Human Identification with Electroencephalogram (EEG) Signal Processing

Xu Huang, Salahiddin Altahat, Dat Tran, Dharmendra Sharma

    Research output: A Conference proceeding or a Chapter in BookConference contribution

    15 Citations (Scopus)

    Abstract

    Human identification becomes huge demand in particular for the security related areas. Biometric systems can employ different kinds of features, e.g., features of fingerprint, face, iris or posture. EEG signals are the signature of neural activities. It is confidential and hard to imitate, since EEG signals are a reflection of individual-dependent inner mental tasks. It has several advantages, such as (i) it is confidential as it corresponds to a mental task, (ii) it is very difficult to mimic and (iii) it is almost impossible to steal as the brain activity is sensitive to the stress and the mood of the person, an aggressor cannot force the person to reproduce his/her mental pass-phrase. In this paper we first proposed a novel algorithm to create a spatial pattern of EEG signals obtained from the open public database. In our EEG signal processing, we have analyzed 64-electrode EEG samples for two databases, one is for 45 people and calculate the equivalent root mean square (rms) values for each electrode signal over 1 second period, by which created a 64-value input for each subject. With neural network (NN) model, our analysis showed that our designed classifier is able to identify all the 45 people correctly (successful rate of 100%) with a mean square error of 2.0334×10-7 and the same algorithm applying to the 2nd database with 116 out of 122 people can be fully identified (successful rate of 95.1%) with a mean square error value of 0.00186. We deeply believe that a low complexity, high resolution, effective and efficient is very attractive for the real life applications become true in the foreseeable future
    Original languageEnglish
    Title of host publication2012 International Symposium on Communications and Information Technologies
    EditorsSalim Bouzerdoum, Michael Heinlich, Ren Oing Liu
    Place of PublicationAustralia
    PublisherIEEE, Institute of Electrical and Electronics Engineers
    Pages1026-1031
    Number of pages6
    Volume1
    ISBN (Print)9781467311557
    DOIs
    Publication statusPublished - 2012
    EventInternational Symposium on Communications and Information Technologies (ISCIT 2012) - Gold Coast, Gold Coast, Australia
    Duration: 2 Oct 20125 Oct 2012

    Conference

    ConferenceInternational Symposium on Communications and Information Technologies (ISCIT 2012)
    CountryAustralia
    CityGold Coast
    Period2/10/125/10/12

    Fingerprint

    Electroencephalography
    Signal processing
    Mean square error
    Electrodes
    Biometrics
    Brain
    Classifiers
    Neural networks

    Cite this

    Huang, X., Altahat, S., Tran, D., & Sharma, D. (2012). Human Identification with Electroencephalogram (EEG) Signal Processing. In S. Bouzerdoum, M. Heinlich, & R. O. Liu (Eds.), 2012 International Symposium on Communications and Information Technologies (Vol. 1, pp. 1026-1031). Australia: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ISCIT.2012.6380841
    Huang, Xu ; Altahat, Salahiddin ; Tran, Dat ; Sharma, Dharmendra. / Human Identification with Electroencephalogram (EEG) Signal Processing. 2012 International Symposium on Communications and Information Technologies. editor / Salim Bouzerdoum ; Michael Heinlich ; Ren Oing Liu. Vol. 1 Australia : IEEE, Institute of Electrical and Electronics Engineers, 2012. pp. 1026-1031
    @inproceedings{5d1e3dc2ca344bb290142a9e41a9f07a,
    title = "Human Identification with Electroencephalogram (EEG) Signal Processing",
    abstract = "Human identification becomes huge demand in particular for the security related areas. Biometric systems can employ different kinds of features, e.g., features of fingerprint, face, iris or posture. EEG signals are the signature of neural activities. It is confidential and hard to imitate, since EEG signals are a reflection of individual-dependent inner mental tasks. It has several advantages, such as (i) it is confidential as it corresponds to a mental task, (ii) it is very difficult to mimic and (iii) it is almost impossible to steal as the brain activity is sensitive to the stress and the mood of the person, an aggressor cannot force the person to reproduce his/her mental pass-phrase. In this paper we first proposed a novel algorithm to create a spatial pattern of EEG signals obtained from the open public database. In our EEG signal processing, we have analyzed 64-electrode EEG samples for two databases, one is for 45 people and calculate the equivalent root mean square (rms) values for each electrode signal over 1 second period, by which created a 64-value input for each subject. With neural network (NN) model, our analysis showed that our designed classifier is able to identify all the 45 people correctly (successful rate of 100{\%}) with a mean square error of 2.0334×10-7 and the same algorithm applying to the 2nd database with 116 out of 122 people can be fully identified (successful rate of 95.1{\%}) with a mean square error value of 0.00186. We deeply believe that a low complexity, high resolution, effective and efficient is very attractive for the real life applications become true in the foreseeable future",
    author = "Xu Huang and Salahiddin Altahat and Dat Tran and Dharmendra Sharma",
    year = "2012",
    doi = "10.1109/ISCIT.2012.6380841",
    language = "English",
    isbn = "9781467311557",
    volume = "1",
    pages = "1026--1031",
    editor = "Salim Bouzerdoum and Michael Heinlich and Liu, {Ren Oing}",
    booktitle = "2012 International Symposium on Communications and Information Technologies",
    publisher = "IEEE, Institute of Electrical and Electronics Engineers",
    address = "United States",

    }

    Huang, X, Altahat, S, Tran, D & Sharma, D 2012, Human Identification with Electroencephalogram (EEG) Signal Processing. in S Bouzerdoum, M Heinlich & RO Liu (eds), 2012 International Symposium on Communications and Information Technologies. vol. 1, IEEE, Institute of Electrical and Electronics Engineers, Australia, pp. 1026-1031, International Symposium on Communications and Information Technologies (ISCIT 2012), Gold Coast, Australia, 2/10/12. https://doi.org/10.1109/ISCIT.2012.6380841

    Human Identification with Electroencephalogram (EEG) Signal Processing. / Huang, Xu; Altahat, Salahiddin; Tran, Dat; Sharma, Dharmendra.

    2012 International Symposium on Communications and Information Technologies. ed. / Salim Bouzerdoum; Michael Heinlich; Ren Oing Liu. Vol. 1 Australia : IEEE, Institute of Electrical and Electronics Engineers, 2012. p. 1026-1031.

    Research output: A Conference proceeding or a Chapter in BookConference contribution

    TY - GEN

    T1 - Human Identification with Electroencephalogram (EEG) Signal Processing

    AU - Huang, Xu

    AU - Altahat, Salahiddin

    AU - Tran, Dat

    AU - Sharma, Dharmendra

    PY - 2012

    Y1 - 2012

    N2 - Human identification becomes huge demand in particular for the security related areas. Biometric systems can employ different kinds of features, e.g., features of fingerprint, face, iris or posture. EEG signals are the signature of neural activities. It is confidential and hard to imitate, since EEG signals are a reflection of individual-dependent inner mental tasks. It has several advantages, such as (i) it is confidential as it corresponds to a mental task, (ii) it is very difficult to mimic and (iii) it is almost impossible to steal as the brain activity is sensitive to the stress and the mood of the person, an aggressor cannot force the person to reproduce his/her mental pass-phrase. In this paper we first proposed a novel algorithm to create a spatial pattern of EEG signals obtained from the open public database. In our EEG signal processing, we have analyzed 64-electrode EEG samples for two databases, one is for 45 people and calculate the equivalent root mean square (rms) values for each electrode signal over 1 second period, by which created a 64-value input for each subject. With neural network (NN) model, our analysis showed that our designed classifier is able to identify all the 45 people correctly (successful rate of 100%) with a mean square error of 2.0334×10-7 and the same algorithm applying to the 2nd database with 116 out of 122 people can be fully identified (successful rate of 95.1%) with a mean square error value of 0.00186. We deeply believe that a low complexity, high resolution, effective and efficient is very attractive for the real life applications become true in the foreseeable future

    AB - Human identification becomes huge demand in particular for the security related areas. Biometric systems can employ different kinds of features, e.g., features of fingerprint, face, iris or posture. EEG signals are the signature of neural activities. It is confidential and hard to imitate, since EEG signals are a reflection of individual-dependent inner mental tasks. It has several advantages, such as (i) it is confidential as it corresponds to a mental task, (ii) it is very difficult to mimic and (iii) it is almost impossible to steal as the brain activity is sensitive to the stress and the mood of the person, an aggressor cannot force the person to reproduce his/her mental pass-phrase. In this paper we first proposed a novel algorithm to create a spatial pattern of EEG signals obtained from the open public database. In our EEG signal processing, we have analyzed 64-electrode EEG samples for two databases, one is for 45 people and calculate the equivalent root mean square (rms) values for each electrode signal over 1 second period, by which created a 64-value input for each subject. With neural network (NN) model, our analysis showed that our designed classifier is able to identify all the 45 people correctly (successful rate of 100%) with a mean square error of 2.0334×10-7 and the same algorithm applying to the 2nd database with 116 out of 122 people can be fully identified (successful rate of 95.1%) with a mean square error value of 0.00186. We deeply believe that a low complexity, high resolution, effective and efficient is very attractive for the real life applications become true in the foreseeable future

    U2 - 10.1109/ISCIT.2012.6380841

    DO - 10.1109/ISCIT.2012.6380841

    M3 - Conference contribution

    SN - 9781467311557

    VL - 1

    SP - 1026

    EP - 1031

    BT - 2012 International Symposium on Communications and Information Technologies

    A2 - Bouzerdoum, Salim

    A2 - Heinlich, Michael

    A2 - Liu, Ren Oing

    PB - IEEE, Institute of Electrical and Electronics Engineers

    CY - Australia

    ER -

    Huang X, Altahat S, Tran D, Sharma D. Human Identification with Electroencephalogram (EEG) Signal Processing. In Bouzerdoum S, Heinlich M, Liu RO, editors, 2012 International Symposium on Communications and Information Technologies. Vol. 1. Australia: IEEE, Institute of Electrical and Electronics Engineers. 2012. p. 1026-1031 https://doi.org/10.1109/ISCIT.2012.6380841