Skip to main content

Frontiers of Engineering Reports on Leading-Edge Engineering from the 2017 Symposium (2018) / Chapter Skim
Currently Skimming:

Efficient Feature Extraction and Classification Methods in Neural Interfaces - Mahsa Shoaran, Benyamin A. Haghi, Masoud Farivar, and Azita Emami
Pages 73-80

The Chapter Skim interface presents what we've algorithmically identified as the most significant single chunk of text within every page in the chapter.
Select key terms on the right to highlight them within pages of the chapter.


From page 73...
... Such devices are designed to interface with the brain, monitor and detect neurological abnormalities, and trigger an appropriate type of therapy such as neuromodulation to restore normal function. A key challenge to these new treatments is to integrate state-of-the-art signal acquisition techniques, as well as efficient biomarker extraction and classification methods to accurately identify symptoms, using low-cost, highly integrated, wireless, and miniaturized devices.
Read the entire page →
From page 74...
... In addition, because of the severity of refractory epilepsy and the need for surgery, human tissue and epileptic EEG datasets are largely available. Most therapeutic neural interfaces reported in the literature have therefore focused on extracting epileptic biomarkers for automated seizure detection (Shoaran et al.
Read the entire page →
From page 75...
... Numerous studies show that a large number of acquisition channels are required to obtain an accurate representation of brain activity, and that the therapeutic potential of neural devices is limited at low spatiotemporal resolution. It is expected that future interfaces will integrate thousands of channels at relatively high sampling rates, making it crucial to operate at extremely low power.
Read the entire page →
From page 76...
... With only simple comparators as their core building blocks, DT classifiers are a preferable solution to reduce hardware design complexity. Using a gradientboosted ensemble of decision trees, we achieve a reasonable tradeoff between detection accuracy and implementation cost.
Read the entire page →
From page 77...
... Sens. 1 0.9 0.8 0.86 0.6 0.82 0.4 0.78 0.74 0.2 Average F1 score Sensitivity and specificity 0.7 DT SVM-LIN SVM-PLY3 KNN3 0 0 5 10 15 20 Classifier Patient number FIGURE 3  Comparison of predictive ability of different classification methods with an ensemble of 8 decision trees (DT)
Read the entire page →
From page 78...
... decision tree model, we introduce efficient hardware architectures and related training algorithms to predict the abnormal neurological states in various disorders, such as epilepsy, Parkinson's disease, and migraine. Such classifiers may allow the full integra
Read the entire page →
From page 79...
... and a greedy training algorithm to meet the delay constraints (bottom)
Read the entire page →
From page 80...
... 2010. A micropower EEG acquisition SoC with integrated feature extraction processor for a chronic seizure detection system.
Read the entire page →

Key Terms

  • seizure detection
  • decision trees
  • decision tree
  • classification methods
  • efficient feature

  • neural devices
  • machine learning
  • boosted ensemble
  • therapeutic neural
  • neural data

  • block diagram
  • intracranial eeg
  • gradient boosting
  • eeg acquisition
  • vector machine

  • support vector
  • extraction processor
  • conventional classification
  • learning models
  • acquisition soc

  • neural interfaces
  • hardware intensive
  • epileptic patients
  • chip integration
  • implement ensembles

  • ensemble sizes
  • emerging field
  • simple models
  • neural channels
  • space dimensionality


    • This material may be derived from roughly machine-read images, and so is provided only to facilitate research.
    More information on Chapter Skim is available.