Novelty detection in data streams is the task of detecting concepts that were not known prior, in streams of data. Many machine learning algorithms have been proposed to detect these novelties, as well as integrate them. This study provides a systematic literature review of the state of novelty detection in data streams, including its advancement in recent years, its main challenges and solutions, an updated taxonomy for the classification of the proposed frameworks, and a comparative analysis of different key algorithms in this field. Additionally, we highlight ongoing challenges and future research directions that could be tackled moving forward.

中文翻译：

---

数据流中新颖性检测的系统文献综述：挑战与机遇

数据流中的新颖性检测是检测数据流中先前未知的概念的任务。人们已经提出了许多机器学习算法来检测这些新奇事物并将它们集成。本研究对数据流中新颖性检测的状态进行了系统的文献综述，包括近年来的进展、主要挑战和解决方案、所提出框架分类的更新分类法，以及不同关键算法的比较分析。这个领域。此外，我们还强调了当前的挑战和可以解决的未来研究方向。