Spiking Neural Network for On-line Cognitive Activity Classification Based on EEG Data Stefan Schliebs, Elisa Capecci ⋆ , and Nikola Kasabov KEDRI, Auckland University of Technology, New Zealand {sschlieb,ecapecci,nkasabov}@aut.ac.nz Abstract. The paper presents a method for the classification of EEG data recorded in two cognitive scenarios, a relaxing and memory task. The method uses a reservoir of spiking neurons that are activated by the spatio-temporal EEG data. The states of the reservoir are periodically read out and classified producing in a continuous classification result over time. After suitable optimization of the model parameters, we achieve a test accuracy of 82% on a small data set. Future applications of the proposed model are discussed including its use for an early detection of a cognitive impairment such as in Alzheimers disease. Keywords: Spiking Neural Networks, Liquid State Machines, Reservoir Computing, EEG data classification, Cognitive tasks. 1 Introduction Intellectual functioning including memory testing is a commonly used diagnosis tool to characterize the state of cognitive impairments such as Alzheimer’s dis- ease. In this paper, we investigate the idea to use the classification ability of a machine learning algorithm as an indicator for the detection of memory related cognitive diseases. We have collected EEG recordings from a single healthy sub- ject performing a relaxing and a memory task; the latter represents the cognitive scenario. If the subject is healthy, a distinct difference between the EEG record- ings of the two scenarios is expected and a classification algorithm should be able to tell the memory and relax scenarios reliably apart. Therefore, if a high classification accuracy is observed, the subject is expected to be healthy. On the other hand, if the classification performance is poor, it may be an indicator for memory related cognitive disease. In this paper, we investigate a brief proof of concept only. We are especially interested in establishing the suitability of a reservoir computing approach for the described learning scenario. Reservoir com- puting has reported promising results on the detection of epileptic seizures [1] and the classification of motor imagery based on EEG data streams [6]. While the above studies have investigated the suitability of Echo State Networks [4], we explore Liquid State Machines (LSM) [7] for classifying spatio-temporal EEG signals in this paper. ⋆ Corresponding author. M. Lee et al. (Eds.): ICONIP 2013, Part III, LNCS 8228, pp. 55–62, 2013. c  Springer-Verlag Berlin Heidelberg 2013