Human-building interaction under various indoor temperatures through neural-signal electroencephalogram (EEG) methods

In this study, potential of neural-signal electroencephalogram (EEG)-based methods for enhancing human building interaction under various indoor temperatures were explored. Correlations between EEG and subjective perceptions/tasks performance were experimentally investigated. Machine learning-based EEG pattern recognition was further studied. Results showed that the EEG frontal asymmetrical activity related well to the subjective questionnaire and objective tasks performance, which can be used as a more objective metric to corroborate traditional subjective questionnaire-based methods and task-based methods. Machine learning based EEG pattern recognition with linear discriminant analysis (LDA) classifiers can well classify the different mental states under different thermal conditions. Utilization of the EEG frontal asymmetrical activities and the machine learning-based EEG pattern recognition method as a feedback mechanism of occupants, which can be implemented on a routine basis, has a great potential to enhance the human-building interaction in a more objective and holistic way.