IoT Anomaly Detection uses the IoT-23 dataset[1]. The data set is downloaded and its path is written to the necessary places in the data_preprocessing.py script. Then the code is run. The resulting .csv file is given to classifiers.
[1] https://www.stratosphereips.org/datasets-iot23 (The small one was used in the project.)
Colab Notebook was used because the training of the model requires a lot of memory and takes a long time. (You need to edit the paths in each script for the project to work.)
Accuracies are given below.
F1 Scores are given below.
