Track topics on Twitter Track topics that are important to you
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 an order of magnitude, in terms of power efficiency, the conventional CPU-based approaches.
This article was published in the following journal.
Name: IEEE transactions on biomedical circuits and systems
Resistive RAM crossbar arrays offer an attractive solution to minimize off-chip data transfer and parallelize on-chip computations for neural networks. Here, we report a hardware/software co-design ap...
Neural networks and other machine learning approaches have been successfully used to accurately represent atomic interaction potentials derived from computationally demanding electronic structure calc...
The rapid growth of applications that rely on artificial neural network (ANN) concepts gives rise to a staggering increase in the demand for hardware implementations of neural networks. New types of h...
Zeroing neural network (ZNN), as a powerful calculating tool, is extensively applied in various computation and optimization fields. Convergence and noise-tolerance performance are always pursued and ...
The breaking of ergodicity in isolated quantum systems with a single-particle mobility edge is an intriguing subject that has not yet been fully understood. In particular, whether a nonergodic but met...
Identifying the correct arrhythmia at the time of a clinic event including cardiac arrest is of high priority to patients, healthcare organizations, and to public health. Recent developmen...
The purpose of this study is to examine effectiveness and implementation for the Unified Protocol for the Transdiagnostic Treatment of Emotional Disorders in trauma exposed veterans.
The purpose of the study is to determine the validity of the prediction model in reducing the rate of CPAP titration failure and in achieving a shorter time to optimal pressure
This study aims to first identify the optimal estradiol (E2) dose that best engages the fear extinction network among healthy women using oral contraceptives. The second objective is to th...
Healthy ageing and pathological ageing in the context of a neurodegenerative disease are both associated with changes in brain network integrity. Episodic memory is especially affected in ...
A computer architecture, implementable in either hardware or software, modeled after biological neural networks. Like the biological system in which the processing capability is a result of the interconnection strengths between arrays of nonlinear processing nodes, computerized neural networks, often called perceptrons or multilayer connectionist models, consist of neuron-like units. A homogeneous group of units makes up a layer. These networks are good at pattern recognition. They are adaptive, performing tasks by example, and thus are better for decision-making than are linear learning machines or cluster analysis. They do not require explicit programming.
A research and development program initiated by the NATIONAL LIBRARY OF MEDICINE to build knowledge sources for the purpose of aiding the development of systems that help health professionals retrieve and integrate biomedical information. The knowledge sources can be used to link disparate information systems to overcome retrieval problems caused by differences in terminology and the scattering of relevant information across many databases. The three knowledge sources are the Metathesaurus, the Semantic Network, and the Specialist Lexicon.
Instrumentation consisting of hardware and software that communicates with the BRAIN. The hardware component of the interface records brain signals, while the software component analyzes the signals and converts them into a command that controls a device or sends a feedback signal to the brain.
An early embryonic developmental process of CHORDATES that is characterized by morphogenic movements of ECTODERM resulting in the formation of the NEURAL PLATE; the NEURAL CREST; and the NEURAL TUBE. Improper closure of the NEURAL GROOVE results in congenital NEURAL TUBE DEFECTS.
A ubiquitous target SNARE protein that interacts with SYNTAXIN and SYNAPTOBREVIN. It is a core component of the machinery for intracellular MEMBRANE FUSION. The sequence contains 2 SNARE domains, one is the prototype for the Qb-SNARES, and the other is the prototype for the Qc-SNARES.
Standard antiretroviral therapy (ART) consists of the combination of at least three antiretroviral (ARV) drugs to maximally suppress the HIV virus and stop the progression of HIV disease. Huge reductions have been seen in rates of death and suffering whe...