Classification of Working Memory Performance from EEG with Deep Artificial Neural Networks

被引：3
作者：
Kwak, Youngchul [1 ]
Song, Woo-Jin [1 ]
Kim, Seong-Eun [2 ]
机构：
[1] Pohang Univ Sci & Technol, Dept Elect Engn, Pohang, South Korea
[2] Hanbat Natl Univ, Dept Elect & Control Engn, Daejeon, South Korea
来源：
2019 7TH INTERNATIONAL WINTER CONFERENCE ON BRAIN-COMPUTER INTERFACE (BCI) | 2019年
基金：
新加坡国家研究基金会;
关键词：
Artificial neural network (ANN); EEG band power; working memory;
D O I：
10.1109/iww-bci.2019.8737343
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
Individuals have different working memory performance and some studies investigated a relationship between working memory performance and electroencephalography (EEG) band power. In this paper, we study EEG features to classify low performance group and high performance group and find that the power ratio feature of alpha and beta is more separable than their absolute powers. We test a deep artificial neural network (ANN) using the power ratio feature to classify the low performance group and high performance group. Experimental results on the working memory tasks show that some subjects have quite low accuracies (<20%) and it results in a low average classification accuracy of 61%, but we can see a possibility in the estimation of working memory performance using EEG data.
引用
收藏
页码：149 / 151
页数：3
相关论文
共 50 条
  • [21] EEG Induced Working Memory Performance Analysis Using Inverse Fuzzy Relational Approach
    Ghosh, Lidia
    Konar, Amit
    Rakshit, Pratyusha
    Ralescu, Anca L.
    Nagar, Atulya K.
    2017 IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS (FUZZ-IEEE), 2017,
  • [22] Relationship of working memory and EEG to academic performance:: A study among high school students
    Aguirre-Perez, Dalia M.
    Otero-Ojeda, Gloria A.
    Pliego-Rivero, F. Bernardo
    Ferreira-Martinez, Alonso A.
    INTERNATIONAL JOURNAL OF NEUROSCIENCE, 2007, 117 (06) : 869 - 882
  • [23] Genetic Networks Predict Brain Activity During Working Memory Performance
    Bertolino, Alessandro
    Pergola, Giulio
    Di Carlo, Pasquale
    D'Ambrosio, Enrico
    Fazio, Leonardo
    Rampino, Antonio
    Mattay, Venkata S.
    Weinberger, Daniel R.
    Blasi, Giuseppe
    BIOLOGICAL PSYCHIATRY, 2016, 79 (09) : 175S - 175S
  • [24] Application of empirical mode decomposition and artificial neural network for the classification of normal and epileptic EEG signals
    Djemili, Rafik
    Bourouba, Hocine
    Korba, M. C. Amara
    BIOCYBERNETICS AND BIOMEDICAL ENGINEERING, 2016, 36 (01) : 285 - 291
  • [25] Working memory prioritization impacts neural recovery from distraction
    Mallett, Remington
    Lewis-Peacock, Jarrod A.
    CORTEX, 2019, 121 : 225 - 238
  • [26] Analysis of working memory from EEG signals under different emotional states
    Barkana, Buket D.
    Ozkan, Yusuf
    Badara, Joanna A.
    BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2022, 71
  • [27] A continuous time-resolved measure decoded from EEG oscillatory activity predicts working memory task performance
    Astrand, Elaine
    JOURNAL OF NEURAL ENGINEERING, 2018, 15 (03)
  • [28] Active maintenance of sentence meaning in working memory: Evidence from EEG coherences
    Haarmann, HJ
    Cameron, KA
    INTERNATIONAL JOURNAL OF PSYCHOPHYSIOLOGY, 2005, 57 (02) : 115 - 128
  • [29] A Biologically Inspired Deep Neural Network of Basal Ganglia Switching in Working Memory Tasks
    Hajj, Nadine
    Awad, Mariette
    2017 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (SSCI), 2017,
  • [30] Effects of acute nicotine administration on behavioral and neural (EEG) correlates of working memory in non-smokers
    Fisher, Derek J.
    Daniels, Richelle
    Jaworska, Natalia
    Knobelsdorf, Amy
    Knott, Verner J.
    BRAIN RESEARCH, 2012, 1429 : 72 - 81
12345