Application of Multivariable Time Series Classification and Clustering Algorithm
Yuqi Wang
DOI: https://doi.org/10.59429/pmcs.v5i4.1187
Keywords: Multivariate Time Series Classification; Clustering Algorithm; Applied Research
Abstract
With the advent of the era of big data and the development of artificial intelligence technology, more and more fields need to use time series analysis. In order to solve the clustering problem of multivariate time series, a deep learning-based algorithm is adopted, which is optimized by deep neural network. The algorithm uses different types of networks to complete the work of feature extraction, feature selection and classifier design in the process of data classification, so as to realize the effective clustering analysis of multivariate time series. At present, multi-source data clustering class analysis based on deep learning has become a research hotspot, but there is no mature and stable theoretical framework and perfect and practical technical scheme. This paper proposes an innovative algorithm, a multi-variable time series clustering algorithm based on deep learning, to solve two major problems faced by existing models and algorithms.
References
Ren YY, Wang CJ. Time series classification of remote sensing images with abnormal data [J]. Journal of Computer Applications, 2019,41(3):662-668. (in Chinese)
Wang KY, Du HD, Jia R, Liu H, Liang Y, Wang XY. Short-term interval probability prediction of photovoltaic power based on similar daily clustering and QR-CNN-BiLSTM model [J]. High Voltage Technology, 2019,48(11):4372-4384.
Zhang X, Zhang L, Jin B, Zhang HZ. Research on multivariate time series classification algorithm based on uncertainty [J]. Acta Automatica Sinica, 2023, 49(4): 790-804.