Recognition and Dynamics of Changes in the Emotional States of Aviation Personnel in the Context of Aviation Safety Using Markov Chains

DOI

10.2991/978-94-6239-668-5_96How to use a DOI?

Keywords

Aviation Safety; Emotion Recognition; Markov Chains; Psychophysiological State; Convolutional Neural Networks (CNN)

Abstract

Modern aviation safety largely depends on the psychophysiological stability and emotional regulation of aviation personnel. Errors caused by emotional destabilization, stress, and fatigue are among the most common factors leading to incidents in both civil and military aviation. Pilots, air traffic controllers, and onboard operators perform their duties under conditions of high cognitive tension, information overload, and multitasking, where emotional fluctuations directly affect situational awareness, reaction speed, and the adequacy of decision-making. This study is devoted to the development of an integrated model for recognizing and analyzing the dynamics of changes in the emotional states of aviation personnel aimed at enhancing aviation safety. The proposed methodology combines emotion recognition using a convolutional neural network (CNN) with dynamic modeling of transitions between emotional states based on the framework of Markov chains. Seven basic emotions according to Paul Ekman are used as the target categories. The first subsystem the emotion recognition module is implemented using a CNN. Recognized emotions are treated as discrete system states reflecting the internal psycho-emotional condition of the operator. At the second level of the model, a first-order Markov chain is applied to quantitatively describe the probabilities of transitions between emotional states. Each transition probability reflects the temporal dynamics of emotional changes and serves as an indicator of the operator’s emotional stability. The proposed Markov model of emotional dynamics provides quantitative and predictive tools for assessing the emotional readiness and cognitive stability of aviation personnel. Integrating the emotion recognition module with probabilistic modeling enables real-time detection of stress growth, prediction of emotional exhaustion, and prevention of conditions that may lead to operational errors or threats to flight safety. In the future, the system is planned to be expanded through the use of non-homogeneous and hidden Markov chains (HMM, NHMM), as well as multi-agent analysis aimed at studying the group emotional synchronization of crews and controllers. Thus, the presented methodology establishes a foundation for next-generation intelligent aviation safety systems, in which human emotional dynamics are treated as measurable, predictable, and controllable variables that directly influence reliability and efficiency in complex human–machine environments.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - F. Taghiyeva
AU  - N. Huseynov
AU  - E. Asadov
PY  - 2026
DA  - 2026/05/14
TI  - Recognition and Dynamics of Changes in the Emotional States of Aviation Personnel in the Context of Aviation Safety Using Markov Chains
BT  - Proceedings of the International Conference on Current Problems in Engineering and Applied Sciences (ICCPEAS 2025)
PB  - Atlantis Press
SP  - 907
EP  - 916
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-668-5_96
DO  - 10.2991/978-94-6239-668-5_96
ID  - Taghiyeva2026
ER  -