• Home
  • Search
  • Transfer learning for time series classification
  • Open Access IconOpen Access
  • Cite Icon299
  • https://doi.org/10.1109/bigdata.2018.8621990Copy DOI Icon

Transfer learning for time series classification

  • Nov 5, 2018
  • Hassan Ismail Fawaz +4 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Transfer learning for deep neural networks is the process of first training a\nbase network on a source dataset, and then transferring the learned features\n(the network's weights) to a second network to be trained on a target dataset.\nThis idea has been shown to improve deep neural network's generalization\ncapabilities in many computer vision tasks such as image recognition and object\nlocalization. Apart from these applications, deep Convolutional Neural Networks\n(CNNs) have also recently gained popularity in the Time Series Classification\n(TSC) community. However, unlike for image recognition problems, transfer\nlearning techniques have not yet been investigated thoroughly for the TSC task.\nThis is surprising as the accuracy of deep learning models for TSC could\npotentially be improved if the model is fine-tuned from a pre-trained neural\nnetwork instead of training it from scratch. In this paper, we fill this gap by\ninvestigating how to transfer deep CNNs for the TSC task. To evaluate the\npotential of transfer learning, we performed extensive experiments using the\nUCR archive which is the largest publicly available TSC benchmark containing 85\ndatasets. For each dataset in the archive, we pre-trained a model and then\nfine-tuned it on the other datasets resulting in 7140 different deep neural\nnetworks. These experiments revealed that transfer learning can improve or\ndegrade the model's predictions depending on the dataset used for transfer.\nTherefore, in an effort to predict the best source dataset for a given target\ndataset, we propose a new method relying on Dynamic Time Warping to measure\ninter-datasets similarities. We describe how our method can guide the transfer\nto choose the best source dataset leading to an improvement in accuracy on 71\nout of 85 datasets.\n

Similar Papers
  • Conference Article
  • Citations3

A Priori Quantification of Transfer Learning Performance on Time Series Classification for Cyber-Physical Health Systems

  • Sep 18, 2022
  • Ryan Clark +1
  • Research Article
  • Citations3291

Deep learning for time series classification: a review

  • Mar 02, 2019
  • Data Mining and Knowledge Discovery
  • Hassan Ismail Fawaz +4
  • Research Article
  • Citations25

Site-agnostic 3D dose distribution prediction with deep learning neural networks.

  • Jan 27, 2022
  • Medical Physics
  • Maryam Mashayekhi +8
  • PDF
  • Research Article
  • Citations2

Pseudo-labeling of transfer learning convolutional neural network data for human facial emotion recognition

  • Oct 12, 2023
  • Herald of Advanced Information Technology
  • Olena О Arsirii +1
  • Conference Article

Patient's Pain Recognition by Using Deep Models Based on Transfer Learning

  • Nov 01, 2022
  • Elaf Noori Saddam +2
  • Research Article
  • Citations36

Transfer learning to detect neonatal seizure from electroencephalography signals

  • Mar 26, 2021
  • Neural Computing and Applications
  • Abdullah Caliskan +1
  • PDF
  • Research Article
  • Citations7

Application of Transfer Learning Algorithm and Real Time Speech Detection in Music Education Platform

  • Oct 11, 2021
  • Scientific Programming
  • Hexue Shen
  • PDF
  • Research Article
  • Citations1079

Deep convolutional neural network based medical image classification for disease diagnosis

  • Dec 01, 2019
  • Journal of Big Data
  • Samir S Yadav +1
  • PDF
  • Research Article
  • Citations29

Digital Twin Modeling Method for Hierarchical Stiffened Plate Based on Transfer Learning

  • Jan 09, 2023
  • Aerospace
  • Ziyu Xu +5
  • Research Article
  • Citations60

Transfer learning for drug-target interaction prediction.

  • Jun 30, 2023
  • Bioinformatics
  • Alperen Dalkıran +7
  • Conference Article
  • Citations26

Improving Automatic Jazz Melody Generation by Transfer Learning Techniques

  • Nov 01, 2019
  • Hsiao-Tzu Hung +3
  • PDF
  • Research Article
  • Citations1

Optimizing Breast Cancer Detection: Deep Transfer Learning Empowered by SVM Classifiers

  • May 14, 2024
  • Indian Journal Of Science And Technology
  • M Jayanthi Rao +5
  • PDF
  • Research Article
  • Citations7

Transfer Learning with Deep Neural Network toward the Prediction of Wake Flow Characteristics of Containerships

  • Sep 29, 2023
  • Journal of Marine Science and Engineering
  • Min-Kyung Lee +1
  • Dissertation

Deep neural networks for time series classification

  • Jan 01, 2023
  • Wen Xin Cheng
  • Research Article
  • Citations6

Autoencoder and restricted Boltzmann machine for transfer learning in functional magnetic resonance imaging task classification

  • Jul 01, 2023
  • Heliyon
  • Jundong Hwang +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.