This paper is devoted to the relevant problem of the astronaut's emotional states identification. The latest research in this domain have revealed the tendency of the emotional state definition via facial expression recognition. Besides, some other technologies are applied: heartrate monitors, brain activity analyzers, speech tone recognition, etc. Nevertheless, the problem of the emotional state monitoring relates to the classification one, so, a wide range of solutions has been proposed, including artificial neural networks, K-nearest neighbors, fuzzy logic and others. The main contribution of this paper is the development of the cognitive-map based classifier. The results of testing demonstrate the robustness and the adequacy of the cognitive map proposed.

本文致力于宇航员情绪状态识别的相关问题。在该领域的最新研究已经揭示了通过面部表情识别来定义情绪状态的趋势。此外，还应用了其他技术：心率监测器，脑活动分析器，语音识别等。然而，情绪状态监测的问题与分类有关，因此，提出了广泛的解决方案，包括人工神经网络。网络，K近邻，模糊逻辑等。本文的主要贡献是基于认知图的分类器的发展。测试结果证明了所提出的认知图的鲁棒性和充分性。