دانشگاه مازندران

 آمار

تعداد نشریات32
تعداد شماره‌ها562
تعداد مقالات5,465
تعداد مشاهده مقاله8,311,045
تعداد دریافت فایل اصل مقاله6,150,598
AKHBARI, Mahsa, Pournorouz, Amir Hossein. (1405). Five-channel EEG-based Emotion Recognition using CNN and LSTM Networks. پژوهشنامه مدیریت اجرایی, (), 15-27. doi: 10.22080/frai.2026.30818.1040
Mahsa AKHBARI; Amir Hossein Pournorouz. "Five-channel EEG-based Emotion Recognition using CNN and LSTM Networks". پژوهشنامه مدیریت اجرایی, , , 1405, 15-27. doi: 10.22080/frai.2026.30818.1040
AKHBARI, Mahsa, Pournorouz, Amir Hossein. (1405). 'Five-channel EEG-based Emotion Recognition using CNN and LSTM Networks', پژوهشنامه مدیریت اجرایی, (), pp. 15-27. doi: 10.22080/frai.2026.30818.1040
AKHBARI, Mahsa, Pournorouz, Amir Hossein. Five-channel EEG-based Emotion Recognition using CNN and LSTM Networks. پژوهشنامه مدیریت اجرایی, 1405; (): 15-27. doi: 10.22080/frai.2026.30818.1040

Five-channel EEG-based Emotion Recognition using CNN and LSTM Networks

Future Research on AI and IoT
مقالات آماده انتشار، اصلاح شده برای چاپ، انتشار آنلاین از تاریخ 15 خرداد 1405    اصل مقاله (928.6 K)
نوع مقاله: Research Article
شناسه دیجیتال (DOI): 10.22080/frai.2026.30818.1040
نویسندگان
Mahsa AKHBARI* ؛ Amir Hossein Pournorouz
Department of Biomedical Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran
تاریخ دریافت: 25 آذر 1404،  تاریخ بازنگری: 08 اسفند 1404،  تاریخ پذیرش: 15 خرداد 1405 
چکیده
This study presents an emotion recognition approach using five-channel electroencephalogram (EEG) signals analyzed through convolutional neural networks (CNN) and long short-term memory (LSTM) networks. The goal is to achieve robust binary classification (positive vs. negative emotion) using minimal electrode input to reduce computational cost. We employed five electrodes positioned in the prefrontal and temporal regions of the brain to reduce computational complexity and enhance classification accuracy. Using the SEED dataset (SJTU Emotion EEG Dataset), we applied continuous wavelet transform (CWT) to generate 2-D images for the CNN model and wavelet packet transform (WPT) for gamma band extraction in the LSTM model. Our results show an average classification accuracy of 94.57±0.06% for CNN and 74.6% for LSTM. We emphasize that, despite using basic architectures, effective performance was achieved with minimal electrodes. Training time for the CNN model was 3 minutes and for LSTM model was 31 minutes that indicates the robustness of this methodology. This lightweight system has practical applications in emotion-aware technologies, mental health tools, and human-computer interaction.
کلیدواژه‌ها
Emotion Recognition؛ Electroencephalogram (EEG)؛ Deep Learning؛ Convolutional Neural Network (CNN)؛ Long Short Time Memory (LSTM)؛ Time-Series
آمار
تعداد مشاهده مقاله: 3
تعداد دریافت فایل اصل مقاله: 11


سامانه مدیریت نشریات علمی. قدرت گرفته از سیناوب