Fast Mining and Dynamic Time-to-Event Prediction over Multi-sensor Data Streams

TL;DR

This paper introduces TimeCast, a scalable, adaptive framework for real-time prediction of machine failures from multi-sensor data streams, effectively capturing evolving patterns to improve accuracy and efficiency.

Contribution

We propose a novel dynamic prediction framework that identifies evolving data patterns and learns separate models for each, enhancing real-time failure prediction accuracy.

Findings

TimeCast outperforms existing methods in prediction accuracy.

It effectively detects dynamic pattern changes in data streams.

The approach scales linearly and supports online updates.

Abstract

Given real-time sensor data streams obtained from machines, how can we continuously predict when a machine failure will occur? This work aims to continuously forecast the timing of future events by analyzing multi-sensor data streams. A key characteristic of real-world data streams is their dynamic nature, where the underlying patterns evolve over time. To address this, we present TimeCast, a dynamic prediction framework designed to adapt to these changes and provide accurate, real-time predictions of future event time. Our proposed method has the following properties: (a) Dynamic: it identifies the distinct time-evolving patterns (i.e., stages) and learns individual models for each, enabling us to make adaptive predictions based on pattern shifts. (b) Practical: it finds meaningful stages that capture time-varying interdependencies between multiple sensors and improve prediction performance; (c) Scalable: our algorithm scales linearly with the input size and enables online model updates on data streams. Extensive experiments on real datasets demonstrate that TimeCast provides higher prediction accuracy than state-of-the-art methods while finding dynamic changes in data streams with a great reduction in computational time.