by Mariusz Zebik, Marcin Korytkowski, Rafal Angryk, Rafa\l Scherer
Abstract:
This article concerns identifying objects generating signals from various sensors. Instead of using traditional hand-made time series features we feed the signals as input channels to a convolutional neural network. The network learned low- and high-level features from data. We describe the process of data preparation, filtering, and the structure of the convolutional network. Experiment results showed that the network was able to learn to recognize objects with high accuracy.
Reference:
Convolutional Neural Networks for Time Series Classification (Mariusz Zebik, Marcin Korytkowski, Rafal Angryk, Rafa\l Scherer), Chapter in , Springer International Publishing, 2017.
Bibtex Entry:
@Inbook{Zebik2017,
author="Zebik, Mariusz
and Korytkowski, Marcin
and Angryk, Rafal
and Scherer, Rafa{\l}",
title="Convolutional Neural Networks for Time Series Classification",
bookTitle="Artificial Intelligence and Soft Computing: 16th International Conference, ICAISC 2017, Zakopane, Poland, June 11-15, 2017, Proceedings, Part II",
year="2017",
publisher="Springer International Publishing",
address="Cham",
pages="635--642",
abstract="This article concerns identifying objects generating signals from various sensors. Instead of using traditional hand-made time series features we feed the signals as input channels to a convolutional neural network. The network learned low- and high-level features from data. We describe the process of data preparation, filtering, and the structure of the convolutional network. Experiment results showed that the network was able to learn to recognize objects with high accuracy.",
isbn="978-3-319-59060-8",
doi="10.1007/978-3-319-59060-8_57",
url="https://doi.org/10.1007/978-3-319-59060-8_57"
}