Hankel-structured Tensor Robust PCA for Multivariate Traffic Time Series Anomaly Detection

Abstract

Spatiotemporal traffic data (e.g., link speed/flow) collected from sensor networks can be organized as multivariate time series with additional spatial attributes. A crucial task in analyzing such data is to identify and detect anomalous observations and events from the data with complex spatial and temporal dependencies. Robust Principal Component Analysis (RPCA) is a widely used tool for anomaly detection. However, the traditional RPCA purely relies on the global low-rank assumption while ignoring the local temporal correlations. In light of this, this study proposes a Hankel-structured tensor version of RPCA for anomaly detection in spatiotemporal data. We treat the raw data with anomalies as a multivariate time series matrix (location × time) and assume the denoised matrix has a lowrank structure. Then we transform the low-rank matrix to a third-order tensor by applying temporal Hankelization. In the end, we decompose the corrupted matrix into a low-rank Hankel tensor and a sparse matrix. With the Hankelization operation, the model can simultaneously capture the global and local spatiotemporal correlations and exhibit more robust performance. We formulate the problem as an optimization problem and use tensor nuclear norm (TNN) to approximate the tensor rank and l1 norm to approximate the sparsity. We develop an efficient solution algorithm based on the Alternating Direction Method of Multipliers (ADMM). Despite having three hyper-parameters, the model is easy to set in practice. We evaluate the proposed method by synthetic data and metro passenger flow time series and the results demonstrate the accuracy of anomaly detection.

Anti-circulant dynamic mode decomposition with sparsity-promoting for highway traffic dynamics analysis

“…The most common way to enable linear approximation is through data augmentation. Hankel dynamic mode decomposition (HankelDMD) employs DMD on a Hankel transformation of data (Brunton et al, 2016a;Avila and Mezić, 2020;Lehmberg et al, 2021;Wang et al, 2021). Given an N × T matrix X, the Hankel matrix H ∈ R N τ ×(T −τ +1) with the delay embedding length τ is defined as…”

IoT Anomaly Detection Based on Autoencoder and Bayesian Gaussian Mixture Model

“…[9]. Traditional methods in this category include principal component analysis (PCA) with explicit linear projections [10], kernel PCA (KPCA) with implicit nonlinear predictions induced by a specific kernel [11], and robust PCA (RPCA) that makes PCA less sensitive to noise by enforcing sparse structure [12]. However, the performance of the reconstruction-based anomaly detection method is limited.…”