Ing. Zoltán Galáž, Ing. Jiří Mekyska, prof. Ing. Zdeněk Smékal, CSc.
Date of creation: 4. 4. 2017
It is possible to download software here.
Publication to be cited
MEKYSKA, J.; FAÚNDEZ ZANUY, M.; MŽOUREK, Z.; GALÁŽ, Z.; SMÉKAL, Z.; ROSENBLUM, S. Identification and Rating of Developmental Dysgraphia by Handwriting Analysis. IEEE Transactions on Human-Machine Systems, 2016, roč. PP, č. 99, s. 1-14. ISSN: 2168-2291.
In the case that the analysed data comprise skewed groups/labels that are not distributed evenly (e.g. healthy peaplo vs. patients suffering from some rare disorder), it is recommended to use so called anomaly detection algorithm to mark such observations. Anomaly detection tool (ADT) perform the detection using computation of probability density function estimate of the multivariate Gaussian distribution.
The ADT software is written in the MATLAB programming environment. The testing script can be used to test functionality of the software. It loads the 2D data (2 features) and marks the potential anomalies (outliers). It also graphs the distribution of the data/anomalies (x = x1, y = x2) according to the selection of the probability density function threshold.
This work was supported by projects AZV 16-30805A and LO1401. The described research was performed in laboratories supported by the SIX project; the registration number CZ.1.05/2.1.00/03.0072, the operational program Research and Development for Innovation.