Health monitoring technology in everyday situations is expected to improve the quality of life and supporting aging populations. One of the mental stress is health identification of individuals due to association with cognitive performances and health outcomes in younger and older adults. Here, we propose a model to identification of mental stress of younger and older adults in natural viewing situations. Our model includes two unique aspects: (i) Feature sets to better capture stress in natural viewing situations and (ii) An automated feature selection method to select a feature subset enabling the model to be robust to the target's age. To test our model, we collected eye-tracking image from younger and older adults as they before and after performing cognitive tasks. In our model detected the accuracy in this project.
