A Unified Novel Neural Network Approach and a Prototype Hardware Implementation for Ultra-Low Power EEG Classification.

This paper introduces a novel electroencephalogram (EEG) data classification scheme together with its implementation in hardware using an innovative approach. The proposed scheme integrates into a single, end-to-end trainable model a spatial filtering technique and a neural network based classifier. The spatial filters, as well as, the coefficients of the neural network classifier are simultaneously estimated during training. By using different time-locked spatial filters, we introduce for the first time the notion of "attention" in EEG processing, which allows for the efficient capturing of the temporal dependencies and/or variability of the EEG sequential data. One of the most important benefits of our approach is that the proposed classifier is able to construct highly discriminative features directly from raw EEG data and, at the same time, to exploit the function approximation properties of neural networks, in order to produce highly accurate classification results. The evaluation of the proposed methodology, using public available EEG datasets, indicates that it outperforms the standard EEG classification approach based on filtering and classification as two separated steps. Moreover, we present a prototype implementation of the proposed scheme in state-of-the-art reconfigurable hardware; our novel implementation outperforms by more than one order of magnitude, in terms of power efficiency, the conventional CPU-based approaches.

The vulnerable atherosclerotic plaque: evaluation of the lipid core in human coronary arteries using morphometry.

In Greece, mortality due to coronary artery disease has alarmingly increased during the past 3 decades, especially among younger adults between 30 and 40 years old. Many studies have been conducted over the years in an effort to interpret the presence of acute coronary phenomena-myocardial infarction, thrombosis, and sudden death-in early diagnosis and treatment. The current study focuses on postmortem data from individuals who had sudden coronary death. The coronary arteries of 100 individuals who were routinely subjected to autopsy at the Department of Forensic Sciences of the University of Crete were removed and examined, aiming at the evaluation of the degree of stenosis of the lumen and measurement of proportion of cholesterol in the plaque using Image Pro Plus 4.5. The average degree of stenosis was 79.01%, ranging from 11% to 99%. The cholesterol proportion was measured in 66 specimens, and the average was 25.05%, ranging between 5.3% and 66.3%, whereas 25 of them (37.8% overall) were found to contain cholesterol above the average. It resulted that the degree of stenosis was not of major importance in vulnerable plaques and that the amount of cholesterol followed an almost linear pattern of accumulation.