Home > Research > Publications & Outputs > Interpolating the missing values for multi-dime...

Links

Text available via DOI:

View graph of relations

Interpolating the missing values for multi-dimensional spatial-temporal sensor data: A tensor SVD approach

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

Interpolating the missing values for multi-dimensional spatial-temporal sensor data : A tensor SVD approach. / Xu, Peipei; Ruan, Wenjie; Sheng, Quan Z. et al.

14th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MobiQuitous 2017. Association for Computing Machinery (ACM), 2017. p. 442-451.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Xu, P, Ruan, W, Sheng, QZ, Gu, T & Yao, L 2017, Interpolating the missing values for multi-dimensional spatial-temporal sensor data: A tensor SVD approach. in 14th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MobiQuitous 2017. Association for Computing Machinery (ACM), pp. 442-451, 14th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MobiQuitous 2017, Melbourne, Australia, 7/11/17. https://doi.org/10.1145/3144457.3144474

APA

Xu, P., Ruan, W., Sheng, Q. Z., Gu, T., & Yao, L. (2017). Interpolating the missing values for multi-dimensional spatial-temporal sensor data: A tensor SVD approach. In 14th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MobiQuitous 2017 (pp. 442-451). Association for Computing Machinery (ACM). https://doi.org/10.1145/3144457.3144474

Vancouver

Xu P, Ruan W, Sheng QZ, Gu T, Yao L. Interpolating the missing values for multi-dimensional spatial-temporal sensor data: A tensor SVD approach. In 14th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MobiQuitous 2017. Association for Computing Machinery (ACM). 2017. p. 442-451 doi: 10.1145/3144457.3144474

Author

Xu, Peipei ; Ruan, Wenjie ; Sheng, Quan Z. et al. / Interpolating the missing values for multi-dimensional spatial-temporal sensor data : A tensor SVD approach. 14th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MobiQuitous 2017. Association for Computing Machinery (ACM), 2017. pp. 442-451

Bibtex

@inproceedings{1a5560bd5cf64768b01ce61a9f6947b7,
title = "Interpolating the missing values for multi-dimensional spatial-temporal sensor data: A tensor SVD approach",
abstract = "With the booming of the Internet of Things, enormous number of smart devices/sensors have been deployed in the physical world to monitor our surroundings. Usually those devices generate high-dimensional geo-tagged time-series data. However, these sensor readings are easily missing due to the hardware malfunction, connection errors or data corruption, which severely compromise the back-end data analysis. To solve this problem, in this paper we exploit tensor-based Singular Value Decomposition method to recover the missing sensor readings. The main novelty of this paper lies in that, i) our tensor-based recovery method can well capture the multi-dimensional spatial and temporal features by transforming the irregularly deployed sensors into a sensor-array and folding the periodic temporal patterns into multiple time dimensions, ii) it only requires to tune one key parameter in an unsupervised manner, and iii) Tensor Singular Value Decomposition structure is more efficient on representation of high-dimension sensor data than other tensor recovery methods based on tensor{\textquoteright}s vectorization or flattening. The experimental results in several real-world one-year air quality and meteorology datasets demonstrate the effectiveness and accuracy of our approach.",
keywords = "ADMM, Sensor Data Recovery, T-SVD, Tensor Completion",
author = "Peipei Xu and Wenjie Ruan and Sheng, {Quan Z.} and Tao Gu and Lina Yao",
year = "2017",
month = nov,
day = "7",
doi = "10.1145/3144457.3144474",
language = "English",
isbn = "9781450353687",
pages = "442--451",
booktitle = "14th EAI International Conference on Mobile and Ubiquitous Systems",
publisher = "Association for Computing Machinery (ACM)",
address = "United States",
note = "14th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MobiQuitous 2017 ; Conference date: 07-11-2017 Through 10-11-2017",

}

RIS

TY - GEN

T1 - Interpolating the missing values for multi-dimensional spatial-temporal sensor data

T2 - 14th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MobiQuitous 2017

AU - Xu, Peipei

AU - Ruan, Wenjie

AU - Sheng, Quan Z.

AU - Gu, Tao

AU - Yao, Lina

PY - 2017/11/7

Y1 - 2017/11/7

N2 - With the booming of the Internet of Things, enormous number of smart devices/sensors have been deployed in the physical world to monitor our surroundings. Usually those devices generate high-dimensional geo-tagged time-series data. However, these sensor readings are easily missing due to the hardware malfunction, connection errors or data corruption, which severely compromise the back-end data analysis. To solve this problem, in this paper we exploit tensor-based Singular Value Decomposition method to recover the missing sensor readings. The main novelty of this paper lies in that, i) our tensor-based recovery method can well capture the multi-dimensional spatial and temporal features by transforming the irregularly deployed sensors into a sensor-array and folding the periodic temporal patterns into multiple time dimensions, ii) it only requires to tune one key parameter in an unsupervised manner, and iii) Tensor Singular Value Decomposition structure is more efficient on representation of high-dimension sensor data than other tensor recovery methods based on tensor’s vectorization or flattening. The experimental results in several real-world one-year air quality and meteorology datasets demonstrate the effectiveness and accuracy of our approach.

AB - With the booming of the Internet of Things, enormous number of smart devices/sensors have been deployed in the physical world to monitor our surroundings. Usually those devices generate high-dimensional geo-tagged time-series data. However, these sensor readings are easily missing due to the hardware malfunction, connection errors or data corruption, which severely compromise the back-end data analysis. To solve this problem, in this paper we exploit tensor-based Singular Value Decomposition method to recover the missing sensor readings. The main novelty of this paper lies in that, i) our tensor-based recovery method can well capture the multi-dimensional spatial and temporal features by transforming the irregularly deployed sensors into a sensor-array and folding the periodic temporal patterns into multiple time dimensions, ii) it only requires to tune one key parameter in an unsupervised manner, and iii) Tensor Singular Value Decomposition structure is more efficient on representation of high-dimension sensor data than other tensor recovery methods based on tensor’s vectorization or flattening. The experimental results in several real-world one-year air quality and meteorology datasets demonstrate the effectiveness and accuracy of our approach.

KW - ADMM

KW - Sensor Data Recovery

KW - T-SVD

KW - Tensor Completion

U2 - 10.1145/3144457.3144474

DO - 10.1145/3144457.3144474

M3 - Conference contribution/Paper

AN - SCOPUS:85052517467

SN - 9781450353687

SP - 442

EP - 451

BT - 14th EAI International Conference on Mobile and Ubiquitous Systems

PB - Association for Computing Machinery (ACM)

Y2 - 7 November 2017 through 10 November 2017

ER -