標題: A Sliced Inverse Regression (SIR) Decoding the Forelimb Movement from Neuronal Spikes in the Rat Motor Cortex
作者: Yang, Shih-Hung
Chen, You-Yin
Lin, Sheng-Huang
Liao, Lun-De
Lu, Henry Horng-Shing
Wang, Ching-Fu
Chen, Po-Chuan
Lo, Yu-Chun
Dat Phan, Thanh
Chao, Hsiang-Ya
Lin, Hui-Ching
Lai, Hsin-Yi
Huang, Wei-Chen
統計學研究所
Institute of Statistics
關鍵字: sliced inverse regression (SIR);neural decoding;forelimb movement prediction;neural networks (NN);principle component analysis (PCA)
公開日期: 9-十二月-2016
摘要: Several 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 (RCA) to achieve effective dimension reduction for nonlinear regression. To demonstrate the decoding performance, SIR was compared to PVA, OLE, and NN. Furthermore, RCA 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.
URI: http://dx.doi.org/10.3389/fnins.2016.00556
http://hdl.handle.net/11536/132743
ISSN: 1662-453X
DOI: 10.3389/fnins.2016.00556
期刊: FRONTIERS IN NEUROSCIENCE
Volume: 10
起始頁: 0
結束頁: 0
顯示於類別:期刊論文


文件中的檔案:

  1. 8de5ef9a518e0f1a8d9a3d61c5bdf0dd.pdf

若為 zip 檔案,請下載檔案解壓縮後,用瀏覽器開啟資料夾中的 index.html 瀏覽全文。