International Journal of Neural Systems

This study introduces a novel learning algorithm for spiking neurons, called CCDS, which is able to learn and reproduce arbitrary spike patterns in a supervised fashion allowing the processing of spatiotemporal information encoded in the precise timing of spikes. Unlike the Remote Supervised Method (ReSuMe), synapse delays and axonal delays in CCDS are variants which are modulated together with weights during learning. The CCDS rule is both biologically plausible and computationally efficient. The properties of this learning rule are investigated extensively through experimental evaluations in terms of reliability, adaptive learning performance, generality to different neuron models, learning in the presence of noise, effects of its learning parameters and classification performance. Results presented show that the CCDS learning method achieves learning accuracy and learning speed comparable with ReSuMe, but improves classification accuracy when compared to both the Spike Pattern Association Neuron (SPAN) learning rule and the Tempotron learning rule. The merit of CCDS rule is further validated on a practical example involving the automated detection of interictal spikes in EEG records of patients with epilepsy. Results again show that with proper encoding, the CCDS rule achieves good recognition performance.

Currently, there are no developed methods to detect sharp wave transients that exist in the latent phase after hypoxia-ischemia (HI) in the electroencephalogram (EEG) in order to determine if these micro-scale transients are potential biomarkers of HI. A major issue with sharp waves in the HI-EEG is that they possess a large variability in their sharp wave profile making it difficult to build a compact ‘footprint of uncertainty’ (FOU) required for ideal performance of a Type-2 fuzzy logic system (FLS) classifier. In this paper, we develop a novel computational EEG analysis method to robustly detect sharp waves using over 30h of post occlusion HI-EEG from an equivalent, in utero, preterm fetal sheep model cohort. We demonstrate that initial wavelet transform (WT) of the sharp waves stabilizes the variation in their profile and thus permits a highly compact FOU to be built, hence, optimizing the performance of a Type-2 FLS. We demonstrate that this method leads to higher overall performance of $94\%\pm 1$ for the clinical $64\mathrm{\text{Hz}}$ sampled EEG and $97\%\pm 1$ for the high resolution $1024\mathrm{\text{Hz}}$ sampled EEG that is improved upon over conventional standard wavelet $67\%\pm 5$ and $82\%\pm 3$, respectively, and fuzzy approaches $88\%\pm 2$ and $90\%\pm 3$, respectively, when performed in isolation.

A patient-specific algorithm, for epileptic seizure prediction, based on multiclass support-vector machines (SVM) and using multi-channel high-dimensional feature sets, is presented. The feature sets, combined with multiclass classification and post-processing schemes aim at the generation of alarms and reduced influence of false positives. This study considers 216 patients from the European Epilepsy Database, and includes 185 patients with scalp EEG recordings and 31 with intracranial data. The strategy was tested over a total of 16,729.80h of inter-ictal data, including 1206 seizures. We found an overall sensitivity of 38.47% and a false positive rate per hour of 0.20. The performance of the method achieved statistical significance in 24 patients (11% of the patients). Despite the encouraging results previously reported in specific datasets, the prospective demonstration on long-term EEG recording has been limited. Our study presents a prospective analysis of a large heterogeneous, multicentric dataset. The statistical framework based on conservative assumptions, reflects a realistic approach compared to constrained datasets, and/or in-sample evaluations. The improvement of these results, with the definition of an appropriate set of features able to improve the distinction between the pre-ictal and nonpre-ictal states, hence minimizing the effect of confounding variables, remains a key aspect.

Computer-aided diagnosis (CAD) systems constitute a powerful tool for early diagnosis of Alzheimer’s disease (AD), but limitations on interpretability and performance exist. In this work, a fully automatic CAD system based on supervised learning methods is proposed to be applied on segmented brain magnetic resonance imaging (MRI) from Alzheimer’s disease neuroimaging initiative (ADNI) participants for automatic classification. The proposed CAD system possesses two relevant characteristics: optimal performance and visual support for decision making. The CAD is built in two stages: a first feature extraction based on independent component analysis (ICA) on class mean images and, secondly, a support vector machine (SVM) training and classification. The obtained features for classification offer a full graphical representation of the images, giving an understandable logic in the CAD output, that can increase confidence in the CAD support. The proposed method yields classification results up to 89% of accuracy (with 92% of sensitivity and 86% of specificity) for normal controls (NC) and AD patients, 79% of accuracy (with 82% of sensitivity and 76% of specificity) for NC and mild cognitive impairment (MCI), and 85% of accuracy (with 85% of sensitivity and 86% of specificity) for MCI and AD patients.

Cognitive fault detection and diagnosis systems are systems able to provide timely information about possibly occurring faults without requiring any a priori knowledge about the process generating the data or the possible faults. This ability is crucial in sensor network scenarios where a priori information about the data generating process, the noise level or the dictionary of the possibly occurring faults is generally hard to obtain. We here present a novel cognitive fault detection and isolation system for sensor networks. The proposed solution relies on the modeling of spatial and temporal relationships present in the acquired datastreams and an ensemble of Hidden Markov Model change-detection tests working in the space of estimated parameters for fault detection and isolation purposes. The effectiveness of the proposed solution has been evaluated on both synthetically generated and real datasets.