Further, a second experiment demonstrated that the classification performance for patients with large time gaps between preictal and interictal recordings was noticeably higher than the classification performance for patients with contiguous preictal and interictal files.
Also, the classification performance on stimuli and/or responses using all the correct trials was higher than the classification on responses using all the incorrect trials in the left preCG, although the difference was not significant (t15=1.447, P=0.168, paired t-test).
Through the comparison of the results of the SVM and BP classification models, the SME credit risk assessment based on SVM from the perspective of SCF results in a high classification accuracy of 93.65 %, which is significantly higher than the classification accuracy of 55.56 % of the BP neural network.
This was much higher than the classification accuracies of IPRE (C) and other existing algorithms (see Table 4).
In this comparison, the accuracy of classifier learnt by PLF is 91.56% which is about 18% higher than the classification accuracy with CLF (73.44%).
A classification accuracy of 82 ± 7% for PWP group was very similar to the classification accuracy of 82 ± 4% for AB group and was higher than the classification accuracy of 78 ± 5% for PNP group (Fig. 4d).
When classifier was based on a configuration with only 4 common spatial patterns (Fig. 4b), the average BCI classification accuracy for PWP group was 74 ± 9% which was comparable with the average classification accuracy for AB group of 74 ± 7% and was higher than the classification accuracy for the PNP group of 69 ± 8%.
When the number of common spatial patterns increased to 14 (Fig. 4c), the average BCI classification accuracy for PWP group was 78 ± 9% which was comparable with the average classification accuracy for AB group of 76 ± 5% and was higher than the classification accuracy for the PNP group of 73±7%7% (Fig. 4c).
Through simple comparison, Antweiler and Frank (2004) found that the accuracy of algorithm classification is actually higher than that of manual classification.
Although not statistically different from the conventional classification of the late images, the average accuracy resulting from signature expansion was statistically higher than that of conventional classification of early images.
The area under the ROC curve of this prediction tool was much higher than that of ATS/IDSA classification (0.69 vs. 0.54; P < 0.001).
