Monitoring dynamic networks: A simulation‐based strategy for comparing monitoring methods and a comparative study

Abstract

Recently, there has been a lot of interest in monitoring and identifying changes in dynamic networks, which has led to the development of a variety of monitoring methods. New methods are often designed for a specialized use‐case and rarely compared to competing methods in a systematic fashion. In light of this, the use of simulation is proposed to compare the performance of network monitoring methods over a variety of dynamic network changes. Using the family of simulated dynamic networks, the performance of several state‐of‐the‐art social network monitoring methods from the literature are compared. Their performance over a variety of types of change is compared; both increases in communication levels as well as changes in community structure are considered. It is shown that there does not exist one method that is uniformly superior to the others; the best method depends on the context and the type of change one wishes to detect. As such, it is concluded that a variety of methods are needed for network monitoring and that it is important to understand in which scenarios a given method is appropriate.

Research on dynamic monitoring of green mine geological environment based on remote sensing and GIS technology

“…Then, the NIR and Red values of each pixel point were calculated to obtain the corresponding NDVI values. The specific classification standard can be adjusted and optimized according to the actual situation [9] . In the inversion of canopy density, it is necessary to obtain the NDVI value of the ground sampling point and the corresponding canopy density data.…”

A real‐time monitoring approach for bivariate event data

“…Another field with transient shifts is network monitoring. For example, Yu et al 31 study shifts of length 50. Social media data often display transient shifts as illustrated in, for example, Zwetsloot and Woodall; Sparks and Paris; Sparks et al 9,15,32 Overall, transient shifts occur in many fields and are important to detect.…”

Real-Time Monitoring and Management of Hardware and Software Resources in Heterogeneous Computer Networks through an Integrated System Architecture

“…Novel approaches are often intended to be used in particular real-world use case scenarios, and they are generally not comparatively analysed against similar methods. Thus, paper of Yu et al [67] describes a simulation that is intended to support the comparison of various network-monitoring methods relative to various dynamic network changes. Considering the set of simulated dynamic networks, the performances of several networkmonitoring methods presented in the surveyed literature are compared.…”