An approach to detect and predict epileptic seizures with high accuracy using convolutional neural networks and single-lead-ECG signal.

One of the epileptic patients' challenges is to detect the time of seizures and the possibility of predicting. This research aims to provide an algorithm based on deep learning to detect and predict the time of seizure from one to two minutes before its occurrence. The proposed Convolutional Neural Network (CNN) can detect and predict the occurrence of focal epilepsy seizures through single-lead-ECG signal processing instead of using EEG signals. The structure of the proposed CNN for seizure detection and prediction is the same. Considering the requirements of a wearable system, after a few light pre-processing steps, the ECG signal can be used as input to the neural network without any manual feature extraction step. The desired neural network learns purposeful features according to the labelled ECG signals and then performs the classification of these signals. Training of 39-layer CNN for seizure detection and prediction has been done separately. The proposed method can detect seizures with an accuracy of 98.84% and predict them with an accuracy of 94.29%. With this approach, the ECG signal can be a promising indicator for the construction of portable systems for monitoring the status of epileptic patients.

Ultra-thin broadband solar absorber based on stadium-shaped silicon nanowire arrays.

This paper investigates how the dimensions and arrangements of stadium silicon nanowires (NWs) affect their absorption properties. Compared to other NWs, the structure proposed here has a simple geometry, while its absorption rate is comparable to that of very complex structures. It is shown that changing the cross-section of NW from circular (or rectangular) to a stadium shape leads to change in the position and the number of absorption modes of the NW. In a special case, these modes result in the maximum absorption inside NWs. Another method used in this paper to attain broadband absorption is utilization of multiple NWs which have different geometries. However, the maximum enhancement is achieved using non-close packed NW. These structures can support more cavity modes, while NW scattering leads to broadening of the absorption spectra. All the structures are optimized using particle swarm optimizations. Using these optimized structures, it is viable to enhance the absorption by solar cells without introducing more absorbent materials.

Calibration time reduction through local activities estimation in motor imagery-based brain-computer interfaces.

OBJECTIVE: One of the main limitations for the practical use of brain-computer interfaces (BCI) is the calibration phase. Several methods have been suggested for the truncating of this undesirable time, including various variants of the popular CSP method. In this study, we cope with the problem, using local activities estimation (LAE). APPROACH: LAE is a spatial filtering technique that uses the EEG data of all electrodes along with their position information to emphasize the local activities. After spatial filtering by LAE, a few electrodes are selected based on physiological information. Then the features are extracted from the signal using FFT and classified by the support vector machine. In this study, the LAE is compared with CSP, RCSP, FBCSP and FBRCSP in two different electrode configurations of 118 and 64-channel. MAIN RESULTS: The LAE outperforms CSP-based methods in all experiments using the different number of training samples. The LAE method also obtains an average classification accuracy of 84% even with a calibration time of fewer than 2 min Significance: Unlike CSP-based methods, the LAE does not use the covariance matrix, and also uses a priori physiological information. Therefore, LAE can significantly reduce the calibration time while maintaining proper accuracy. It works well even with a few training samples.