Figure 1: The overview of an AutoML pipeline for IoT data analytics.
Table 1: A comprehensive overview of traditional ML algorithms, their hyperparameters, their advantages and limitations, and suitable IoT tasks.
Table 2: A comprehensive overview of DL and RL models, their hyperparameters, their advantages and limitations, and suitable IoT tasks.
Table 3: The comparison of common optimization methods for CASH and HPO problems.
Table 4: The comparison of common imputation methods.
Table 5: The comparison of concept drift methods for automated model updating.
Table 6: The specifications of the proposed AutoML pipeline.
Table 12: The challenges and research directions of applying AutoML to IoT data analytics.
