A novel high accuracy fast gas detection algorithm based on multi-task learning

doi:10.1016/j.measurement.2024.114383

2024-03-01

PRE

DOI：10.1016/j.measurement.2024.114383

原文链接

原文求助

摘要

En 中文

As an advanced sensor system, electronic nose (E-nose) has been widely used in the field of gas analysis. A novel algorithm that leverages Long Short-Term Memory Attention as a shared framework and integrates it with multitask learning (MTL-LSTMA) is proposed to enable concurrent prediction of gas category and concentration. Numerous experiments have demonstrated that the MTL-LSTMA model effectively integrates these tasks, fast and simultaneous gas detection for CO, ethylene, and methane gas was achieved (response time of 30 s). All of the classification accuracies exceed 0.98, and the concentration prediction task also exhibits a high degree to match actually. Additionally, we compared results at a variety of response times. It is revealed that MTL-LSTMA model is the best for type identification and concentration prediction of gas mixtures and achieves good results using only the first 30 s of response data.

Keyword:

LSTM

Multi -task learning

Mixture gases recognition

Concentration prediction

Fast detection

期刊

Measurement

IF:

5.6

论文数:

2.0W

被引数:

5.4W

机构

southwest university - china

学者数:

2.6W

论文数: 1.9W

被引数: 21

引用论文

Blood

IF0

1996-06-01

OAAI

C Peters; M Balthazor; EG Shapiro; RJ King; C Kollman; JD Hegland; J Henslee- Downey; ME Trigg; MJ Cowan; J Sanders; N Bunin; H Weinstein; C Lenarsky; P Falk; R Harris; T Bowen; TE Williams; GH Grayson; P Warkentin; L Sender; VA Cool; M Crittenden; S Packman; P Kaplan; LA Lockman

Activated T-Cell and Bispecific Antibody Immunotherapy for High-Risk Breast Cancer

Acta Haematologica

IF0

2001-07-18

PREAI

Lawrence G. Lum; Manjula Sen

Use of single case study research in child speech, language and communication interventions

Child Language Teaching and Therapy

IF0

2012-10-30

PREAI

Maggie Vance; Judy Clegg