Emotion Recognition Based on Fusion of Local Cortial Activations and Dynamic Functional Networks Connectivity: An EEG Study

被引:39
作者
Al-Shargie, Fares [1 ]
Tariq, Usman [1 ]
Alex, Meera [1 ]
Mir, Hasan [1 ]
Al-Nashash, Hasan [1 ]
机构
[1] Amer Univ Sharjah, Dept Elect Engn, Sharjah, U Arab Emirates
来源
IEEE ACCESS | 2019年 / 7卷 / 143550-143562期
关键词
Emotion; electroencephalogram (EEG); cortical activation; functional connectivity network patterns; fusion; classification; PHASE SYNCHRONIZATION; FRONTAL EEG; MODEL; CLASSIFICATION; PERCEPTION; SELECTION; MUSIC; STATE;
D O I
10.1109/ACCESS.2019.2944008
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In this paper, we present a method to improve emotion recognition based on the fusion of local cortical activations and dynamic functional network patterns. We estimate the cortical activations using power spectral density (PSD) with the Burg autoregressive model. On the other hand, we estimate the functional connectivity networks by utilizing the phase locking value (PLV). The results of cortical activations and connectivity networks show different patterns across three emotions at all frequency bands. Similarly, the results of fusion significantly improve the classification rate in terms of accuracy, sensitivity, specificity and the area under the receiver operator characteristics curve (AROC), p < 0.05. The average improvement with fusion in all evaluation metrics are 6.84% and 4.1% when compared to PSD and PLV alone, respectively. The results clearly demonstrate the advantage of fusion of cortical activations with dynamic functional networks for developing human-computer interaction system in real-world applications.
引用
收藏
页码:143550 / 143562
页数:13
相关论文
共 86 条
  • [61] Review of advanced techniques for the estimation of brain connectivity measured with EEG/MEG
    Sakkalis, V.
    [J]. COMPUTERS IN BIOLOGY AND MEDICINE, 2011, 41 (12) : 1110 - 1117
  • [62] Robust electroencephalogram phase estimation with applications in brain-computer interface systems
    Seraj, Esmaeil
    Sameni, Reza
    [J]. PHYSIOLOGICAL MEASUREMENT, 2017, 38 (03) : 501 - 523
  • [63] Toward automatic detection of brain responses to emotional music through analysis of EEG effective connectivity
    Shahabi, Hossein
    Moghimi, Sahar
    [J]. COMPUTERS IN HUMAN BEHAVIOR, 2016, 58 : 231 - 239
  • [64] Analysis of EEG Signals and Facial Expressions for Continuous Emotion Detection
    Soleymani, Mohammad
    Asghari-Esfeden, Sadjad
    Fu, Yun
    Pantic, Maja
    [J]. IEEE TRANSACTIONS ON AFFECTIVE COMPUTING, 2016, 7 (01) : 17 - 28
  • [65] Multimodal Emotion Recognition in Response to Videos
    Soleymani, Mohammad
    Pantic, Maja
    Pun, Thierry
    [J]. IEEE TRANSACTIONS ON AFFECTIVE COMPUTING, 2012, 3 (02) : 211 - 223
  • [66] A Multimodal Database for Affect Recognition and Implicit Tagging
    Soleymani, Mohammad
    Lichtenauer, Jeroen
    Pun, Thierry
    Pantic, Maja
    [J]. IEEE TRANSACTIONS ON AFFECTIVE COMPUTING, 2012, 3 (01) : 42 - 55
  • [67] Graph theoretical analysis of magnetoencephalographic functional connectivity in Alzheimers disease
    Stam, C. J.
    de Haan, W.
    Daffertshofer, A.
    Jones, B. F.
    Manshanden, I.
    van Walsum, A. M. van Cappellen
    Montez, T.
    Verbunt, J. P. A.
    de Munck, J. C.
    van Dijk, B. W.
    Berendse, H. W.
    Scheltens, P.
    [J]. BRAIN, 2009, 132 : 213 - 224
  • [68] Phase lag index: Assessment of functional connectivity from multi channel EEG and MEG with diminished bias from common sources
    Stam, Cornelis J.
    Nolte, Guido
    Daffertshofer, Andreas
    [J]. HUMAN BRAIN MAPPING, 2007, 28 (11) : 1178 - 1193
  • [69] Application of classical and model-based spectral methods to describe the state of alertness in EEG
    Subasi A.
    [J]. Journal of Medical Systems, 2005, 29 (5) : 473 - 486
  • [70] Supervised super-vector encoding for facial expression recognition
    Tariq, Usman
    Yang, Jianchao
    Huang, Thomas S.
    [J]. PATTERN RECOGNITION LETTERS, 2014, 46 : 89 - 95