Affective Man-Machine Interface: Unveiling human emotions through biosignals

Egon van den Broek, Viliam Lisy, Joris H. Janssen, Joyce H.D.M. Westerink, Marleen H. Schut, Kees Tuinenbreijer

    Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

    47 Citations (Scopus)
    447 Downloads (Pure)

    Abstract

    As is known for centuries, humans exhibit an electrical profile. This profile is altered through various psychological and physiological processes, which can be measured through biosignals; e.g., electromyography (EMG) and electrodermal activity (EDA). These biosignals can reveal our emotions and, as such, can serve as an advanced man-machine interface (MMI) for empathic consumer products. However, such a MMI requires the correct classification of biosignals to emotion classes. This chapter starts with an introduction on biosignals for emotion detection. Next, a state-of-the-art review is presented on automatic emotion classification. Moreover, guidelines are presented for affective MMI. Subsequently, a research is presented that explores the use of EDA and three facial EMG signals to determine neutral, positive, negative, and mixed emotions, using recordings of 21 people. A range of techniques is tested, which resulted in a generic framework for automated emotion classification with up to 61.31% correct classification of the four emotion classes, without the need of personal profiles. Among various other directives for future research, the results emphasize the need for parallel processing of multiple biosignals.
    Original languageUndefined
    Title of host publicationBiomedical Engineering Systems and Technologies
    EditorsA. Fred, J. Filipe, H. Gamboa
    Place of PublicationBerlin
    PublisherSpringer
    Pages21-47
    Number of pages27
    ISBN (Print)978-3-642-11720-6
    DOIs
    Publication statusPublished - 2010

    Publication series

    NameCommunications in Computer and Information Science
    PublisherSpringer Verlag
    Number52
    Volume52
    ISSN (Print)1865-0929

    Keywords

    • METIS-270950
    • Man-machine interaction
    • Machine Learning
    • IR-72477
    • Affect
    • HMI-CI: Computational Intelligence
    • Emotion
    • Physiological Signals
    • EWI-18234
    • HMI-MI: MULTIMODAL INTERACTIONS
    • HMI-IE: Information Engineering
    • BioSignals

    Cite this