Design an intelligent system based on a computational cognitive model using attention network task

Introduction: The attention is a gateway for learning and a limited resource. Attention cognitive model helps to perceive and use it efficiently. This research aimed to find an intelligent model for a different level of attention. Methods: Developing a cognitive model based on the attention network task and brain signals. The model builds on machine learning techniques. The initial research population consists of 92 adult volunteers who completed the Depression Anxiety Stress Scales test (DASS-21). Based on the test results, 31 subjects selected and invited to take Attention Network test and during the test, brain signals were captured for this purpose, Brain-computer Interface (BCI) was used and a model constructed based on different levels which used subject’s brain signal, reaction time and test result. Results: Data were classified based on different machine learning methods such as Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Adaboost. The correct classification rate for these classifiers is 68, 90, and 87 percent. Conclusion: The final model is selected based on the accuracy. So the KNN classifier has better generalization and it estimates test data better than other classifers. The desired Nero-cognitive model is based on the results and KNN classifiers are the best option for these types of cognitive models which is difficult to gather data and the dataset’s size are small. doi.org/10.30699/icss.22.1.81