Assessment of eye fatigue caused by head-mounted displays using eye-tracking

Table 6 Correlation between the regression results and the ground truth of eye fatigue

Feature	Correlation with epsilon regression				Correlation with nonlinear regression
Feature	Kernel 1	Kernel 2	Kernel 3	Kernel 4	Kernel 1	Kernel 2	Kernel 3	Kernel 4
Feature set 1	0.6271	0.6989	0.6807	0.0237	0.6266	0.6712	0.6414	0.0663
Feature set 2	0.7364	0.7616	0.7456	0.4662	0.7449	0.7713	0.7369	0.4217
Feature set 3	0.7416	0.7707	0.7548	0.5674	0.7471	0.7779	0.7551	0.5401
Feature set 4	0.7536	0.7853	0.7557	0.6317	0.7547	0.7827	0.7631	0.5926
Feature set 5	0.7621	0.7886	0.7681	0.6593	0.7556	0.7851	0.7663	0.6182
Feature set 6	0.8062	0.8435	0.8122	0.6751	0.8063	0.8316	0.8197	0.6375
Feature set 7	0.8489	0.8514	0.8313	0.6925	0.8416	0.8383	0.8398	0.6597
Feature set 8	0.8563	0.8552	0.8363	0.6946	0.8452	0.8423	0.8469	0.6656
Feature set 9	0.8575	0.8675	0.8421	0.7087	0.8559	0.8583	0.8483	0.6735
Feature set 10	0.8652	0.8737	0.8489	0.7104	0.8568	0.8651	0.8532	0.6857
Blink set	0.7655	0.7966	0.7745	0.4624	0.7541	0.7746	0.7609	0.4731
Mean	0.7837	0.8085	0.7864	0.5720	0.7808	0.7999	0.7847	0.5485

ISSN: 1475-925X