Brief episodes of momentarily falling asleep - microsleeps - can have fatal consequences, especially in the transportation sector. In this study, the EEG data of eight subjects, while performing a 1-D tracking task, were used to predict imminent microsleeps. A novel algorithm was developed to improve the accuracy of microsleep identification from two independent measures: tracking performance and face-video. The uncertain labels of gold-standard were then pruned out. Additionally, the state of microsleep at 0.25 s ahead was continuously predicted. Log-power spectral features were then extracted from EEG data. The most relevant features were selected by mutual information. Leave-one-subject-out was performed to test the classifier on an independent subject and this procedure was done for all the subjects. Two oversampling methods, synthetic minority oversampling technique (SMOTE) and adaptive sampling (ADASYN), were utilized to improve the training in the presence of imbalanced data. The best average area under the curve of receiver operating characteristic (AUCroc) of 0.90 was achieved using SMOTE oversampling over a 5.25 s window length, with a corresponding geometric mean (GM) of 0.74. ADASYN oversampling achieved the best sensitivity of 0.76 (cf. 0.70 for SMOTE), but with a lower specificity of 0.77 (cf. 0.86 for SMOTE).