Skip to main content
EURASIP Journal on Wireless Communications and Networking
EURASIP Journal on Wireless Communications and Networking Cover Image
Fig. 4 | EURASIP Journal on Wireless Communications and Networking

Fig. 4

From: Intrusion detection in internet of things using supervised machine learning based on application and transport layer features using UNSW-NB15 data-set

Fig. 4

Feature importance of clusters. Feature importance using RF for a Flow and MQTT features, b TCP features and c Top features from flow/MQTT and TCP with mean imputation. Multiple and linear regression has same trend of feature importance in all three categories. Top contributing features are, a sport, dttl and dbytes, b dloss, dur and dtcpb and c dur, dpkts and dmeansz. Generally, the trend toward information contribution is smooth in all three categories

Back to article page
\