Λεπτομέρειες βιβλιογραφικής εγγραφής
| Τίτλος: |
Performance Evaluation of Structural Health Monitoring Anomaly Data Processing Algorithms in Resource-Constrained Edge Computing. |
| Συγγραφείς: |
Lei K; School of Architecture and Engineering, Xinjiang University, Urumqi 830017, China., Li Y; School of Civil Engineering, Southeast University, Nanjing 210096, China.; National and Local Joint Engineering Research Center for Intelligent Construction and Maintenance, Nanjing 210096, China., Hou S; School of Civil Engineering, Southeast University, Nanjing 210096, China.; National and Local Joint Engineering Research Center for Intelligent Construction and Maintenance, Nanjing 210096, China., Yan W; School of Architecture and Engineering, Xinjiang University, Urumqi 830017, China., Qin Y; School of Architecture and Engineering, Xinjiang University, Urumqi 830017, China., Zuo F; National and Local Joint Engineering Research Center for Intelligent Construction and Maintenance, Nanjing 210096, China. |
| Πηγή: |
Sensors (Basel, Switzerland) [Sensors (Basel)] 2026 Jul 22; Vol. 26 (14). Date of Electronic Publication: 2026 Jul 22. |
| Τύπος έκδοσης: |
Journal Article |
| Γλώσσα: |
English |
| Στοιχεία περιοδικού: |
Publisher: MDPI Country of Publication: Switzerland NLM ID: 101204366 Publication Model: Electronic Cited Medium: Internet ISSN: 1424-8220 (Electronic) Linking ISSN: 14248220 NLM ISO Abbreviation: Sensors (Basel) Subsets: MEDLINE; PubMed not MEDLINE |
| Imprint Name(s): |
Original Publication: Basel, Switzerland : MDPI, c2000- |
| Περίληψη: |
Edge computing plays an important role in structural health monitoring (SHM) for transportation infrastructure because it enables local data processing and low-latency decision support. However, SHM systems encounter challenges due to data anomalies caused by sensor faults, transmission errors, or irregular structural behavior. This study evaluates the deployment performance of a SHM anomaly data-processing workflow on resource-constrained edge devices. The workflow includes data cleaning, response separation, and anomaly detection. Missing data are processed using cubic spline interpolation. Jump points and drift are corrected using the Laida criterion, and noise is reduced using wavelet threshold denoising. Response separation is then performed using the detrending method based on time windows, the 3σ criterion, or wavelet packet decomposition. Anomaly detection is then performed using autoregressive integrated moving average with explanatory variables, support vector machines, and recurrent neural networks. Simulation data and field monitoring data from bridge displacement and highway pavement strain are used to evaluate the workflow. The evaluation focuses on runtime, memory usage, central processing unit usage, and a data-processing throughput proxy. This analysis helps to understand the performance and trade-offs of algorithms on edge devices under the resource constraints typical of SHM applications. |
| Grant Information: |
2024B04013 Key R&D Program of Xinjiang Uygur Autonomous Region; XJ2025G047 Autonomous Region Graduate Research and Innovation Project; XJRC-2025-ZZB-ZDXQ-008 Xinjiang Major Talent Demand Support Program; 5105260182G The "Tianchi Talent" Introduction Program of Xinjiang Uygur Autonomous Region |
| Contributed Indexing: |
Keywords: anomaly data processing; edge computing; machine learning; performance evaluation; structural health monitoring (SHM) |
| Entry Date(s): |
Date Created: 20260728 Latest Revision: 20260731 |
| Update Code: |
20260731 |
| PubMed Central ID: |
PMC13417254 |
| DOI: |
10.3390/s26144658 |
| PMID: |
42515540 |
| Βάση Δεδομένων: |
MEDLINE |