A Study of Data Fusion Based on Combining Rough Set with BP Neural Network

Abstract

Based on rough set and basic theory of data fusion, the data fusion algorithm combining rough set theory and BP neural network is studied. Since rough set theory can effectively simplify information, cut down the tagged dimension . This paper will be rough set theory and neural networks combined, using channel capacity of knowledge relative reduction algorithms to simplify the input information. Rough set theory is first used to process the sample data, and eliminate the redundant information, then reduce the scale of neural network, improve the identification rate, and improve the efficiency of the whole data fusion system. The effectiveness of the improved algorithm is demonstrated by an example compared with the traditional neural network system.

A framework to facilitate cyber defense situational awareness modeled in an emulated virtual machine testbed

“…Recently researchers created systems able to fuse data of homogeneous sensors, such as observations of multiple intrusion detection systems (IDSs). [3][4][5] Unfortunately, the aggregation of homogeneous sensor data only increases the accuracy of traffic identification. Heterogeneous sensor data fusion must augment such capabilities in order to obtain more precise information and give network defenders the appropriate form of situational awareness to identify and respond to attacks.…”

Data Fusion Based on Hybrid Intelligent Optimization

“…In recent years, scholars have devoted much effort to fuzzy measurement of sensor. Literature 5-7 employed Vague set to describe each sensor's fuzzy measurement information of the target, literature [8][9][10] adopted similar degree and signal to noise ratio to describe the relation among the objects tested by sensors. However, the degrees of certainty and uncertainty, proximity and signal-noise ratio are defined in these methods are not objective enough when describing proximity.…”