OpenBCI

Abstract: Electrooculography (EOG) signals have been widely used in Human-Computer Interfaces (HCI). The HCI systems proposed in the literature make use of self-designed or closed environments, which restrict the number of potential users and applications. Here, we present a system for classifying four directions of eye movements employing EOG signals. The system is based on open source ecosystems, the Raspberry Pi single-board computer, the OpenBCI biosignal acquisition device, and an open-source python library. The designed system provides a cheap, compact, and easy to carry system that can be replicated or modified. We used Maximum, Minimum, and Median trial values as features to create a Support Vector Machine (SVM) classifier. A mean of 90% accuracy was obtained from 7 out of 10 subjects for online classification of Up, Down, Left, and Right movements. This classification system can be used as an input for an HCI, i.e., for assisted communication in paralyzed people.

Abstract: In this paper we present Electromyography/Electrooculography (EMG/EOG) speller. It allows users to write sentences or phrases using blinking exclusively. Eye blinks are detected through simple threshold method. Moreover, the speller is comfortable to use. We based it on Open Source software available for free, as well as low-cost OpenBCI hardware. We measured the performance of the interface in an experiment. The results showed that: (1) symbols were recognised at 90% accuracy rate; (2) 100% of eye blinks was detected; (3) Information Transfer Rate (ITR) we achieved equaled 43,3 bit/min. Streszczenie. W artykule zaprezentowano interfejs człowiek-komputer wykorzystujący Elektromiografię i Elektrookulografię. Interfejs umożliwia pisanie jedynie za pomocą wykrywanych mrugnięć. Do ich wykrywania zastosowano prostą detekcję progową. Ponadto, interfejs jest wygodny w użyciu. Bazuje on na darmowym oprogramowaniu Open Source i tanim urządzeniu OpenBCI. Przeprowadzono eksperyment testujący możliwośći interfejsu. Uzyskano następujące rezultaty: (1) 90% skuteczności w rozpoznawaniu znaków; (2) 100% skuteczność w detekcji mrugnięcia; (3) Współczynnik Information Transfer Rate (ITR) wyniósł 43,3 bit/min(Projekt i ewaluacja interfejsu człowiek komputer wykorzystującego EMG/EOG)

Abstract: Many brain-computer-interface (BCI) approaches, such as the steady-state-visually-evoked-potential (SSVEP) and BCI speller paradigms, rely on evoking neural signals using presentation of audiovisual stimuli. These exogenous BCIs typically involve the user staring at a physical stimulus presentation apparatus resulting in prolonged system setup and degraded portability. We present a research platform for BCI implementations in mixed reality (XR) environments, enabling less-invasive holographic stimulus presentation and greatly enhanced portability at low-cost. The platform consists of a 3D-printable electroencephalography (EEG) attachment for the Microsoft HoloLens, firmware for the OpenBCI Cyton EEG amplifier evaluation kit, and Unity software supporting direct Bluetooth low-energy communication between the EEG device and the HoloLens. The platform allows researchers and hobbyists to prototype BCIs with an easy to don/doff EEG attachment for the HoloLens that is capable of recording high-quality EEG using dry electrodes in an untethered XR environment without the need for external compute resources.