Algorithms Predicting Attention and Memory Ability based on the Combination of Childrens Physiological Data

Abstract

Good performance is regarded as important element not only in workplace but also in daily activities. Performance of the human depends on the mental capacity and mental workload. Performance declines when the mental workload exceeds mental capacity. The point the mental capacity is exceeded by mental workload is regarded to as the cognitive redline of workload. Performance declines faster at this point, as task demand is greater than the mental capacity. Few studies of the cognitive redline of workload have been done. In addition, for good performance, mental workload is regarded as more important than physical workload. Especially, according to piagets cognitive development theory, children in concrete operational stage is critical for further learning ability that they develop their ability to distinguish between quality and quantity. However, the reason that mental workload is difficult to quantify through physiological measures, makes it more complicated to demonstrate the cognitive redline. When it comes to childrens development, physical change is visible and easy to identify but mental change is not. Moreover, EEG which is one of the representative measuring tool of physiological data requires accurate process of measuring and analyzing with the expert. HRV is relatively easy to measure but has limitation because it is indirect way of measuring brain signal. Above all things, many researches of real-time indicator measuring physiological data such as heart rate variability (HRV), skin conductance response (SCR) have been done sporadically but not integrated. Therefore, In this study I tried to demonstrate if I can predict the mental capacity (attention and memory ability) not mental workload with the EEG. In addition, with the combination of EEG and HRV, I tried to overcome disadvantages of physiological tool and tried to develop advanced algorithm which predicts mental capacity. Attention ability was measured with Stroop task, and memory ability was measured with digit span task. Elementary school students aged 6-13 were participated, whose brain development is in important phase according to Piaget theory. In conclusion, right-temporal EEG data significantly predicts attention score, and occipital EEG data significantly predicts memory score. I also analyzed brain wave EEG model, and found out beta EEG power significantly predicted attention score but not memory score. I also analyzed HRV data with all other physiological data to earn more predictable algorithms model. These data can be used as daily performance parameter of attention and memory ability. However, in the further study more number of population are needed to increase the accuracy of the model. Moreover, Application which can collect and analyze physiological data needs to be more sophisticated and needs to be properly connected to wearable devices.