- 349 views
- 167 downloads
Validating Koalacademy, a neuro-guided language learning platform
-
- Author(s) / Creator(s)
-
Koalacademy is a language learning tool predicated on the subsequent memory effect
(SME), which differentiates the brain activity between the successful or unsuccessfulencoding of a studied word to memory, relaying this information back to the user in real-
time. We take advantage of the SME in confirming or denying the encoding of words duringthe process of studying them, allowing for selective repetition of poorly studied words, thus
improving the success-rate of learning. The present study is focussed on validating the
underlying framework of Koalacademy, a scalable Brain Computer Interface (BCI) platform
that is able to present stimuli and stream brain data in a timely fashion comparable to
other traditionally validated means of obtaining electroencephalography (EEG) data from
BCI headsets. The present study utilizes a comparison oddball task. We have two
conditions, including a control condition using a single board computer—which brain data
is streamed to and is triggered via a light sensor at the onset of stimulus on the
Koalacademy platform—, and an experimental condition consisting of brain data streaming
and triggered through Koalacademy. The present study is the first of two, while the latter
aims to validate whether a cloud trained machine learning model based on data collected
through Koalacademy is able to successfully predict subsequent recall in real-time. -
- Date created
- 2021-08-13
-
- Type of Item
- Conference/Workshop Poster