This study proposes a two- level classification technique for the anomaly detection-based IDS architecture for fog-edge sides. Targeted for IoT-smart city networks, the upper layer network uses a gradient boosting classifier while the lower layer network employs deep learning (DL) based on the combination of a long-short-term memory and a convolutional neural network (CNN-LSTM).
This research proposes a two- level classification technique for the anomaly detection-based IDS architecture for fog-edge sides. Targeted for IoT-smart city networks, the upper layer network uses a gradient boosting classifier while the lower layer network employs deep learning (DL) based on the combination of a long-short-term memory and a convolutional neural network (CNN-LSTM). Download the dataset from: https://research.unsw.edu.au/projects/unsw-nb15-dataset
This study proposes a two- level classification technique for the anomaly detection-based IDS architecture for fog-edge sides. Targeted for IoT-smart city networks, the upper layer network uses a gradient boosting classifier while the lower layer network employs deep learning (DL) based on the combination of a long-short-term memory and a convolutional neural network (CNN-LSTM).