A spectral-based approach for clustering of multivariate time series

碩士 === 國立臺北大學 === 統計學系 === 100 === The application of spectral analysis in time series clustering can overcome the problem of starting point or different scaling, and it can enhance the data reduction. However, the relative researches for multivariate time series clustering are rare, we propose the...

Full description

Bibliographic Details
Main Authors:	Lee, Chihchieh, 李志傑
Other Authors:	Lin, Tsairchuan
Format:	Others
Language:	zh-TW
Published:	2012
Online Access:	http://ndltd.ncl.edu.tw/handle/02712332477362275365

id	ndltd-TW-100NTPU0337002
record_format	oai_dc
spelling	ndltd-TW-100NTPU03370022015-10-13T21:12:08Z http://ndltd.ncl.edu.tw/handle/02712332477362275365 A spectral-based approach for clustering of multivariate time series 利用頻譜分析於多變量時間序列分群 Lee, Chihchieh 李志傑碩士國立臺北大學統計學系 100 The application of spectral analysis in time series clustering can overcome the problem of starting point or different scaling, and it can enhance the data reduction. However, the relative researches for multivariate time series clustering are rare, we propose the multi-dimension Linear Predictive Coding (LPC) cepstrum by using the Euclidean distance between two time series as their dissimilarity measure for time series clustering. In the simulations , we find that multivariate Linear Predictive Coding clustering perform better than other multivariate spectral clustering beyond on the simulated or silhouette criteria. We also apply this method for the international stock market clustering. Lin, Tsairchuan 林財川 2012 學位論文 ; thesis 75 zh-TW
collection	NDLTD
language	zh-TW
format	Others
sources	NDLTD
description	碩士 === 國立臺北大學 === 統計學系 === 100 === The application of spectral analysis in time series clustering can overcome the problem of starting point or different scaling, and it can enhance the data reduction. However, the relative researches for multivariate time series clustering are rare, we propose the multi-dimension Linear Predictive Coding (LPC) cepstrum by using the Euclidean distance between two time series as their dissimilarity measure for time series clustering. In the simulations , we find that multivariate Linear Predictive Coding clustering perform better than other multivariate spectral clustering beyond on the simulated or silhouette criteria. We also apply this method for the international stock market clustering.
author2	Lin, Tsairchuan
author_facet	Lin, Tsairchuan Lee, Chihchieh 李志傑
author	Lee, Chihchieh 李志傑
spellingShingle	Lee, Chihchieh 李志傑 A spectral-based approach for clustering of multivariate time series
author_sort	Lee, Chihchieh
title	A spectral-based approach for clustering of multivariate time series
title_short	A spectral-based approach for clustering of multivariate time series
title_full	A spectral-based approach for clustering of multivariate time series
title_fullStr	A spectral-based approach for clustering of multivariate time series
title_full_unstemmed	A spectral-based approach for clustering of multivariate time series
title_sort	spectral-based approach for clustering of multivariate time series
publishDate	2012
url	http://ndltd.ncl.edu.tw/handle/02712332477362275365
work_keys_str_mv	AT leechihchieh aspectralbasedapproachforclusteringofmultivariatetimeseries AT lǐzhìjié aspectralbasedapproachforclusteringofmultivariatetimeseries AT leechihchieh lìyòngpínpǔfēnxīyúduōbiànliàngshíjiānxùlièfēnqún AT lǐzhìjié lìyòngpínpǔfēnxīyúduōbiànliàngshíjiānxùlièfēnqún AT leechihchieh spectralbasedapproachforclusteringofmultivariatetimeseries AT lǐzhìjié spectralbasedapproachforclusteringofmultivariatetimeseries
_version_	1718057108624113664

A spectral-based approach for clustering of multivariate time series

Similar Items