DeepFilter: A Transformer-style Framework for Accurate and Efficient Process Monitoring
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917181419159552 |
|---|---|
| author | Wang, Hao Chen, Zhichao Pan, Licheng Jiang, Xiaoyu Song, Yichen He, Qunshan Liu, Xinggao |
| author_facet | Wang, Hao Chen, Zhichao Pan, Licheng Jiang, Xiaoyu Song, Yichen He, Qunshan Liu, Xinggao |
| contents | The process monitoring task is characterized by stringent demands for accuracy and efficiency. Current transformer-based methods, characterized by self-attention for temporal fusion, exhibit limitations in accurately understanding the semantic context and efficiently processing monitoring logs, rendering them inadequate for process monitoring. To address these limitations, we introduce DeepFilter, which revises the self-attention mechanism to improve both accuracy and efficiency. As a straightforward yet versatile approach, DeepFilter provides an instrumental baseline for practitioners in process monitoring, whether initiating new projects or enhancing existing capabilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_01342 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DeepFilter: A Transformer-style Framework for Accurate and Efficient Process Monitoring Wang, Hao Chen, Zhichao Pan, Licheng Jiang, Xiaoyu Song, Yichen He, Qunshan Liu, Xinggao Artificial Intelligence Machine Learning The process monitoring task is characterized by stringent demands for accuracy and efficiency. Current transformer-based methods, characterized by self-attention for temporal fusion, exhibit limitations in accurately understanding the semantic context and efficiently processing monitoring logs, rendering them inadequate for process monitoring. To address these limitations, we introduce DeepFilter, which revises the self-attention mechanism to improve both accuracy and efficiency. As a straightforward yet versatile approach, DeepFilter provides an instrumental baseline for practitioners in process monitoring, whether initiating new projects or enhancing existing capabilities. |
| title | DeepFilter: A Transformer-style Framework for Accurate and Efficient Process Monitoring |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2501.01342 |