Missing and Corrupted Data Recovery in Wireless Sensor Networks Based on Weighted Robust Principal Component...

Area of Science:

• Computer Science
• Electrical Engineering
• Data Science

Background:

• Wireless sensor networks (WSNs) are crucial for data monitoring but suffer from data loss and corruption.
• Issues like poor network conditions, limited bandwidth, and node failures compromise data integrity.
• Credibility of monitoring data is significantly impacted by these transmission errors.

Purpose of the Study:

• To propose a novel method for recovering corrupted and missing data in WSNs.
• To enhance the reliability and accuracy of data collected from WSNs.
• To address the limitations of existing data recovery techniques in WSN environments.

Main Methods:

• Developed a weighted robust principal component analysis (RPCA) method.
• Decomposed data into low-rank normal and sparse abnormal matrices for identification and separation.
• Utilized weighted nuclear norm minimization for preserving key data components during reconstruction.
• Employed an alternating direction method of multipliers (ADMM) algorithm for optimization.

Main Results:

• The proposed weighted RPCA method effectively identifies and reconstructs corrupted and missing data.
• Weighted nuclear norm minimization enhances the preservation of major data components.
• The ADMM algorithm efficiently solves the complex optimization problem.
• Experimental results show superior recovery accuracy compared to state-of-the-art methods in real WSNs.

Conclusions:

• The weighted robust principal component analysis offers a robust solution for data recovery in WSNs.
• The method significantly improves the credibility of monitoring data despite network imperfections.
• This approach provides a reliable way to ensure data integrity in critical WSN applications.