Next Article in Journal
TabNet: Locally Interpretable Estimation and Prediction for Advanced Proton Exchange Membrane Fuel Cell Health Management
Previous Article in Journal
A New 3-Dimensional Graphene Vertical Transistor with Channel Length Determination Using Dielectric Thickness
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Electronics
Volume 13
Issue 7
10.3390/electronics13071357
electronics-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

A Dual-Branch Structure Network of Custom Computing for Multivariate Time Series

by
Jingfeng Yu
1,2,
Yingqi Feng
2,3 and
Zunkai Huang
2,3,*
1
School of Information Science and Technology, Shanghaitech University, Shanghai 201210, China
2
Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai 201210, China
3
University of Chinese Academy of Sciences, Beijing 100049, China
*
Author to whom correspondence should be addressed.
Electronics 2024, 13(7), 1357; https://doi.org/10.3390/electronics13071357
Submission received: 29 February 2024 / Revised: 22 March 2024 / Accepted: 2 April 2024 / Published: 3 April 2024
Browse Figures
Versions Notes

Abstract

Time series are a common form of data, which are of great importance in multiple fields. Multivariate time series whose relationship of dimension is indeterminacy are particularly common within these. For multivariate time series, we proposed a dual-branch structure model, composed of an attention branch and a convolution branch, respectively. The algorithm proposed in our work is implemented for custom computing optimization and deployed on the Xilinx Ultra 96V2 device. Comparative results with other state-of-the-art time series algorithms on public datasets indicate that the proposed method achieves optimal performance. The power consumption of the system is 6.38 W, which is 47.02 times lower than that of a GPU.
Keywords: time series; custom computing; convolution; attention mechanism time series; custom computing; convolution; attention mechanism

Share and Cite

MDPI and ACS Style

Yu, J.; Feng, Y.; Huang, Z. A Dual-Branch Structure Network of Custom Computing for Multivariate Time Series. Electronics 2024, 13, 1357. https://doi.org/10.3390/electronics13071357

AMA Style

Yu J, Feng Y, Huang Z. A Dual-Branch Structure Network of Custom Computing for Multivariate Time Series. Electronics. 2024; 13(7):1357. https://doi.org/10.3390/electronics13071357

Chicago/Turabian Style

Yu, Jingfeng, Yingqi Feng, and Zunkai Huang. 2024. "A Dual-Branch Structure Network of Custom Computing for Multivariate Time Series" Electronics 13, no. 7: 1357. https://doi.org/10.3390/electronics13071357

APA Style

Yu, J., Feng, Y., & Huang, Z. (2024). A Dual-Branch Structure Network of Custom Computing for Multivariate Time Series. Electronics, 13(7), 1357. https://doi.org/10.3390/electronics13071357

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop