English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Event detection in time series data is crucial in various domains, includingfinance, healthcare, cybersecurity, and science. Accurately identifying eventsin time series data is vital for making informed decisions, detectinganomalies, and predicting future trends. Despite extensive research exploringdiverse methods for event detection in time series, with deep learningapproaches being among the most advanced, there is still room for improvementand innovation in this field. In this paper, we present a new deep learningsupervised method for detecting events in multivariate time series data. Ourmethod combines four distinct novelties compared to existing deep-learningsupervised methods. Firstly, it is based on regression instead of binaryclassification. Secondly, it does not require labeled datasets where each pointis labeled; instead, it only requires reference events defined as time pointsor intervals of time. Thirdly, it is designed to be robust by using a stackedensemble learning meta-model that combines deep learning models, ranging fromclassic feed-forward neural networks (FFNs) to state-of-the-art architectureslike transformers. This ensemble approach can mitigate individual modelweaknesses and biases, resulting in more robust predictions. Finally, tofacilitate practical implementation, we have developed a Python package toaccompany our proposed method. The package, called eventdetector-ts, can beinstalled through the Python Package Index (PyPI). In this paper, we presentour method and provide a comprehensive guide on the usage of the package. Weshowcase its versatility and effectiveness through different real-world usecases from natural language processing (NLP) to financial security domains.

A Comprehensive Python Library for Deep Learning-Based Event Detection in Multivariate Time Series Data and Information Retrieval in NLP