File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/TII.2022.3205638
- Scopus: eid_2-s2.0-85139449426
- WOS: WOS:000880654600044
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Trustworthiness of Process Monitoring in IIoT Based on Self-Weighted Dictionary Learning
Title | Trustworthiness of Process Monitoring in IIoT Based on Self-Weighted Dictionary Learning |
---|---|
Authors | |
Keywords | Process monitoring self-weighted semisupervised learning trustworthiness |
Issue Date | 2023 |
Citation | IEEE Transactions on Industrial Informatics, 2023, v. 19, n. 1, p. 436-446 How to Cite? |
Abstract | Process monitoring, a typical application of industrial Internet of Things (IIOT), is crucial to ensure the reliable operation of the industrial system. In practice, due to the harsh environment and unreliable sensors and actuators, it is often difficult for IIoT to collect enough tagged and highly reliable data, which further degrades the process monitoring performance and makes the monitoring results not trustworthy. In order to reduce the negative impact of these unreliable factors, a self-weighted dictionary learning process monitoring method is proposed. In particular, a label propagation classifier is implemented from the labeled data to unlabeled data to obtain a credible label prediction. Subsequently, considering the interference of low-quality data and label information, we reweight the classification loss and label-consistency constraints to enhance the trustworthiness of feature extraction. Finally, a novel iterative optimization algorithm that combines the block coordinate descent method with the alternating direction multiplier method is developed to ensure the convergence speed of the learned classifier and dictionary. Extensive experiments indicate that the proposed method can guarantee the trustworthiness of the process monitoring results. |
Persistent Identifier | http://hdl.handle.net/10722/336335 |
ISSN | 2023 Impact Factor: 11.7 2023 SCImago Journal Rankings: 4.420 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Huang, Keke | - |
dc.contributor.author | Tao, Shijun | - |
dc.contributor.author | Wu, Dehao | - |
dc.contributor.author | Yang, Chunhua | - |
dc.contributor.author | Gui, Weihua | - |
dc.contributor.author | Hu, Shiyan | - |
dc.date.accessioned | 2024-01-15T08:25:43Z | - |
dc.date.available | 2024-01-15T08:25:43Z | - |
dc.date.issued | 2023 | - |
dc.identifier.citation | IEEE Transactions on Industrial Informatics, 2023, v. 19, n. 1, p. 436-446 | - |
dc.identifier.issn | 1551-3203 | - |
dc.identifier.uri | http://hdl.handle.net/10722/336335 | - |
dc.description.abstract | Process monitoring, a typical application of industrial Internet of Things (IIOT), is crucial to ensure the reliable operation of the industrial system. In practice, due to the harsh environment and unreliable sensors and actuators, it is often difficult for IIoT to collect enough tagged and highly reliable data, which further degrades the process monitoring performance and makes the monitoring results not trustworthy. In order to reduce the negative impact of these unreliable factors, a self-weighted dictionary learning process monitoring method is proposed. In particular, a label propagation classifier is implemented from the labeled data to unlabeled data to obtain a credible label prediction. Subsequently, considering the interference of low-quality data and label information, we reweight the classification loss and label-consistency constraints to enhance the trustworthiness of feature extraction. Finally, a novel iterative optimization algorithm that combines the block coordinate descent method with the alternating direction multiplier method is developed to ensure the convergence speed of the learned classifier and dictionary. Extensive experiments indicate that the proposed method can guarantee the trustworthiness of the process monitoring results. | - |
dc.language | eng | - |
dc.relation.ispartof | IEEE Transactions on Industrial Informatics | - |
dc.subject | Process monitoring | - |
dc.subject | self-weighted | - |
dc.subject | semisupervised learning | - |
dc.subject | trustworthiness | - |
dc.title | Trustworthiness of Process Monitoring in IIoT Based on Self-Weighted Dictionary Learning | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/TII.2022.3205638 | - |
dc.identifier.scopus | eid_2-s2.0-85139449426 | - |
dc.identifier.volume | 19 | - |
dc.identifier.issue | 1 | - |
dc.identifier.spage | 436 | - |
dc.identifier.epage | 446 | - |
dc.identifier.eissn | 1941-0050 | - |
dc.identifier.isi | WOS:000880654600044 | - |