Abstract
In this paper, we propose a mixture of probabilistic partial canonical correlation analysis (MPPCCA) that extracts the Causal Patterns from two multivariate time series. Causal patterns refer to the signal patterns within interactions of two elements having multiple types of mutually causal relationships, rather than a mixture of simultaneous correlations or the absence of presence of a causal relationship between the elements. In multivariate statistics, partial canonical correlation analysis (PCCA) evaluates the correlation between two multivariates after subtracting the effect of the third multivariate. PCCA can calculate the Granger Causality Index (which tests whether a time-series can be predicted from another time-series), but is not applicable to data containing multiple partial canonical correlations. After introducing the MPPCCA, we propose an expectation-maxmization (EM) algorithm that estimates the parameters and latent variables of the MPPCCA. The MPPCCA is expected to extract multiple partial canonical correlations from data series without any supervised signals to split the data as clusters. The method was then evaluated in synthetic data experiments. In the synthetic dataset, our method estimated the multiple partial canonical correlations more accurately than the existing method. To determine the types of patterns detectable by the method, experiments were also conducted on real datasets. The method estimated the communication patterns In motion-capture data. The MPPCCA is applicable to various type of signals such as brain signals, human communication and nonlinear complex multibody systems.
| Original language | English |
|---|---|
| Title of host publication | Proceedings - 2017 International Conference on Data Science and Advanced Analytics, DSAA 2017 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 744-754 |
| Number of pages | 11 |
| ISBN (Electronic) | 9781509050048 |
| DOIs | |
| Publication status | Published - 2018 Jan 16 |
| Event | 4th International Conference on Data Science and Advanced Analytics, DSAA 2017 - Tokyo, Japan Duration: 2017 Oct 19 → 2017 Oct 21 |
Publication series
| Name | Proceedings - 2017 International Conference on Data Science and Advanced Analytics, DSAA 2017 |
|---|---|
| Volume | 2018-January |
Conference
| Conference | 4th International Conference on Data Science and Advanced Analytics, DSAA 2017 |
|---|---|
| Country | Japan |
| City | Tokyo |
| Period | 17/10/19 → 17/10/21 |
Fingerprint
Keywords
- Causal pattern
- Granger causality
- Mixture model
- Probabilistic partial canonical correlation analysis
ASJC Scopus subject areas
- Signal Processing
- Information Systems and Management
- Statistics, Probability and Uncertainty
- Computer Networks and Communications
Cite this
Causal patterns : Extraction of multiple causal relationships by mixture of probabilistic partial canonical correlation analysis. / Mori, Hiroki; Kawano, Keisuke; Yokoyama, Hiroki.
Proceedings - 2017 International Conference on Data Science and Advanced Analytics, DSAA 2017. Institute of Electrical and Electronics Engineers Inc., 2018. p. 744-754 (Proceedings - 2017 International Conference on Data Science and Advanced Analytics, DSAA 2017; Vol. 2018-January).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Causal patterns
T2 - Extraction of multiple causal relationships by mixture of probabilistic partial canonical correlation analysis
AU - Mori, Hiroki
AU - Kawano, Keisuke
AU - Yokoyama, Hiroki
PY - 2018/1/16
Y1 - 2018/1/16
N2 - In this paper, we propose a mixture of probabilistic partial canonical correlation analysis (MPPCCA) that extracts the Causal Patterns from two multivariate time series. Causal patterns refer to the signal patterns within interactions of two elements having multiple types of mutually causal relationships, rather than a mixture of simultaneous correlations or the absence of presence of a causal relationship between the elements. In multivariate statistics, partial canonical correlation analysis (PCCA) evaluates the correlation between two multivariates after subtracting the effect of the third multivariate. PCCA can calculate the Granger Causality Index (which tests whether a time-series can be predicted from another time-series), but is not applicable to data containing multiple partial canonical correlations. After introducing the MPPCCA, we propose an expectation-maxmization (EM) algorithm that estimates the parameters and latent variables of the MPPCCA. The MPPCCA is expected to extract multiple partial canonical correlations from data series without any supervised signals to split the data as clusters. The method was then evaluated in synthetic data experiments. In the synthetic dataset, our method estimated the multiple partial canonical correlations more accurately than the existing method. To determine the types of patterns detectable by the method, experiments were also conducted on real datasets. The method estimated the communication patterns In motion-capture data. The MPPCCA is applicable to various type of signals such as brain signals, human communication and nonlinear complex multibody systems.
AB - In this paper, we propose a mixture of probabilistic partial canonical correlation analysis (MPPCCA) that extracts the Causal Patterns from two multivariate time series. Causal patterns refer to the signal patterns within interactions of two elements having multiple types of mutually causal relationships, rather than a mixture of simultaneous correlations or the absence of presence of a causal relationship between the elements. In multivariate statistics, partial canonical correlation analysis (PCCA) evaluates the correlation between two multivariates after subtracting the effect of the third multivariate. PCCA can calculate the Granger Causality Index (which tests whether a time-series can be predicted from another time-series), but is not applicable to data containing multiple partial canonical correlations. After introducing the MPPCCA, we propose an expectation-maxmization (EM) algorithm that estimates the parameters and latent variables of the MPPCCA. The MPPCCA is expected to extract multiple partial canonical correlations from data series without any supervised signals to split the data as clusters. The method was then evaluated in synthetic data experiments. In the synthetic dataset, our method estimated the multiple partial canonical correlations more accurately than the existing method. To determine the types of patterns detectable by the method, experiments were also conducted on real datasets. The method estimated the communication patterns In motion-capture data. The MPPCCA is applicable to various type of signals such as brain signals, human communication and nonlinear complex multibody systems.
KW - Causal pattern
KW - Granger causality
KW - Mixture model
KW - Probabilistic partial canonical correlation analysis
UR - http://www.scopus.com/inward/record.url?scp=85046276055&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85046276055&partnerID=8YFLogxK
U2 - 10.1109/DSAA.2017.60
DO - 10.1109/DSAA.2017.60
M3 - Conference contribution
AN - SCOPUS:85046276055
T3 - Proceedings - 2017 International Conference on Data Science and Advanced Analytics, DSAA 2017
SP - 744
EP - 754
BT - Proceedings - 2017 International Conference on Data Science and Advanced Analytics, DSAA 2017
PB - Institute of Electrical and Electronics Engineers Inc.
ER -