Multivariate LSTM-FCNs for Time Series Classification

Details

• Personal Author:
  Darabi H ; Harford S ; Karim F ; Majumdar S
• Description:
  Over the past decade, multivariate time series classification has received great attention. We propose transforming the existing univariate time series classification models, the Long Short Term Memory Fully Convolutional Network (LSTM-FCN) and Attention LSTM-FCN (ALSTM-FCN), into a multivariate time series classification model by augmenting the fully convolutional block with a squeeze-and-excitation block to further improve accuracy. Our proposed models outperform most state-of-the-art models while requiring minimum preprocessing. The proposed models work efficiently on various complex multivariate time series classification tasks such as activity recognition or action recognition. Furthermore, the proposed models are highly efficient at test time and small enough to deploy on memory constrained systems. [Description provided by NIOSH]
• Subjects:
  Occupational Health Safety Software
• Keywords:
  Author Keywords: Convolutional Neural Network Computer Applications Long Short Term Memory Models Multivariate Time Series Classification Neural Networks Recurrent Neural Network Statistical Analysis
• ISSN:
  0893-6080
• Document Type:
  Text
• Funding:
  Grant
• Genre:
  Journal Article
• Place as Subject:
  Illinois ; OSHA Region 5
• CIO:
  National Institute for Occupational Safety and Health (NIOSH)
• Topic:
  Workplace Safety & Health
• Location:
  North America
• Pages in Document:
  237-245
• Volume:
  116
• NIOSHTIC Number:
  nn:20063646
• Citation:
  Neural Netw 2019 Aug; 116:237-245
• Contact Point Address:
  Houshang Darabi, Mechanical and Industrial Engineering, University of Illinois at Chicago, 900 W. Taylor St., Chicago, IL, 60607, USA
• Email:
  hdarabi@uic.edu
• Federal Fiscal Year:
  2019
• Performing Organization:
  University of Illinois at Chicago
• Peer Reviewed:
  True
• Start Date:
  20050701
• Source Full Name:
  Neural Networks
• End Date:
  20290630
• Collection(s):
  National Institute for Occupational Safety and Health
• Main Document Checksum:
  urn:sha-512:0b06266704cd000364553d522f658bd16d7dbc3bf20f2826e3382ef79bcdb4612737afe9595372110b321fd842cb4eb082c4f6ec88d513fcdd6c341742aa3f57
• Download URL:
  https://stacks.cdc.gov/view/cdc/222214/cdc_222214_DS1.pdf
• File Type:
  [PDF - 1.07 MB ]