Automatic detection of cognitive events using machine learning and understanding models’ interpretations of human cognition
Abstract The pupillary response is a valuable indicator of cognitive workload, capturing fluctuations in attention and arousal governed by the autonomic nervous system. Cognitive events, defined as the initiation of mental processes, are closely linked to cognitive workload as they trigger cognitive...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-08-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-16165-4 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849226390333816832 |
|---|---|
| author | Quang Dang Murat Kucukosmanoglu Michael Anoruo Golshan Kargosha Sarah Conklin Justin Brooks |
| author_facet | Quang Dang Murat Kucukosmanoglu Michael Anoruo Golshan Kargosha Sarah Conklin Justin Brooks |
| author_sort | Quang Dang |
| collection | DOAJ |
| description | Abstract The pupillary response is a valuable indicator of cognitive workload, capturing fluctuations in attention and arousal governed by the autonomic nervous system. Cognitive events, defined as the initiation of mental processes, are closely linked to cognitive workload as they trigger cognitive responses. In this study, we detect cognitive events for the task-evoked pupillary response across four domains (vigilance, emotion processing, numerical reasoning, and short-term memory). The problem is framed as a binary classification. We train one generalized model and four task-specific models on 1-s pupil diameter and gaze position segments. Five models achieve MCC between 0.43 and 0.75. We report three key findings: (1) the generalized model reduces the specificity to enhance the sensitivity, illustrating the trade-off from specialization to generalization; (2) the permutation feature importance analyses show that both pupil dilation and gaze position contribute to model predictions, with task-specific models focusing on task-specific structure patterns to predict while the generalized model is using human cognitive responses; and (3) in an online simulation environment, models performance decreases by approximately 0.05 on MCC. The findings highlight the potential of machine learning applied to pupillary signals for rapid, individualized detection of cognitive events. |
| format | Article |
| id | doaj-art-e5cc45f1a8614da5aa007f6faf391518 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-e5cc45f1a8614da5aa007f6faf3915182025-08-24T11:26:00ZengNature PortfolioScientific Reports2045-23222025-08-0115111310.1038/s41598-025-16165-4Automatic detection of cognitive events using machine learning and understanding models’ interpretations of human cognitionQuang Dang0Murat Kucukosmanoglu1Michael Anoruo2Golshan Kargosha3Sarah Conklin4Justin Brooks5Department of Computer Science and Electrical Engineering, University of Maryland, Baltimore CountyD-Prime LLCDepartment of Computer Science and Electrical Engineering, University of Maryland, Baltimore CountyD-Prime LLCCenter for Women’s Biobehavioral Health Research, Department of Psychiatry, University of Pittsburgh Medical CenterDepartment of Computer Science and Electrical Engineering, University of Maryland, Baltimore CountyAbstract The pupillary response is a valuable indicator of cognitive workload, capturing fluctuations in attention and arousal governed by the autonomic nervous system. Cognitive events, defined as the initiation of mental processes, are closely linked to cognitive workload as they trigger cognitive responses. In this study, we detect cognitive events for the task-evoked pupillary response across four domains (vigilance, emotion processing, numerical reasoning, and short-term memory). The problem is framed as a binary classification. We train one generalized model and four task-specific models on 1-s pupil diameter and gaze position segments. Five models achieve MCC between 0.43 and 0.75. We report three key findings: (1) the generalized model reduces the specificity to enhance the sensitivity, illustrating the trade-off from specialization to generalization; (2) the permutation feature importance analyses show that both pupil dilation and gaze position contribute to model predictions, with task-specific models focusing on task-specific structure patterns to predict while the generalized model is using human cognitive responses; and (3) in an online simulation environment, models performance decreases by approximately 0.05 on MCC. The findings highlight the potential of machine learning applied to pupillary signals for rapid, individualized detection of cognitive events.https://doi.org/10.1038/s41598-025-16165-4Cognitive events detectionCognitive classificationFeature importanceNeural networksExplainable AIMachine learning |
| spellingShingle | Quang Dang Murat Kucukosmanoglu Michael Anoruo Golshan Kargosha Sarah Conklin Justin Brooks Automatic detection of cognitive events using machine learning and understanding models’ interpretations of human cognition Scientific Reports Cognitive events detection Cognitive classification Feature importance Neural networks Explainable AI Machine learning |
| title | Automatic detection of cognitive events using machine learning and understanding models’ interpretations of human cognition |
| title_full | Automatic detection of cognitive events using machine learning and understanding models’ interpretations of human cognition |
| title_fullStr | Automatic detection of cognitive events using machine learning and understanding models’ interpretations of human cognition |
| title_full_unstemmed | Automatic detection of cognitive events using machine learning and understanding models’ interpretations of human cognition |
| title_short | Automatic detection of cognitive events using machine learning and understanding models’ interpretations of human cognition |
| title_sort | automatic detection of cognitive events using machine learning and understanding models interpretations of human cognition |
| topic | Cognitive events detection Cognitive classification Feature importance Neural networks Explainable AI Machine learning |
| url | https://doi.org/10.1038/s41598-025-16165-4 |
| work_keys_str_mv | AT quangdang automaticdetectionofcognitiveeventsusingmachinelearningandunderstandingmodelsinterpretationsofhumancognition AT muratkucukosmanoglu automaticdetectionofcognitiveeventsusingmachinelearningandunderstandingmodelsinterpretationsofhumancognition AT michaelanoruo automaticdetectionofcognitiveeventsusingmachinelearningandunderstandingmodelsinterpretationsofhumancognition AT golshankargosha automaticdetectionofcognitiveeventsusingmachinelearningandunderstandingmodelsinterpretationsofhumancognition AT sarahconklin automaticdetectionofcognitiveeventsusingmachinelearningandunderstandingmodelsinterpretationsofhumancognition AT justinbrooks automaticdetectionofcognitiveeventsusingmachinelearningandunderstandingmodelsinterpretationsofhumancognition |