Anomaly Detection for Non-stationary Time Series using Recurrent Wavelet Probabilistic Neural Network

TL;DR

This paper introduces an unsupervised neural network framework combining recurrent encoding and wavelet probabilistic modeling to detect anomalies in non-stationary time series data effectively.

Contribution

It presents a novel RWPNN architecture that extends wavelet probabilistic networks to handle high-dimensional data and adapt to varying data rates without strong distribution assumptions.

Findings

Effective anomaly detection on 45 real-world datasets.

Robust early warning capabilities for anomalous events.

Outperforms existing methods in non-stationary environments.

Abstract

In this paper, an unsupervised Recurrent Wavelet Probabilistic Neural Network (RWPNN) is proposed, which aims at detecting anomalies in non-stationary environments by modelling the temporal features using a nonparametric density estimation network. The novel framework consists of two components, a Stacked Recurrent Encoder-Decoder (SREnc-Dec) module that captures temporal features in a latent space, and a Multi-Receptive-field Wavelet Probabilistic Network (MRWPN) that creates an ensemble probabilistic model to characterise the latent space. This formulation extends the standard wavelet probabilistic networks to wavelet deep probabilistic networks, which can handle higher data dimensionality. The MRWPN module can adapt to different rates of data variation in different datasets without imposing strong distribution assumptions, resulting in a more robust and accurate detection for Time Series Anomaly Detection (TSAD) tasks in the non-stationary environment. We carry out the assessment on 45 real-world time series datasets from various domains, verify the performance of RWPNN in TSAD tasks with several constraints, and show its ability to provide early warnings for anomalous events.