SUPPRESSION OF COGNITIVE BIASES IN OF A PERSON AND HIS INTENTION IDENTIFICATION TASK FOR NEURO-COMPUTER SYSTEMS
DOI:
https://doi.org/10.17721/2519-481X/2024/84-10Keywords:
neurosecurity, non-invasive neurocomputer interface, EEG-identification of intention, mitigation of cognitive biasesAbstract
The study is devoted to the problem of security of information systems in the case of recognition of a person and his intentions using an electroencephalogram. The method is designed for a non-invasive neurocomputer interface, can be used in multi-level research (emotional intelligence, memory development, monitoring well-being, optimization of decision-making), which is its advantage. The versatility of the neuro-computer interface allows you to use it for several purposes at the same time, combining different methods of analysis of one data set (encephalogram, response time and adequacy). An applied combined approach to quality assessment based on design indicators based on the results of previous studies, taking into account the specifics of user tasks and roles, data processing methods, and the objectivity of the selected models, is proposed. The experiments were carried out in simulated conditions in two stages of 3 months each based on the results of neuroplasticity training and solving tasks of obtaining access in the presence of rights and in the conditions of an unexpected request. The individual style of performing tasks is taken into account, and the emotion recognition strategy based on the Chikszentmihalyi’s model is used to predict the intention. The results meet modern standards of neuroethics and neurolaw. Cognitive biases can negatively affect the task of identifying a person and his intentions, for this, mitigation methods are proposed. The ease of use of the model lies in the simple interpretation of the collected data. Frontal alpha asymmetry, event-related potential, and alpha-beta band power ratio of synchronization rhythms were used for assessment. The results are convincing that the expected implementation can be effective. The work takes into account the rich experience of previous research on the identification of a person and his intentions based on the analysis of the electroencephalogram. In this study, the impermanence of the EEG image ("brain imprint") is taken into account and attention is focused on the importance of its renewal, an experiment was conducted in the course of a comprehensive study. The result is a substantiation of requirements for the frequency and procedure of updating "brain prints", proposed indicators of the quality of recognition, proposals for ranking the level of neuroliteracy based on testing typical activities. In order to study the intention of a person, it is proposed to study the background cognitive states, taking into account their duration and intensity of typical patterns of synchronization rhythms, on the basis of which machine learning of the cognitive bias suppression model was carried out. Data were compared with moments of loss of control, the need to rethink and update brain synchronization networks was taken into account. These results are currently basic and require special attention in further experiments, their thorough investigation will be important for improving the quality of any research on the use of neuro-computer interfaces. The risk of unwanted cognitive states and the appearance of cognitive biases has been assessed, and requirements for taking tests are provided to prevent such situations. The influence of experience and training level of neurocomputer literacy, individual suitability to work in neuro-computer environments (in particular, neurosignal power and control of mental efforts, cognitive properties and emotional backgrounds) are taken into account.
References
1. Brunner, Clemens, et al. “BNCI Horizon 2020: Towards a Roadmap for the BCI Community.” Brain-Computer Interfaces, vol. 2, no. 1, 2015
2. Yang, YY., Hwang, A.HC., Wu, CT. et al. Person-identifying brainprints are stably embedded in EEG mindprints. Sci Rep 12, 17031 (2022). https://doi.org/10.1038/s41598-022-21384-0
3. Jayarathne, I., Cohen, M., & Amarakeerthi, S. “Person identification from EEG using various machine learning techniques with inter-hemispheric amplitude ratio.” PLoS ONE, vol. 15, no. 9, 2020, e0238872. DOI: 10.1371/journal.pone.02388
4. López-Silva, Pablo, and Luca Valera, editors. Protecting the Mind: Challenges in Law, Neuroprotection, and Neurorights. Springer International Publishing, 2023.
5. Nam, Chang S., Anton Nijholt, and Fabien Lotte, editors. Brain–Computer Interfaces Handbook: Technological and Theoretical Advances. 1st ed., CRC Press, 2018.
6.Mykhalchuk V., Druzhynin V. Targeting mind in challengable conditions of biased nature of performance (preliminary results on individual experience). 1st international scientific and practical conference «Information Systems and Technology: Results and Prospects» (IST 2024)", Kyiv, 2024.
7. Imagerie Cérébrale: Enjeux Épistémologiques, Éthiques Et Politiques, Espace Ethique d’Ile de France, 2017. 97p.
8. Park Sang-Eon et al. Digital Assessment of Cognitive-Affective Biases Related to Mental Health. PLOS Digital Health, vol. 1, no. 1, 2024, article e0000595, https://doi.org/10.1371/journal.pdig.0000595.
9. Schreiner, Leonhard, et al. “Mapping of the Central Sulcus Using Non-Invasive Ultra-High-Density Brain Recordings.” Scientific Reports, vol. 14, no. 6527, 19 Mar. 2024, doi:10.1038/s41598-024-57167-y.
10. Korteling, J. E., Gerritsma, J. Y. J., & Toet, A. (2021)1. Retention and transfer of cognitive bias mitigation interventions: A systematic literature study23. Frontiers in Psychology, 12, 629354. https://doi.org/10.3389/fpsyg.2021.629354
11.Mykhalchuk, V. “Cognitive Design of Educational Brain-Computer Interfaces.” CEUR Workshop Proceedings, vol. 3309, 2022, 1. DOI: 10.1007/978-3-319-64274-1_8.
12. Siritzky M. Emma. Standard Experimental Paradigm Designs and Data Exclusion Practices in Cognitive Bias Research. Cognitive Research: Principles and Implications, vol. 8, no. 1, 2023, article 520, https://doi.org/10.1186/s41235-023-00520-y.
13. Tmienova N., Mykhalchuk V. Brain-Computer Interface as Tool of Cognitive Optimization (Case of Biases Reducing in Decision-Making and Control Improvement). CEUR Workshop Proceedings, vol. 3309, 2022, 1. DOI: 10.1007/978-3-319-64274-1_8.
14. A Review on Evaluating Mental Stress by Deep Learning Using EEG Signals. Proceedings of the 1st International Scientific and Practical Conference ‘Information Systems and Technology: Results and Prospects’ (IST 2024), 2024, pp. 45-56.
15. An Evaluation of Mental Workload with Frontal EEG. PLOS ONE, vol. 12, no. 4, 2017, article e0174949, https://doi.org/10.1371/journal.pone.0174949.
17.Mental Workload Monitoring: New Perspectives from Neuroscience. Advances in Neuroergonomics and Cognitive Engineering, edited by Hasan Ayaz and Umer Asgher, Springer, 2020, pp. 1-12, https://doi.org/10.1007/978-3-030-32423-0_1.
18. Real-Time Mental Workload Estimation Using EEG. Advances in Neuroergonomics and Cognitive Engineering, edited by Hasan Ayaz and Umer Asgher, Springer, 2020, pp. 13-24, https://doi.org/10.1007/978-3-030-32423-0_2.
