Details
| Original language | English |
|---|---|
| Title of host publication | International Symposium on Performance Evaluation of Computer and Telecommunication Systems 2008, SPECTS 2008, Part of the 2008 Summer Simulation Multiconference, SummerSim 2008 |
| Pages | 67-73 |
| Number of pages | 7 |
| Publication status | Published - 2008 |
| Event | International Symposium on Performance Evaluation of Computer and Telecommunication Systems 2008, SPECTS 2008, Part of the 2008 Summer Simulation Multiconference, SummerSim 2008 - Edinburgh, United Kingdom (UK) Duration: 16 Jun 2008 → 19 Jun 2008 |
Publication series
| Name | International Symposium on Performance Evaluation of Computer and Telecommunication Systems 2008, SPECTS 2008, Part of the 2008 Summer Simulation Multiconference, SummerSim 2008 |
|---|
Abstract
In this work we evaluate the feasibility of both classical machine learning algorithms and bio-inspired algorithms for misbehavior detection in sensor networks, since recent works in that field seem to concentrate mainly on bio-inspired approaches, without a convincing rational reason. As a first step, we analyze the packet traffic of a simulated sensor network in order to find relevant features that distinguish normal network operation from misbehaving nodes. This kind of data analysis is often missing in previous studies. Using these features acquired by the systematic data analysis we study the suitability of classical machine learning algorithms as well as bio-inspired learning algorithms for the given classification problem. We conclude which algorithms perform best in this special scenario, considering classification success and resource-friendliness of the algorithms. As result we can say that classical algorithms have equal or even better detection capabilities compared to some bio-inspired algorithms. It turns out that it is even possible to detect different levels of misbehavior with nearly 100% accuracy.
Keywords
- Classification algorithms, Machine learning, Traffic analysis, Wireless sensor networks
ASJC Scopus subject areas
- Computer Science(all)
- Computer Networks and Communications
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
International Symposium on Performance Evaluation of Computer and Telecommunication Systems 2008, SPECTS 2008, Part of the 2008 Summer Simulation Multiconference, SummerSim 2008. 2008. p. 67-73 (International Symposium on Performance Evaluation of Computer and Telecommunication Systems 2008, SPECTS 2008, Part of the 2008 Summer Simulation Multiconference, SummerSim 2008).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Traffic analysis and classification with bio-inspired and classical algorithms in sensor networks
AU - Becker, Matthias
AU - Bohlmann, Sebastian
AU - Schaust, Sven
PY - 2008
Y1 - 2008
N2 - In this work we evaluate the feasibility of both classical machine learning algorithms and bio-inspired algorithms for misbehavior detection in sensor networks, since recent works in that field seem to concentrate mainly on bio-inspired approaches, without a convincing rational reason. As a first step, we analyze the packet traffic of a simulated sensor network in order to find relevant features that distinguish normal network operation from misbehaving nodes. This kind of data analysis is often missing in previous studies. Using these features acquired by the systematic data analysis we study the suitability of classical machine learning algorithms as well as bio-inspired learning algorithms for the given classification problem. We conclude which algorithms perform best in this special scenario, considering classification success and resource-friendliness of the algorithms. As result we can say that classical algorithms have equal or even better detection capabilities compared to some bio-inspired algorithms. It turns out that it is even possible to detect different levels of misbehavior with nearly 100% accuracy.
AB - In this work we evaluate the feasibility of both classical machine learning algorithms and bio-inspired algorithms for misbehavior detection in sensor networks, since recent works in that field seem to concentrate mainly on bio-inspired approaches, without a convincing rational reason. As a first step, we analyze the packet traffic of a simulated sensor network in order to find relevant features that distinguish normal network operation from misbehaving nodes. This kind of data analysis is often missing in previous studies. Using these features acquired by the systematic data analysis we study the suitability of classical machine learning algorithms as well as bio-inspired learning algorithms for the given classification problem. We conclude which algorithms perform best in this special scenario, considering classification success and resource-friendliness of the algorithms. As result we can say that classical algorithms have equal or even better detection capabilities compared to some bio-inspired algorithms. It turns out that it is even possible to detect different levels of misbehavior with nearly 100% accuracy.
KW - Classification algorithms
KW - Machine learning
KW - Traffic analysis
KW - Wireless sensor networks
UR - http://www.scopus.com/inward/record.url?scp=84870993003&partnerID=8YFLogxK
UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-60349086857&origin=inward&txGid=e94bdf267b3d438b094e6968e856e063
M3 - Conference contribution
AN - SCOPUS:84870993003
SN - 9781622763566
T3 - International Symposium on Performance Evaluation of Computer and Telecommunication Systems 2008, SPECTS 2008, Part of the 2008 Summer Simulation Multiconference, SummerSim 2008
SP - 67
EP - 73
BT - International Symposium on Performance Evaluation of Computer and Telecommunication Systems 2008, SPECTS 2008, Part of the 2008 Summer Simulation Multiconference, SummerSim 2008
T2 - International Symposium on Performance Evaluation of Computer and Telecommunication Systems 2008, SPECTS 2008, Part of the 2008 Summer Simulation Multiconference, SummerSim 2008
Y2 - 16 June 2008 through 19 June 2008
ER -