Granular information has emerged as a potent tool for data represen-tation and processing across various domains.However,existing time series data granulation techniques often overlook the influence of external factors...Granular information has emerged as a potent tool for data represen-tation and processing across various domains.However,existing time series data granulation techniques often overlook the influence of external factors.In this study,a multisource time series data granularity conversion model is proposed that achieves granularity conversion effectively while maintaining result consis-tency and stability.The model incorporates the impact of external source data using a multivariate linear regression model,and the entropy weighting method is employed to allocate weights andfinalize the granularity conversion.Through experimental analysis using Beijing’s 2022 air quality dataset,our proposed method outperforms traditional information granulation approaches,providing valuable decision-making insights for industrial system optimization and research.展开更多
基金This work was supported by the National Key R&D Program of China under Grant No.2020YFB1710200.
文摘Granular information has emerged as a potent tool for data represen-tation and processing across various domains.However,existing time series data granulation techniques often overlook the influence of external factors.In this study,a multisource time series data granularity conversion model is proposed that achieves granularity conversion effectively while maintaining result consis-tency and stability.The model incorporates the impact of external source data using a multivariate linear regression model,and the entropy weighting method is employed to allocate weights andfinalize the granularity conversion.Through experimental analysis using Beijing’s 2022 air quality dataset,our proposed method outperforms traditional information granulation approaches,providing valuable decision-making insights for industrial system optimization and research.
