A WSN Missing Data Reconstruction Method Based on Bayesian Network Model

Abstract

The invention relates to a WSN missing data reconstruction method based on a Bayesian network model, and belongs to the technical field of wireless sensor network data processing. The method first divides each time period into different time slots, and each time slot includes three time periods: data collection, node evaluation, and missing data reconstruction; data collection phase: sensor nodes with missing data send request data to neighboring nodes information; node evaluation stage: the sensor node selects the optimal data candidate node according to the criteria of the best trust node; missing data reconstruction stage: the sensor node with missing data first establishes a Bayesian network model, and then the best candidate node The node data is introduced into the Bayesian network model as an auxiliary variable, and the data corresponding to the maximum conditional probability is calculated and selected to replace the missing value of the sensor. The invention reduces the data error rate and can meet the requirement of real-time information processing of nodes in a mobile environment.

Description

technical field [0001] The invention belongs to the technical field of wireless sensor network data processing, and relates to a method for reconstructing missing data of wireless sensor nodes in a mobile scene based on a Bayesian network model. Background technique [0002] With the wide application of Wireless Sensor Network (WSN) in the fields of environmental perception, industrial process control, ecological monitoring, and emergency solutions, its data-centric characteristics have become increasingly prominent. Data itself is the carrier of information, and true and complete data is the basic premise to support data analysis and decision-making. WSN has strict requirements on data integrity, correctness and punctual delivery. However, due to the limited storage capacity, communication capacity, computing power of sensing nodes, external failures, human interference and other reasons, the collected sensing data usually has inevitable missing or abnormalities. Therefore,...

AI Technical Summary

Problems solved by technology

The traditional missing data reconstruction method uses the spatial-temporal correlation or attribute correlation of its own sensory data to reconstruct the missing data, but the processed data is the sensory data collected within a long sampling time, and the reconstructed sensory node is in a high-speed mobile environment in a short time. There is still room for research on the information transmitted within

Images