Figures & data
Figure 1 Result of automatic segmentation using fractal dimension on occipital area electrode signal from a patient with Jeavons syndrome.
Abbreviations: EEG, electroencephalography; FDFV, fractal dimension feature vector.
![Figure 1 Result of automatic segmentation using fractal dimension on occipital area electrode signal from a patient with Jeavons syndrome.](/cms/asset/23fddc05-e37e-40a3-b688-4ad71fa2efcb/dndt_a_167841_f0001_c.jpg)
Figure 2 Schematic flow chart for set extraction and further processing (compression, classification using GP+SVM).
![Figure 2 Schematic flow chart for set extraction and further processing (compression, classification using GP+SVM).](/cms/asset/a0ba4b5a-f031-4e1d-b023-0db78564390e/dndt_a_167841_f0002_c.jpg)
Figure 3 Population tree of suggested algorithm with two F functions (nodes) that make up new flagged vectors that are expressed by the offspring.
![Figure 3 Population tree of suggested algorithm with two F functions (nodes) that make up new flagged vectors that are expressed by the offspring.](/cms/asset/182588b0-0cea-4f20-bacf-142df233f292/dndt_a_167841_f0003_b.jpg)
Figure 4 GP–SVM block scheme.
![Figure 4 GP–SVM block scheme.](/cms/asset/b1a248e7-2d10-4c44-9e7a-232f67b9832d/dndt_a_167841_f0004_b.jpg)
Table 1 Clinically diagnosed epilepsy types of patients
Table 2 Frequency bands for four-level DWT decomposition
Figure 5 Four-level DWT decomposition for interictal EEG.
![Figure 5 Four-level DWT decomposition for interictal EEG.](/cms/asset/131e93a6-6bd6-4197-b547-a07f74c2ab60/dndt_a_167841_f0005_c.jpg)
Figure 6 Four-level DWT decomposition for ictal EEG.
![Figure 6 Four-level DWT decomposition for ictal EEG.](/cms/asset/c5dd9285-bd0d-4c1d-be68-5d5ca985354e/dndt_a_167841_f0006_c.jpg)
Table 3 Basic set feature vector mapping
Figure 7 Training stage of population tree samples separation. Population tree descendants combining the input features x9+x10 are clearly distinguishable from the population member genetically combining the input features x17+x18.
![Figure 7 Training stage of population tree samples separation. Population tree descendants combining the input features x9+x10 are clearly distinguishable from the population member genetically combining the input features x17+x18.](/cms/asset/f218a8d1-78df-4a30-83f4-7787c83b40f1/dndt_a_167841_f0007_c.jpg)
Figure 8 Confusion matrix for dataset shown in .
![Figure 8 Confusion matrix for dataset shown in Figure 7.](/cms/asset/d76e0515-865e-4714-a861-b9842c0dc974/dndt_a_167841_f0008_c.jpg)
Table 4 Classification accuracy
Table 5 Compressed feature vector with compression level 5
Table 6 Compressed and basic feature vectors-based classification performance comparison