Publication detail

Machine Learning Method for Changepoint Detection in Short Time Series Data

SMEJKALOVÁ, V. ŠOMPLÁK, R. ROSECKÝ, M. ŠRAMKOVÁ, K.

Original Title

Machine Learning Method for Changepoint Detection in Short Time Series Data

Type

journal article in Web of Science

Language

English

Original Abstract

Analysis of data is crucial in waste management to improve effective planning from both short- and long-term perspectives. Real-world data often presents anomalies, but in the waste management sector, anomaly detection is seldom performed. The main goal and contribution of this paper is a proposal of a complex machine learning framework for changepoint detection in a large number of short time series from waste management. In such a case, it is not possible to use only an expert-based approach due to the time-consuming nature of this process and subjectivity. The proposed framework consists of two steps: (1) outlier detection via outlier test for trend-adjusted data, and (2) changepoints are identified via comparison of linear model parameters. In order to use the proposed method, it is necessary to have a sufficient number of experts’ assessments of the presence of anomalies in time series. The proposed framework is demonstrated on waste management data from the Czech Republic. It is observed that certain waste categories in specific regions frequently exhibit changepoints. On the micro-regional level, approximately 31.1% of time series contain at least one outlier and 16.4% exhibit changepoints. Certain groups of waste are more prone to the occurrence of anomalies. The results indicate that even in the case of aggregated data, anomalies are not rare, and their presence should always be checked.

Keywords

machine learning for time series; waste generation; short time series; anomaly detection; outlier; changepoint

Authors

SMEJKALOVÁ, V.; ŠOMPLÁK, R.; ROSECKÝ, M.; ŠRAMKOVÁ, K.

Released

5. 10. 2023

Publisher

MDPI

ISBN

2504-4990

Periodical

Machine Learning and Knowledge Extraction

Year of study

5

Number

4

State

Swiss Confederation

Pages from

1407

Pages to

1432

Pages count

26

URL

https://www.mdpi.com/2504-4990/5/4/71

Full text in the Digital Library

http://hdl.handle.net/11012/245096

BibTex

@article{BUT186887,
  author="Veronika {Smejkalová} and Radovan {Šomplák} and Martin {Rosecký} and Kristína {Šramková}",
  title="Machine Learning Method for Changepoint Detection in Short Time Series Data",
  journal="Machine Learning and Knowledge Extraction",
  year="2023",
  volume="5",
  number="4",
  pages="1407--1432",
  doi="10.3390/make5040071",
  issn="2504-4990",
  url="https://www.mdpi.com/2504-4990/5/4/71"
}