Laboratory for Cognitive Modelling

LKM carries out research in cognitive modelling, machine learning, neural networks, statistics, picture and data mining. Research results concern the modelling of noisy data related to cognitive, medical, biological and other processes. We are developing, testing and applying new approaches and algorithms for modelling from numeric, symbolic and pictorial data, and new approaches to building, evaluation and explanation of models, derived from data. Recent research is related to evaluating the utility of ordinal attributes, generation of semi-artificial data, analysis of big data with map-reduce approach, analysis of graphs, evaluating the reliability of single models’ predictions in classification and regression, evaluating the reliability of clustering, explaining single predictions by arbitrary classification and regression model, text summarization using archetypal analysis, analysing and modelling of sport data, user profiling by mining the web-logs, recommendation systems, learning of imbalanced classification problems, applying evolutionary computation to data mining focused on using ant colony optimization, prediction intervals which represent the distribution of individual future points in a more informative manner, spatial data mining with multi-level directed graphs, employing background knowledge analysis for search space reduction in inductive logic programming, detection of (non)-ischemic episodes in ECG signals, heuristic search methods in clickstream mining and mining of data streams. A notable aspect of much of this research is its application to problems in image analysis, medical diagnosis, ecological modelling, marketing and financial modelling.

We are located...

at the 2nd floor, northern part of building, the room number R2.26, facing the office of prof. Kononenko (R2.07), the head of LKM. .



Selected References (2014)

  • Z. Bosnić, J. Demšar, G. Kešpret, P.P. Rodrigues, J. Gama, I. Kononenko. Enhancing data stream predictions with reliability estimators and explanation. Eng. appl. artif. intell., vol. 34, p.p. 178-192, 2014.
  • E. Canhasi, I Kononenko. Weighted archetypal analysis of the multi-element graph for query-focused multi-document summarization. Expert systems with applications, Feb. 2014, vol. 41, no. 2, pp. 535-543.
  • E. Canhasi, I. Kononenko. Multi-document summarization via archetypal analysis of the content-graph joint model. Knowledge and information systems, 2014, vol. 41, no. 3, str. 821-842
  • D. Košir, I. Kononenko, Z. Bosnić. Web user profiles with time-decay and prototyping. Appl. intell., vol. 41, no. 4, p.p. 1081-1096, Dec. 2014.
  • U. Ocepek, Z. Bosnić, I. Nančovska Šerbec, J. Rugelj. Exploring the relation between learning style models and preferred multimedia types. Computers & Education, Nov. 2013, vol. 69, pp. 343-355.
  • B. Petelin, I. Kononenko, V. Malačič, M. Kukar. Multi-level association rules and directed graphs for spatial data analysis. Expert systems with applications,  2013, vol. 40, issue 12, pp. 4957-4970
  • B. Petelin, I. Kononenko, V. Malačič. M. Kukar, Dynamic fuzzy paths and cycles in multi-level directed graphs. Engineering applications of artificial intelligence, 2014, vol. 37, p. 194-206.
  • D. Pevec, I. Kononenko. Input dependent prediction intervals for supervised regression. Intelligent data analysis, 18(5):873-887, 2014.
  • Pičulin, Matej, Robnik Šikonja, Marko. Handling numeric attributes with ant colony based classifier for medical decision making. Expert systems with applications, 2014, 41(16):7524-7535
  • M. Robnik Šikonja, E. Štrumbelj, I. Kononenko. Efficiently explaining the predictions of a probabilistic radial basis function classification network. Intelligent data analysis, 2013, vol. 17, no. 5, pp. 791-802.
  • E. Štrumbelj. On determining probability forecasts from betting odds. International journal of forecasting, 2014, vol. 30, no. 4, 934-943.
  • E. Štrumbelj., F.Erčulj. Analysis of experts` quantitative assessment of adolescent basketball players and the role of anthropometric and physiological attributes. Journal of Human Kinetics, 2014, vol. 42, 267-276.
  • E. Štrumbelj.. A comment on the bias of  probabilities derived from betting odds and their use in measuring outcome uncertainty. Journal of sports economics, 2014, (in print, available online)
  • E. Štrumbelj., I. Kononenko. Explaining prediction models and individual predictions with feature contributions. Knowledge and information systems, 2014, vol. 41, no. 3, 647-665.
  • M. Toplak, R. Močnik, M. Polajnar, Z. Bosnić, L. Carlsson, C. Hasselgren, J. Demšar, S. Boyer, B. Zupan, J. Stålring. Assessment of machine learning reliability methods for quantifying the applicability domain of QSAR regression models. J. chem. inf. mod., vol. 54, no. 2, p.p. 431-441, Feb. 2014.


Current Projects

Closed Projects

Web Page

More about this laboratory