A growing trend in Human Computer Interaction (HCI) is to integrate computational capabilities into wearable devices, to enable sophisticated and natural interaction modalities. Acting directly by decoding neural activity is a very natural way of interaction and one of the fundamental paradigms of Brain Computer Interfaces (BCIs) as well. In this work we present a wearable IoT node designed for BCI spelling. The system is based on Visual Evoked Potentials detection and runs the Canonical Correlation Analysis (CCA) on a low power microcontroller. Neural data is acquired by an array of EEG active dry electrodes, suitable for a minimally intrusive interface. To evaluate our solution, we optimized the system on eight subjects and tested it on five different subjects for four and eight stimuli, reaching a peak transfer rate of 1.57 b/s, comparable with those achieved by state-of-the-art non-embedded systems. The power consumption of the device is less than 30 mW, resulting in 122 hours of operation with a standard 1000 mAh battery.

Salvaro, M., Benatti, S., Kartsch, V., Guermandi, M., Benini, L. (2019). A Minimally Invasive Low-Power Platform for Real-Time Brain Computer Interaction based on Canonical Correlation Analysis. IEEE INTERNET OF THINGS JOURNAL, 6(1), 967-977 [10.1109/JIOT.2018.2866341].

A Minimally Invasive Low-Power Platform for Real-Time Brain Computer Interaction based on Canonical Correlation Analysis

Salvaro, Mattia;Benatti, Simone;Kartsch, Victor;Guermandi, Marco;Benini, Luca
2019

Abstract

A growing trend in Human Computer Interaction (HCI) is to integrate computational capabilities into wearable devices, to enable sophisticated and natural interaction modalities. Acting directly by decoding neural activity is a very natural way of interaction and one of the fundamental paradigms of Brain Computer Interfaces (BCIs) as well. In this work we present a wearable IoT node designed for BCI spelling. The system is based on Visual Evoked Potentials detection and runs the Canonical Correlation Analysis (CCA) on a low power microcontroller. Neural data is acquired by an array of EEG active dry electrodes, suitable for a minimally intrusive interface. To evaluate our solution, we optimized the system on eight subjects and tested it on five different subjects for four and eight stimuli, reaching a peak transfer rate of 1.57 b/s, comparable with those achieved by state-of-the-art non-embedded systems. The power consumption of the device is less than 30 mW, resulting in 122 hours of operation with a standard 1000 mAh battery.
2019
Salvaro, M., Benatti, S., Kartsch, V., Guermandi, M., Benini, L. (2019). A Minimally Invasive Low-Power Platform for Real-Time Brain Computer Interaction based on Canonical Correlation Analysis. IEEE INTERNET OF THINGS JOURNAL, 6(1), 967-977 [10.1109/JIOT.2018.2866341].
Salvaro, Mattia; Benatti, Simone; Kartsch, Victor; Guermandi, Marco; Benini, Luca
File in questo prodotto:
File Dimensione Formato  
merge.pdf

Open Access dal 26/08/2019

Tipo: Postprint
Licenza: Licenza per accesso libero gratuito
Dimensione 1.53 MB
Formato Adobe PDF
1.53 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/677797
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 13
  • ???jsp.display-item.citation.isi??? 10
social impact