Information-based Adaptive Stimulus Selection to Optimize Communication Efficiency in Brain-Computer Interfaces
Authors: Boyla Mainsah, Dmitry Kalika, Leslie Collins, Siyuan Liu, Chandra Throckmorton
NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We demonstrate the utility of our adaptive stimulus selection algorithm in improving BCI performance with results from simulation and real-time human experiments. |
| Researcher Affiliation | Academia | Boyla O. Mainsah,1 Dmitry Kalika,2 Leslie M. Collins,1 Siyuan Liu,1 Chandra S. Throckmorton1 1Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA 2Johns Hopkins University Applied Physics Laboratory, Laurel, MD, USA Corresponding author: leslie.collins@duke.edu |
| Pseudocode | Yes | Algorithm 1: Adaptive BCI Stimulus Selection Using Mutual Information (MI). |
| Open Source Code | No | The paper mentions using 'The open source BCI2000 software [24]' but does not provide a link or statement for the source code of their *own* methodology. |
| Open Datasets | No | The paper mentions using 'Eight healthy participants were recruited' for an online experiment and collecting 'EEG data to estimate user-specific BCI parameters' during a 'calibration block', indicating custom data collection. However, no specific link, DOI, repository, or citation for public access to this dataset is provided. |
| Dataset Splits | No | The paper describes calibration (training) and testing, but does not explicitly mention a distinct validation set or specific split percentages/counts for training, validation, and testing needed for reproduction. It mentions fixed parameters like stopping thresholds but not data splits for hyperparameter tuning. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory amounts, or cloud instance types) used for running its simulations or experiments. |
| Software Dependencies | No | The paper mentions 'simulations (in MATLAB)' and 'The open source BCI2000 software [24]' but does not provide specific version numbers for these software components. |
| Experiment Setup | Yes | The paper provides specific experimental setup details such as simulation constraints ('a data processing delay τ = 6; a flash group size limit of 9; and a stochastic TTI restriction using a pre-defined probability distribution with a minimum value of 3'), stopping thresholds ('Pth = 0.9 and 120 stimulus flashes' for simulation, 'Pth = 0.9 and 145 stimulus flashes' for online), and timing parameters for the online experiment ('flash duration, ISI and time pause between character selections were set to 62.5 ms, 62.5 ms and 3.5 s, respectively'). It also details signal processing parameters ('EEG signals were sampled at a rate of 256 Hz and filtered between 0.5-30 Hz', 'Features were extracted from an 800 ms segment of EEG data... by down-sampling to a rate of 20 Hz using bin averaging'). |