Convolutional Neural Network-based Transfer Learning and Knowledge Distillation using Multi-Subject Data in Motor Imagery BCI

被引：0

作者：

Sakhavi, Siavash ^{[1
,2
]}

Guan, Cuntai ^{[3
]}

机构：

[1] Natl Univ Singapore, Fac Elect & Comp Engn, Singapore, Singapore

[2] ASTAR, Inst Infocomm Res I2R, Singapore, Singapore

[3] Nanyang Technol Univ, Sch Comp Sci & Engn, Singapore, Singapore

来源：

2017 8TH INTERNATIONAL IEEE/EMBS CONFERENCE ON NEURAL ENGINEERING (NER) | 2017年

关键词：

D O I：

暂无

中图分类号：

R318 [生物医学工程];

学科分类号：

0831 ;

摘要：

In Brain Computer Interfaces (BCIs), with multiple recordings from different subjects in hand, a question arises regarding whether the knowledge of previously recorded subjects can be transferred to a new subject. In this study, we explore the possibility of transferring knowledge by using a convolutional network model trained on multiple subjects and fine-tuning the model on a small amount of data from a new subject, thus, reducing the calibration time by reducing the time needed to record data and train a model. Our results show a significant increase in 4-class classification accuracy on the BCI IV-2a competition data, even when a small subset of the data is provided for training.

引用

下载

页码：588 / 591

页数：4

共 50 条

[21] Investigation of deep convolutional neural network for classification of motor imagery fNIRS signals for BCI applications
Janani, A.
Sasikala, M.
Chhabra, Harleen
Shajil, Nijisha
Venkatasubramanian, Ganesan
BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2020, 62
[22] Exploring a Deeper Convolutional Neural Network Architecture with high dropout for Motor Imagery BCI Decoding
Alami, Ramtin
Partovi, Andi
Goodarzy, Farhad
2021 9TH IEEE INTERNATIONAL WINTER CONFERENCE ON BRAIN-COMPUTER INTERFACE (BCI), 2021, : 253 - 257
[23] MOTOR IMAGERY FOR EEG BIOMETRICS USING CONVOLUTIONAL NEURAL NETWORK
Das, Rig
Maiorana, Emanuele
Campisi, Patrizio
2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 2062 - 2066
[24] Active Transfer Learning and Selective Instance Transfer with Active Learning for Motor Imagery based BCI
Hossain, Ibrahim
Khosravi, Abbas
Nahavandhi, Saeid
2016 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2016, : 4048 - 4055
[25] Golden subject is everyone: A subject transfer neural network for motor imagery-based brain computer interfaces
Sun, Biao
Wu, Zexu
Hu, Yong
Li, Ting
NEURAL NETWORKS, 2022, 151 : 111 - 120
[26] Fusion Convolutional Neural Network for Cross-Subject EEG Motor Imagery Classification
Roots, Karel
Muhammad, Yar
Muhammad, Naveed
COMPUTERS, 2020, 9 (03) : 1 - 9
[27] Hybrid Zero-Training BCI based on Convolutional Neural Network for Lower-limb Motor-Imagery
Jeong, Ji Hyeok
Kim, Dong-Joo
Kim, Hyungmin
2021 9TH IEEE INTERNATIONAL WINTER CONFERENCE ON BRAIN-COMPUTER INTERFACE (BCI), 2021, : 9 - 12
[28] Classification of BCI Multiclass Motor Imagery Task Based on Artificial Neural Network
Echtioui, Amira
Zouch, Wassim
Ghorbel, Mohamed
Mhiri, Chokri
Hamam, Habib
CLINICAL EEG AND NEUROSCIENCE, 2024, 55 (04) : 455 - 464
[29] Improved Decoding of EEG-Based Motor Imagery Using Convolutional Neural Network and Data Space Adaptation
Chua, Shawn
Tao, Yang
So, Rosa Q.
2019 IEEE EMBS INTERNATIONAL CONFERENCE ON BIOMEDICAL & HEALTH INFORMATICS (BHI), 2019,
[30] Similarity-based adversarial knowledge distillation using graph convolutional neural network
Lee, Sungjun
Kim, Sejun
Kim, Seong Soo
Seo, Kisung
ELECTRONICS LETTERS, 2022, 58 (16) : 606 - 608

← 1 2 3 4 5 →