@inproceedings{964efce898e44689a4e1ea2f8a885136,
title = "Cleanits-MEDetect: Multiple Errors Detection for Time Series Data in Cleanits",
abstract = "Data quality problems are seriously prevalent in time series data, and the data suffer from types of errors including single-point errors, continuous errors, and contextual errors. Since it is challenging to achieve high accuracy and efficiency in error detection tasks for time series data, we develop error detection system MEDetect in Cleanits, a data cleaning tool for multi-dimensional industrial time series. We propose an integration detection model for multiple errors, which holds the hierarchical variational automatic encoder as the main structure, and we propose a dimensionality reduction method for k-shape based cluster- ing algorithm, which reduces the time costs of the detection process. MEDetect is designed to allow customized error detection, and users can choose detection and repairing algorithms on their demands.",
keywords = "Error detection, Hierarchical structure, Time series data quality",
author = "Xiaoou Ding and Yichen Song and Hongzhi Wang and Donghua Yang and Yida Liu",
note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 28th International Conference on Database Systems for Advanced Applications, DASFAA 2023 ; Conference date: 17-04-2023 Through 20-04-2023",
year = "2023",
doi = "10.1007/978-3-031-30678-5\_54",
language = "英语",
isbn = "9783031306778",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "674--678",
editor = "Xin Wang and Sapino, \{Maria Luisa\} and Wook-Shin Han and \{El Abbadi\}, Amr and Gill Dobbie and Zhiyong Feng and Yingxiao Shao and Hongzhi Yin",
booktitle = "Database Systems for Advanced Applications - 28th International Conference, DASFAA 2023, Proceedings",
address = "德国",
}