Improved Long Short-Term Memory Network with Multi-Attention for Human Action Flow Evaluation in Workshop
As an indispensable part of workshops, the normalization of workers’ manufacturing processes is an important factor that affects product quality. How to effectively supervise the manufacturing process of workers has always been a difficult problem in intelligent manufacturing. This paper proposes a...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-11-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/10/21/7856 |
id |
doaj-7ba27681e8e547638bc133d476824a3f |
---|---|
record_format |
Article |
spelling |
doaj-7ba27681e8e547638bc133d476824a3f2020-11-25T04:06:09ZengMDPI AGApplied Sciences2076-34172020-11-01107856785610.3390/app10217856Improved Long Short-Term Memory Network with Multi-Attention for Human Action Flow Evaluation in WorkshopYun Yang0Jiacheng Wang1Tianyuan Liu2Xiaolei Lv3Jinsong Bao4College of Mechanical Engineering, Donghua University, Shanghai 201620, ChinaCollege of Mechanical Engineering, Donghua University, Shanghai 201620, ChinaCollege of Mechanical Engineering, Donghua University, Shanghai 201620, ChinaShanghai Space Propulsion Technology Research Institute, Shanghai 201620, ChinaCollege of Mechanical Engineering, Donghua University, Shanghai 201620, ChinaAs an indispensable part of workshops, the normalization of workers’ manufacturing processes is an important factor that affects product quality. How to effectively supervise the manufacturing process of workers has always been a difficult problem in intelligent manufacturing. This paper proposes a method for action detection and process evaluation of workers based on a deep learning model. In this method, the human skeleton and workpiece features are separately obtained by the monitoring frame and then input into an action detection network in chronological order. The model uses two inputs to predict frame-by-frame classification results, which are then merged into a continuous action flow, and finally, input into the action flow evaluation network. The network effectively improves the ability to evaluate action flow through the attention mechanism of key actions in the process. The experimental results show that our method can effectively recognize operation actions in workshops, and can evaluate the manufacturing process with 99% accuracy using the experimental verification dataset.https://www.mdpi.com/2076-3417/10/21/7856intelligent monitoringhuman factorsaction recognitionlong short-term memory networkattention mechanism |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yun Yang Jiacheng Wang Tianyuan Liu Xiaolei Lv Jinsong Bao |
spellingShingle |
Yun Yang Jiacheng Wang Tianyuan Liu Xiaolei Lv Jinsong Bao Improved Long Short-Term Memory Network with Multi-Attention for Human Action Flow Evaluation in Workshop Applied Sciences intelligent monitoring human factors action recognition long short-term memory network attention mechanism |
author_facet |
Yun Yang Jiacheng Wang Tianyuan Liu Xiaolei Lv Jinsong Bao |
author_sort |
Yun Yang |
title |
Improved Long Short-Term Memory Network with Multi-Attention for Human Action Flow Evaluation in Workshop |
title_short |
Improved Long Short-Term Memory Network with Multi-Attention for Human Action Flow Evaluation in Workshop |
title_full |
Improved Long Short-Term Memory Network with Multi-Attention for Human Action Flow Evaluation in Workshop |
title_fullStr |
Improved Long Short-Term Memory Network with Multi-Attention for Human Action Flow Evaluation in Workshop |
title_full_unstemmed |
Improved Long Short-Term Memory Network with Multi-Attention for Human Action Flow Evaluation in Workshop |
title_sort |
improved long short-term memory network with multi-attention for human action flow evaluation in workshop |
publisher |
MDPI AG |
series |
Applied Sciences |
issn |
2076-3417 |
publishDate |
2020-11-01 |
description |
As an indispensable part of workshops, the normalization of workers’ manufacturing processes is an important factor that affects product quality. How to effectively supervise the manufacturing process of workers has always been a difficult problem in intelligent manufacturing. This paper proposes a method for action detection and process evaluation of workers based on a deep learning model. In this method, the human skeleton and workpiece features are separately obtained by the monitoring frame and then input into an action detection network in chronological order. The model uses two inputs to predict frame-by-frame classification results, which are then merged into a continuous action flow, and finally, input into the action flow evaluation network. The network effectively improves the ability to evaluate action flow through the attention mechanism of key actions in the process. The experimental results show that our method can effectively recognize operation actions in workshops, and can evaluate the manufacturing process with 99% accuracy using the experimental verification dataset. |
topic |
intelligent monitoring human factors action recognition long short-term memory network attention mechanism |
url |
https://www.mdpi.com/2076-3417/10/21/7856 |
work_keys_str_mv |
AT yunyang improvedlongshorttermmemorynetworkwithmultiattentionforhumanactionflowevaluationinworkshop AT jiachengwang improvedlongshorttermmemorynetworkwithmultiattentionforhumanactionflowevaluationinworkshop AT tianyuanliu improvedlongshorttermmemorynetworkwithmultiattentionforhumanactionflowevaluationinworkshop AT xiaoleilv improvedlongshorttermmemorynetworkwithmultiattentionforhumanactionflowevaluationinworkshop AT jinsongbao improvedlongshorttermmemorynetworkwithmultiattentionforhumanactionflowevaluationinworkshop |
_version_ |
1724432122590003200 |