1D-Convolutional Neural Network Architecture for Generalized Time-Segmentation Tasks

Time segmentation of experimental data is a common and often difficult task. Consequently,
it is of interest to automate this type of segmentation to reduce manual inputs, which are labor
intensive and less consistent. However, simple thresholding algorithms are often insufficiently
robust due either to noise or inconsistent data. This paper proposes a simple 1D convolutional
neural net (CNN) architecture as a generalized solution for typical time segmentation tasks.
The layer architecture, training methods, and methods for simple customization are described
as well as the results of application to three separate arc jet data streams: facility condition
segmentation, video highlight segmentation, and calorimeter time-series segmentation.