An Anomaly Detection Approach for Dyslexia Diagnosis Using EEG Signals
Developmental dyslexia (DD) is a specific difficulty in the acquisition of reading skills not related to mental age or inadequate schooling. Its prevalence is estimated between 5% and 12% of the population. Currently, biological causes and processes of DD are not well known and it is usually diagnosed by means of specifically designed tests to measure different behavioural variables involved in the reading process. Thus, the diagnosis results depend on the analysis of the test results which is a time-consuming task and prone to error. In this paper we use EEG signals to search for brain activation patterns related to DD that could result useful for differential diagnosis by an objective test. Specifically, we extract spectral features from each electrode. Moreover, the exploration of the activation levels at different brain areas constitutes an step towards the best knowledge of the brain proccesses involved in DD.
KeywordsEEG Dyslexia One-Class-SVM Automatic diagnosis
This work was partly supported by the MINECO/FEDER under PSI2015-65848-R and TEC2015-64718-R projects.
- 5.Li, R., Principe, J.C.: Blinking artifact removal in cognitive EEG data using ICA. In: 2006 International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 5273–5276 (2006)Google Scholar
- 9.Schölkopf, B., Williamson, R., Smola, A., Shawe-Taylor, J., Platt, J.: Support vector method for novelty detection. In: Proceedings of the 12th International Conference on Neural Information Processing Systems, NIPS 1999, pp. 582–588. MIT Press, Cambridge (1999)Google Scholar