English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Key properties of brain-inspired hyperdimensional (HD) computing make it aprime candidate for energy-efficient and fast learning in biosignal processing.The main challenge is however to formulate embedding methods that map biosignalmeasures to a binary HD space. In this paper, we explore variety of suchembedding methods and examine them with a challenging application of motorimagery brain-computer interface (MI-BCI) from electroencephalography (EEG)recordings. We explore embedding methods including random projections,quantization based thermometer and Gray coding, and learning HD representationsusing end-to-end training. All these methods, differing in complexity, aim torepresent EEG signals in binary HD space, e.g. with 10,000 bits. This leads todevelopment of a set of HD learning and classification methods that can beselectively chosen (or configured) based on accuracy and/or computationalcomplexity requirements of a given task. We compare them with state-of-the-artlinear support vector machine (SVM) on an NVIDIA TX2 board using the 4-classBCI competition IV-2a dataset as well as a new 3-class dataset. Compared toSVM, results on 3-class dataset show that simple thermometer embedding achievesmoderate average accuracy (79.56% vs. 82.67%) with 26.8$\times$ faster trainingtime and 22.3$\times$ lower energy; on the other hand, switching to end-to-endtraining with learned HD representations wipes out these training benefitswhile boosting the accuracy to 84.22% (1.55% higher than SVM). Similar trend isobserved on the 4-class dataset where SVM achieves on average 74.29%: thethermometer embedding achieves 89.9$\times$ faster training time and58.7$\times$ lower energy, but a lower accuracy (67.09%) than the learnedrepresentation of 72.54%.

Exploring Embedding Methods in Binary Hyperdimensional Computing: A Case Study for Motor-Imagery based Brain-Computer Interfaces