An Intelligent Functional Diagnostics of Wireless Sensor Network

Krivulya, Gennady; Skarga-Bandurova, Inna; Tatarchenko, Zakhar; Seredina, Olena; Shcherbakova, Maryna; Shcherbakov, E. V.

doi:10.1109/ficloudw.2019.00037

Cited by 4 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the derived model, deviations of the actual sensor readings from the expected values can then be detected. Thereby, particularly neural networks [38,39] and support-vector machine (SVM)-based detection approaches [40] have shown to be suitable in identifying anomalous sensor readings, especially when being augmented with statistical features as described in [41]. But also approaches based on decision trees have been proposed for fault detection [42].…”

Section: Sensor Data Analysismentioning

confidence: 99%

An Open-Source Wireless Sensor Node Platform with Active Node-Level Reliability for Monitoring Applications

Widhalm

Goeschka

Kästner

2021

Sensors

View full text Add to dashboard Cite

In wireless sensor networks, the quality of the provided data is influenced by the properties of the sensor nodes. Often deployed in large numbers, they usually consist of low-cost components where failures are the norm, even more so in harsh outdoor environments. Current fault detection techniques, however, consider the sensor data alone and neglect vital information from the nodes’ hard- and software. As a consequence, they can not distinguish between rare data anomalies caused by proper events in the sensed data on one side and fault-induced data distortion on the other side. In this paper, we contribute with a novel, open-source sensor node platform for monitoring applications such as environmental monitoring. For long battery life, it comprises mainly low-power components. In contrast to other sensor nodes, our platform provides self-diagnostic measures to enable active node-level reliability. The entire sensor node platform including the hardware and software components has been implemented and is publicly available and free to use for everyone. Based on an extensive and long-running practical experiment setup, we show that the detectability of node faults is improved and the distinction between rare but proper events and fault-induced data distortion is indeed possible. We also show that these measures have a negligible overhead on the node’s energy efficiency and hardware costs. This improves the overall reliability of wireless sensor networks with both, long battery life and high-quality data.

show abstract

Section: Sensor Data Analysismentioning

confidence: 99%

An Open-Source Wireless Sensor Node Platform with Active Node-Level Reliability for Monitoring Applications

Widhalm

Goeschka

Kästner

2021

Sensors

View full text Add to dashboard Cite

show abstract

Investigating and Analyzing Simulation Tools of Wireless Sensor Networks: A Comprehensive Survey

Adday,

Subramaniam,

Zukarnain

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Wireless Sensor Networks (WSNs) serve as the backbone for the Internet of Things (IoT) and smart cities, enabling the gathering of essential data and vital information. The widespread deployment of sensors created new scenarios that presented new domains for various applications. Due to their numerous advantages, WSN's simulators are still gaining considerable attention as the primary method for testing and evaluating new protocols and approaches for WSN. The scientific community has developed various simulators, some tailored explicitly for WSNs and others for general use. In addition, an old but renovated direction has been enormously grown recently, representing the researcher's attention to building its own simulator. However, many researchers struggle to select the most appropriate tool for performance analysis, which requires extensive research into available options. Choosing a suitable simulator to meet the necessary simulation criteria necessitates exhaustive research into the available options. The published studies on WSN's simulators have limitations, such as the limited number of simulators under examination, ignoring the essential functions of the simulators, and inadequate performance criteria for precise comparison. To get beyond these restrictions in previous studies and offer a fresh study that compares the simulation tools comprehensively, an analysis of thirty-three different simulators was conducted based on a new taxonomy. Furthermore, this study examines the advantages and constraints of each simulator regarding many specific academic areas in WSNs. Moreover, the study presented a detailed comparison among the performance analysis tools according to many famous performance metrics.

show abstract