FilterNet: A Many-to-Many Deep Learning Architecture for Time Series Classification

FilterNet: A Many-to-Many Deep Learning Architecture for Time Series Classification

In this paper, we present and benchmark FilterNet, a flexible deep learning architecture for time series classification tasks, such as activity recognition via multichannel sensor data. It adapts popular convolutional neural network (CNN) and long short-term memory (LSTM) motifs which have excelled...

Full description

Bibliographic Details
Main Authors: Robert D. Chambers, Nathanael C. Yoder
Format: Article
Language:English
Published: MDPI AG 2020-04-01
Series:Sensors
Subjects:
activity recognition
time series classification
neural
networks
deep learning
machine learning
Online Access:https://www.mdpi.com/1424-8220/20/9/2498

Internet

https://www.mdpi.com/1424-8220/20/9/2498

Similar Items