Please use this identifier to cite or link to this item: https://doi.org/10.3389/fnins.2016.00556
DC FieldValue
dc.titleA sliced inverse regression (SIR) decoding the forelimb movement from neuronal spikes in the rat motor cortex
dc.contributor.authorYang, S.-H
dc.contributor.authorChen, Y.-Y
dc.contributor.authorLin, S.-H
dc.contributor.authorLiao, L.-D
dc.contributor.authorLu, H.H.-S
dc.contributor.authorWang, C.-F
dc.contributor.authorChen, P.-C:
dc.contributor.authorLo, Y.-C
dc.contributor.authorPhan, T.D
dc.contributor.authorChao, H.-Y
dc.contributor.authorLin, H.-C
dc.contributor.authorLai, H.-Y
dc.contributor.authorHuang, W.-C
dc.date.accessioned2020-11-10T08:03:56Z
dc.date.available2020-11-10T08:03:56Z
dc.date.issued2016
dc.identifier.citationYang, S.-H, Chen, Y.-Y, Lin, S.-H, Liao, L.-D, Lu, H.H.-S, Wang, C.-F, Chen, P.-C:, Lo, Y.-C, Phan, T.D, Chao, H.-Y, Lin, H.-C, Lai, H.-Y, Huang, W.-C (2016). A sliced inverse regression (SIR) decoding the forelimb movement from neuronal spikes in the rat motor cortex. Frontiers in Neuroscience 10 (DEC) : 556. ScholarBank@NUS Repository. https://doi.org/10.3389/fnins.2016.00556
dc.identifier.issn16624548
dc.identifier.urihttps://scholarbank.nus.edu.sg/handle/10635/183358
dc.description.abstractSeveral neural decoding algorithms have successfully converted brain signals into commands to control a computer cursor and prosthetic devices. A majority of decoding methods, such as population vector algorithms (PVA), optimal linear estimators (OLE), and neural networks (NN), are effective in predicting movement kinematics, including movement direction, speed and trajectory but usually require a large number of neurons to achieve desirable performance. This study proposed a novel decoding algorithm even with signals obtained from a smaller numbers of neurons. We adopted sliced inverse regression (SIR) to predict forelimb movement from single-unit activities recorded in the rat primary motor (M1) cortex in a water-reward lever-pressing task. SIR performed weighted principal component analysis (PCA) to achieve effective dimension reduction for nonlinear regression. To demonstrate the decoding performance, SIR was compared to PVA, OLE, and NN. Furthermore, PCA and sequential feature selection (SFS) which are popular feature selection techniques were implemented for comparison of feature selection effectiveness. Among SIR, PVA, OLE, PCA, SFS, and NN decoding methods, the trajectories predicted by SIR (with a root mean square error, RMSE, of 8.47 � 1.32 mm) was closer to the actual trajectories compared with those predicted by PVA (30.41 � 11.73 mm), OLE (20.17 � 6.43 mm), PCA (19.13 � 0.75 mm), SFS (22.75 � 2.01 mm), and NN (16.75 � 2.02 mm). The superiority of SIR was most obvious when the sample size of neurons was small. We concluded that SIR sorted the input data to obtain the effective transform matrices for movement prediction, making it a robust decoding method for conditions with sparse neuronal information. @ 2016 Yang, Chen, Lin, Liao, Lu, Wang, Chen, Lo, Phan, Chao, Lin, Lai and Huang.
dc.rightsAttribution 4.0 International
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.sourceUnpaywall 20201031
dc.subjectanimal cell
dc.subjectanimal experiment
dc.subjectcomparative effectiveness
dc.subjectforelimb
dc.subjectintermethod comparison
dc.subjectmotor cortex
dc.subjectnonhuman
dc.subjectprediction
dc.subjectprincipal component analysis
dc.subjectreward
dc.subjectsample size
dc.subjectsingle unit activity
dc.subjectspike
dc.typeArticle
dc.contributor.departmentLIFE SCIENCES INSTITUTE
dc.description.doi10.3389/fnins.2016.00556
dc.description.sourcetitleFrontiers in Neuroscience
dc.description.volume10
dc.description.issueDEC
dc.description.page556
Appears in Collections:Staff Publications
Elements

Show simple item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
10_3389_fnins_2016_00556.pdf1.65 MBAdobe PDF

OPEN

NoneView/Download

SCOPUSTM   
Citations

1
checked on Jun 7, 2021

Page view(s)

50
checked on Jun 10, 2021

Google ScholarTM

Check

Altmetric


This item is licensed under a Creative Commons License Creative Commons