Unsupervised anomaly detection in multivariate time series with online evolving spiking neural networks

Abstract

With the increasing demand for digital products, processes and services the research area of automatic detection of signal outliers in streaming data has gained a lot of attention. The range of possible applications for this kind of algorithms is versatile and ranges from the monitoring of digital machinery and predictive maintenance up to applications in analyzing big data healthcare sensor data. In this paper we present a method for detecting anomalies in streaming multivariate times series by using an adapted evolving Spiking Neural Network. As the main components of this work we contribute (1) an alternative rank-order-based learning algorithm which uses the precise times of the incoming spikes for adjusting the synaptic weights, (2) an adapted, realtime-capable and efficient encoding technique for multivariate data based on multi-dimensional Gaussian Receptive Fields and (3) a continuous outlier scoring function for an improved interpretability of the classifications. Spiking neural networks are extremely efficient when it comes to process time dependent information. We demonstrate the effectiveness of our model on a synthetic dataset based on the Numenta Anomaly Benchmark with various anomaly types. We compare our algorithm to other streaming anomaly detecting algorithms and can prove that our algorithm performs better in detecting anomalies while demanding less computational resources for processing high dimensional data.

A Deep Spiking Neural Network Anomaly Detection Method

“…Using an adjusted evolving Spiking Neural Network, Dennis et al [ 9 ] presented a model for detecting anomalies in flowing multivariate time series. They contributed a substitute rank-order-based autoencoder that used the precise times of incoming spikes for adjusting network parameters, an adapted, real-time-capable, and reliable learning algorithm for multivariate data based on multidimensional Gaussian Receptive Fields, and a constant outlier scoring function for enhanced interpretability of the classifications.…”

“…For example, a severe simplifying assumption of simple neural networks concerns the view that the neural code used to exchange information between neurons is based on the average value of emitted spikes, a fact modeled as the propagation of continuous variables from one computing unit to another. But, it has been shown experimentally that not only is there not a constant propagation of spikes from which it is tentative to obtain their average value but also that the spikes appear periodically after the application of action and that the exact time of the spikes plays a significant role, if not the more critical role in neural information processing [ 9 ].…”

One Model to Find Them All Deep Learning for Multivariate Time-Series Anomaly Detection in Mobile Network Data

“…Modern approaches to time-series anomaly detection based on deep learning technology have flourished in recent years [6], [24], [25]. Due to their data-driven nature and achieved performance in multiple domains, generative models such as VAEs [15], and GANs [26] have gained relevance in the anomaly detection field [20], [21], [27]- [31].…”

SEHIDS: Self Evolving Host-Based Intrusion Detection System for IoT Networks

“…The use of this approach to devise evolving schemes for learning-based algorithms is not uncommon. The work presented in [74], for instance, uses a similar approach to evolve a simple version of Spiking Neural Networks and use it as an unsupervised anomaly detector. Another example is the unsupervised Growing Hierarchical Self-Organising Maps, which extend the fixed architecture of unsupervised self-organising maps by measuring the output error and then using it to determine the evolving orientation of the map [75].…”