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

Wei Chih Li; Cheng Jie Yang; Wai Chi Fang

doi:10.1109/ISOCC50952.2020.9333072

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

Wei Chih Li
, Cheng Jie Yang
, Wai Chi Fang^*

^*Corresponding author for this work

Institute of Electronics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

8 Scopus citations

Abstract

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.

Original language	English
Title of host publication	Proceedings - International SoC Design Conference, ISOCC 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	29-30
Number of pages	2
ISBN (Electronic)	9781728183312
DOIs	https://doi.org/10.1109/ISOCC50952.2020.9333072
State	Published - 21 Oct 2020
Event	17th International System-on-Chip Design Conference, ISOCC 2020 - Yeosu, Korea, Republic of Duration: 21 Oct 2020 → 24 Oct 2020

Publication series

Name	Proceedings - International SoC Design Conference, ISOCC 2020

Conference

Conference	17th International System-on-Chip Design Conference, ISOCC 2020
Country/Territory	Korea, Republic of
City	Yeosu
Period	21/10/20 → 24/10/20

Keywords

affective computing
convolutional neural network
Emotion recognition
multimodal analysis
physiological signals

Access to Document

10.1109/ISOCC50952.2020.9333072

Cite this

Li, W. C., Yang, C. J., & Fang, W. C. (2020). A Real-Time Emotion Recognition System Based on an AI System-On-Chip Design. In Proceedings - International SoC Design Conference, ISOCC 2020 (pp. 29-30). Article 9333072 (Proceedings - International SoC Design Conference, ISOCC 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISOCC50952.2020.9333072

@inproceedings{300f7b6500684550937a6272f6b9da38,

title = "A Real-Time Emotion Recognition System Based on an AI System-On-Chip Design",

abstract = "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. ",

keywords = "affective computing, convolutional neural network, Emotion recognition, multimodal analysis, physiological signals",

author = "Li, \{Wei Chih\} and Yang, \{Cheng Jie\} and Fang, \{Wai Chi\}",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.; 17th International System-on-Chip Design Conference, ISOCC 2020 ; Conference date: 21-10-2020 Through 24-10-2020",

year = "2020",

month = oct,

day = "21",

doi = "10.1109/ISOCC50952.2020.9333072",

language = "English",

series = "Proceedings - International SoC Design Conference, ISOCC 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "29--30",

booktitle = "Proceedings - International SoC Design Conference, ISOCC 2020",

address = "美國",

}

Li, WC, Yang, CJ & Fang, WC 2020, A Real-Time Emotion Recognition System Based on an AI System-On-Chip Design. in Proceedings - International SoC Design Conference, ISOCC 2020., 9333072, Proceedings - International SoC Design Conference, ISOCC 2020, Institute of Electrical and Electronics Engineers Inc., pp. 29-30, 17th International System-on-Chip Design Conference, ISOCC 2020, Yeosu, Korea, Republic of, 21/10/20. https://doi.org/10.1109/ISOCC50952.2020.9333072

A Real-Time Emotion Recognition System Based on an AI System-On-Chip Design. / Li, Wei Chih; Yang, Cheng Jie; Fang, Wai Chi.
Proceedings - International SoC Design Conference, ISOCC 2020. Institute of Electrical and Electronics Engineers Inc., 2020. p. 29-30 9333072 (Proceedings - International SoC Design Conference, ISOCC 2020).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Real-Time Emotion Recognition System Based on an AI System-On-Chip Design

AU - Li, Wei Chih

AU - Yang, Cheng Jie

AU - Fang, Wai Chi

PY - 2020/10/21

Y1 - 2020/10/21

N2 - 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.

AB - 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.

KW - affective computing

KW - convolutional neural network

KW - Emotion recognition

KW - multimodal analysis

KW - physiological signals

UR - https://www.scopus.com/pages/publications/85100828795

U2 - 10.1109/ISOCC50952.2020.9333072

DO - 10.1109/ISOCC50952.2020.9333072

M3 - Conference contribution

AN - SCOPUS:85100828795

T3 - Proceedings - International SoC Design Conference, ISOCC 2020

SP - 29

EP - 30

BT - Proceedings - International SoC Design Conference, ISOCC 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 17th International System-on-Chip Design Conference, ISOCC 2020

Y2 - 21 October 2020 through 24 October 2020

ER -

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

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this