Online Processing of Vehicular Data on the Edge Through an Unsupervised TinyML Regression Technique

The Internet of Things (IoT) has made it possible to include everyday objects in a connected network, allowing them intelligently process data and respond their environment. Thus, is expected that those will gain an intelligent understanding environment be able more efficiently than before. Particularly, such edge computing paradigm allowed the execution inference methods on resource-constrained devices as microcontrollers, significantly changing way IoT applications have evolved recent years. However, although this scenario supported development Tiny Machine Learning (TinyML) approaches devices, there are still some challenges require further investigation when optimizing streaming edge. Therefore, article proposes new unsupervised TinyML regression technique based typicality eccentricity samples processed. Moreover, proposed also exploits Recursive Least Squares (RLS) filter approach. Combining all these features, method uses similarities between identify patterns processing streams, predicting outcomes patterns. results obtained through extensive experimentation utilizing vehicular streams were highly encouraging. algorithm was meticulously compared with RLS Convolutional Neural Networks (CNN). It exhibited superior performance, mean squared errors 4.68 12.02 times lower, respectively, aforementioned techniques.