Propagation-aware Knowledge Extraction for Fault Detection in Wireless Sensor Networks via RF Link Quality, Text, and Data Mining
Wireless sensor networks (WSNs) form the foundation of data-driven environments in contemporary industries, agriculture, healthcare, and smart cities. However, early fault identification in WSNs remains a persistent challenge due to severe propagation conditions, the uncertainty of environmental fac...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | , , , , , |
| التنسيق: | article |
| منشور في: |
2025
|
| الوصول للمادة أونلاين: | http://hdl.handle.net/11675/14496 https: |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| الملخص: | Wireless sensor networks (WSNs) form the foundation of data-driven environments in contemporary industries, agriculture, healthcare, and smart cities. However, early fault identification in WSNs remains a persistent challenge due to severe propagation conditions, the uncertainty of environmental factors, and unreliable sensor operation. In this article, the authors describe a state-of-the-art propagation-aware knowledge extraction framework to address robust fault detection through the combination of RF link-quality characterization, text mining in network logs, and scalable data-mining algorithms. The given approach integrates multi-source information, including physical-layer measurements, semantic event logs, and real-time data streams into an adaptive decision engine. The system achieves significantly greater fault localization accuracy and responsiveness because, using both advanced propagation modeling and machine learning, the system dynamically adapts to channel conditions and semantic context, unlike the legacy methods. Decades of simulation and real-world sensor field results indicate that it can improve by more than 15% the detection accuracy, lowering the false negative rates, and able to scale itself to a variety of propagation situations. Such an approach solves major shortcomings of the previous research and paves the way to robust, context-sensitive sensor platforms that are needed by the next-generation IoT and communication networks. |
|---|