Personal HomePage

+55

Hui Liu

Personal Information

Name (English):Hui Liu

Name (Pinyin):Liu Hui

School/Department:Artificial Intelligence (Future Technology)

Administrative Position:Researcher and Teacher

Education Level:With Certificate of Graduation for Doctorate Study

Gender:Male

Contact Information:hui.liu@nuist.edu.cn

Degree:Doctoral Degree in Engineering

Status:在岗

Academic Titles:Dr.-Inginieur, Universität Bremen

Other Post:Invited Chief Expert in Guodian Nanjing Authomation Co., Ltd.; Invited Chief Professor at the School of Art, Xi'an University of Architecture Technolgy

Alma Mater:Universität Bremen

[sensORder Dataset] Taxonomy and Real-Time Classification of Artifacts during Biosignal Acquisition: A Starter Study and Dataset of ECG

Date:2025-05-17  Hits:

Impact Factor:4.3

DOI Number:10.1109/JSEN.2024.3356651

Affiliation of Author(s):University of Bremen; Nanjing University of Information Science and Technology

Journal:IEEE Sensors Journal

Place of Publication:UNITED STATES

Key Words:artifact; biosignal; electrocardiogram; ECG; electrocardiography; pattern recognition; real-time system; signal quality

Abstract:This article investigates electrocardiogram (ECG) acquisition artifacts often occurring in experiments due to human negligence or environmental influences, such as electrode detachment, misuse of electrodes, and unanticipated magnetic field interference, which are not easily noticeable by humans or software during acquisition. Such artifacts usually result in useless and irreparable signals; therefore, it would be a great help to research if the problems are detected during the acquisition process to alert experimenters instantly. We put forward a taxonomy of real-time artifacts during ECG acquisition, provide the simulation methods of each category, collect and share a 10-subject data corpus, and investigate machine learning (ML) solutions with a proposal of appropriate handcrafted features that reach an offline recognition rate of 90.89% in a five-best-output person-independent (PI) leave-one-out cross-validation (LOOCV). We also preliminarily validate the real-time applicability of our approach.

Note:ESI Hot Paper (top 0.1%) and Highly-Cited Paper (top 1%).
Dataset: https://www.uni-bremen.de/en/csl/research/sensorder-artifact-classification-during-biosignal-acquisition.

All the Authors:Hui Liu*, Shiyao Zhang, Hugo Gamboa, Tingting Xue, Congcong Zhou, Tanja Schultz

Indexed by:Journal paper

Discipline:Engineering

Document Type:J

Volume:24

Issue:6

Page Number:9162-9171

ISSN No.:1530-437X

Translation or Not:no

Date of Publication:2024-01-16

Included Journals:SCI

Publication links:https://ieeexplore.ieee.org/document/10415350

Pre One:[CSL-SHARE Dataset] CSL-SHARE: A Multimodal Wearable Sensor-Based Human Activity Dataset Next One:[TSFEL Codebank] TSFEL: Time Series Feature Extraction Library