A Real-time Emotion Recognition System Based on an AI System-On-Chip Design

In this paper, we developed and integrated a realtime emotion recognition system using an AI system-on-chip design. The emotion recognition platform combined three different physiological signals, Electroencephalogram (EEG), electrocardiogram (ECG), and photoplethysmogram (PPG) as the classification...

Full description

Saved in:
Bibliographic Details
Published in2020 International SoC Design Conference (ISOCC) pp. 29 - 30
Main Authors Li, Wei-Chih, Yang, Cheng-Jie, Fang, Wai-Chi
Format Conference Proceeding
LanguageEnglish
Published IEEE 21.10.2020
Subjects
affective computing
Artificial intelligence
Biomedical monitoring
convolutional neural network
Electroencephalography
Emotion recognition
multimodal analysis
Neural networks
physiological signals
Real-time systems
System-on-chip
Online AccessGet full text
DOI10.1109/ISOCC50952.2020.9333072

Cover

More Information
Summary:In this paper, we developed and integrated a realtime emotion recognition system using an AI system-on-chip design. The emotion recognition platform combined three different physiological signals, Electroencephalogram (EEG), electrocardiogram (ECG), and photoplethysmogram (PPG) as the classification resources. A 3-to-1 Bluetooth piconet was deployed to transmit all physiological signals on a single platform access point and to make use of low power wireless technologies. The system then integrated an AI computing chip with a convolution neural network (CNN) structure to classify three emotions, happiness, anger, and sadness. The average accuracy for a subject-independent classification reached 72.66%. The proposed system was integrated with the RISC-V processor and AI SOC to implement real-time monitoring and classification on edge.
DOI:10.1109/ISOCC50952.2020.9333072