Mind-Reading AI : Re-Create Scenario from Brain Database

EasyChair Preprint 1774

Abstract

An electroencephalography (EEG) based Brain Computer Interface (BCI) enables people to communicate with the outside world by interpreting the EEG signals of their brains.  In their study, Xiang Zhang et all, proposed a novel deep neural network based learning framework that affords perceptive insights into the relationship between the EEG data and brain activities and designed a joint convolutional recurrent neural network that simultaneously learns robust high-level feature presentations through low-dimensional dense embeddings from raw EEG signals. The proposed approach has been to use results of this study as it is and use simulated conditions as true input for our  study. We have  developed a  method called “deep text reconstruction,” which uses a reconstruction algorithm capable of “decoding” a “hierarchy” of textual information from different sources, such as statements, facts, etc. Our algorithm also optimizes the output of the decoded text  so that it more closely resembles the actual or true testimony, in combination with a multiple-layered feed forward neural network (NN) to simulate the same processes that occur when a human brain perceives language or text.   The results show that our approach performs a baseline  and the  state-of-the art methods, yielding a good classification accuracy. The applicability of our proposed approach is further demonstrated with a practical  system for crime detection.

Keyphrases: Artificial Intelligence, Crime Detection, mind-reading, word vectors

@booklet{EasyChair:1774,
  author    = {Poondru Prithvinath Reddy},
  title     = {Mind-Reading AI :  Re-Create Scenario  from  Brain Database},
  howpublished = {EasyChair Preprint 1774},
  year      = {EasyChair, 2019}}