Comparison of neural signal preprocessing methods and their impact on classification performance.

<p><b>A</b>, Comparison of neural signal preprocessing strategies: The upper panel illustrates the time-interval-based preprocessing method (quantifying spike counts within fixed time windows); the lower panel shows the equal-segment-based preprocessing method (dividing decision ti...

Full description

Saved in:
Bibliographic Details
Main Author: Yuhang Zhang (3144870) (author)
Other Authors: Tao Sun (91038) (author), Boyang Zang (21464459) (author), Sen Wan (14509499) (author)
Published: 2025
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1855367827718930432
author Yuhang Zhang (3144870)
author2 Tao Sun (91038)
Boyang Zang (21464459)
Sen Wan (14509499)
author2_role author
author
author
author_facet Yuhang Zhang (3144870)
Tao Sun (91038)
Boyang Zang (21464459)
Sen Wan (14509499)
author_role author
dc.creator.none.fl_str_mv Yuhang Zhang (3144870)
Tao Sun (91038)
Boyang Zang (21464459)
Sen Wan (14509499)
dc.date.none.fl_str_mv 2025-08-21T17:57:13Z
dc.identifier.none.fl_str_mv 10.1371/journal.pcbi.1013335.g003
dc.relation.none.fl_str_mv https://figshare.com/articles/figure/Comparison_of_neural_signal_preprocessing_methods_and_their_impact_on_classification_performance_/29963013
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Neuroscience
Biotechnology
Science Policy
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
term memory network
reproducible electrophysiology dataset
particularly challenging problem
international brain laboratory
directional long short
channel attention bi
making stability within
accurately forecasting decision
making decoding model
making behavior
decoding decision
proposed model
model serves
remarkable capacity
novel perspective
neural decision
investigation furnishes
ibl ),
crucial purpose
bilstm ),
dc.title.none.fl_str_mv Comparison of neural signal preprocessing methods and their impact on classification performance.
dc.type.none.fl_str_mv Image
Figure
info:eu-repo/semantics/publishedVersion
image
description <p><b>A</b>, Comparison of neural signal preprocessing strategies: The upper panel illustrates the time-interval-based preprocessing method (quantifying spike counts within fixed time windows); the lower panel shows the equal-segment-based preprocessing method (dividing decision time uniformly across trials and calculating spike counts within each segment). Due to significant variations in decision times across trials, the equal-segment-based approach enables standardized dimensional representation of data from different trials, effectively minimizing interference from redundant information. <b>B</b>, Performance comparison of preprocessing methods: Scatter plot showing classification accuracy of the CA-BiLSTM model for individual mouse samples under different preprocessing approaches, with triangular markers indicating mean accuracy across all mice. Results demonstrate that the equal-segment-based preprocessing method yields significantly higher accuracy for the majority of samples, validating the effectiveness of the proposed preprocessing strategy.</p>
eu_rights_str_mv openAccess
id Manara_ed9300a89b60d7892e8272f8b032adbc
identifier_str_mv 10.1371/journal.pcbi.1013335.g003
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/29963013
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Comparison of neural signal preprocessing methods and their impact on classification performance.Yuhang Zhang (3144870)Tao Sun (91038)Boyang Zang (21464459)Sen Wan (14509499)NeuroscienceBiotechnologyScience PolicyBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedterm memory networkreproducible electrophysiology datasetparticularly challenging probleminternational brain laboratorydirectional long shortchannel attention bimaking stability withinaccurately forecasting decisionmaking decoding modelmaking behaviordecoding decisionproposed modelmodel servesremarkable capacitynovel perspectiveneural decisioninvestigation furnishesibl ),crucial purposebilstm ),<p><b>A</b>, Comparison of neural signal preprocessing strategies: The upper panel illustrates the time-interval-based preprocessing method (quantifying spike counts within fixed time windows); the lower panel shows the equal-segment-based preprocessing method (dividing decision time uniformly across trials and calculating spike counts within each segment). Due to significant variations in decision times across trials, the equal-segment-based approach enables standardized dimensional representation of data from different trials, effectively minimizing interference from redundant information. <b>B</b>, Performance comparison of preprocessing methods: Scatter plot showing classification accuracy of the CA-BiLSTM model for individual mouse samples under different preprocessing approaches, with triangular markers indicating mean accuracy across all mice. Results demonstrate that the equal-segment-based preprocessing method yields significantly higher accuracy for the majority of samples, validating the effectiveness of the proposed preprocessing strategy.</p>2025-08-21T17:57:13ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pcbi.1013335.g003https://figshare.com/articles/figure/Comparison_of_neural_signal_preprocessing_methods_and_their_impact_on_classification_performance_/29963013CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/299630132025-08-21T17:57:13Z
spellingShingle Comparison of neural signal preprocessing methods and their impact on classification performance.
Yuhang Zhang (3144870)
Neuroscience
Biotechnology
Science Policy
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
term memory network
reproducible electrophysiology dataset
particularly challenging problem
international brain laboratory
directional long short
channel attention bi
making stability within
accurately forecasting decision
making decoding model
making behavior
decoding decision
proposed model
model serves
remarkable capacity
novel perspective
neural decision
investigation furnishes
ibl ),
crucial purpose
bilstm ),
status_str publishedVersion
title Comparison of neural signal preprocessing methods and their impact on classification performance.
title_full Comparison of neural signal preprocessing methods and their impact on classification performance.
title_fullStr Comparison of neural signal preprocessing methods and their impact on classification performance.
title_full_unstemmed Comparison of neural signal preprocessing methods and their impact on classification performance.
title_short Comparison of neural signal preprocessing methods and their impact on classification performance.
title_sort Comparison of neural signal preprocessing methods and their impact on classification performance.
topic Neuroscience
Biotechnology
Science Policy
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
term memory network
reproducible electrophysiology dataset
particularly challenging problem
international brain laboratory
directional long short
channel attention bi
making stability within
accurately forecasting decision
making decoding model
making behavior
decoding decision
proposed model
model serves
remarkable capacity
novel perspective
neural decision
investigation furnishes
ibl ),
crucial purpose
bilstm ),