An investigation on dimensionality reduction in the source-space-based hand trajectory decoding

Nitikorn Srisrisawang, Gernot Müller-Putz*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review


In this work, the hand trajectory decoding was investigated in the source space. A couple of di-mensionality reduction techniques were utilized to re-duce the number of the source-space signals, namely, computing the mean, principle component analysis (PCA), locality preserving projection (LPP).
The decoding performances from the source-space approaches were compared to the sensor-space ap-proach. We found that every approach showed perfor-mance metrics in a similar range and only slight differ-ences across approaches could be observed. The source-space approach with PCA with 8 components exhibited higher performance metrics than other ap-proaches and slightly higher performance metrics than the sensor-space approach (improvement for correla-tion 0.01 to 0.09, SNR 0.05 to 0.1 dB). The results sug-gested that the source-space-based decoding is pos-sible, and it can achieve comparable performance to the sensor-space approach.
Original languageEnglish
Title of host publicationProceedings Annual Meeting of the Austrian Society for Biomedical Engineering 2021
Subtitle of host publicationÖGBMT 2021
PublisherVerlag der Technischen Universität Graz
ISBN (Electronic)978-3-85125-826-4
Publication statusPublished - 2021
EventAnnual Meeting of the Austrian Society of the Biomedical Engineering 2021: ÖGBMT 2021 - Graz University of Technology, Graz, Austria
Duration: 30 Sept 20211 Oct 2021


ConferenceAnnual Meeting of the Austrian Society of the Biomedical Engineering 2021
Abbreviated titleÖGBMT 2021
Internet address


  • Electroencephalographic (EEG) source imaging
  • Brain-computer interface (BCI)

Cite this