{
  "id": "1412.6502",
  "version": "v1",
  "published": "2014-12-19T20:00:38.000Z",
  "updated": "2014-12-19T20:00:38.000Z",
  "title": "Detecting Epileptic Seizures from EEG Data using Neural Networks",
  "authors": [
    "Siddharth Pramod",
    "Adam Page",
    "Tinoosh Mohsenin",
    "Tim Oates"
  ],
  "comment": "Submission for ICLR 2015, workshop track",
  "categories": [
    "cs.LG",
    "cs.NE",
    "q-bio.NC"
  ],
  "abstract": "We explore the use of neural networks trained with Dropout in predicting Epileptic seizures from Electroencephalographic Data (Scalp EEG). The input to the neural network is a set of 9 pre-defined features extracted from 1-second non-overlapping windows in each of 14 channels per patient selected for the experiment. The models in our experiments achieve high sensitivity and specificity on patient records not used in the training process. This is demonstrated using Leave-One-Out-Cross-Validation across patient records.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2014-12-19T20:00:38.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "neural network",
      "detecting epileptic seizures",
      "eeg data",
      "experiments achieve high sensitivity",
      "patient records"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable",
      "adsabs": "2014arXiv1412.6502P"
    }
  }
}