| Abstract | IOT devices have become an integral part of our daily lives and we depend on them without even realizing this. Almost all IOT devices consist of a system of sensors responsible for detecting changes in the environment and then relying on intelligent Machine Learning Algorithms to extract useful information from the changes detected. However, sensors often need to be replaced or upgraded in the system which poses the challenge of manually retraining the model employed by the newly installed sensor. Training these models is a time-consuming task and requires a lot of effort to collect useful labelled data for the model to learn. With this research we plan to tackle this problem by leveraging the presence of pre-existing sensors in the system. We will investigate the autonomous training of newly installed sensors in a system of heterogenous sensors using pre-existing sensors. If time permits, we will also investigate how we can take advantage of the collective information gathered from all sensors in the system to make more detailed and intelligent observations about a particular event.
|
|---|
