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.
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.