Overcoming selective ensemble averaging: unsupervised identification of event-related brain potentials

Abstract

We present a novel approach to the problem of event-related potential (ERP) identification, based on a competitive artificial neural network (ANN) structure. Our method uses ensembled electroencephalogram (EEG) data just as used in conventional averaging, however without the need for a priori data subgrouping into distinct categories (e.g., stimulus- or event-related), and thus avoids conventional assumptions on response invariability. The competitive ANN, often described as a winner takes all neural structure, is based on dynamic competition among the net neurons where learning takes place only with the winning neuron. Using a simple single-layered structure, the proposed scheme results in convergence of the actual neural weights to the embedded ERP patterns. The method is applied to real event-related potential data recorded during a common odd-ball type paradigm. For the first time, within-session variable signal patterns are automatically identified, dismissing the strong and limiting requirement of a priori stimulus-related selective grouping of the recorded data. The results present new possibilities in ERP research.

Movement-related potentials during the performance of a motor task I: The effect of learning and force

“…Selective ensemble averaging of evoked potentials (EPs) has been attempted in the past. One such application (Lange et al 2000) used self-organizing neural networks to partition an ensemble of EPs into separate classes. In neural networks such as the ones used by that algorithm, the neuron that is best matched to a given EP is strengthened so that its weights give a closer match to that EP.…”

Enhanced Detection of Visual-Evoked Potentials in Brain-Computer Interface Using Genetic Algorithm and Cyclostationary Analysis

“…It is known that ERP is not a homogeneous signal, but instead a combination of different components due to which variations in amplitude and latency between trials are caused. Also, identical stimuli do not necessarily evoke identical responses [3, 4]; trial-to-trial variability can be appreciable, and ERP waveform, amplitude, and latency can change appreciably with time [3, 4]. Therefore, average ERP does not elicit the valid estimate of the VEP components amplitude and shape and hence is usually considered biased [4].…”

Semantic geodesic maps: a unifying geometrical approach for studying the structure and dynamics of single trial evoked responses

“…The main objective is the identification of structure in the data (Geva and Pratt, 1994;Zouridakis et al, 1997a,b;Lange et al, 2000;Hoppe et al, 2000). To this end, features are extracted from the individual ST-patterns (i.e.…”