4.6 Article

Low-Rank Methods in Event Detection With Subsampled Point-to-Subspace Proximity Tests

Journal

IEEE ACCESS
Volume 10, Issue -, Pages 32525-32536

Publisher

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2022.3152206

Keywords

Sensors; Monitoring; Event detection; Internet of Things; Noise measurement; Time series analysis; Sparse matrices; Multidimensional signal processing; monitoring; matrix completion; point-to-subspace proximity; probably approximately correct learning

Funding

  1. Operational Programme Research, Development and Education (OP RDE) Project Research Center for Informatics'' [CZ.02.1.01/0.0/0.0/16_019/0000765]
  2. EU H2020 TAILOR Project [952215]

Ask authors/readers for more resources

Monitoring of streamed data using low-rank techniques is crucial for detecting abnormal behavior in applications such as Internet of Things. The proposed algorithm successfully recovers the subspace representation and performs event detection, showing promising results in the experimental evaluation using induction-loop data from Dublin, Ireland.
Monitoring of streamed data to detect abnormal behaviour (variously known as event detection, anomaly detection, change detection, or outlier detection) underlies many applications, especially within the Internet of Things. There, one often collects data from a variety of sources, with asynchronous sampling, and missing data. In this setting, one can detect abnormal behavior using low-rank techniques. In particular, we assume that normal observations come from a low-rank subspace, prior to being corrupted by a uniformly distributed noise. Correspondingly, we aim to recover a representation of the subspace, and perform event detection by running point-to-subspace distance query for incoming data. We use a variant of low-rank factorisation, which considers interval uncertainty sets around known entries, on a suitable flattening of the input data to obtain a low-rank model. On-line, we compute the distance of incoming data to the low-rank normal subspace and update the subspace to keep it consistent with the seasonal changes present. For the distance computation, we consider subsampling. We bound the one-sided error as a function of the number of coordinates employed. In our computational experiments, we test the proposed algorithm on induction-loop data from Dublin, Ireland.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.6
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available