Verification of statistical properties for hyperspectral images: Heteroscedasticity and non-stationarity

Jihao Yin; Chao Gao; Jianying Sun

Verification of statistical properties for hyperspectral images: Heteroscedasticity and non-stationarity

Jihao Yin
, Chao Gao
, Jianying Sun

School of Astronautics

Beihang University

Research output: Contribution to conference › Paper › peer-review

5 Scopus citations

Abstract

This paper investigates the heteroscedasticity and non-stationarity, two statistical properties, of hyperspectral remote sensing data. In the field of mathematical sciences, a collection of variables is heteroscedastic if there are sub-populations that have different variances or volatilities than others, while a non-stationary process refers to a stochastic process whose joint probability distribution are changing when shifted in time or space. To be treat as sequences, hyperspectral data are investigated via Bartlett Test and Wald-Wolfowitz Runs Test to verify the heteroscedasticity and non-stationarity, respectively. Most experimental results fail to pass Bartlett Test and Wald-Wolfowitz Runs Rest statistically significant, indicating that both heteroscedasticity and non-stationarity are intrinsic properties of spectral response sequence.

Original language	English
Pages	191-195
Number of pages	5
State	Published - 2013
Event	3rd International Conference on Digital Information Processing and Communications, ICDIPC 2013 - Dubai, United Arab Emirates Duration: 30 Jan 2013 → 1 Feb 2013

Conference

Conference	3rd International Conference on Digital Information Processing and Communications, ICDIPC 2013
Country/Territory	United Arab Emirates
City	Dubai
Period	30/01/13 → 1/02/13

Keywords

Heteroscedasticity
Hyperspectral data
Non-stationarity
P-value
Spectral response sequence

Cite this

@conference{c28e222b412f40358ac750f75e7928a5,

title = "Verification of statistical properties for hyperspectral images: Heteroscedasticity and non-stationarity",

abstract = "This paper investigates the heteroscedasticity and non-stationarity, two statistical properties, of hyperspectral remote sensing data. In the field of mathematical sciences, a collection of variables is heteroscedastic if there are sub-populations that have different variances or volatilities than others, while a non-stationary process refers to a stochastic process whose joint probability distribution are changing when shifted in time or space. To be treat as sequences, hyperspectral data are investigated via Bartlett Test and Wald-Wolfowitz Runs Test to verify the heteroscedasticity and non-stationarity, respectively. Most experimental results fail to pass Bartlett Test and Wald-Wolfowitz Runs Rest statistically significant, indicating that both heteroscedasticity and non-stationarity are intrinsic properties of spectral response sequence.",

keywords = "Heteroscedasticity, Hyperspectral data, Non-stationarity, P-value, Spectral response sequence",

author = "Jihao Yin and Chao Gao and Jianying Sun",

note = "Publisher Copyright: {\textcopyright} 2013 SDIWC.; 3rd International Conference on Digital Information Processing and Communications, ICDIPC 2013 ; Conference date: 30-01-2013 Through 01-02-2013",

year = "2013",

language = "英语",

pages = "191--195",

}

Verification of statistical properties for hyperspectral images: Heteroscedasticity and non-stationarity. / Yin, Jihao; Gao, Chao; Sun, Jianying.
2013. 191-195 Paper presented at 3rd International Conference on Digital Information Processing and Communications, ICDIPC 2013, Dubai, United Arab Emirates.

Research output: Contribution to conference › Paper › peer-review

TY - CONF

T1 - Verification of statistical properties for hyperspectral images

T2 - 3rd International Conference on Digital Information Processing and Communications, ICDIPC 2013

AU - Yin, Jihao

AU - Gao, Chao

AU - Sun, Jianying

PY - 2013

Y1 - 2013

N2 - This paper investigates the heteroscedasticity and non-stationarity, two statistical properties, of hyperspectral remote sensing data. In the field of mathematical sciences, a collection of variables is heteroscedastic if there are sub-populations that have different variances or volatilities than others, while a non-stationary process refers to a stochastic process whose joint probability distribution are changing when shifted in time or space. To be treat as sequences, hyperspectral data are investigated via Bartlett Test and Wald-Wolfowitz Runs Test to verify the heteroscedasticity and non-stationarity, respectively. Most experimental results fail to pass Bartlett Test and Wald-Wolfowitz Runs Rest statistically significant, indicating that both heteroscedasticity and non-stationarity are intrinsic properties of spectral response sequence.

AB - This paper investigates the heteroscedasticity and non-stationarity, two statistical properties, of hyperspectral remote sensing data. In the field of mathematical sciences, a collection of variables is heteroscedastic if there are sub-populations that have different variances or volatilities than others, while a non-stationary process refers to a stochastic process whose joint probability distribution are changing when shifted in time or space. To be treat as sequences, hyperspectral data are investigated via Bartlett Test and Wald-Wolfowitz Runs Test to verify the heteroscedasticity and non-stationarity, respectively. Most experimental results fail to pass Bartlett Test and Wald-Wolfowitz Runs Rest statistically significant, indicating that both heteroscedasticity and non-stationarity are intrinsic properties of spectral response sequence.

KW - Heteroscedasticity

KW - Hyperspectral data

KW - Non-stationarity

KW - P-value

KW - Spectral response sequence

UR - https://www.scopus.com/pages/publications/84978743849

M3 - 论文

AN - SCOPUS:84978743849

SP - 191

EP - 195

Y2 - 30 January 2013 through 1 February 2013

ER -

Verification of statistical properties for hyperspectral images: Heteroscedasticity and non-stationarity

Abstract

Conference

Keywords

Other files and links

Fingerprint

Cite this