Dataset: Rare Event Classification in Multivariate Time Series

TL;DR

This paper introduces a real-world multivariate time series dataset from the pulp-and-paper industry, focusing on rare event classification of paper breaks, useful for early prediction and data exploration.

Contribution

It provides a novel dataset for rare event classification in multivariate time series, enabling research in early prediction and data analysis in industrial settings.

Findings

Dataset contains sensor data and event labels for paper breaks.

Useful for developing early prediction models.

Supports exploration of multivariate time series data.

Abstract

A real-world dataset is provided from a pulp-and-paper manufacturing industry. The dataset comes from a multivariate time series process. The data contains a rare event of paper break that commonly occurs in the industry. The data contains sensor readings at regular time-intervals (x's) and the event label (y). The primary purpose of the data is thought to be building a classification model for early prediction of the rare event. However, it can also be used for multivariate time series data exploration and building other supervised and unsupervised models.