EEG-Classification / Git / Diff of /README.md

Models:

ReneeD/

EEG-Classification

Downloads: 1

Diff of /README.md [c01e04] .. [829a08]

Switch to unified view


...


## Network Architecture  
A convolutional neural network was iteratively constructed and tuned to give the best classification accuracy with the data availible. The final architecture is shown below.   






## Results and Discussion
The results obtained are encouraging. Without even using a recurrent neural network (which is the next logical step, see [1]), the CNN is able to correctly classify the test subject’s brain-state about 8.5 times out of 10. This is likely high enough to enable a new level of performance with brain-computer interface (BCI) technologies.   

However, the best results were obtained when the network was trained on samples from the same recording session. While this may be practical for basic brain research, it would be less practical for use in BCI technology.   

	a/README.md		b/README.md
	...		...
53		53
54		54
55	## Network Architecture	55	## Network Architecture
56	A convolutional neural network was iteratively constructed and tuned to give the best classification accuracy with the data availible. The final architecture is shown below.	56	A convolutional neural network was iteratively constructed and tuned to give the best classification accuracy with the data availible. The final architecture is shown below.
57		57
58	#### Table 1: Summary of Convolutional Neural Network in Keras	58
59
60	![alt text][image1]
61
62		59
63	## Results and Discussion	60	## Results and Discussion
64	The results obtained are encouraging. Without even using a recurrent neural network (which is the next logical step, see [1]), the CNN is able to correctly classify the test subject’s brain-state about 8.5 times out of 10. This is likely high enough to enable a new level of performance with brain-computer interface (BCI) technologies.	61	The results obtained are encouraging. Without even using a recurrent neural network (which is the next logical step, see [1]), the CNN is able to correctly classify the test subject’s brain-state about 8.5 times out of 10. This is likely high enough to enable a new level of performance with brain-computer interface (BCI) technologies.
65		62
66	However, the best results were obtained when the network was trained on samples from the same recording session. While this may be practical for basic brain research, it would be less practical for use in BCI technology.	63	However, the best results were obtained when the network was trained on samples from the same recording session. While this may be practical for basic brain research, it would be less practical for use in BCI technology.