Assessing Machine Learning Approaches to Address IoT Sensor Drift
This work highlights a critical problem for IoT applications relying on continuous sensor data, but it is incremental as it evaluates existing approaches rather than proposing new solutions.
The paper tested several state-of-the-art machine learning approaches to address IoT sensor drift using a public gas sensor dataset, finding that sensor drift still causes substantial performance drops despite these methods.
The proliferation of IoT sensors and their deployment in various industries and applications has brought about numerous analysis opportunities in this Big Data era. However, drift of those sensor measurements poses major challenges to automate data analysis and the ability to effectively train and deploy models on a continuous basis. In this paper we study and test several approaches from the literature with regard to their ability to cope with and adapt to sensor drift under realistic conditions. Most of these approaches are recent and thus are representative of the current state-of-the-art. The testing was performed on a publicly available gas sensor dataset exhibiting drift over time. The results show substantial drops in sensing performance due to sensor drift in spite of the approaches. We then discuss several issues identified with current approaches and outline directions for future research to tackle them.