Convolutional Neural Networks for Time-dependent Classification of Variable-length Time Series

Time series data are often obtained only within a limited time range due to interruptions during observation process. To classify such partial time series, we need to account for 1) the variable-length data drawn from 2) different timestamps. To address the first problem, existing convolutional neur...

Full description

Saved in:
Bibliographic Details
Main Authors: Sawada, Azusa, Miyagawa, Taiki, Ebihara, Akinori, Yachida, Shoji, Hosoi, Toshinori
Format: Conference Proceeding
Language:English
Subjects:
Aggregates
convolutional neural networks
Correlation
Encoding
Neural networks
partial data
Radio frequency
Time series analysis
time series classification
Trajectory
variable length
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Time series data are often obtained only within a limited time range due to interruptions during observation process. To classify such partial time series, we need to account for 1) the variable-length data drawn from 2) different timestamps. To address the first problem, existing convolutional neural networks use global pooling after convolutional layers to cancel the length differences. This architecture suffers from the trade-off between incorporating entire temporal correlations in long data and avoiding feature collapse for short data. To resolve this trade-off, we propose Adaptive Multi-scale Pooling, which aggregates features from an adaptive number of layers, i.e., only the first few layers for short data and more layers for long data. Furthermore, to address the second problem, we introduce Temporal Encoding, which embeds the observation timestamps into the intermediate features. Experiments on our private dataset and the UCR/UEA time series archive show that our modules improve classification accuracy especially on short data obtained as partial time series.
ISSN:2161-4407
DOI:10.1109/IJCNN55064.2022.9892605