International Scholarly Research Notices

Research Article

Comparison of Baseline Cepstral Vector and Composite Vectors in the Automatic Seizure Detection Using Probabilistic Neural Networks

Table 4

Descriptive results of PNN analysis using composite cepstral vector (including velocity and acceleration coefficients) for discriminating different classification problems for , , and .
Classification problemAverage accuracy%
196.2
293.3
393.9
493.8
592.1
693.8
791.8