Decoding mental states in bistable perception by using source based wavelet features

Susmita Sen, Katsumi Watanabe, Joydeep Bhattacharya, Goutam Saha

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    This work presents an efficient application of machine learning and signal processing algorithms in decoding the mental states from brain signals. We decoded two internal mental states, transition and maintenance, representing the process of switching and maintaining a perception in bistable perception, respectively. The underlying sources were reconstructed from the Magnetoencephalogram (MEG) signals recorded from human participants while they were presented with six different conditions of bistable stimuli. We extracted features using complex Morlet wavelet transform that captured the temporal dynamics of large scale brain oscillations in the source domain. The mental states were predicted on a trial-by-Trial basis using Support Vector Machine (SVM) and Artificial Neural Network (ANN) classifiers along with Fisher's ratio based feature selection technique. We achieved accuracies of 75.65% and 74.58% using SVM and ANN classifier, respectively. The analysis also exhibits the involvement of the sources of parietal, temporal and cerebellum areas in characterizing the two mental processes.

    Original languageEnglish
    Title of host publication2017 IEEE Calcutta Conference, CALCON 2017 - Proceedings
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages144-149
    Number of pages6
    Volume2018-January
    ISBN (Electronic)9781538637456
    DOIs
    Publication statusPublished - 2018 Feb 2
    Event2017 IEEE Calcutta Conference, CALCON 2017 - Kolkata, India
    Duration: 2017 Dec 22017 Dec 3

    Other

    Other2017 IEEE Calcutta Conference, CALCON 2017
    CountryIndia
    CityKolkata
    Period17/12/217/12/3

    Fingerprint

    Support vector machines
    Decoding
    Brain
    Wavelets
    Classifiers
    Neural networks
    Artificial Neural Network
    Support Vector Machine
    Classifier
    Wavelet transforms
    Cerebellum
    Learning systems
    Feature extraction
    Signal processing
    State Transition
    Feature Selection
    Wavelet Transform
    Signal Processing
    Machine Learning
    Maintenance

    Keywords

    • ANN
    • Bistable Perception
    • Decoding
    • MEG
    • Single-Trial Classification
    • Source Reconstruction
    • SVM

    ASJC Scopus subject areas

    • Energy Engineering and Power Technology
    • Electrical and Electronic Engineering
    • Control and Optimization

    Cite this

    Sen, S., Watanabe, K., Bhattacharya, J., & Saha, G. (2018). Decoding mental states in bistable perception by using source based wavelet features. In 2017 IEEE Calcutta Conference, CALCON 2017 - Proceedings (Vol. 2018-January, pp. 144-149). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CALCON.2017.8280713

    Decoding mental states in bistable perception by using source based wavelet features. / Sen, Susmita; Watanabe, Katsumi; Bhattacharya, Joydeep; Saha, Goutam.

