QuPWM: Feature Extraction Method for Epileptic Spike Classification.

Epilepsy is a neurological disorder ranked as the second most serious neurological disease known to humanity, after stroke. Inter-ictal spiking is an abnormal neuronal discharge after an epileptic seizure. This abnormal activity can originate from one or more cranial lobes, often travels from one lobe to another, and interferes with normal activity from the affected lobe. The common practice for Inter-ictal spike detection of brain signals is via visual scanning of the recordings, which is a subjective and a very time-consuming task. Motivated by that, this article focuses on using machine learning for epileptic spikes classification in magnetoencephalography (MEG) signals. First, we used the Position Weight Matrix (PWM) method combined with a uniform quantizer to generate useful features from time domain and frequency domain through a Fast Fourier Transform (FFT) of the framed raw MEG signals. Second, the extracted features are fed to standard classifiers for inter-ictel spikes classification. The proposed technique shows great potential in spike classification and reducing the feature vector size. Specifically, the proposed technique achieved average sensitivity up to 87% and specificity up to 97% using 5-folds cross-validation applied to a balanced dataset. These samples are extracted from nine epileptic subjects using a sliding frame of size 95 samples-points with a step-size of 8 sample-points.

Feature Generation and Dimensionality Reduction using the Discrete Spectrum of the Schrödinger Operator for Epileptic Spikes Detection.

Epilepsy is a neurological disorder classified as the second most serious neurological disease known to humanity, after stroke. Magnetoencephalography (MEG) is performed to localize the epileptogenic zone in the brain. However, the detection of epileptic spikes requires the visual assessment of long MEG recordings. This task is time-consuming and might lead to wrong decisions. Therefore, the introduction of effective machine learning algorithms for the quick and accurate epileptic spikes detection from MEG recordings would improve the clinical diagnosis of the disease. The efficiency of machine learning based algorithms requires a good characterization of the signal by extracting pertinent features. In this paper, we propose new sets of features for MEG signals. These features are based on a Semi-Classical Signal Analysis (SCSA) method, which allows a good characterization of peak shaped signals. Moreover, this method improves the spike detection accuracy and reduces the feature vector size. We could achieve up to 93.68% and 95.08% in average sensitivity and specificity, respectively. We used the 5-folds cross-validation applied to a balanced dataset of 3104 frames, extracted from eight healthy and eight epileptic subjects with a frame size of 100 samples with a step size of 2 samples, using Random Forest (RF) classifier.