Name
Abstract | ||
|---|---|---|
Mobile robot applications operating in wireless environments require fast detection of link failures in order to enable fast repair. In previous work, we have shown that cross-layer failure detection can reduce failure detection latency significantly. In particular, we monitor the behavior of the WLAN MAC layer to predict failures on the link layer. In this paper, we investigate data mining techniques to determine which parameters, i.e., the events, or combination and timing of events, occurring on the MAC layer most probably lead to link failures. Our results show, that the parameters revealed with the data mining approach produce similar or even more accurate failure predictions than achieved so far. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1109/SRDS.2010.51 | SRDS |
Keywords | Field | DocType |
fast detection,wlan mac layer,data-mining-based link failure detection,data mining approach,failure detection latency,link layer,mac layer,wireless mesh networks,accurate failure prediction,cross-layer failure detection,link failure,data mining technique,data models,mobile robots,reliability,data mining,wireless mesh network,wireless communication,mobile communication,ad hoc networks,mobile robot,training data | Data modeling,Data mining,Wireless,Latency (engineering),Computer science,Link layer,Real-time computing,Wireless mesh network,Wireless ad hoc network,Mobile robot,Mobile telephony,Distributed computing | Conference |
ISSN | Citations | PageRank |
1060-9857 | 3 | 0.43 |
References | Authors | |
11 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Timo Lindhorst | 1 | 14 | 3.45 |
| Georg Lukas | 2 | 3 | 0.43 |
| Edgar Nett | 3 | 345 | 54.29 |
| Michael Mock | 4 | 55 | 8.99 |