Enhancing Emotion Detection with Non-invasive Multi-Channel EEG and Hybrid Deep Learning Architecture

被引:1
|
作者
Nandini, Durgesh [1 ]
Yadav, Jyoti [1 ]
Rani, Asha [1 ]
Singh, Vijander [1 ]
机构
[1] Netaji Subhas Univ Technol, Dept Instrumentat & Control Engn, Sect 3, Dwarka, New Delhi, India
关键词
DEAP EEG database; Emotion detection; HCI; Affective computing; GRU-RNN; 3D VAD model; Hyperopt technique; RECOGNITION; CLASSIFICATION; FUSION;
D O I
10.1007/s40998-024-00710-4
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Emotion recognition is vital for augmenting human-computer interactions by integrating emotional contextual information for enhanced communication. Hence, the study presents an intelligent emotion detection system developed utilizing hybrid stacked gated recurrent units (GRU)-recurrent neural network (RNN) deep learning architecture. Integration of GRU with RNN allows the system to make use of both models' capabilities, making it better at capturing complex emotional patterns and temporal correlations. The EEG signals are investigated in time, frequency, and time-frequency domains, meticulously curated to capture intricate multi-domain patterns. Then, the SMOTE-Tomek method ensures a uniform class distribution, while the PCA technique optimizes features by minimizing data redundancy. A comprehensive experimentation including the well-established emotion datasets: DEAP and AMIGOS, assesses the efficacy of the hybrid stacked GRU and RNN architecture in contrast to 1D convolution neural network, RNN and GRU models. Moreover, the "Hyperopt" technique fine-tunes the model's hyperparameter, improving the average accuracy by about 3.73%. Hence, results revealed that the hybrid GRU-RNN model demonstrates the most optimal performance with the highest classification accuracies of 99.77% +/- 0.13, 99.54% +/- 0.16, 99.82% +/- 0.14, and 99.68% +/- 0.13 for the 3D VAD and liking parameter, respectively. Furthermore, the model's generalizability is examined using the cross-subject and database analysis on the DEAP and AMIGOS datasets, exhibiting a classification with an average accuracy of about 99.75% +/- 0.10 and 99.97% +/- 0.03. Obtained results when compared with the existing methods in literature demonstrate superior performance, highlighting potential in emotion recognition.
引用
收藏
页码:1229 / 1248
页数:20
相关论文
共 50 条
  • [1] Deep Learning Methods for Multi-Channel EEG-Based Emotion Recognition
    Olamat, Ali
    Ozel, Pinar
    Atasever, Sema
    INTERNATIONAL JOURNAL OF NEURAL SYSTEMS, 2022, 32 (05)
  • [2] An optimized deep hybrid learning for multi-channel EEG-based driver drowsiness detection
    Latreche, Imene
    Slatnia, Sihem
    Kazar, Okba
    Harous, Saad
    BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2025, 99
  • [3] A Non-invasive Flexible Multi-channel Electrode For in vivo Mouse EEG Recording
    Kim, Donghyeon
    Yeon, Chanmi
    Chung, Euiheon
    Kim, Kiseon
    2014 IEEE SENSORS, 2014,
  • [4] Improved Deep Feature Learning by Synchronization Measurements for Multi-Channel EEG Emotion Recognition
    Chao, Hao
    Dong, Liang
    Liu, Yongli
    Lu, Baoyun
    COMPLEXITY, 2020, 2020
  • [5] Multi-channel Non-invasive Fetal Electrocardiography Detection using Wavelet Decomposition
    Almeida, Javier
    Ruano, Josue
    Corredor, German
    Romo-Bucheli, David
    Ricardo Navarro-Vargas, Jose
    Romero, Eduardo
    13TH INTERNATIONAL CONFERENCE ON MEDICAL INFORMATION PROCESSING AND ANALYSIS, 2017, 10572
  • [6] Emotion Recognition From Multi-Channel EEG via Deep Forest
    Cheng, Juan
    Chen, Meiyao
    Li, Chang
    Liu, Yu
    Song, Rencheng
    Liu, Aiping
    Chen, Xun
    IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2021, 25 (02) : 453 - 464
  • [7] Non-invasive multi-channel deep learning convolutional neural networks for localization and classification of common hepatic lesions
    Shah, Shubham
    Mishra, Ruby
    Szczurowska, Agata
    Guzinski, Maciej
    POLISH JOURNAL OF RADIOLOGY, 2021, 86 : E440 - E448
  • [8] Multi-Channel Deep Feature Learning for Intrusion Detection
    Andresini, Giuseppina
    Appice, Annalisa
    Di Mauro, Nicola
    Loglisci, Corrado
    Malerba, Donato
    IEEE ACCESS, 2020, 8 : 53346 - 53359
  • [9] Visual Evoked Potential Recordings in Mice Using a Dry Non-invasive Multi-channel Scalp EEG Sensor
    Yeon, Chanmi
    Kim, Donghyeon
    Kim, Kiseon
    Chung, Euiheon
    JOVE-JOURNAL OF VISUALIZED EXPERIMENTS, 2018, (131):
  • [10] Multi-channel simultaneous emission non-invasive flow measurement system
    Fang, Lide
    Sun, Yiqian
    Wang, Zhongliang
    Yuan, Xinyue
    Wang, Mi
    PHYSICS OF FLUIDS, 2024, 36 (10)