Search

Time series events detection relates to the study of techniques for detecting points in a series with special meaning which differs from the expected behavior of the dataset. In scenarios such as digital twins and IoT devices, there is natural generation and traffic of data in the cloud. Event detection is critical for timely decision-making. Since many methods for detecting events target different types selecting a suitable method makes the task more difficult. In this context, this article proposes a cloud-based framework called Harbinger Nimbus. The implementation was evaluated on the Microsoft Azure platform.

The detection of events in time series is an important task in several areas of knowledge where operations monitoring is essential. Experts often have to deal with choosing the most appropriate event detection method for a time series, which can be a complex task. There is a demand for benchmarking different methods in order to guide this choice. For this, standard classification accuracy metrics are usually adopted. However, they are insufficient for a qualitative analysis of the tendency of a method to precede or delay event detections. Such analysis is interesting for applications in which tolerance for "close" detections is important rather than focusing only on accurate ones. In this context, this paper proposes a more comprehensive event detection benchmark process, including an analysis of temporal bias of detection methods. For that, metrics based on the time distance between event detections and identified events (detection delay) are adopted. Computational experiments were conducted using real-world and synthetic datasets from Yahoo Labs and resources from the Harbinger framework for event detection. Adopting the proposed detection delay-based metrics helped obtain a complete overview of the performance and general behavior of detection methods.