Loading web-font TeX/Main/Regular
Adaptive KPCA for Outlier detection in Wireless Sensor Networks: Water pipeline case | IEEE Conference Publication | IEEE Xplore

Adaptive KPCA for Outlier detection in Wireless Sensor Networks: Water pipeline case


Abstract:

In our life, water is considered as an essential resource. Pipelines are taken into consideration as one of the best solutions to transport water through long distance. D...Show More

Abstract:

In our life, water is considered as an essential resource. Pipelines are taken into consideration as one of the best solutions to transport water through long distance. Due to the existence of the harsh environmental condition, many detection methods are developed to monitoring pipelines. But these latter are not effective to leak detection. Most current solutions need to be improved to help in damage detection. To monitoring water pipeline, we use the Wireless Sensors Networks (WSNs) in this way. WSNs are employed now upward of domains like transport, military, agriculture, health care\ldotsKernel principal component analysis (KPCA), also called the kernelized version, are developed to capture the nonlinear data structure. KPCA is derived from the Gram matrix which is not robust when the data contain outliers. In this paper, we develop a new technique that takes into account low-cost and real-time damage detection for outlier. Our proposed technique is based on Adaptive Kernel Principal Component Analysis (AKPCA). This latter help to differentiate the type of data as normal or outlier in the field of water pipeline based on WSN. In the experiments, real data are used for outlier detection to verify the method’s effectiveness. However, our proposed work shows a better performance to detecting outliers.
Date of Conference: 31 October 2021 - 02 November 2021
Date Added to IEEE Xplore: 25 November 2021
ISBN Information:
Conference Location: Dubai, United Arab Emirates

References

References is not available for this document.