skip to content

Inverse pattern identification based on longitudinal clustering with applications to behavioural science

Presented by: 
Mihaela Pricop-jeckstadt Technische Universität Dresden
Friday 3rd November 2017 - 12:00 to 12:50
INI Seminar Room 1
In this talk we consider an example-driven approach for identifying ability patterns from data partitions based on learning behaviour in the water maze experiment.  A modification of the k-means algorithm for longitudinal data as introduced in [1], based on the Mahalanobis distance metric (see e.g. [2]), is used to identify clusters that maximize the covariance between the psychological information and the learning variable (see [3]). Stability of the partition as well as reproducibility of the ability pattern is evaluated based on simulations, and the algorithm is applied to a data set originating in the psychological  tests for German fight pilots. 
References:1. Genolini, C.; Ecochard, R.; Benghezal, M. et al., ''kmlShape: An Efficient Method to Cluster Longitudinal Data (Time-Series) According to Their Shapes'', PLOS ONE,  Vol. 11, 2016.2. Sung, K.K. and Poggio, T., ''Example-based learning for view-based human face detection'',  IEEE Transactions on pattern analysis and machine intelligence, Vol. 20, 39-51, 1998. 3. Rosipal, R. and Kraemer, N. , ''Overview and recent advances in partial least squares'',  Subspace, latent structure and feature selection,  Book Series: Lecture Notes in Computer Science,  Vol. 3940, 34-51, 2006.
University of Cambridge Research Councils UK
    Clay Mathematics Institute London Mathematical Society NM Rothschild and Sons