Compilation and Speedup Learning, pages 1–6, 1993.
  68. H. Boström. Improving example-guided unfolding. In Proceedings of the European Conference on Machine Learning, pages 124–135. Springer, 1993.
  69. H. Boström. Eliminating redundancy in explanation-based learning. In Proceedings of the Ninth International Conference on Machine Learning, pages 37–42. Morgan Kaufmann, 1992.
  70. C. G. Jansson, H. Boström, and P. Idestam-Almquist. Theory revision in a logic programming framework. In Proceedings of theWorkshop on Logical Approaches to Machine Learning at European Conference on Artificial Intelligence, 1992.
  71. C. G. Jansson, H. Boström, and P. Idestam-Almquist. Optimizing horn clause logic programs for particular modes of use: An analysis of explanation-based learning and partial evaluation. In Proceedings of the Third Scandinavian Conference on Artificial Intelligence, pages 252–257, 1991.
  72. H. Boström. Generalizing goal orders as an approach to generalizing number. Licentiate thesis, Dept. of Computer and Systems Sciences, Stockholm University, 1990.
  73. H. Boström. Generalizing the order of goals as an approach to generalizing number. In Proceedings of the Seventh International Conference on Machine Learning, pages 260–267. Morgan Kaufmann, 1990.

U. Johansson, C. Sönströd, T. Löfström and H. Boström. Obtaining accurate and comprehensible classifiers using oracle coaching. Intelligent Data Analysis, vol. 16, no. 2, 2012 (in press)

Comments are closed.