A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Irregularly Sampled Multivariate Time Series Classification: A Graph Learning Approach
https://orcid.org/0000-0002-8637-8375
https://orcid.org/0000-0003-4925-2033
https://orcid.org/0000-0001-7167-6970
https://orcid.org/0000-0002-9363-9908
To date, graph-based learning methods are proven to be effective for modeling spatial and structural dependencies. However, when applied to IS-MTS, they encounter three major challenges due to the complex data characteristics of IS-MTS: 1) variable time intervals between observations; 2) asynchronous time points across dimensions; and 3) a lack of prior knowledge of connectivity structure for message propagation. To fill these gaps, we propose a multivariate temporal graph network to coherently capture structural interactions, learn temporal dependencies, and handle challenging characteristics of IS-MTS data. Specifically, we first build a multivariate interaction module to handle frequent missing values and extract the graph structure relation automatically. Second, we design a novel adjacent graph propagation mechanism to aggregate the neighbor information from multistep snapshots. Third, we construct a masked temporal-aware attention module to explicitly consider the timestamp context and interval irregularity. Based on an extensive experimental evaluation, we demonstrate the superior performance of the proposed method.
Irregularly Sampled Multivariate Time Series Classification: A Graph Learning Approach
https://orcid.org/0000-0002-8637-8375
https://orcid.org/0000-0003-4925-2033
https://orcid.org/0000-0001-7167-6970
https://orcid.org/0000-0002-9363-9908
To date, graph-based learning methods are proven to be effective for modeling spatial and structural dependencies. However, when applied to IS-MTS, they encounter three major challenges due to the complex data characteristics of IS-MTS: 1) variable time intervals between observations; 2) asynchronous time points across dimensions; and 3) a lack of prior knowledge of connectivity structure for message propagation. To fill these gaps, we propose a multivariate temporal graph network to coherently capture structural interactions, learn temporal dependencies, and handle challenging characteristics of IS-MTS data. Specifically, we first build a multivariate interaction module to handle frequent missing values and extract the graph structure relation automatically. Second, we design a novel adjacent graph propagation mechanism to aggregate the neighbor information from multistep snapshots. Third, we construct a masked temporal-aware attention module to explicitly consider the timestamp context and interval irregularity. Based on an extensive experimental evaluation, we demonstrate the superior performance of the proposed method.
Irregularly Sampled Multivariate Time Series Classification: A Graph Learning Approach
https://orcid.org/0000-0002-8637-8375
https://orcid.org/0000-0003-4925-2033
https://orcid.org/0000-0001-7167-6970
https://orcid.org/0000-0002-9363-9908
To date, graph-based learning methods are proven to be effective for modeling spatial and structural dependencies. However, when applied to IS-MTS, they encounter three major challenges due to the complex data characteristics of IS-MTS: 1) variable time intervals between observations; 2) asynchronous time points across dimensions; and 3) a lack of prior knowledge of connectivity structure for message propagation. To fill these gaps, we propose a multivariate temporal graph network to coherently capture structural interactions, learn temporal dependencies, and handle challenging characteristics of IS-MTS data. Specifically, we first build a multivariate interaction module to handle frequent missing values and extract the graph structure relation automatically. Second, we design a novel adjacent graph propagation mechanism to aggregate the neighbor information from multistep snapshots. Third, we construct a masked temporal-aware attention module to explicitly consider the timestamp context and interval irregularity. Based on an extensive experimental evaluation, we demonstrate the superior performance of the proposed method.
Irregularly Sampled Multivariate Time Series Classification: A Graph Learning Approach
Wang, Zhen (author) / Jiang, Ting (author) / Xu, Zenghui (author) / Zhang, Ji (author) / Gao, Jianliang (author)
IEEE Intelligent Systems ; 38 ; 3-11
2023-05-01
1757633 byte
Article (Journal)
Electronic Resource
English
Irregularly Sampled Transit Vehicles Used as Traffic Sensors
| British Library Online Contents | 2000
High resolution reconstruction of irregularly sampled, aliased measurements
| British Library Conference Proceedings | 2009
Modelling of irregularly sampled surfaces by two-dimensional snakes
| Online Contents | 2003
IRREGULARLY-SHAPED-BLOCK INVERTING DEVICE AND IRREGULARLY-SHAPED-BLOCK PLACEMENT METHOD
| European Patent Office | 2017