Excessive sleep arousal affects one's sleep quality that would induce disease. Polysomnography is a powerful tool for sleep related monitoring. Clinically, there are being two kinds of causes on sleep arousal. One is apnea and hypopnea related arousal and the other is non-apnea and nonhypopnea arousal. The latter is relatively hidden and is difficult to determine in clinical. We aim to classify the sleep arousal caused by non-apnea and non-hypopnea from apnea and hypopnea related arousal. We propose an improved ensemble deep learning architecture that use a positional embedding based multi-head attention method to keep temporal relations of multimodal physiological signals. The experimental datasets are based on an open access dataset from the public cardiology challenge 2018. We conduct several groups of comparison experiments among our proposed convolutional-residual network with positional embedding and multi-head attention (CRPEMA) method and other methods that includes methods presented on the cardiology challenge 2018. The results show that CRPEMA has high efficiency and accuracy. When the parameters decrease by more than 50%, the accuracy is keeping improved. Experiment results reflect that CRPEMA outperforms others and obtains the Area Under the Precision-Recall curve (AUPRC) of 0.391.

High-definition transcranial direct current stimulation (HD-tDCS) is a valid brain stimulation technology to optimize cognitive function. Recent evidence indicates that single anodal tDCS session enhances attention; however, the variation in attention produced by repeated anodal HD-tDCS over a longer period of time has not been explored. We examined the modulation of attention function in healthy young participants (39 young adults) who received repeated HD-tDCS sustained for 4 weeks. The results showed a robust benefit of anodal HD-tDCS on executive control and psychomotor efficiency, but not on orienting, alerting, or selective attention (inhibition); the benefit increased successively over 4 weeks; and the enhancement on executive control of each week was significant compared to baseline in the anodal group. In addition, the subjects’ performances on the test of executive control and psychomotor efficiency gradually restored to the initial level in the sham group, which appeared obviously from week 3 (after 9 interventions), but the improvement of attention in the anodal group was persistent. We conclude that repeated anodal HD-tDCS provides a positive benefit on executive control and psychomotor efficiency and has obvious accumulative effect after 9 or more times intervention compared to sham HD-tDCS. Additionally, our findings might provide pivotal guidance for the formulation of a strategy for the use of repeated anodal HD-tDCS to modulate on attention function.