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

Automated event detection has emerged as one of the fundamental practices tomonitor the behavior of technical systems by means of sensor data. In theautomotive industry, these methods are in high demand for tracing events intime series data. For assessing the active vehicle safety systems, a diverserange of driving scenarios is conducted. These scenarios involve the recordingof the vehicle's behavior using external sensors, enabling the evaluation ofoperational performance. In such setting, automated detection methods not onlyaccelerate but also standardize and objectify the evaluation by avoidingsubjective, human-based appraisals in the data inspection. This work proposes anovel event detection method that allows to identify frequency-based events intime series data. To this aim, the time series data is mapped torepresentations in the time-frequency domain, known as scalograms. Afterfiltering scalograms to enhance relevant parts of the signal, an objectdetection model is trained to detect the desired event objects in thescalograms. For the analysis of unseen time series data, events can be detectedin their scalograms with the trained object detection model and are thereaftermapped back to the time series data to mark the corresponding time interval.The algorithm, evaluated on unseen datasets, achieves a precision rate of 0.97in event detection, providing sharp time interval boundaries whose accurateindication by human visual inspection is challenging. Incorporating this methodinto the vehicle development process enhances the accuracy and reliability ofevent detection, which holds major importance for rapid testing analysis.

A Machine Learning-based Algorithm for Automated Detection of Frequency-based Events in Recorded Time Series of Sensor Data