International Journal of Modern Education and Computer Science (IJMECS)
IJMECS Vol. 16, No. 6, 8 Dec. 2024
Cover page and Table of Contents: PDF (size: 1050KB)
Emotion Classification Utilizing Transformer Models with ECG Signal Data
PDF (1050KB), PP.40-55
Views: 0 Downloads: 0
Author(s)
Ch. Raga Madhuri
1
Kundu Bhagya Sri
1,*
Kasaraneni Gagana
1
Tiprineni Sathvika Lakshmi
1
Index Terms
Emotion Recognition, ECG Signals, Transformers, Tokenization, DistilBERT Model
Abstract
In recent years, there has been growing interest in leveraging physiological signals, such as Electrocardiogram (ECG) data, for emotion classification tasks. This study explores the efficacy of utilizing Transformer models, a state-of-the-art architecture in natural language processing, for emotion classification using ECG signal data. The proposed methodology involves preprocessing the ECG signals, extracting relevant features, and model architecture consists of DistilBERT model, Pooling Layer to obtain a fixed-size representation of the ECG signal, Dropout Layer to prevent overfitting, Fully Connected Layer for classification. Experiments are conducted on publicly available dataset, demonstrating the effectiveness of the proposed approach compared to traditional machine learning methods. The results suggest that DistilBERT Transformer model can effectively capture complex temporal dependencies within ECG signals, thereby achieving notable performance of 76% accuracy in emotion classification tasks. This research contributes to the growing body of literature exploring the intersection of physiological signals and deep learning techniques for affective computing applications.
Cite This Paper
Ch. Raga Madhuri, Kundu Bhagya Sri, Kasaraneni Gagana, Tiprineni Sathvika Lakshmi, "Emotion Classification Utilizing Transformer Models with ECG Signal Data", International Journal of Modern Education and Computer Science(IJMECS), Vol.16, No.6, pp. 40-55, 2024. DOI:10.5815/ijmecs.2024.06.03
Reference
[1]Hasnul, Muhammad Anas, Nor Azlina Ab. Aziz, and Azlan Abd. Aziz. "Augmenting ECG data with multiple filters for a better emotion recognition system." Arabian journal for science and engineering 48.8 (2023): 10313-10334.
[2]Vaswani, Ashish, et al. "Attention is all you need." Advances in neural information processing systems 30 (2017).
[3]Wei, Yi, et al. "TC-Net: A Transformer Capsule Network for EEG-based emotion recognition." Computers in biology and med-icine 152 (2023): 106463.
[4]Zheng, Wei, and Bo Pan. "A spatiotemporal symmetrical transformer structure for EEG emotion recognition." Biomedical Signal Processing and Control 87 (2024): 105487.
[5]Gong, Linlin, et al. "EEG emotion recognition using attention-based convolutional transformer neural network." Biomedical Signal Processing and Control 84 (2023): 104835.
[6]Ma, Hui, et al. "A Transformer-Based Model With Self-Distillation for Multimodal Emotion Recognition in Conversations." IEEE Transactions on Multimedia (2023).
[7]Devika, R., et al. "A deep learning model based on BERT and sentence transformer for semantic keyphrase extraction on big social data." IEEE Access 9 (2021): 165252-165261.
[8]Nita, Sihem, et al. "A new data augmentation convolutional neural network for human emotion recognition based on ECG signals." Biomedical Signal Processing and Control 75 (2022): 103580.
[9]Fan, Tianqi, et al. "A new deep convolutional neural network incorporating attentional mechanisms for ECG emotion recognition." Computers in Biology and Medicine 159 (2023): 106938.
[10]"Design and Development of a Non-Contact ECG-Based Human Emotion Recognition System Using SVM and RF Classifiers." Diagnostics 13.12 (2023): 2097.
[11]Sepúlveda, Axel, et al. "Emotion recognition from ECG signals using wavelet scattering and machine learning." Applied Sciences 11.11 (2021): 4945.
[12]Baghizadeh, Maryam, et al. "A new emotion detection algorithm using extracted features of the different time-series generated from ST intervals Poincaré map." Biomedical Signal Processing and Control 59 (2020): 101902.
[13]Lin, Wenqian, and Chao Li. "Review of Studies on Emotion Recognition and Judgment Based on Physiological Signals." Applied Sciences 13.4 (2023): 2573.
[14]Dessai, Amita, and Hassanali Virani. "Emotion Classification Based on CWT of ECG and GSR Signals Using Various CNN Models." Electronics 12.13 (2023): 2795.
[15]Silva, Pedro, and Raquel Sebastião. "Using the Electrocardiogram for Pain Classification under Emotional Contexts." Sensors 23.3 (2023): 1443.
[16]Fang, Ancheng, et al. "ECG-based emotion recognition using random convolutional kernel method." Biomedical Signal Processing and Control 91 (2024): 105907.
[17]Sanh, Victor, et al. "DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter." arXiv preprint arXiv:1910.01108 (2019).
[18]Diwakar, and Deepa Raj. "DistilBERT-based Text Classification for Automated Diagnosis of Mental Health Conditions." Mi-crobial Data Intelligence and Computational Techniques for Sustainable Computing. Singapore: Springer Nature Singapore, 2024. 93-106.
[19]Silva Barbon, Rafael, and Ademar Takeo Akabane. "Towards transfer learning techniques—BERT, DistilBERT, BERTimbau, and DistilBERTimbau for automatic text classification from different languages: a case study." Sensors 22.21 (2022): 8184.
[20]Dogra, Varun, et al. "Analyzing distilbert for sentiment classification of banking financial news." Intelligent Computing and In-novation on Data Science: Proceedings of ICTIDS 2021. Springer Singapore, 2021.
[21]Bahaa, Ahmed, et al. "DB-CBIL: A DistilBert-Based Transformer Hybrid Model using CNN and BiLSTM for Software Vulner-ability Detection." IEEE Access (2024).
[22]Liu, Tianrui, et al. "Spam detection and classification based on distilbert deep learning algorithm." Applied Science and Engineering Journal for Advanced Research 3.3 (2024): 6-10.
[23]Ong, Kah Liang, et al. "MaxMViT-MLP: Multiaxis and Multiscale Vision Transformers Fusion Network for Speech Emotion Recognition." IEEE Access (2024).
[24]Putri, Farica Perdana. "DistilBERT with Adam Optimizer Tuning for Text-based Emotion Detection." IJNMT (International Journal of New Media Technology) 10.1 (2023): 30-34.
[25]Wagner, Johannes, et al. "Dawn of the transformer era in speech emotion recognition: closing the valence gap." IEEE Transactions on Pattern Analysis and Machine Intelligence (2023).