Abstract | ||
---|---|---|
With increasing size, the problems a city faces (e.g., air pollution, traffic congestion or high energy consumption) increase, but so does the amount of implicitly available data. In order to leverage this data for smarter problem solutions, local authorities and businesses require sophisticated analysis preprocessing techniques. Recent work proposes modeling urban data as a graph and applying graph-based anomaly detection, which is traditionally used for fraud and intrusion detection. This demonstrates that a successful application of anomaly detection to selected sources of urban data is possible, but lacks an evaluation of the general applicability. In this survey, we discuss several homogeneous and heterogeneous graph models for urban data and suitable detection approaches. |
Year | Venue | Field |
---|---|---|
2017 | 2017 IEEE SMARTWORLD, UBIQUITOUS INTELLIGENCE & COMPUTING, ADVANCED & TRUSTED COMPUTED, SCALABLE COMPUTING & COMMUNICATIONS, CLOUD & BIG DATA COMPUTING, INTERNET OF PEOPLE AND SMART CITY INNOVATION (SMARTWORLD/SCALCOM/UIC/ATC/CBDCOM/IOP/SCI) | Data modeling,Anomaly detection,Graph,Homogeneous,Computer science,Preprocessor,Intrusion detection system,High energy,Traffic congestion,Distributed computing |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Simon Sudrich | 1 | 1 | 1.02 |
julio de melo borges | 2 | 8 | 3.24 |
M. Beigl | 3 | 2034 | 311.09 |