Estimating intrinsic dimensionality of fMRI dataset incorporating an AR(1) noise model with cubic spline interpolation

Authors:
Xiaoping Xie;Zhitong Cao;Xuchu Weng;Dan Jin
Affiliations:
Physics Department, Zhejiang University, Hangzhou 310027, China;Physics Department, Zhejiang University, Hangzhou 310027, China;Laboratory for Higher Brain Function, Institute of Psychology, The Chinese Academy of Sciences, Beijing, China;Physics Department, Zhejiang University, Hangzhou 310027, China
Venue:
Neurocomputing
Year:
2009

Citing 9
Cited 0

Topology representing networks

Neural Networks
Numerical analysis: mathematics of scientific computing (2nd ed)

Numerical analysis: mathematics of scientific computing (2nd ed)
Nonlinear time series analysis

Nonlinear time series analysis
Bayesian PCA

Proceedings of the 1998 conference on Advances in neural information processing systems II
Estimating the Intrinsic Dimension of Data with a Fractal-Based Method

IEEE Transactions on Pattern Analysis and Machine Intelligence
An Algorithm for Finding Intrinsic Dimensionality of Data

IEEE Transactions on Computers
Stastical Estimation of the Intrinsic Dimensionality of a Noisy Signal Collection

IEEE Transactions on Computers
An Intrinsic Dimensionality Estimator from Near-Neighbor Information

IEEE Transactions on Pattern Analysis and Machine Intelligence
Paper: Modeling by shortest data description

Automatica (Journal of IFAC)

Quantified Score

Hi-index	0.01

Visualization

Abstract

Estimating the true dimensionality of the data to determine what is essential in the data is an important but a difficult problem in fMRI dataset. In this paper, cubic spline interpolation is introduced to detect the number of essential components in fMRI dataset. By constructing proper interpolation variable, more reasonable estimation of the coefficient of an autoregressive noise model of order 1 can be made. Simulation data and real fMRI dataset of resting-state in human brains are used to compare the performance of the new method incorporating an autoregressive noise model of order 1 with cubic spline interpolation (AR1CSI) with that of the method based only on an autoregressive noise model of order 1 (AR1). The results show the AR1CSI method leads to more accurate estimate of the model order at many circumstances, as illustrated in simulated datasets and real fMRI datasets of resting-state human brain.