@article{Chen2024, 
author = {Pengyu Chen and Wendi He and Wenxuan Ma and Xiangdong Huang and Chen Wang},
title = {IoTDQ: An Industrial IoT Data Analysis Library for Apache IoTDB},
year = {2024},
journal = {Big Data Mining and Analytics},
volume = {7},
number = {1},
pages = {29-41},
keywords = {industrial big data, data quality, data mining and analytics},
url = {https://www.sciopen.com/article/10.26599/BDMA.2023.9020010},
doi = {10.26599/BDMA.2023.9020010},
abstract = {There is a growing demand for time series data analysis in industry areas. Apache IoTDB is a time series database designed for the Internet of Things (IoT) with enhanced storage and I/O performance. With User-Defined Functions (UDF) provided, computation for time series can be executed on Apache IoTDB directly. To satisfy most of the common requirements in industrial time series analysis, we create a UDF library, IoTDQ, on Apache IoTDB. This library integrates stream computation functions on data quality analysis, data profiling, anomaly detection, data repairing, etc. IoTDQ enables users to conduct a wide range of analyses, such as monitoring, error diagnosis, equipment reliability analysis. It provides a framework for users to examine IoT time series with data quality problems. Experiments show that IoTDQ keeps the same level of performance compared to mainstream alternatives, and shortens I/O consumption for Apache IoTDB users.}
}