Location
Online
Event Website
https://hicss.hawaii.edu/
Start Date
3-1-2022 12:00 AM
End Date
7-1-2022 12:00 AM
Description
This paper describes a distributed paradigm for human brain-computer interfaces that can incorporate machine learning-directly stimulus feedback to the subject. Specifically, we use OpenBCI hardware and software to capture real-time EEG (Electroencephalography) waveforms from a subject on a host ''client" computer and stream them to another ''server" computer which could perform complex analyses on the waveforms prior to sending commands back to the OpenBCI interface directing alterations to the stimulus. In addition to describing the conceptual system framework, we present here the test results quantifying the closed-loop system latencies under various conditions. Quantifying latency in any feedback control loop (in this case, one that actually contains the human subject's brain) is vital since excess latency can destabilize a system.
The feedback dynamics of brain-computer interfaces in a distributed processing environment
Online
This paper describes a distributed paradigm for human brain-computer interfaces that can incorporate machine learning-directly stimulus feedback to the subject. Specifically, we use OpenBCI hardware and software to capture real-time EEG (Electroencephalography) waveforms from a subject on a host ''client" computer and stream them to another ''server" computer which could perform complex analyses on the waveforms prior to sending commands back to the OpenBCI interface directing alterations to the stimulus. In addition to describing the conceptual system framework, we present here the test results quantifying the closed-loop system latencies under various conditions. Quantifying latency in any feedback control loop (in this case, one that actually contains the human subject's brain) is vital since excess latency can destabilize a system.
https://aisel.aisnet.org/hicss-55/hc/architecture/3