Workflow Detection with Improved Phase Discriminability
Workflow detection is a challenge issue in the process of Industry 4.0, which plays a crucial role in intelligent production. However, it faces the problem of inaccurate phase classification and unclear boundary positioning, which are not well resolved in previous works. To solve them, this paper...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Stefan cel Mare University of Suceava
2024-05-01
|
| Series: | Advances in Electrical and Computer Engineering |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.4316/AECE.2024.02003 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850117080849842176 |
|---|---|
| author | ZHANG, M. HU, H. LI, Z. |
| author_facet | ZHANG, M. HU, H. LI, Z. |
| author_sort | ZHANG, M. |
| collection | DOAJ |
| description | Workflow detection is a challenge issue in the process of Industry 4.0, which plays a crucial role in intelligent production.
However, it faces the problem of inaccurate phase classification and unclear boundary positioning, which are not well resolved
in previous works. To solve them, this paper develops a temporal-aware workflow detection framework (TransGAN) which takes
advantage of the complementarity between Transformer and graph attention network to improve phase discriminability.
Specifically, temporal self-attention is firstly designed to learn the relationship between different positions of
feature sequence. Then, multi-scale Transformer is introduced to encode pyramid features, which fuses multiple context
cues for discriminative feature representation. At last, contextual and surrounding relations are learned in graph
attention network for refined phase classification and boundary localization. Comprehensive experiments are performed
to verify the effectiveness of our method. Compared to the advanced AFSD, the accuracy is improved by 2.3 % and 2.1 % when
tIoU=0.5 on POTFD and THUMOS-14 dataset, respectively. Empirical study of running speed indicates that the proposed TransGAN
can be deployed to real-world industrial environment for workflow detection. |
| format | Article |
| id | doaj-art-d77f87bdad8846cd8facace03131ed95 |
| institution | OA Journals |
| issn | 1582-7445 1844-7600 |
| language | English |
| publishDate | 2024-05-01 |
| publisher | Stefan cel Mare University of Suceava |
| record_format | Article |
| series | Advances in Electrical and Computer Engineering |
| spelling | doaj-art-d77f87bdad8846cd8facace03131ed952025-08-20T02:36:10ZengStefan cel Mare University of SuceavaAdvances in Electrical and Computer Engineering1582-74451844-76002024-05-01242213010.4316/AECE.2024.02003Workflow Detection with Improved Phase DiscriminabilityZHANG, M.HU, H.LI, Z.Workflow detection is a challenge issue in the process of Industry 4.0, which plays a crucial role in intelligent production. However, it faces the problem of inaccurate phase classification and unclear boundary positioning, which are not well resolved in previous works. To solve them, this paper develops a temporal-aware workflow detection framework (TransGAN) which takes advantage of the complementarity between Transformer and graph attention network to improve phase discriminability. Specifically, temporal self-attention is firstly designed to learn the relationship between different positions of feature sequence. Then, multi-scale Transformer is introduced to encode pyramid features, which fuses multiple context cues for discriminative feature representation. At last, contextual and surrounding relations are learned in graph attention network for refined phase classification and boundary localization. Comprehensive experiments are performed to verify the effectiveness of our method. Compared to the advanced AFSD, the accuracy is improved by 2.3 % and 2.1 % when tIoU=0.5 on POTFD and THUMOS-14 dataset, respectively. Empirical study of running speed indicates that the proposed TransGAN can be deployed to real-world industrial environment for workflow detection.http://dx.doi.org/10.4316/AECE.2024.02003intelligent manufacturingworkflow detectionself-attention mechanismgraph relation reasoningtransformer |
| spellingShingle | ZHANG, M. HU, H. LI, Z. Workflow Detection with Improved Phase Discriminability Advances in Electrical and Computer Engineering intelligent manufacturing workflow detection self-attention mechanism graph relation reasoning transformer |
| title | Workflow Detection with Improved Phase Discriminability |
| title_full | Workflow Detection with Improved Phase Discriminability |
| title_fullStr | Workflow Detection with Improved Phase Discriminability |
| title_full_unstemmed | Workflow Detection with Improved Phase Discriminability |
| title_short | Workflow Detection with Improved Phase Discriminability |
| title_sort | workflow detection with improved phase discriminability |
| topic | intelligent manufacturing workflow detection self-attention mechanism graph relation reasoning transformer |
| url | http://dx.doi.org/10.4316/AECE.2024.02003 |
| work_keys_str_mv | AT zhangm workflowdetectionwithimprovedphasediscriminability AT huh workflowdetectionwithimprovedphasediscriminability AT liz workflowdetectionwithimprovedphasediscriminability |