Reconstructing Multi-Stroke Characters From Brain Signals Toward Generalizable Handwriting Brain–Computer Interfaces

Handwriting Brain-Computer Interfaces (BCIs) provides a promising communication avenue for individuals with paralysis. While English-based handwriting BCIs have achieved rapid typewriting with 26 lowercase letters (mostly containing one stroke each), it is difficult to extend to complex characters,...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaomeng Yang, Xinzhu Xiong, Xufei Li, Qi Lian, Junming Zhu, Jianmin Zhang, Yu Qi, Yueming Wang
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Transactions on Neural Systems and Rehabilitation Engineering
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10745614/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846126358788308992
author Xiaomeng Yang
Xinzhu Xiong
Xufei Li
Qi Lian
Junming Zhu
Jianmin Zhang
Yu Qi
Yueming Wang
author_facet Xiaomeng Yang
Xinzhu Xiong
Xufei Li
Qi Lian
Junming Zhu
Jianmin Zhang
Yu Qi
Yueming Wang
author_sort Xiaomeng Yang
collection DOAJ
description Handwriting Brain-Computer Interfaces (BCIs) provides a promising communication avenue for individuals with paralysis. While English-based handwriting BCIs have achieved rapid typewriting with 26 lowercase letters (mostly containing one stroke each), it is difficult to extend to complex characters, especially those with multiple strokes and large character sets. The Chinese characters, including over 3500 commonly used characters with 10.3 strokes per character on average, represent a highly complex writing system. This paper proposes a Chinese handwriting BCI system, which reconstructs multi-stroke handwriting trajectories from brain signals. Through the recording of cortical neural signals from the motor cortex, we reveal distinct neural representations for stroke-writing and pen-lift phases. Leveraging this finding, we propose a stroke-aware approach to decode stroke-writing trajectories and pen-lift movements individually, which can reconstruct recognizable characters (accuracy of 86% with 400 characters). Our approach demonstrates high stability over 5 months, shedding light on generalized and adaptable handwriting BCIs.
format Article
id doaj-art-7cb8811252b444608bcd1d6e97a8f52b
institution Kabale University
issn 1534-4320
1558-0210
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Transactions on Neural Systems and Rehabilitation Engineering
spelling doaj-art-7cb8811252b444608bcd1d6e97a8f52b2024-12-13T00:00:11ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1534-43201558-02102024-01-01324230423910.1109/TNSRE.2024.349219110745614Reconstructing Multi-Stroke Characters From Brain Signals Toward Generalizable Handwriting Brain–Computer InterfacesXiaomeng Yang0https://orcid.org/0009-0002-7527-1211Xinzhu Xiong1Xufei Li2Qi Lian3Junming Zhu4https://orcid.org/0000-0002-2781-3306Jianmin Zhang5https://orcid.org/0000-0002-3184-1502Yu Qi6https://orcid.org/0000-0002-9789-8907Yueming Wang7https://orcid.org/0000-0001-7742-0722Mental Health Center and Hangzhou Seventh People’s Hospital, Zhejiang University School of Medicine, Hangzhou, ChinaMental Health Center and Hangzhou Seventh People’s Hospital, Zhejiang University School of Medicine, Hangzhou, ChinaNanhu Brain-computer Interface Institute, Hangzhou, ChinaCollege of Computer Science, Zhejiang University, Hangzhou, ChinaHospital of Zhejiang University School of Medicine, Hangzhou, ChinaHospital of Zhejiang University School of Medicine, Hangzhou, ChinaMental Health Center and Hangzhou Seventh People’s Hospital, Zhejiang University School of Medicine, Hangzhou, ChinaCollege of Computer Science, Zhejiang University, Hangzhou, ChinaHandwriting Brain-Computer Interfaces (BCIs) provides a promising communication avenue for individuals with paralysis. While English-based handwriting BCIs have achieved rapid typewriting with 26 lowercase letters (mostly containing one stroke each), it is difficult to extend to complex characters, especially those with multiple strokes and large character sets. The Chinese characters, including over 3500 commonly used characters with 10.3 strokes per character on average, represent a highly complex writing system. This paper proposes a Chinese handwriting BCI system, which reconstructs multi-stroke handwriting trajectories from brain signals. Through the recording of cortical neural signals from the motor cortex, we reveal distinct neural representations for stroke-writing and pen-lift phases. Leveraging this finding, we propose a stroke-aware approach to decode stroke-writing trajectories and pen-lift movements individually, which can reconstruct recognizable characters (accuracy of 86% with 400 characters). Our approach demonstrates high stability over 5 months, shedding light on generalized and adaptable handwriting BCIs.https://ieeexplore.ieee.org/document/10745614/Brain-computer interfaces (BCIs)neural signal decodinghandwriting reconstructionmulti-stroke characters
spellingShingle Xiaomeng Yang
Xinzhu Xiong
Xufei Li
Qi Lian
Junming Zhu
Jianmin Zhang
Yu Qi
Yueming Wang
Reconstructing Multi-Stroke Characters From Brain Signals Toward Generalizable Handwriting Brain–Computer Interfaces
IEEE Transactions on Neural Systems and Rehabilitation Engineering
Brain-computer interfaces (BCIs)
neural signal decoding
handwriting reconstruction
multi-stroke characters
title Reconstructing Multi-Stroke Characters From Brain Signals Toward Generalizable Handwriting Brain–Computer Interfaces
title_full Reconstructing Multi-Stroke Characters From Brain Signals Toward Generalizable Handwriting Brain–Computer Interfaces
title_fullStr Reconstructing Multi-Stroke Characters From Brain Signals Toward Generalizable Handwriting Brain–Computer Interfaces
title_full_unstemmed Reconstructing Multi-Stroke Characters From Brain Signals Toward Generalizable Handwriting Brain–Computer Interfaces
title_short Reconstructing Multi-Stroke Characters From Brain Signals Toward Generalizable Handwriting Brain–Computer Interfaces
title_sort reconstructing multi stroke characters from brain signals toward generalizable handwriting brain x2013 computer interfaces
topic Brain-computer interfaces (BCIs)
neural signal decoding
handwriting reconstruction
multi-stroke characters
url https://ieeexplore.ieee.org/document/10745614/
work_keys_str_mv AT xiaomengyang reconstructingmultistrokecharactersfrombrainsignalstowardgeneralizablehandwritingbrainx2013computerinterfaces
AT xinzhuxiong reconstructingmultistrokecharactersfrombrainsignalstowardgeneralizablehandwritingbrainx2013computerinterfaces
AT xufeili reconstructingmultistrokecharactersfrombrainsignalstowardgeneralizablehandwritingbrainx2013computerinterfaces
AT qilian reconstructingmultistrokecharactersfrombrainsignalstowardgeneralizablehandwritingbrainx2013computerinterfaces
AT junmingzhu reconstructingmultistrokecharactersfrombrainsignalstowardgeneralizablehandwritingbrainx2013computerinterfaces
AT jianminzhang reconstructingmultistrokecharactersfrombrainsignalstowardgeneralizablehandwritingbrainx2013computerinterfaces
AT yuqi reconstructingmultistrokecharactersfrombrainsignalstowardgeneralizablehandwritingbrainx2013computerinterfaces
AT yuemingwang reconstructingmultistrokecharactersfrombrainsignalstowardgeneralizablehandwritingbrainx2013computerinterfaces