📄 中文摘要
单变量时间序列中的异常检测是数据分析和监控领域的重要任务。该研究综述了当前在这一领域的最新技术和方法，包括基于统计、机器学习和深度学习的算法。通过对不同方法的比较，分析了它们在检测精度、计算效率和应用场景等方面的优势与不足。此外，研究还探讨了未来的研究方向，强调了对实时监控和大数据处理能力的需求。随着技术的不断进步，异常检测在金融、医疗、工业等多个领域的应用前景广阔。
单变量时间序列中的异常检测：最新进展综述
📄 English Summary
Anomaly Detection in Univariate Time-series: A Survey on the State-of-the-Art
Anomaly detection in univariate time-series is a critical task in data analysis and monitoring. This survey reviews the latest techniques and methods in this domain, including statistical, machine learning, and deep learning-based algorithms. By comparing various approaches, the advantages and limitations in terms of detection accuracy, computational efficiency, and application scenarios are analyzed. Furthermore, future research directions are discussed, emphasizing the need for real-time monitoring and big data processing capabilities. With the continuous advancement of technology, the application prospects of anomaly detection are broad across multiple fields such as finance, healthcare, and industry.