| A network provides a powerful means of representing complex relationships between entities by abstracting entities as vertices, and relationships as edges connecting vertices in a graph. In the majority of real-world applications, such as online social networks, financial networks and transactional networks, unusual changes may indicate potential fraudulent activities or intrusions. Change detection is a challenging problem because it involves a time series of graphs, each of which is a complex, high-dimensional object consisting of a large number of nodes, edges and attributes. In this paper, we combine spectral embedding techniques in linear algebra with statistical shape analysis techniques and propose a novel change detection algorithm. We apply our developed algorithm to both simulated and real world datasets to evaluate its performance. The results provide sufficient evidence to show the ability of our algorithm in detecting interesting change scenarios occurring in dynamic networks. |  |
|
|
Isuru Udayangani Hewapathirana, Dominic Lee, Elena Moltchanova & Jeanette McLeod Social Network Analysis and Mining |
||
Abstract :- https://doi.org/10.1007/s13278-020-0625-3 |
||
- 011 2903539 / 539
- officerc@kln.ac.lk
- Mon - Fri 8:00 - 17:00
Quick Links
Contact us
Research council
University of Kelaniya, Kelaniya 11600,
Sri Lanka
+094 (112) 903 539
officerc@kln.ac.lk
Latest News
Test