Backpropagation Artificial Neural Network To Detect Hyperthermic Seizures In Rats



Figure-1 : S chematic diagram of patter n recognition by ANN.

For the present work, the error tolerance was assigned as 0.001 to activate the network and the network was
trained for 1 million of iterations with different training sets having variable number of training patterns. The ANN
was trained with a training data file containing 100 training patterns (same number of seizures and normal
patterns) arranged randomly. After training, the network was tested for other files having patterns which were not
present during training session. The performance of the network in detecting these events (normal and seizure)
was calculated with help of following formula.

Number of correctly classified patterns

Performance of ANN(%) =    τota∣ number of patterns tested          X 100

The results of the seizure and normal events detected by the network compared with those detected manually are
summarized in the Table-1 . Manually detected events were taken as standard and agreement per centage represent
the percentage of epochs in which ANN detected seizure or normal events agreed with manually detected ones.



More intriguing information

1. A Note on Costly Sequential Search and Oligopoly Pricing (new title: Truly Costly Sequential Search and Oligopolistic Pricing,)
2. Developmental changes in the theta response system: a single sweep analysis
3. Permanent and Transitory Policy Shocks in an Empirical Macro Model with Asymmetric Information
4. How do investors' expectations drive asset prices?
5. Wirtschaftslage und Reformprozesse in Estland, Lettland, und Litauen: Bericht 2001
6. The name is absent
7. The name is absent
8. Ronald Patterson, Violinist; Brooks Smith, Pianist
9. Death as a Fateful Moment? The Reflexive Individual and Scottish Funeral Practices
10. Opciones de política económica en el Perú 2011-2015