Here, we introduce the method based on artificial neural networks (ANNs) for recognition and classification of patterns in electroencephalograms (EEGs) associated with imaginary and real movements of untrained volunteers. In order to get the fastest and the most accurate classification performance of multichannel motor imagery EEG-patterns, we propose our approach to selection of appropriate type, topology, learning algorithm and other parameters of neural network. We considered linear neural network, multilayer perceptron, radial basis function network (RBFN) and support vector machine. We revealed that appropriate quality of recognition can be obtained by using particular groups of electrodes according to extended international 10−10 system. Besides, pre-processing of EEGs by low-pass filter can significantly increase the classification performance. We developed mathematical model based on ANN for classification of EEG patterns corresponding to imaginary or real movements, which demonstrated high efficiency for untrained subjects. Achieved recognition accuracy of movements was up to 90−95% for group of subjects. RBFN demonstrated more accurate classification performance in both cases. Pre-filtering of input data using low-pass filter significantly increases recognition accuracy on 10−20% in average, and the low-pass filter with cutoff frequency 4 Hz shows the best results. It was revealed that using different sets of electrodes placed on different brain areas and consisted of 6-12 channels, one can achieve close to maximal classification accuracy. It is convenient to use electrodes on frontal and temporal lobes for real movements, and several sets containing 6-9 electrodes — in case with imagery movements.
In this paper we propose a model of the spatially distributed network based on the spatially correlated preferential attachments. Nodes in the spatially distributed networks of the real word, such as various urban or biological networks, aren't establishing randomly: the probability of emergence of new nodes is higher in the area of already existing ones. In this work we unite two principles of the real network modeling: the correlated percolation model and preferential attachment. To regulate spatial limitations of the network, we use density gradient, which determines the decrease of the probability of the connection emergence between two nodes with increase of the distance between them. We also consider the consistency of our results in the context of the real-world system modeling.
The paper considers the phenomena of competition in multiplex network whose structure evolves corresponding to dynamics of it’s elements, forming closed loop of self-learning with the aim to reach the optimal topology. Numerical analysis of proposed model shows that it is possible to obtain scale-invariant structures for corresponding parameters as well as the structures with homogeneous distribution of connections in the layers. Revealed phenomena emerges as the consequence of the self-organization processes related to structure-dynamical selflearning based on homeostasis and homophily, as well as the result of the competition between the network’s layers for optimal topology. It was shown that in the mode of partial and cluster synchronization the network reaches scale-free topology of complex nature that is different from layer to layer. However, in the mode of global synchronization the homogeneous topologies on all layer of the network are observed. This phenomenon is tightly connected with the competitive processes that represent themselves as the natural mechanism of reaching the optimal topology of the links in variety of real-world systems.
This paper considers the possibility of classification of electroencephalogram (EEG) and electromyogram (EMG) signals corresponding to different phases of sleep and wakefulness of mice by the means of artificial neural networks. A feed-forward artificial neural network based on multilayer perceptron was created and trained on the data of one of the rodents. The trained network was used to read and classify the EEG and EMG data corresponding to different phases of sleep and wakefulness of the same mouse and other mouse. The results show a good recognition quality of all phases for the rodent on which the training was conducted (80–99%) and acceptable recognition quality for the data collected from the same mouse after a stroke.