An Event based Prediction Suffix Tree
This work addresses event-based prediction for applications like anomaly detection or pattern recognition, but it appears incremental as it builds on existing suffix tree methods with a focus on event-based data.
The paper tackles the problem of predicting event-based data by introducing the Event-based Prediction Suffix Tree (EPST), a biologically inspired algorithm that learns online and makes predictions over multiple overlapping patterns, demonstrating properties like fault tolerance and one-shot learning in synthetic tasks with noise, jitter, and dropout.
This article introduces the Event based Prediction Suffix Tree (EPST), a biologically inspired, event-based prediction algorithm. The EPST learns a model online based on the statistics of an event based input and can make predictions over multiple overlapping patterns. The EPST uses a representation specific to event based data, defined as a portion of the power set of event subsequences within a short context window. It is explainable, and possesses many promising properties such as fault tolerance, resistance to event noise, as well as the capability for one-shot learning. The computational features of the EPST are examined in a synthetic data prediction task with additive event noise, event jitter, and dropout. The resulting algorithm outputs predicted projections for the near term future of the signal, which may be applied to tasks such as event based anomaly detection or pattern recognition.