Enhanced Template Matching Using Dynamic Positional Warping for Identification of Specific Patterns in Electroencephalogram

Abstract

Template matching is an approach for signal pattern recognition, often used for biomedical signals including electroencephalogram (EEG). Since EEG is often severely contaminated by various physiological or pathological artifacts, identification and rejection of these artifacts with improved template matching algorithms would enhance the overall quality of EEG signals. In this paper, we propose a novel approach to improve the accuracy of conventional template matching methods by adopting the dynamic positional warping (DPW) technique, developed recently for handwriting pattern analysis. To validate the feasibility and superiority of the proposed method, eye-blink artifacts in the EEG signals were detected, and the results were then compared to those from conventional methods. DPW was found to outperform the conventional methods in terms of artifact detection accuracy, demonstrating the power of DPW in identifying specific one-dimensional data patterns.

Correlation between Inter-Blink Interval and Episodic Encoding during Movie Watching

“…Eye blink data were measured from electromyography signals in EEG channels. The eye blink component was extracted from the FP1 and FP2 electrodes by a template-matching algorithm that used dynamic positional warping to identify specific patterns in the EEG [ 20 ]. The data were analyzed offline using MATLAB (The MathWorks, Inc., Natick, MA, USA).…”

Clustering of interictal spikes by dynamic time warping and affinity propagation

“…DTW is a robust method for calculating the similarity between temporal sequences. DTW has been applied for face detection [8], template matching [9], clustering [10] and many other applications. DTW has also been shown to improve the performance of various clustering methods such as K-means clustering, hierarchical clustering, and fuzzy clustering [11-13].…”

An automatic algorithm for blink-artifact suppression based on iterative template matching: application to single channel recording of cortical auditory evoked potentials

“…The performance of template matching is highly dependent on the template selection [57]. Previous methods used a library of blink-artifact templates of different waveforms to adapt the inter-subject variability [55,56], however this approach presented the drawbacks of (a) generating a sufficiently large database of templates, and (b) the selected template would never perfectly match the blink-artifact waveform of the analyzed subjects. In contrast, ITMS solves the problem of template selection through an iterative process.…”

“…A second limitation of previously implemented template matching-based methods is that the threshold that separates the blink-events from the noise distribution was selected manually by the user [55,56], which makes these methods inconsistent worldwide and dependent on human expertise. Moreover, this paper highlighted the limitations of methods relying on manual thresholds.…”