    2017 IEEE Calcutta Conference, CALCON 2017 - Proceedings. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. p. 144-149.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Sen, S, Watanabe, K, Bhattacharya, J & Saha, G 2018, Decoding mental states in bistable perception by using source based wavelet features. in 2017 IEEE Calcutta Conference, CALCON 2017 - Proceedings. vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 144-149, 2017 IEEE Calcutta Conference, CALCON 2017, Kolkata, India, 17/12/2. https://doi.org/10.1109/CALCON.2017.8280713
    Sen S, Watanabe K, Bhattacharya J, Saha G. Decoding mental states in bistable perception by using source based wavelet features. In 2017 IEEE Calcutta Conference, CALCON 2017 - Proceedings. Vol. 2018-January. Institute of Electrical and Electronics Engineers Inc. 2018. p. 144-149 https://doi.org/10.1109/CALCON.2017.8280713
    Sen, Susmita ; Watanabe, Katsumi ; Bhattacharya, Joydeep ; Saha, Goutam. / Decoding mental states in bistable perception by using source based wavelet features. 2017 IEEE Calcutta Conference, CALCON 2017 - Proceedings. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. pp. 144-149
    @inproceedings{1149792d19d849c08b5d60071a0fce23,
    title = "Decoding mental states in bistable perception by using source based wavelet features",
    abstract = "This work presents an efficient application of machine learning and signal processing algorithms in decoding the mental states from brain signals. We decoded two internal mental states, transition and maintenance, representing the process of switching and maintaining a perception in bistable perception, respectively. The underlying sources were reconstructed from the Magnetoencephalogram (MEG) signals recorded from human participants while they were presented with six different conditions of bistable stimuli. We extracted features using complex Morlet wavelet transform that captured the temporal dynamics of large scale brain oscillations in the source domain. The mental states were predicted on a trial-by-Trial basis using Support Vector Machine (SVM) and Artificial Neural Network (ANN) classifiers along with Fisher's ratio based feature selection technique. We achieved accuracies of 75.65{\%} and 74.58{\%} using SVM and ANN classifier, respectively. The analysis also exhibits the involvement of the sources of parietal, temporal and cerebellum areas in characterizing the two mental processes.",
    keywords = "ANN, Bistable Perception, Decoding, MEG, Single-Trial Classification, Source Reconstruction, SVM",
    author = "Susmita Sen and Katsumi Watanabe and Joydeep Bhattacharya and Goutam Saha",
    year = "2018",
    month = "2",
    day = "2",
    doi = "10.1109/CALCON.2017.8280713",
    language = "English",
    volume = "2018-January",
    pages = "144--149",
    booktitle = "2017 IEEE Calcutta Conference, CALCON 2017 - Proceedings",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",

    }

    TY - GEN

    T1 - Decoding mental states in bistable perception by using source based wavelet features

    AU - Sen, Susmita

    AU - Watanabe, Katsumi

    AU - Bhattacharya, Joydeep

    AU - Saha, Goutam

    PY - 2018/2/2

    Y1 - 2018/2/2

    N2 - This work presents an efficient application of machine learning and signal processing algorithms in decoding the mental states from brain signals. We decoded two internal mental states, transition and maintenance, representing the process of switching and maintaining a perception in bistable perception, respectively. The underlying sources were reconstructed from the Magnetoencephalogram (MEG) signals recorded from human participants while they were presented with six different conditions of bistable stimuli. We extracted features using complex Morlet wavelet transform that captured the temporal dynamics of large scale brain oscillations in the source domain. The mental states were predicted on a trial-by-Trial basis using Support Vector Machine (SVM) and Artificial Neural Network (ANN) classifiers along with Fisher's ratio based feature selection technique. We achieved accuracies of 75.65% and 74.58% using SVM and ANN classifier, respectively. The analysis also exhibits the involvement of the sources of parietal, temporal and cerebellum areas in characterizing the two mental processes.

    AB - This work presents an efficient application of machine learning and signal processing algorithms in decoding the mental states from brain signals. We decoded two internal mental states, transition and maintenance, representing the process of switching and maintaining a perception in bistable perception, respectively. The underlying sources were reconstructed from the Magnetoencephalogram (MEG) signals recorded from human participants while they were presented with six different conditions of bistable stimuli. We extracted features using complex Morlet wavelet transform that captured the temporal dynamics of large scale brain oscillations in the source domain. The mental states were predicted on a trial-by-Trial basis using Support Vector Machine (SVM) and Artificial Neural Network (ANN) classifiers along with Fisher's ratio based feature selection technique. We achieved accuracies of 75.65% and 74.58% using SVM and ANN classifier, respectively. The analysis also exhibits the involvement of the sources of parietal, temporal and cerebellum areas in characterizing the two mental processes.

    KW - ANN

    KW - Bistable Perception

    KW - Decoding

    KW - MEG

    KW - Single-Trial Classification

    KW - Source Reconstruction

    KW - SVM

    UR - http://www.scopus.com/inward/record.url?scp=85047392618&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85047392618&partnerID=8YFLogxK

    U2 - 10.1109/CALCON.2017.8280713

    DO - 10.1109/CALCON.2017.8280713

    M3 - Conference contribution

    AN - SCOPUS:85047392618

    VL - 2018-January

    SP - 144

    EP - 149

    BT - 2017 IEEE Calcutta Conference, CALCON 2017 - Proceedings

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -