Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Nov 20, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

807

Multi-scale Attention Convolutional Neural Network for time series classification.

Wei Chen1, Ke Shi1

  • 1School of Computer Science and Technology, Huazhong University of Science and Technology, China.

Neural Networks : the Official Journal of the International Neural Network Society
|January 23, 2021
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Time-Series Graph00:54

Time-Series Graph

4.8K
A time-series graph is a line graph with repeated measurements taken at successive intervals of time. It is also called a time series chart. To construct a time-series graph, one must look at both pieces of a paired data set. The horizontal axis is used to plot the time increments, and the vertical axis is used to plot the values of the variable that one is measuring. By using the axes in this way, each point on the graph will correspond to time and a measured quantity. The points on the graph...
4.8K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Altered lipid metabolism and ferroptosis in sodium hydroxide-induced skin burns: a comprehensive rat model-based analysis.

International journal of burns and trauma·2025
Same author

1,25(OH)<sub>2</sub>D<sub>3</sub> up-regulated mitochondrial dynamics and biogenesis to modulate steroidogenesis in the scent glands of muskrats (Ondatra zibethicus).

The Journal of steroid biochemistry and molecular biology·2025
Same author

Prognostic Nutritional Index Trajectories Predict Kidney Function in Kidney Transplant Recipients: A Latent Class Growth Model Study.

Annals of transplantation·2025
Same author

The actual performance of large language models in providing liver cirrhosis-related information: A comparative study.

International journal of medical informatics·2025
Same author

Ferroptosis and necroptosis may be involved in the formation and progression of hydrofluoric acid burn wounds: Results from an RNA-Seq analysis.

Burns : journal of the International Society for Burn Injuries·2025
Same author

A review shows that ATG10 has been identified as a potential prognostic marker and therapeutic target for cancer patients based on real-world studies.

Frontiers in oncology·2025
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

IGFD-Net: Illumination-guided frequency decoupling for polarization image fusion.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Multiple-Strategies dung beetle optimizer and its applications in engineering optimization and bankruptcy prediction.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Aggregating global-scale pixel-wise forgery cues within a graph.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Finite-Time intermittent control for secure synchronization of Neutral-Type stochastic delayed neural networks under aperiodic DoS attacks.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

A new deep learning model, Multi-scale Attention Convolutional Neural Network (MACNN), improves time series classification accuracy. This novel approach effectively captures multi-scale information and enhances feature representation for better generalization.

Area of Science:

  • Computer Science
  • Machine Learning
  • Artificial Intelligence

Background:

  • Time series classification (TSC) is crucial across many fields due to increasing data availability.
  • Existing TSC methods, both traditional and deep learning-based, face challenges in improving accuracy and generalization.
  • The need for advanced models to handle complex time series data is evident.

Purpose of the Study:

  • To introduce a novel deep learning model, the Multi-scale Attention Convolutional Neural Network (MACNN), for enhanced time series classification.
  • To address the limitations of single-scale convolutions and equal feature map weighting in existing TSC methods.
  • To improve both the accuracy and generalization ability of time series classification models.

Main Methods:

  • Developed an end-to-end deep learning model, MACNN, incorporating multi-scale convolutions.
Keywords:
Convolutional neural networkMulti-scale attention mechanismTime series classification

Related Experiment Videos

Last Updated: Nov 20, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

807
  • Applied multi-scale convolutions to extract information at various scales along the time axis, generating diverse feature maps.
  • Integrated an attention mechanism to automatically learn and assign importance to different feature maps, enhancing relevant information.

    • Main Results:

    • MACNN demonstrated superior performance on 85 standard UCR datasets.
    • The proposed model significantly outperformed existing traditional and deep learning-based time series classification methods.
    • The multi-scale approach combined with attention mechanism proved effective in improving classification accuracy and generalization.

    Conclusions:

    • MACNN offers a significant advancement in time series classification by effectively utilizing multi-scale features and attention.
    • The model's ability to outperform existing methods highlights its potential for real-world applications.
    • This research provides a robust deep learning framework for tackling complex time series classification tasks.