A clustering based variable sub-window approach using particle swarm optimisation for biomedical sensor data monitoring

ABSTRACT

Advances in information technologies enable data to be ubiquitously generated from sensors, especially in the industrial healthcare research and application fields. The aim is to develop an adaptive windowing pre-processing approach using clustering-based metaheuristics search for biomedical data stream classification, which uses a sliding window to scan the multivariate data stream segment to segment. Our new model is put under test with other temporal data stream pre-processing methods on those biomedical sensor datasets. The experiments give higher accuracy and less time cost especially in dynamically adjusting the window size according to clustering outcomes that are optimised by metaheuristics.

KEYWORDS:

• Data stream mining
• biomedical healthcare
• sensor
• pre-processing
• metaheuristics
• adaptive windowing

Acknowledgements

This research was supported by Fujian Provincial Key Laboratory of Data-Intensive Computing, Fujian University Laboratory of Intelligent Computing and Information Processing, and Fujian Provincial Big Data Research Institute of Intelligent Manufacturing.

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

This research was funded by the Research Grant, titled Temporal Data Stream Mining by Using Incrementally Optimized Very Fast Decision Forest (iOVFDF), Grant no. MYRG2015-00128-FST, offered by the University of Macau, FST, and RDAO.