A dynamic feature selection and intelligent model serving for hybrid batch-stream processing
作者：
Highlights：
• Integrating advantages of batch and stream processing in one architecture.
• Proposing dynamic feature selection compatible with hybrid processing.
• Providing various batch and stream models, and merging their results.
• An enhanced solution for accurate real-time anomaly detection.
摘要
•Integrating advantages of batch and stream processing in one architecture.•Proposing dynamic feature selection compatible with hybrid processing.•Providing various batch and stream models, and merging their results.•An enhanced solution for accurate real-time anomaly detection.
论文关键词：Dynamic feature selection,Model selection,Batch-stream hybrid processing,Genetic algorithm,Big data analytics
论文评审过程：Received 17 February 2022, Revised 17 August 2022, Accepted 18 August 2022, Available online 24 August 2022, Version of Record 14 September 2022.
论文官网地址：https://doi.org/10.1016/j.knosys.2022.109749
