Call for Presentations

BDBC-2020 Call for Presentations:

General Topics of interest, but not limited to:

  • Multi-modal physiological signal interactions and interpretations
  • Banking the frontiers in brain imaging data for elderly applications: depression, Alzheimer’s disease, etc.
  • Brain image data compression – advanced feature selection schemes and classification states
  • Machine Learning/Neural Network algorithms complementing brain data idiosyncrasy
  • 3D spatial and temporal visual display – dynamic brain image processing
  • Graph-centric brain network analysis
  • Harmonization of brain data performance, accuracy, sensitivity, confidence, and reliability.

Participating teams are encouraged to use the downloadable presentation template attached below.

More details can be found in IEEE Brain Initiative

 Entries to BDBC-2020

  • Focus: the “Aging Brain”.
  • Recommended datasets (MRI, EEG and/or others:)
    1. The National Institute’s Alzheimer’s Disease Neuro Imaging in Instructions for ADNI access permission can be downloaded using the button above.
      About ADNI data, please refer to training slides:
      ADNI Data Training Slides Part 1
      ADNI Data Training Slides Part 2
    2. The NeuroImaging Tools & Resources Collaboratory:
    3. Open-source brain signal or image datasets, > 10 GB or more.
  • Multiple Entries (with improvements from the previous entry) are allowed to compete for BDBC Awards:
    • Taiwan/St. Petersburg: Up to $1,000 total for the Preliminary Round
    • Silicon Valley: In the plan for the Final Round of BDBC to offer prizes including 1st place, up to $5,000.

Scope of BDBC-2020

Questions to be addressed, regarding the aging brain:

  1. How effectively do EEG, fNIRS, and/or fMRI datasets capture the aging brain?
  2. How non-verbal signal inputs: vision, facial expression, body language and temperature, or other physiological stimulus affect the aging brain?
  3. How can emerging techniques, e.g., Big Data Analytics, Artificial Intelligence, and Deep Learning, enhance the prediction of brain aging?
  4. How to facilitate ease of use, reliability and protection of brain datasets?

Lessons learned from past BDBC presentations can lead improvements in reference to –

  1. Using Machine Learning localized EEG dimensionality with optimized spatial temporal correlation to compress data by 280 folds.
  2. Using AI/Deep Learning improved dataset performance and prediction sensitivity to above 90%.
  3. Low power CNN microchip with nano-sensor was implanted for near real-time prediction.
  4. 3D model manufacturing made comprehensive brain display cost-effective.
For any inquiry about BDBC-2020, send an email to –

%d bloggers like this: