A new approach to analyze data from EEG-based concealed face recognition system

被引:9
|
作者
Mehrnam, A. H. [1 ]
Nasrabadi, A. M. [1 ]
Ghodousi, Mahrad [1 ]
Mohammadian, A. [2 ,3 ]
Torabi, Sh [3 ]
机构
[1] Shahed Univ, Dept Biomed Engn, Fac Engn, POB 3319118651, Tehran, Iran
[2] Amirkabir Univ Technol, Dept Biomed Engn, Fac Engn, POB 4413-15875, Tehran, Iran
[3] Res Ctr Intelligent Signal Proc, POB 16765-3739, Tehran, Iran
关键词
Concealed face recognition test; Single-trial ERP; Non-linear features; Recurrence Quantification Analysis; RECURRENCE PLOTS; P300; BRAIN;
D O I
10.1016/j.ijpsycho.2017.02.005
中图分类号
B84 [心理学];
学科分类号
04 ; 0402 ;
摘要
The purpose of this study is to extend a feature set with non-linear features to improve classification rate of guilty and innocent subjects. Non-linear features can provide extra information about phase space. The Event-Related Potential (ERP) signals were recorded from 49 subjects who participated in concealed face recognition test. For feature extraction, at first, several morphological characteristics, frequency bands, and wavelet coefficients (we call them basic-features) are extracted from each single-trial ERP. Recurrence Quantification Analysis (RQA) measures are then computed as non-linear features from each single-trial. We apply Genetic Algorithm (GA) to select the best feature set and this feature set is used for classification of data using Linear Discriminant Analysis (LDA) classifier. Next, we use a new approach to improve classification results based on introducing an adaptive-threshold. Results indicate that our method is able to correctly detect 91.83% of subjects (45 correct detection of 49 subjects) using combination of basic and non-linear features, that is higher than 87.75% for basic and 79.59% for non-linear features. This shows that combination of non-linear and basic-features could improve classification rate. (C) 2017 Elsevier B.V. All rights reserved.
引用
收藏
页码:1 / 8
页数:8
相关论文
共 50 条
  • [21] Face recognition based on EEG
    Mu, Zhendong, 1600, Transport and Telecommunication Institute, Lomonosova street 1, Riga, LV-1019, Latvia (18):
  • [22] EEG-based Person Recognition: Analysis and criticism
    Boubakeur, Meriem Romaissa
    Wang, Guoyin
    Zhang, Chenglin
    Liu, Ke
    2017 IEEE INTERNATIONAL CONFERENCE ON BIG KNOWLEDGE (IEEE ICBK 2017), 2017, : 155 - 160
  • [23] EEG-based Emotion Recognition of Quran Listeners
    Fattouh, Anas
    Albidewi, Ibrahim
    Baterfi, Bader
    PROCEEDINGS OF THE 10TH INDIACOM - 2016 3RD INTERNATIONAL CONFERENCE ON COMPUTING FOR SUSTAINABLE GLOBAL DEVELOPMENT, 2016, : 1338 - 1342
  • [24] EEG-Based Emotion Recognition in Music Listening
    Lin, Yuan-Pin
    Wang, Chi-Hong
    Jung, Tzyy-Ping
    Wu, Tien-Lin
    Jeng, Shyh-Kang
    Duann, Jeng-Ren
    Chen, Jyh-Horng
    IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2010, 57 (07) : 1798 - 1806
  • [25] EEG-BASED BIOMETRIC RECOGNITION USING EIGENBRAINS
    Maiorana, Emanuele
    La Rocca, Daria
    Campisi, Patrizio
    2015 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO WORKSHOPS (ICMEW), 2015,
  • [26] Frequency Filter Networks for EEG-based recognition
    Yanagimoto, Miku
    Sugimoto, Chika
    Nagao, Tomoharu
    2017 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC), 2017, : 270 - 275
  • [27] EEG-Based BCI Emotion Recognition: A Survey
    Torres, Edgar P.
    Torres, Edgar A.
    Hernandez-Alvarez, Myriam
    Yoo, Sang Guun
    SENSORS, 2020, 20 (18) : 1 - 36
  • [28] DECISION FUSION FOR EEG-BASED EMOTION RECOGNITION
    Wang, Shuai
    Du, Jiachen
    Xu, Ruifeng
    PROCEEDINGS OF 2015 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOL. 2, 2015, : 883 - 889
  • [29] A hybrid model for EEG-based gender recognition
    Ping Wang
    Jianfeng Hu
    Cognitive Neurodynamics, 2019, 13 : 541 - 554
  • [30] A hybrid model for EEG-based gender recognition
    Wang, Ping
    Hu, Jianfeng
    COGNITIVE NEURODYNAMICS, 2019, 13 (06) : 541 - 554